Updated on 2025/03/04

写真a

 
UEDA DAIJU
 
Organization
Graduate School of Medicine Department of Basic Medical Science Associate Professor
School of Medicine Department of Medical Science
Title
Associate Professor
Affiliation
Institute of Medicine
Affiliation campus
Abeno Campus

Position

  • Graduate School of Medicine Department of Basic Medical Science 

    Associate Professor  2024.04 - Now

  • School of Medicine Department of Medical Science 

    Associate Professor  2024.04 - Now

Degree

  • 博士(医学) ( Osaka City University )

Research Areas

  • Life Science / Radiological sciences  / Artificial intelligence

Research Interests

  • artificial intelligence

  • deep learning

  • medical image

  • Fairness

  • Planetary health

  • radiology

Professional Memberships

  • Institute of Electrical and Electronics Engineers

    2018 - Now

  • Radiological Society of North America

    2016.04 - Now

  • Japan Radiological Society

    2016.04 - Now

  • Japanese Society of Interventional Radiology

    2016.04 - Now

Awards

  • 島津奨励賞

    植田大樹

    2025.01   島津科学技術振興財団   医用画像への科学計測としての人工知能の応用研究

  • KDDI Foundation Award

    Daiju Ueda

    2024.12   KDDI Foundation  

  • DISTINGUISHED REVIEWER for the years 2023–2024

    Daiju Ueda

    2024.06   American Journal of Neuroradiology  

  • Medical Imaging Artificial Intelligence Research Award

    Daiju Ueda

    2023.04   Japan Radiological Society  

  • Association Award

    Akitoshi Shimazaki, Daiju Ueda, Antoine Choppin, Akira Yamamoto, Takashi Honjo, Yuki Shimahara, Yukio Miki

    2023.03   Osaka City Medical Association   Deep learning-based algorithm for lung cancer detection on chest radiographs using the segmentation method.

  • Yoichiro Nambu Memorial Award

    Daiju Ueda

    2022.12   Osaka Metropolitan University  

  • Certificate of Merit

    2022.09   The Cardiovascular and Interventional Radiological Society of Europe   Generation of synthetic subtraction angiograms in abdominal region using deep learning

  • Best Paper Award

    2022.06   Japanese Society of Interventional Radiology   Deep Learning–based Angiogram Generation Model for Cerebral Angiography without Misregistration Artifacts

  • Japanese Journal of Radiology Best Paper Award

    2022.04   Japan Radiological Society   Visualizing “featureless” regions on mammograms classified as invasive ductal carcinomas by a deep learning algorithm: the promise of AI support in radiology

  • Featured Abstract

    2020.08   Japanese Society of Interventional Radiology   Deep Learning–based Angiogram Generation Model for Cerebral Angiography without Misregistration Artifacts

  • Outstanding Paper Award

    2020.05   Japanese Radiological Society   Deep Learning for MR Angiography: Automated Detection of Cerebral Aneurysms

  • The Best of Radiology

    2019.12   RSNA   Deep Learning for MR Angiography: Automated Detection of Cerebral Aneurysms

  • Excellent Award

    2019.03   Osaka City University   Deep Learning for MR Angiography: Automated Detection of Cerebral Aneurysms

▼display all

Job Career (off-campus)

  • Graduate School of Medicine, Osaka Metropolitan University   Department of Artificial Intelligence

    2024.04 - Now

  • Osaka Metropolitan University   Center for Health Science Innovation   Deputy Director

    2024.04 - Now

  • Osaka Metropolitan University   Center for Health Science Innovation   Associate Professor

    2022.04 - 2024.03

  • Graduate School of Medicine, Osaka Metropolitan University   Department of Diagnostic and Interventional Radiology

    2022.04 - 2024.03

Papers

  • Correction: Generative AI and large language models in nuclear medicine: current status and future prospects.

    Hirata K, Matsui Y, Yamada A, Fujioka T, Yanagawa M, Nakaura T, Ito R, Ueda D, Fujita S, Tatsugami F, Fushimi Y, Tsuboyama T, Kamagata K, Nozaki T, Fujima N, Kawamura M, Naganawa S

    Annals of nuclear medicine   2025.02( ISSN:0914-7187

  • Recent trends in scientific research in chest radiology: What to do or not to do? That is the critical question in research.

    Hiroto Hatabu, Masahiro Yanagawa, Yoshitake Yamada, Takuya Hino, Yuzo Yamasaki, Akinori Hata, Daiju Ueda, Yusei Nakamura, Yoshiyuki Ozawa, Masahiro Jinzaki, Yoshiharu Ohno

    Japanese journal of radiology   2025.01( ISSN:18671071

     More details

    Publishing type:Research paper (scientific journal)   International / domestic magazine:Domestic journal  

    Hereby inviting young rising stars in chest radiology in Japan for contributing what they are working currently, we would like to show the potentials and directions of the near future research trends in the research field. I will provide a reflection on my own research topics. At the end, we also would like to discuss on how to choose the themes and topics of research: What to do or not to do? We strongly believe it will stimulate and help investigators in the field.

    DOI: 10.1007/s11604-025-01735-3

    PubMed

  • The critical need for an open medical imaging database in Japan: implications for global health and AI development Reviewed

    Daiju Ueda, Shannon Walston, Hirotaka Takita, Yasuhito Mitsuyama, Yukio Miki

    Japanese Journal of Radiology   2024.12( ISSN:1867-1071 ( eISSN:1867-108X

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Research paper (scientific journal)  

    Abstract

    Japan leads OECD countries in medical imaging technology deployment but lacks open, large-scale medical imaging databases crucial for AI development. While Japan maintains extensive repositories, access restrictions limit their research utility, contrasting with open databases like the US Cancer Imaging Archive and UK Biobank. The 2018 Next Generation Medical Infrastructure Act attempted to address this through new data-sharing frameworks, but implementation has been limited by strict privacy regulations and institutional resistance. This data gap risks compromising AI system performance for Japanese patients and limits global medical AI advancement. The solution lies not in developing individual AI models, but in democratizing access to well-curated Japanese medical imaging data. By implementing privacy-preserving techniques and streamlining regulatory processes, Japan could enhance domestic healthcare outcomes while contributing to more robust global AI models, ultimately reclaiming its position as a leader in medical innovation.

    DOI: 10.1007/s11604-024-01716-y

    PubMed

    Other URL: https://link.springer.com/article/10.1007/s11604-024-01716-y/fulltext.html

  • Stereotactic arrhythmia radioablation for ventricular tachycardia: a review of clinical trials and emerging roles of imaging

    Mariko Kawamura, Masafumi Shimojo, Fuminari Tatsugami, Kenji Hirata, Shohei Fujita, Daiju Ueda, Yusuke Matsui, Yasutaka Fushimi, Tomoyuki Fujioka, Taiki Nozaki, Akira Yamada, Rintaro Ito, Noriyuki Fujima, Masahiro Yanagawa, Takeshi Nakaura, Takahiro Tsuboyama, Koji Kamagata, Shinji Naganawa

    Journal of Radiation Research   66 ( 1 )   1 - 9   2024.12( ISSN:0449-3060 ( eISSN:1349-9157

     More details

    Publishing type:Research paper (scientific journal)  

    ABSTRACT

    Ventricular tachycardia (VT) is a severe arrhythmia commonly treated with implantable cardioverter defibrillators, antiarrhythmic drugs and catheter ablation (CA). Although CA is effective in reducing recurrent VT, its impact on survival remains uncertain, especially in patients with extensive scarring. Stereotactic arrhythmia radioablation (STAR) has emerged as a novel treatment for VT in patients unresponsive to CA, leveraging techniques from stereotactic body radiation therapy used in cancer treatments. Recent clinical trials and case series have demonstrated the short-term efficacy and safety of STAR, although long-term outcomes remain unclear. Imaging techniques, such as electroanatomical mapping, contrast-enhanced magnetic resonance imaging and nuclear imaging, play a crucial role in treatment planning by identifying VT substrates and guiding target delineation. However, challenges persist owing to the complex anatomy and variability in target volume definitions. Advances in imaging and artificial intelligence are expected to improve the precision and efficacy of STAR. The exact mechanisms underlying the antiarrhythmic effects of STAR, including potential fibrosis and improvement in cardiac conduction, are still being explored. Despite its potential, STAR should be cautiously applied in prospective clinical trials, with a focus on optimizing dose delivery and understanding long-term outcomes. Collaborative efforts are necessary to standardize treatment strategies and enhance the quality of life for patients with refractory VT.

    DOI: 10.1093/jrr/rrae090

    PubMed

  • Diagnostic accuracy of vision-language models on Japanese diagnostic radiology, nuclear medicine, and interventional radiology specialty board examinations(タイトル和訳中)

    Oura Tatsushi, Tatekawa Hiroyuki, Horiuchi Daisuke, Matsushita Shu, Takita Hirotaka, Atsukawa Natsuko, Mitsuyama Yasuhito, Yoshida Atsushi, Murai Kazuki, Tanaka Rikako, Shimono Taro, Yamamoto Akira, Miki Yukio, Ueda Daiju

    Japanese Journal of Radiology   42 ( 12 )   1392 - 1398   2024.12( ISSN:1867-1071

  • Challenges of AI-based pulmonary function estimation from chest x-rays – Authors' reply

    Daiju Ueda, Shannon L Walston, Yasuhito Mitsuyama, Hirotaka Takita, Yukio Miki

    The Lancet Digital Health   6 ( 12 )   e881 - e881   2024.12( ISSN:2589-7500

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Research paper (scientific journal)  

    DOI: 10.1016/s2589-7500(24)00248-6

    PubMed

  • Advancing clinical MRI exams with artificial intelligence: Japan’s contributions and future prospects

    Shohei Fujita, Yasutaka Fushimi, Rintaro Ito, Yusuke Matsui, Fuminari Tatsugami, Tomoyuki Fujioka, Daiju Ueda, Noriyuki Fujima, Kenji Hirata, Takahiro Tsuboyama, Taiki Nozaki, Masahiro Yanagawa, Koji Kamagata, Mariko Kawamura, Akira Yamada, Takeshi Nakaura, Shinji Naganawa

    Japanese Journal of Radiology   2024.11( ISSN:1867-1071 ( eISSN:1867-108X

     More details

    Publishing type:Research paper (scientific journal)  

    Abstract

    In this narrative review, we review the applications of artificial intelligence (AI) into clinical magnetic resonance imaging (MRI) exams, with a particular focus on Japan’s contributions to this field. In the first part of the review, we introduce the various applications of AI in optimizing different aspects of the MRI process, including scan protocols, patient preparation, image acquisition, image reconstruction, and postprocessing techniques. Additionally, we examine AI’s growing influence in clinical decision-making, particularly in areas such as segmentation, radiation therapy planning, and reporting assistance. By emphasizing studies conducted in Japan, we highlight the nation’s contributions to the advancement of AI in MRI. In the latter part of the review, we highlight the characteristics that make Japan a unique environment for the development and implementation of AI in MRI examinations. Japan’s healthcare landscape is distinguished by several key factors that collectively create a fertile ground for AI research and development. Notably, Japan boasts one of the highest densities of MRI scanners per capita globally, ensuring widespread access to the exam. Japan’s national health insurance system plays a pivotal role by providing MRI scans to all citizens irrespective of socioeconomic status, which facilitates the collection of inclusive and unbiased imaging data across a diverse population. Japan’s extensive health screening programs, coupled with collaborative research initiatives like the Japan Medical Imaging Database (J-MID), enable the aggregation and sharing of large, high-quality datasets. With its technological expertise and healthcare infrastructure, Japan is well-positioned to make meaningful contributions to the MRI–AI domain. The collaborative efforts of researchers, clinicians, and technology experts, including those in Japan, will continue to advance the future of AI in clinical MRI, potentially leading to improvements in patient care and healthcare efficiency.

    DOI: 10.1007/s11604-024-01689-y

    PubMed

    Other URL: https://link.springer.com/article/10.1007/s11604-024-01689-y/fulltext.html

  • Visualizing the association between the location and prognosis of isocitrate dehydrogenase wild-type glioblastoma: a voxel-wise Cox regression analysis with open-source datasets.

    Natsuko Atsukawa, Hiroyuki Tatekawa, Daiju Ueda, Tatsushi Oura, Shu Matsushita, Daisuke Horiuchi, Hirotaka Takita, Yasuhito Mitsuyama, Reia Baba, Taro Tsukamoto, Taro Shimono, Yukio Miki

    Neuroradiology   2024.11( ISSN:00283940

     More details

    Publishing type:Research paper (scientific journal)   International / domestic magazine:International journal  

    PURPOSE: This study examined the correlation between tumor location and prognosis in patients with glioblastoma using magnetic resonance images of various isocitrate dehydrogenase (IDH) wild-type glioblastomas from The Cancer Imaging Archive (TCIA). The relationship between tumor location and prognosis was visualized using voxel-wise Cox regression analysis. METHODS: Participants with IDH wild-type glioblastoma were selected, and their survival and demographic data and tumor characteristics were collected from TCIA datasets. Post-contrast-enhanced T1-weighted imaging, T2-fluid attenuated inversion recovery imaging, and tumor segmentation data were also compiled. Following affine registration of each image and tumor segmentation region of interest to the MNI standard space, a voxel-wise Cox regression analysis was conducted. This analysis determined the association of the presence or absence of the tumor with the prognosis in each voxel after adjusting for the covariates. RESULTS: The study included 769 participants of 464 men and 305 women (mean age, 63 years ± 12 [standard deviation]). The hazard ratio map indicated that tumors in the medial frontobasal region and around the third and fourth ventricles were associated with poorer prognoses, underscoring the challenges of complete resection and treatment accessibility in these areas regardless of the tumor volume. Conversely, tumors located in the right temporal and occipital lobes had favorable prognoses. CONCLUSION: This study showed an association between tumor location and prognosis. These findings may assist clinicians in developing more precise and effective treatment plans for patients with glioblastoma to improve their management.

    DOI: 10.1007/s00234-024-03503-y

    PubMed

  • 症例 嚢胞変性を伴う縦隔腫瘍と鑑別を要した肺過誤腫の1例

    辻坂 拓実, 田北 大昂, 立川 裕之, 植田 大樹, 番 義仁, 池田 明央, 泉 信博, 三木 幸雄

    臨床放射線   69 ( 6 )   883 - 887   2024.11( ISSN:00099252

     More details

  • 嚢胞変性を伴う縦隔腫瘍と鑑別を要した肺過誤腫の1例

    辻坂 拓実, 田北 大昂, 立川 裕之, 植田 大樹, 番 義仁, 池田 明央, 泉 信博, 三木 幸雄

    臨床放射線   69 ( 6 )   883 - 887   2024.11( ISSN:0009-9252

  • Applications of artificial intelligence in interventional oncology: An up-to-date review of the literature

    Yusuke Matsui, Daiju Ueda, Shohei Fujita, Yasutaka Fushimi, Takahiro Tsuboyama, Koji Kamagata, Rintaro Ito, Masahiro Yanagawa, Akira Yamada, Mariko Kawamura, Takeshi Nakaura, Noriyuki Fujima, Taiki Nozaki, Fuminari Tatsugami, Tomoyuki Fujioka, Kenji Hirata, Shinji Naganawa

    Japanese Journal of Radiology   43 ( 2 )   164 - 176   2024.10( ISSN:1867-1071 ( eISSN:1867-108X

     More details

    Publishing type:Research paper (scientific journal)  

    Abstract

    Interventional oncology provides image-guided therapies, including transarterial tumor embolization and percutaneous tumor ablation, for malignant tumors in a minimally invasive manner. As in other medical fields, the application of artificial intelligence (AI) in interventional oncology has garnered significant attention. This narrative review describes the current state of AI applications in interventional oncology based on recent literature. A literature search revealed a rapid increase in the number of studies relevant to this topic recently. Investigators have attempted to use AI for various tasks, including automatic segmentation of organs, tumors, and treatment areas; treatment simulation; improvement of intraprocedural image quality; prediction of treatment outcomes; and detection of post-treatment recurrence. Among these, the AI-based prediction of treatment outcomes has been the most studied. Various deep and conventional machine learning algorithms have been proposed for these tasks. Radiomics has often been incorporated into prediction and detection models. Current literature suggests that AI is potentially useful in various aspects of interventional oncology, from treatment planning to post-treatment follow-up. However, most AI-based methods discussed in this review are still at the research stage, and few have been implemented in clinical practice. To achieve widespread adoption of AI technologies in interventional oncology procedures, further research on their reliability and clinical utility is necessary. Nevertheless, considering the rapid research progress in this field, various AI technologies will be integrated into interventional oncology practices in the near future.

    DOI: 10.1007/s11604-024-01668-3

    PubMed

    Other URL: https://link.springer.com/article/10.1007/s11604-024-01668-3/fulltext.html

  • Clarifications on the Differentiation of Vertebral Fractures Using Deep Learning Models Reviewed

    Shannon L. Walston, Shingo Sato, Yasuhito Mitsuyama, Hirotaka Takita, Daiju Ueda

    Radiology   313 ( 1 )   e241162   2024.10( ISSN:0033-8419 ( eISSN:1527-1315

     More details

    Authorship:Last author, Corresponding author   Publishing type:Research paper (scientific journal)  

    DOI: 10.1148/radiol.241162

    PubMed

  • Generative AI and large language models in nuclear medicine: current status and future prospects.

    Kenji Hirata, Yusuke Matsui, Akira Yamada, Tomoyuki Fujioka, Masahiro Yanagawa, Takeshi Nakaura, Rintaro Ito, Daiju Ueda, Shohei Fujita, Fuminari Tatsugami, Yasutaka Fushimi, Takahiro Tsuboyama, Koji Kamagata, Taiki Nozaki, Noriyuki Fujima, Mariko Kawamura, Shinji Naganawa

    Annals of nuclear medicine   38 ( 11 )   853 - 864   2024.09( ISSN:09147187

     More details

    Publishing type:Research paper (scientific journal)   International / domestic magazine:Domestic journal  

    This review explores the potential applications of Large Language Models (LLMs) in nuclear medicine, especially nuclear medicine examinations such as PET and SPECT, reviewing recent advancements in both fields. Despite the rapid adoption of LLMs in various medical specialties, their integration into nuclear medicine has not yet been sufficiently explored. We first discuss the latest developments in nuclear medicine, including new radiopharmaceuticals, imaging techniques, and clinical applications. We then analyze how LLMs are being utilized in radiology, particularly in report generation, image interpretation, and medical education. We highlight the potential of LLMs to enhance nuclear medicine practices, such as improving report structuring, assisting in diagnosis, and facilitating research. However, challenges remain, including the need for improved reliability, explainability, and bias reduction in LLMs. The review also addresses the ethical considerations and potential limitations of AI in healthcare. In conclusion, LLMs have significant potential to transform existing frameworks in nuclear medicine, making it a critical area for future research and development.

    DOI: 10.1007/s12149-024-01981-x

    PubMed

  • Comparative analysis of GPT-4-based ChatGPT’s diagnostic performance with radiologists using real-world radiology reports of brain tumors Reviewed

    Yasuhito Mitsuyama, Hiroyuki Tatekawa, Hirotaka Takita, Fumi Sasaki, Akane Tashiro, Satoshi Oue, Shannon L. Walston, Yuta Nonomiya, Ayumi Shintani, Yukio Miki, Daiju Ueda

    European Radiology   2024.08( ISSN:09387994 ( eISSN:1432-1084

     More details

    Authorship:Last author, Corresponding author   Publishing type:Research paper (scientific journal)   International / domestic magazine:International journal  

    Abstract

    Objectives

    Large language models like GPT-4 have demonstrated potential for diagnosis in radiology. Previous studies investigating this potential primarily utilized quizzes from academic journals. This study aimed to assess the diagnostic capabilities of GPT-4-based Chat Generative Pre-trained Transformer (ChatGPT) using actual clinical radiology reports of brain tumors and compare its performance with that of neuroradiologists and general radiologists.

    Methods

    We collected brain MRI reports written in Japanese from preoperative brain tumor patients at two institutions from January 2017 to December 2021. The MRI reports were translated into English by radiologists. GPT-4 and five radiologists were presented with the same textual findings from the reports and asked to suggest differential and final diagnoses. The pathological diagnosis of the excised tumor served as the ground truth. McNemar’s test and Fisher’s exact test were used for statistical analysis.

    Results

    In a study analyzing 150 radiological reports, GPT-4 achieved a final diagnostic accuracy of 73%, while radiologists’ accuracy ranged from 65 to 79%. GPT-4’s final diagnostic accuracy using reports from neuroradiologists was higher at 80%, compared to 60% using those from general radiologists. In the realm of differential diagnoses, GPT-4’s accuracy was 94%, while radiologists’ fell between 73 and 89%. Notably, for these differential diagnoses, GPT-4’s accuracy remained consistent whether reports were from neuroradiologists or general radiologists.

    Conclusion

    GPT-4 exhibited good diagnostic capability, comparable to neuroradiologists in differentiating brain tumors from MRI reports. GPT-4 can be a second opinion for neuroradiologists on final diagnoses and a guidance tool for general radiologists and residents.

    Clinical relevance statement

    This study evaluated GPT-4-based ChatGPT’s diagnostic capabilities using real-world clinical MRI reports from brain tumor cases, revealing that its accuracy in interpreting brain tumors from MRI findings is competitive with radiologists.

    Key Points

    We investigated the diagnostic accuracy of GPT-4 using real-world clinical MRI reports of brain tumors.

    GPT-4 achieved final and differential diagnostic accuracy that is comparable with neuroradiologists.

    GPT-4 has the potential to improve the diagnostic process in clinical radiology.



    Graphical Abstract

    DOI: 10.1007/s00330-024-11032-8

    PubMed

    Other URL: https://link.springer.com/article/10.1007/s00330-024-11032-8/fulltext.html

  • Letter to the Editor: “Feasibility study on the clinical application of CT-based synthetic brain T1-weighted MRI: comparison with conventional T1-weighted MRI” Reviewed

    Shannon Leigh Walston, Daiju Ueda

    European Radiology   35 ( 2 )   592 - 593   2024.08( ISSN:09387994 ( eISSN:1432-1084

     More details

    Authorship:Last author, Corresponding author   Publishing type:Research paper (scientific journal)   International / domestic magazine:International journal  

    DOI: 10.1007/s00330-024-10874-6

    PubMed

    Other URL: https://link.springer.com/article/10.1007/s00330-024-10874-6/fulltext.html

  • Recent trends in AI applications for pelvic MRI: a comprehensive review Reviewed

    Takahiro Tsuboyama, Masahiro Yanagawa, Tomoyuki Fujioka, Shohei Fujita, Daiju Ueda, Rintaro Ito, Akira Yamada, Yasutaka Fushimi, Fuminari Tatsugami, Takeshi Nakaura, Taiki Nozaki, Koji Kamagata, Yusuke Matsui, Kenji Hirata, Noriyuki Fujima, Mariko Kawamura, Shinji Naganawa

    La radiologia medica   129 ( 9 )   1275 - 1287   2024.08( ISSN:00338362 ( eISSN:1826-6983

     More details

    Publishing type:Research paper (scientific journal)  

    DOI: 10.1007/s11547-024-01861-4

    PubMed

    Other URL: https://link.springer.com/article/10.1007/s11547-024-01861-4/fulltext.html

  • Diagnostic accuracy of vision-language models on Japanese diagnostic radiology, nuclear medicine, and interventional radiology specialty board examinations Reviewed

    Tatsushi Oura, Hiroyuki Tatekawa, Daisuke Horiuchi, Shu Matsushita, Hirotaka Takita, Natsuko Atsukawa, Yasuhito Mitsuyama, Atsushi Yoshida, Kazuki Murai, Rikako Tanaka, Taro Shimono, Akira Yamamoto, Yukio Miki, Daiju Ueda

    Japanese Journal of Radiology   42 ( 12 )   1392 - 1398   2024.07( ISSN:1867-1071 ( eISSN:1867-108X

     More details

    Authorship:Last author   Publishing type:Research paper (scientific journal)  

    Abstract

    Purpose

    The performance of vision-language models (VLMs) with image interpretation capabilities, such as GPT-4 omni (GPT-4o), GPT-4 vision (GPT-4V), and Claude-3, has not been compared and remains unexplored in specialized radiological fields, including nuclear medicine and interventional radiology. This study aimed to evaluate and compare the diagnostic accuracy of various VLMs, including GPT-4 + GPT-4V, GPT-4o, Claude-3 Sonnet, and Claude-3 Opus, using Japanese diagnostic radiology, nuclear medicine, and interventional radiology (JDR, JNM, and JIR, respectively) board certification tests.

    Materials and methods

    In total, 383 questions from the JDR test (358 images), 300 from the JNM test (92 images), and 322 from the JIR test (96 images) from 2019 to 2023 were consecutively collected. The accuracy rates of the GPT-4 + GPT-4V, GPT-4o, Claude-3 Sonnet, and Claude-3 Opus were calculated for all questions or questions with images. The accuracy rates of the VLMs were compared using McNemar’s test.

    Results

    GPT-4o demonstrated the highest accuracy rates across all evaluations with the JDR (all questions, 49%; questions with images, 48%), JNM (all questions, 64%; questions with images, 59%), and JIR tests (all questions, 43%; questions with images, 34%), followed by Claude-3 Opus with the JDR (all questions, 40%; questions with images, 38%), JNM (all questions, 42%; questions with images, 43%), and JIR tests (all questions, 40%; questions with images, 30%). For all questions, McNemar’s test showed that GPT-4o significantly outperformed the other VLMs (all P < 0.007), except for Claude-3 Opus in the JIR test. For questions with images, GPT-4o outperformed the other VLMs in the JDR and JNM tests (all P < 0.001), except Claude-3 Opus in the JNM test.

    Conclusion

    The GPT-4o had the highest success rates for questions with images and all questions from the JDR, JNM, and JIR board certification tests.

    DOI: 10.1007/s11604-024-01633-0

    PubMed

    Other URL: https://link.springer.com/article/10.1007/s11604-024-01633-0/fulltext.html

  • ChatGPT's diagnostic performance based on textual vs. visual information compared to radiologists' diagnostic performance in musculoskeletal radiology. Reviewed

    Daisuke Horiuchi, Hiroyuki Tatekawa, Tatsushi Oura, Taro Shimono, Shannon L Walston, Hirotaka Takita, Shu Matsushita, Yasuhito Mitsuyama, Yukio Miki, Daiju Ueda

    European radiology   35 ( 1 )   506 - 516   2024.07( ISSN:09387994

     More details

    Authorship:Last author   Publishing type:Research paper (scientific journal)   International / domestic magazine:International journal  

    OBJECTIVES: To compare the diagnostic accuracy of Generative Pre-trained Transformer (GPT)-4-based ChatGPT, GPT-4 with vision (GPT-4V) based ChatGPT, and radiologists in musculoskeletal radiology. MATERIALS AND METHODS: We included 106 "Test Yourself" cases from Skeletal Radiology between January 2014 and September 2023. We input the medical history and imaging findings into GPT-4-based ChatGPT and the medical history and images into GPT-4V-based ChatGPT, then both generated a diagnosis for each case. Two radiologists (a radiology resident and a board-certified radiologist) independently provided diagnoses for all cases. The diagnostic accuracy rates were determined based on the published ground truth. Chi-square tests were performed to compare the diagnostic accuracy of GPT-4-based ChatGPT, GPT-4V-based ChatGPT, and radiologists. RESULTS: GPT-4-based ChatGPT significantly outperformed GPT-4V-based ChatGPT (p < 0.001) with accuracy rates of 43% (46/106) and 8% (9/106), respectively. The radiology resident and the board-certified radiologist achieved accuracy rates of 41% (43/106) and 53% (56/106). The diagnostic accuracy of GPT-4-based ChatGPT was comparable to that of the radiology resident, but was lower than that of the board-certified radiologist although the differences were not significant (p = 0.78 and 0.22, respectively). The diagnostic accuracy of GPT-4V-based ChatGPT was significantly lower than those of both radiologists (p < 0.001 and < 0.001, respectively). CONCLUSION: GPT-4-based ChatGPT demonstrated significantly higher diagnostic accuracy than GPT-4V-based ChatGPT. While GPT-4-based ChatGPT's diagnostic performance was comparable to radiology residents, it did not reach the performance level of board-certified radiologists in musculoskeletal radiology. CLINICAL RELEVANCE STATEMENT: GPT-4-based ChatGPT outperformed GPT-4V-based ChatGPT and was comparable to radiology residents, but it did not reach the level of board-certified radiologists in musculoskeletal radiology. Radiologists should comprehend ChatGPT's current performance as a diagnostic tool for optimal utilization. KEY POINTS: This study compared the diagnostic performance of GPT-4-based ChatGPT, GPT-4V-based ChatGPT, and radiologists in musculoskeletal radiology. GPT-4-based ChatGPT was comparable to radiology residents, but did not reach the level of board-certified radiologists. When utilizing ChatGPT, it is crucial to input appropriate descriptions of imaging findings rather than the images.

    DOI: 10.1007/s00330-024-10902-5

    PubMed

  • Development and Validation of Artificial Intelligence-Based Algorithms for Predicting the Segments Debulked by Rotational Atherectomy Using Intravascular Ultrasound Images Reviewed

    Kenta Hashimoto, Kenichi Fujii, Daiju Ueda, Akinori Sumiyoshi, Katsuyuki Hasegawa, Rei Fukuhara, Munemitsu Otagaki, Atsunori Okamura, Wataru Yamamoto, Naoki Kawano, Akira Yamamoto, Yukio Miki, Iichiro Shiojima

    The American Journal of Cardiology   223   1 - 6   2024.07( ISSN:0002-9149

     More details

    Publishing type:Research paper (scientific journal)  

    DOI: 10.1016/j.amjcard.2024.05.027

    PubMed

  • A deep learning-based model to estimate pulmonary function from chest x-rays: multi-institutional model development and validation study in Japan Reviewed

    Daiju Ueda, Toshimasa Matsumoto, Akira Yamamoto, Shannon L Walston, Yasuhito Mitsuyama, Hirotaka Takita, Kazuhisa Asai, Tetsuya Watanabe, Koji Abo, Tatsuo Kimura, Shinya Fukumoto, Toshio Watanabe, Tohru Takeshita, Yukio Miki

    The Lancet Digital Health   6 ( 8 )   e580 - e588   2024.07( ISSN:2589-7500

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Research paper (scientific journal)   International / domestic magazine:International journal  

    DOI: 10.1016/s2589-7500(24)00113-4

    PubMed

  • Seeking Details on Artificial Intelligence Diagnosis for Acute Otitis Media Reviewed International coauthorship

    Shannon L. Walston, Shingo Sato, Daiju Ueda

    JAMA Pediatrics   178 ( 8 )   839 - 840   2024.06( ISSN:2168-6203

     More details

    Authorship:Last author, Corresponding author   Publishing type:Research paper (scientific journal)   International / domestic magazine:International journal  

    DOI: 10.1001/jamapediatrics.2024.1740

    PubMed

  • Data set terminology of deep learning in medicine: a historical review and recommendation. Invited Reviewed International coauthorship

    Shannon L Walston, Hiroshi Seki, Hirotaka Takita, Yasuhito Mitsuyama, Shingo Sato, Akifumi Hagiwara, Rintaro Ito, Shouhei Hanaoka, Yukio Miki, Daiju Ueda

    Japanese journal of radiology   42 ( 10 )   1100 - 1109   2024.06( ISSN:18671071

     More details

    Authorship:Last author, Corresponding author   Publishing type:Research paper (scientific journal)   International / domestic magazine:Domestic journal  

    Medicine and deep learning-based artificial intelligence (AI) engineering represent two distinct fields each with decades of published history. The current rapid convergence of deep learning and medicine has led to significant advancements, yet it has also introduced ambiguity regarding data set terms common to both fields, potentially leading to miscommunication and methodological discrepancies. This narrative review aims to give historical context for these terms, accentuate the importance of clarity when these terms are used in medical deep learning contexts, and offer solutions to mitigate misunderstandings by readers from either field. Through an examination of historical documents, including articles, writing guidelines, and textbooks, this review traces the divergent evolution of terms for data sets and their impact. Initially, the discordant interpretations of the word 'validation' in medical and AI contexts are explored. We then show that in the medical field as well, terms traditionally used in the deep learning domain are becoming more common, with the data for creating models referred to as the 'training set', the data for tuning of parameters referred to as the 'validation (or tuning) set', and the data for the evaluation of models as the 'test set'. Additionally, the test sets used for model evaluation are classified into internal (random splitting, cross-validation, and leave-one-out) sets and external (temporal and geographic) sets. This review then identifies often misunderstood terms and proposes pragmatic solutions to mitigate terminological confusion in the field of deep learning in medicine. We support the accurate and standardized description of these data sets and the explicit definition of data set splitting terminologies in each publication. These are crucial methods for demonstrating the robustness and generalizability of deep learning applications in medicine. This review aspires to enhance the precision of communication, thereby fostering more effective and transparent research methodologies in this interdisciplinary field.

    DOI: 10.1007/s11604-024-01608-1

    PubMed

  • Enhancing Self-Supervised Learning for Rare Diseases in OCT Reviewed International coauthorship

    Shannon L. Walston, Shingo Sato, Daiju Ueda

    JAMA Ophthalmology   142 ( 7 )   688   2024.06( ISSN:2168-6165

     More details

    Authorship:Last author, Corresponding author   Publishing type:Research paper (scientific journal)   International / domestic magazine:International journal  

    DOI: 10.1001/jamaophthalmol.2024.1870

    PubMed

  • Climate change and artificial intelligence in healthcare: Review and recommendations towards a sustainable future Reviewed

    Daiju Ueda, Shannon L Walston, Shohei Fujita, Yasutaka Fushimi, Takahiro Tsuboyama, Koji Kamagata, Akira Yamada, Masahiro Yanagawa, Rintaro Ito, Noriyuki Fujima, Mariko Kawamura, Takeshi Nakaura, Yusuke Matsui, Fuminari Tatsugami, Tomoyuki Fujioka, Taiki Nozaki, Kenji Hirata, Shinji Naganawa

    Diagnostic and Interventional Imaging   105 ( 11 )   453 - 459   2024.06( ISSN:2211-5684

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Research paper (scientific journal)   International / domestic magazine:International journal  

    DOI: 10.1016/j.diii.2024.06.002

    PubMed

  • Comparing the Diagnostic Performance of GPT-4-based ChatGPT, GPT-4V-based ChatGPT, and Radiologists in Challenging Neuroradiology Cases Reviewed OA

    Daisuke Horiuchi, Hiroyuki Tatekawa, Tatsushi Oura, Satoshi Oue, Shannon L Walston, Hirotaka Takita, Shu Matsushita, Yasuhito Mitsuyama, Taro Shimono, Yukio Miki, Daiju Ueda

    Clinical Neuroradiology   34 ( 4 )   779 - 787   2024.05( ISSN:1869-1439 ( eISSN:1869-1447

     More details

    Authorship:Last author, Corresponding author   Publishing type:Research paper (scientific journal)   International / domestic magazine:International journal  

    DOI: 10.1007/s00062-024-01426-y

    PubMed

    Other URL: https://link.springer.com/article/10.1007/s00062-024-01426-y/fulltext.html

  • Enhancing AI-assisted Interpretation of Chest Radiographs: A Critical Analysis of Methods and Applicability. Reviewed

    Shannon L Walston, Daiju Ueda

    Radiology   311 ( 2 )   e233428   2024.05( ISSN:0033-8419

     More details

    Publishing type:Research paper (scientific journal)   International / domestic magazine:International journal  

    DOI: 10.1148/radiol.233428

    PubMed

  • Deep learning-based screening tool for rotator cuff tears on shoulder radiography(タイトル和訳中)

    Iio Ryosuke, Ueda Daiju, Matsumoto Toshimasa, Manaka Tomoya, Nakazawa Katsumasa, Ito Yoichi, Hirakawa Yoshihiro, Yamamoto Akira, Shiba Masatsugu, Nakamura Hiroaki

    Journal of Orthopaedic Science   29 ( 3 )   828 - 834   2024.05( ISSN:0949-2658

  • Evaluating Biases and Quality Issues in Intermodality Image Translation Studies for Neuroradiology: A Systematic Review. Reviewed

    Shannon L Walston, Hiroyuki Tatekawa, Hirotaka Takita, Yukio Miki, Daiju Ueda

    AJNR. American journal of neuroradiology   45 ( 6 )   826 - 832   2024.04( ISSN:0195-6108

     More details

    Publishing type:Research paper (scientific journal)   International / domestic magazine:International journal  

    BACKGROUND: Intermodality image-to-image translation is an artificial intelligence technique for generating one technique from another. PURPOSE: This review was designed to systematically identify and quantify biases and quality issues preventing validation and clinical application of artificial intelligence models for intermodality image-to-image translation of brain imaging. DATA SOURCES: PubMed, Scopus, and IEEE Xplore were searched through August 2, 2023, for artificial intelligence-based image translation models of radiologic brain images. STUDY SELECTION: This review collected 102 works published between April 2017 and August 2023. DATA ANALYSIS: Eligible studies were evaluated for quality using the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) and for bias using the Prediction model Risk Of Bias ASsessment Tool (PROBAST). Medically-focused article adherence was compared with that of engineering-focused articles overall with the Mann-Whitney U test and for each criterion using the Fisher exact test. DATA SYNTHESIS: Median adherence to the relevant CLAIM criteria was 69% and 38% for PROBAST questions. CLAIM adherence was lower for engineering-focused articles compared with medically-focused articles (65% versus 73%, P < .001). Engineering-focused studies had higher adherence for model description criteria, and medically-focused studies had higher adherence for data set and evaluation descriptions. LIMITATIONS: Our review is limited by the study design and model heterogeneity. CONCLUSIONS: Nearly all studies revealed critical issues preventing clinical application, with engineering-focused studies showing higher adherence for the technical model description but significantly lower overall adherence than medically-focused studies. The pursuit of clinical application requires collaboration from both fields to improve reporting.

    DOI: 10.3174/ajnr.A8211

    PubMed

  • The impact of large language models on radiology: a guide for radiologists on the latest innovations in AI. Reviewed

    Takeshi Nakaura, Rintaro Ito, Daiju Ueda, Taiki Nozaki, Yasutaka Fushimi, Yusuke Matsui, Masahiro Yanagawa, Akira Yamada, Takahiro Tsuboyama, Noriyuki Fujima, Fuminari Tatsugami, Kenji Hirata, Shohei Fujita, Koji Kamagata, Tomoyuki Fujioka, Mariko Kawamura, Shinji Naganawa

    Japanese journal of radiology   42 ( 7 )   685 - 696   2024.03( ISSN:18671071

     More details

    Publishing type:Research paper (scientific journal)   International / domestic magazine:Domestic journal  

    The advent of Deep Learning (DL) has significantly propelled the field of diagnostic radiology forward by enhancing image analysis and interpretation. The introduction of the Transformer architecture, followed by the development of Large Language Models (LLMs), has further revolutionized this domain. LLMs now possess the potential to automate and refine the radiology workflow, extending from report generation to assistance in diagnostics and patient care. The integration of multimodal technology with LLMs could potentially leapfrog these applications to unprecedented levels.However, LLMs come with unresolved challenges such as information hallucinations and biases, which can affect clinical reliability. Despite these issues, the legislative and guideline frameworks have yet to catch up with technological advancements. Radiologists must acquire a thorough understanding of these technologies to leverage LLMs' potential to the fullest while maintaining medical safety and ethics. This review aims to aid in that endeavor.

    DOI: 10.1007/s11604-024-01552-0

    PubMed

  • Evaluation of cranial nerve involvement in chordomas and chondrosarcomas: a retrospective imaging study. Reviewed

    Tatsushi Oura, Taro Shimono, Daisuke Horiuchi, Takeo Goto, Hirotaka Takita, Taro Tsukamoto, Hiroyuki Tatekawa, Daiju Ueda, Shu Matsushita, Yasuhito Mitsuyama, Natsuko Atsukawa, Yukio Miki

    Neuroradiology   66 ( 6 )   955 - 961   2024.02( ISSN:00283940

     More details

    Publishing type:Research paper (scientific journal)   International / domestic magazine:International journal  

    PURPOSE: Cranial nerve involvement (CNI) influences the treatment strategies and prognosis of head and neck tumors. However, its incidence in skull base chordomas and chondrosarcomas remains to be investigated. This study evaluated the imaging features of chordoma and chondrosarcoma, with a focus on the differences in CNI. METHODS: Forty-two patients (26 and 16 patients with chordomas and chondrosarcomas, respectively) treated at our institution between January 2007 and January 2023 were included in this retrospective study. Imaging features, such as the maximum diameter, tumor location (midline or off-midline), calcification, signal intensity on T2-weighted image, mean apparent diffusion coefficient (ADC) values, contrast enhancement, and CNI, were evaluated and compared using Fisher's exact test or the Mann-Whitney U-test. The odds ratio (OR) was calculated to evaluate the association between the histological type and imaging features. RESULTS: The incidence of CNI in chondrosarcomas was significantly higher than that in chordomas (63% vs. 8%, P < 0.001). An off-midline location was more common in chondrosarcomas than in chordomas (86% vs. 13%; P < 0.001). The mean ADC values of chondrosarcomas were significantly higher than those of chordomas (P < 0.001). Significant associations were identified between chondrosarcomas and CNI (OR = 20.00; P < 0.001), location (OR = 53.70; P < 0.001), and mean ADC values (OR = 1.01; P = 0.002). CONCLUSION: The incidence of CNI and off-midline location in chondrosarcomas was significantly higher than that in chordomas. CNI, tumor location, and the mean ADC can help distinguish between these entities.

    DOI: 10.1007/s00234-024-03322-1

    PubMed

  • Deep learning-based diffusion tensor image generation model: a proof-of-concept study. Reviewed

    Hiroyuki Tatekawa, Daiju Ueda, Hirotaka Takita, Toshimasa Matsumoto, Shannon L Walston, Yasuhito Mitsuyama, Daisuke Horiuchi, Shu Matsushita, Tatsushi Oura, Yuichiro Tomita, Taro Tsukamoto, Taro Shimono, Yukio Miki

    Scientific reports   14 ( 1 )   2911 - 2911   2024.02

     More details

    Publishing type:Research paper (scientific journal)   International / domestic magazine:International journal  

    This study created an image-to-image translation model that synthesizes diffusion tensor images (DTI) from conventional diffusion weighted images, and validated the similarities between the original and synthetic DTI. Thirty-two healthy volunteers were prospectively recruited. DTI and DWI were obtained with six and three directions of the motion probing gradient (MPG), respectively. The identical imaging plane was paired for the image-to-image translation model that synthesized one direction of the MPG from DWI. This process was repeated six times in the respective MPG directions. Regions of interest (ROIs) in the lentiform nucleus, thalamus, posterior limb of the internal capsule, posterior thalamic radiation, and splenium of the corpus callosum were created and applied to maps derived from the original and synthetic DTI. The mean values and signal-to-noise ratio (SNR) of the original and synthetic maps for each ROI were compared. The Bland-Altman plot between the original and synthetic data was evaluated. Although the test dataset showed a larger standard deviation of all values and lower SNR in the synthetic data than in the original data, the Bland-Altman plots showed each plot localizing in a similar distribution. Synthetic DTI could be generated from conventional DWI with an image-to-image translation model.

    DOI: 10.1038/s41598-024-53278-8

    PubMed

  • Diagnostic Performance of Generative AI and Physicians: A Systematic Review and Meta-Analysis

    Hirotaka Takita, Shannon L Walston, Hiroyuki Tatekawa, Kenichi Saito, Yasushi Tsujimoto, Yukio Miki, Daiju Ueda

    medRxiv   2024.01

     More details

    Authorship:Last author, Corresponding author  

    Abstract

    Background

    The rapid advancement of generative artificial intelligence (AI) has revolutionized understanding and generation of human language. Their integration into healthcare has shown potential for improving medical diagnostics, yet a comprehensive diagnostic performance evaluation of generative AI models and the comparison of their diagnostic performance with that of physicians has not been extensively explored.

    Methods

    In this systematic review and meta-analysis, a comprehensive search of Medline, Scopus, Web of Science, Cochrane Central, and medRxiv was conducted for studies published from June 2018 through December 2023, focusing on those that validate generative AI models for diagnostic tasks. Meta-analysis was performed to summarize the performance of the models and to compare the accuracy of the models with that of physicians. The quality of studies was assessed using the Prediction Model Study Risk of Bias Assessment Tool.

    Results

    The search resulted in 54 studies being included in the meta-analysis, with 13 of these also used in the comparative analysis. Eight models were evaluated across 17 medical specialties. The overall accuracy for generative AI models across 54 studies was 57% (95% confidence interval [CI]: 51–63%). The I-squared statistic of 96% signifies a high degree of heterogeneity among the study results. Meta-regression analysis of generative AI models revealed significantly improved accuracy for GPT-4, and reduced accuracy for some specialties such as Neurology, Endocrinology, Rheumatology, and Radiology. The comparison meta-analysis demonstrated that, on average, physicians exceeded the accuracy of the models (difference in accuracy: 14% [95% CI: 8–19%], p-value &lt;0.001). However, in the performance comparison between GPT-4 and physicians, GPT-4 performed slightly higher than non-experts (–4% [95% CI: –10–2%], p-value = 0.173), and slightly underperformed compared to experts (6% [95% CI: –1–13%], p-value = 0.091). The quality assessment indicated a high risk of bias in the majority of studies, primarily due to small sample sizes.

    Conclusions

    Generative AI exhibits promising diagnostic capabilities, with accuracy varying significantly by model and medical specialty. Although they have not reached the reliability of expert physicians, the findings suggest that generative AI models have the potential to enhance healthcare delivery and medical education, provided they are integrated with caution and their limitations are well-understood. This study also highlights the need for more rigorous research standards and a larger number of cases in the future.

    DOI: 10.1101/2024.01.20.24301563

  • Evaluating GPT-4-based ChatGPT's clinical potential on the NEJM quiz Reviewed

    Daiju Ueda, Shannon L. Walston, Toshimasa Matsumoto, Ryo Deguchi, Hiroyuki Tatekawa, Yukio Miki

    BMC Digital Health   2 ( 1 )   2024.01( eISSN:2731-684X

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Research paper (scientific journal)  

    Abstract

    Background

    GPT-4-based ChatGPT demonstrates significant potential in various industries; however, its potential clinical applications remain largely unexplored.

    Methods

    We employed the New England Journal of Medicine (NEJM) quiz “Image Challenge” from October 2021 to March 2023 to assess ChatGPT's clinical capabilities. The quiz, designed for healthcare professionals, tests the ability to analyze clinical scenarios and make appropriate decisions. We evaluated ChatGPT's performance on the NEJM quiz, analyzing its accuracy rate by questioning type and specialty after excluding quizzes which were impossible to answer without images. ChatGPT was first asked to answer without the five multiple-choice options, and then after being given the options.

    Results

    ChatGPT achieved an 87% (54/62) accuracy without choices and a 97% (60/62) accuracy with choices, after excluding 16 image-based quizzes. Upon analyzing performance by quiz type, ChatGPT excelled in the Diagnosis category, attaining 89% (49/55) accuracy without choices and 98% (54/55) with choices. Although other categories featured fewer cases, ChatGPT's performance remained consistent. It demonstrated strong performance across the majority of medical specialties; however, Genetics had the lowest accuracy at 67% (2/3).

    Conclusion

    ChatGPT demonstrates potential for diagnostic applications, suggesting its usefulness in supporting healthcare professionals in making differential diagnoses and enhancing AI-driven healthcare.

    DOI: 10.1186/s44247-023-00058-5

    Other URL: https://link.springer.com/article/10.1186/s44247-023-00058-5/fulltext.html

  • Challenges of using artificial intelligence to detect valvular heart disease from chest radiography – Authors' reply Reviewed

    Daiju Ueda, Shoichi Ehara, Akira Yamamoto, Shannon L Walston, Taro Shimono, Yukio Miki

    The Lancet Digital Health   6 ( 1 )   e10 - e10   2024.01( ISSN:2589-7500

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Research paper (scientific journal)  

    DOI: 10.1016/s2589-7500(23)00224-8

    PubMed

  • The Evolution and Clinical Impact of Deep Learning Technologies in Breast MRI

    Fujioka Tomoyuki, Fujita Shohei, Ueda Daiju, Ito Rintaro, Kawamura Mariko, Fushimi Yasutaka, Tsuboyama Takahiro, Yanagawa Masahiro, Yamada Akira, Tatsugami Fuminari, Kamagata Koji, Nozaki Taiki, Matsui Yusuke, Fujima Noriyuki, Hirata Kenji, Nakaura Takeshi, Tateishi Ukihide, Naganawa Shinji

    Magnetic Resonance in Medical Sciences   advpub ( 0 )   2024( ISSN:13473182 ( eISSN:18802206

     More details

    Publishing type:Research paper (scientific journal)   International / domestic magazine:Domestic journal  

    <p>The integration of deep learning (DL) in breast MRI has revolutionized the field of medical imaging, notably enhancing diagnostic accuracy and efficiency. This review discusses the substantial influence of DL technologies across various facets of breast MRI, including image reconstruction, classification, object detection, segmentation, and prediction of clinical outcomes such as response to neoadjuvant chemotherapy and recurrence of breast cancer. Utilizing sophisticated models such as convolutional neural networks, recurrent neural networks, and generative adversarial networks, DL has improved image quality and precision, enabling more accurate differentiation between benign and malignant lesions and providing deeper insights into disease behavior and treatment responses. DL’s predictive capabilities for patient-specific outcomes also suggest potential for more personalized treatment strategies. The advancements in DL are pioneering a new era in breast cancer diagnostics, promising more personalized and effective healthcare solutions. Nonetheless, the integration of this technology into clinical practice faces challenges, necessitating further research, validation, and development of legal and ethical frameworks to fully leverage its potential.</p>

    DOI: 10.2463/mrms.rev.2024-0056

    PubMed

  • Comparison of the diagnostic accuracy among GPT-4 based ChatGPT, GPT-4V based ChatGPT, and radiologists in musculoskeletal radiology

    Daisuke Horiuchi, Hiroyuki Tatekawa, Tatsushi Oura, Taro Shimono, Shannon L Walston, Hirotaka Takita, Shu Matsushita, Yasuhito Mitsuyama, Yukio Miki, Daiju Ueda

    medRxiv   2023.12

     More details

    Authorship:Last author, Corresponding author  

    Abstract

    Objective

    To compare the diagnostic accuracy of Generative Pre-trained Transformer (GPT)-4 based ChatGPT, GPT-4 with vision (GPT-4V) based ChatGPT, and radiologists in musculoskeletal radiology.

    Materials and Methods

    We included 106 “Test Yourself” cases fromSkeletal Radiologybetween January 2014 and September 2023. We input the medical history and imaging findings into GPT-4 based ChatGPT and the medical history and images into GPT-4V based ChatGPT, then both generated a diagnosis for each case. Two radiologists (a radiology resident and a board-certified radiologist) independently provided diagnoses for all cases. The diagnostic accuracy rates were determined based on the published ground truth. Chi-square tests were performed to compare the diagnostic accuracy of GPT-4 based ChatGPT, GPT-4V based ChatGPT, and radiologists.

    Results

    GPT-4 based ChatGPT significantly outperformed GPT-4V based ChatGPT (p&lt; 0.001) with accuracy rates of 43% (46/106) and 8% (9/106), respectively. The radiology resident and the board-certified radiologist achieved accuracy rates of 41% (43/106) and 53% (56/106). The diagnostic accuracy of GPT-4 based ChatGPT was comparable to that of the radiology resident but was lower than that of the board-certified radiologist, although the differences were not significant (p= 0.78 and 0.22, respectively). The diagnostic accuracy of GPT-4V based ChatGPT was significantly lower than those of both radiologists (p&lt; 0.001 and &lt; 0.001, respectively).

    Conclusion

    GPT-4 based ChatGPT demonstrated significantly higher diagnostic accuracy than GPT-4V based ChatGPT. While GPT-4 based ChatGPT’s diagnostic performance was comparable to radiology residents, it did not reach the performance level of board-certified radiologists in musculoskeletal radiology.

    DOI: 10.1101/2023.12.07.23299707

  • Accuracy of ChatGPT generated diagnosis from patient's medical history and imaging findings in neuroradiology cases. Reviewed

    Daisuke Horiuchi, Hiroyuki Tatekawa, Taro Shimono, Shannon L Walston, Hirotaka Takita, Shu Matsushita, Tatsushi Oura, Yasuhito Mitsuyama, Yukio Miki, Daiju Ueda

    Neuroradiology   66 ( 1 )   73 - 79   2023.11( ISSN:00283940

     More details

    Authorship:Last author, Corresponding author   Publishing type:Research paper (scientific journal)   International / domestic magazine:International journal  

    PURPOSE: The noteworthy performance of Chat Generative Pre-trained Transformer (ChatGPT), an artificial intelligence text generation model based on the GPT-4 architecture, has been demonstrated in various fields; however, its potential applications in neuroradiology remain unexplored. This study aimed to evaluate the diagnostic performance of GPT-4 based ChatGPT in neuroradiology. METHODS: We collected 100 consecutive "Case of the Week" cases from the American Journal of Neuroradiology between October 2021 and September 2023. ChatGPT generated a diagnosis from patient's medical history and imaging findings for each case. Then the diagnostic accuracy rate was determined using the published ground truth. Each case was categorized by anatomical location (brain, spine, and head & neck), and brain cases were further divided into central nervous system (CNS) tumor and non-CNS tumor groups. Fisher's exact test was conducted to compare the accuracy rates among the three anatomical locations, as well as between the CNS tumor and non-CNS tumor groups. RESULTS: ChatGPT achieved a diagnostic accuracy rate of 50% (50/100 cases). There were no significant differences between the accuracy rates of the three anatomical locations (p = 0.89). The accuracy rate was significantly lower for the CNS tumor group compared to the non-CNS tumor group in the brain cases (16% [3/19] vs. 62% [36/58], p < 0.001). CONCLUSION: This study demonstrated the diagnostic performance of ChatGPT in neuroradiology. ChatGPT's diagnostic accuracy varied depending on disease etiologies, and its diagnostic accuracy was significantly lower in CNS tumors compared to non-CNS tumors.

    DOI: 10.1007/s00234-023-03252-4

    PubMed

  • Revolutionizing radiation therapy: the role of AI in clinical practice Reviewed

    Mariko Kawamura, Takeshi Kamomae, Masahiro Yanagawa, Koji Kamagata, Shohei Fujita, Daiju Ueda, Yusuke Matsui, Yasutaka Fushimi, Tomoyuki Fujioka, Taiki Nozaki, Akira Yamada, Kenji Hirata, Rintaro Ito, Noriyuki Fujima, Fuminari Tatsugami, Takeshi Nakaura, Takahiro Tsuboyama, Shinji Naganawa

    Journal of Radiation Research   65 ( 1 )   1 - 9   2023.11( ISSN:0449-3060 ( eISSN:1349-9157

     More details

    Publishing type:Research paper (scientific journal)  

    Abstract

    This review provides an overview of the application of artificial intelligence (AI) in radiation therapy (RT) from a radiation oncologist’s perspective. Over the years, advances in diagnostic imaging have significantly improved the efficiency and effectiveness of radiotherapy. The introduction of AI has further optimized the segmentation of tumors and organs at risk, thereby saving considerable time for radiation oncologists. AI has also been utilized in treatment planning and optimization, reducing the planning time from several days to minutes or even seconds. Knowledge-based treatment planning and deep learning techniques have been employed to produce treatment plans comparable to those generated by humans. Additionally, AI has potential applications in quality control and assurance of treatment plans, optimization of image-guided RT and monitoring of mobile tumors during treatment. Prognostic evaluation and prediction using AI have been increasingly explored, with radiomics being a prominent area of research. The future of AI in radiation oncology offers the potential to establish treatment standardization by minimizing inter-observer differences in segmentation and improving dose adequacy evaluation. RT standardization through AI may have global implications, providing world-standard treatment even in resource-limited settings. However, there are challenges in accumulating big data, including patient background information and correlating treatment plans with disease outcomes. Although challenges remain, ongoing research and the integration of AI technology hold promise for further advancements in radiation oncology.

    DOI: 10.1093/jrr/rrad090

    PubMed

  • Development and validation of artificial intelligence-based algorithms for predicting the segments debulked by rotational atherectomy using intravascular ultrasound

    Kenta Hashimoto, Kenichi Fujii, Daiju Ueda, Akinori Sumiyoshi, Katsuyuki Hasegawa, Rei Fukuhara, Munemitsu Otagaki, Atsunori Okamura, Wataru Yamamoto, Naoki Kawano, Akira Yamamoto, Yukio Miki, Iichiro Shiojima

    medRxiv   2023.11

     More details

    Abstract

    Background

    Although rotation atherectomy (RA) is a useful technique for severely calcified lesions, patients undergoing RA show a greater incidence of catastrophic complications, such as coronary perforation. Therefore, prior to the RA procedure, it is important to predict which regions of the coronary plaque will be debulked by RA.

    Objectives

    We develop and evaluate an artificial intelligence–based algorithm that uses pre-RA intravascular ultrasound (IVUS) images to automatically predict regions debulked by RA

    Methods

    A total of 2106 IVUS cross-sections from 60 patients with de novo severely calcified coronary lesions who underwent IVUS-guided RA were consecutively collected. The two identical IVUS images of pre-and post-RA were merged, and the orientations of the debulked segments identified in the merged images are marked on the outer circle of each IVUS image. The artificial intelligence model was developed based on ResNet (deep residual learning for image recognition). The architecture connected 36 fully connected layers, each corresponding to one of the 36 orientations segmented every 10°, to a single feature extractor.

    Results

    In each cross-sectional analysis, our artificial intelligence model achieved an average sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of 81%, 72%, 46%, 90%, and 75%, respectively.

    Conclusions

    The artificial intelligence–based algorithm can use information from pre-RA IVUS images to accurately predict regions debulked by RA. The proposed method will assist interventional cardiologists in determining the treatment strategies for severely calcified coronary lesions.

    DOI: 10.1101/2023.11.07.23298239

  • Bridging Language and Stylistic Barriers in Interventional Radiology Standardized Reporting: Enhancing Translation and Structure using ChatGPT-4 Reviewed

    Fumi Sasaki, Hiroyuki Tatekawa, Yasuhito Mitsuyama, Ken Kageyama, Atsushi Jogo, Akira Yamamoto, Yukio Miki, Daiju Ueda

    Journal of Vascular and Interventional Radiology   35 ( 3 )   472 - 475.e1   2023.11( ISSN:1051-0443

     More details

    Authorship:Last author   Publishing type:Research paper (scientific journal)  

    DOI: 10.1016/j.jvir.2023.11.014

    PubMed

  • Comparative Analysis of ChatGPT’s Diagnostic Performance with Radiologists Using Real-World Radiology Reports of Brain Tumors

    Yasuhito Mitsuyama, Hiroyuki Tatekawa, Hirotaka Takita, Fumi Sasaki, Akane Tashiro, Satoshi Oue, Shannon L Walston, Yukio Miki, Daiju Ueda

    medRxiv   2023.10

     More details

    Authorship:Last author, Corresponding author  

    Abstract

    Background

    Large Language Models like Chat Generative Pre-trained Transformer (ChatGPT) have demonstrated potential for differential diagnosis in radiology. Previous studies investigating this potential primarily utilized quizzes from academic journals, which may not accurately represent real-world clinical scenarios.

    Purpose

    This study aimed to assess the diagnostic capabilities of ChatGPT using actual clinical radiology reports of brain tumors and compare its performance with that of neuroradiologists and general radiologists.

    Methods

    We consecutively collected brain MRI reports from preoperative brain tumor patients at Osaka Metropolitan University Hospital, taken from January to December 2021. ChatGPT and five radiologists were presented with the same findings from the reports and asked to suggest differential and final diagnoses. The pathological diagnosis of the excised tumor served as the ground truth. Chi-square tests and Fisher’s exact test were used for statistical analysis.

    Results

    In a study analyzing 99 radiological reports, ChatGPT achieved a final diagnostic accuracy of 75% (95% CI: 66, 83%), while radiologists’ accuracy ranged from 64% to 82%. ChatGPT’s final diagnostic accuracy using reports from neuroradiologists was higher at 82% (95% CI: 71, 89%), compared to 52% (95% CI: 33, 71%) using those from general radiologists with a p-value of 0.012. In the realm of differential diagnoses, ChatGPT’s accuracy was 95% (95% CI: 91, 99%), while radiologists’ fell between 74% and 88%. Notably, for these differential diagnoses, ChatGPT’s accuracy remained consistent whether reports were from neuroradiologists (96%, 95% CI: 89, 99%) or general radiologists (91%, 95% CI: 73, 98%) with a p-value of 0.33.

    Conclusion

    ChatGPT exhibited good diagnostic capability, comparable to neuroradiologists in differentiating brain tumors from MRI reports. ChatGPT can be a second opinion for neuroradiologists on final diagnoses and a guidance tool for general radiologists and residents, especially for understanding diagnostic cues and handling challenging cases.

    Summary

    This study evaluated ChatGPT’s diagnostic capabilities using real-world clinical MRI reports from brain tumor cases, revealing that its accuracy in interpreting brain tumors from MRI findings is competitive with radiologists.

    Key results

    ChatGPT demonstrated a diagnostic accuracy rate of 75% for final diagnoses based on preoperative MRI findings from 99 brain tumor cases, competing favorably with five radiologists whose accuracies ranged between 64% and 82%. For differential diagnoses, ChatGPT achieved a remarkable 95% accuracy, outperforming several of the radiologists.

    Radiology reports from neuroradiologists and general radiologists showed varying accuracy when input into ChatGPT. Reports from neuroradiologists resulted in higher diagnostic accuracy for final diagnoses, while there was no difference in accuracy for differential diagnoses between neuroradiologists and general radiologists.

    DOI: 10.1101/2023.10.27.23297585

  • New trend in artificial intelligence-based assistive technology for thoracic imaging. Reviewed

    Masahiro Yanagawa, Rintaro Ito, Taiki Nozaki, Tomoyuki Fujioka, Akira Yamada, Shohei Fujita, Koji Kamagata, Yasutaka Fushimi, Takahiro Tsuboyama, Yusuke Matsui, Fuminari Tatsugami, Mariko Kawamura, Daiju Ueda, Noriyuki Fujima, Takeshi Nakaura, Kenji Hirata, Shinji Naganawa

    La Radiologia medica   128 ( 10 )   1236 - 1249   2023.10( ISSN:00338362

     More details

    Publishing type:Research paper (scientific journal)   International / domestic magazine:International journal  

    Although there is no solid agreement for artificial intelligence (AI), it refers to a computer system with intelligence similar to that of humans. Deep learning appeared in 2006, and more than 10 years have passed since the third AI boom was triggered by improvements in computing power, algorithm development, and the use of big data. In recent years, the application and development of AI technology in the medical field have intensified internationally. There is no doubt that AI will be used in clinical practice to assist in diagnostic imaging in the future. In qualitative diagnosis, it is desirable to develop an explainable AI that at least represents the basis of the diagnostic process. However, it must be kept in mind that AI is a physician-assistant system, and the final decision should be made by the physician while understanding the limitations of AI. The aim of this article is to review the application of AI technology in diagnostic imaging from PubMed database while particularly focusing on diagnostic imaging in thorax such as lesion detection and qualitative diagnosis in order to help radiologists and clinicians to become more familiar with AI in thorax.

    DOI: 10.1007/s11547-023-01691-w

    PubMed

  • From FDG and beyond: the evolving potential of nuclear medicine. Reviewed

    Kenji Hirata, Koji Kamagata, Daiju Ueda, Masahiro Yanagawa, Mariko Kawamura, Takeshi Nakaura, Rintaro Ito, Fuminari Tatsugami, Yusuke Matsui, Akira Yamada, Yasutaka Fushimi, Taiki Nozaki, Shohei Fujita, Tomoyuki Fujioka, Takahiro Tsuboyama, Noriyuki Fujima, Shinji Naganawa

    Annals of nuclear medicine   37 ( 11 )   583 - 595   2023.09( ISSN:09147187

     More details

    Publishing type:Research paper (scientific journal)   International / domestic magazine:Domestic journal  

    The radiopharmaceutical 2-[fluorine-18]fluoro-2-deoxy-D-glucose (FDG) has been dominantly used in positron emission tomography (PET) scans for over 20 years, and due to its vast utility its applications have expanded and are continuing to expand into oncology, neurology, cardiology, and infectious/inflammatory diseases. More recently, the addition of artificial intelligence (AI) has enhanced nuclear medicine diagnosis and imaging with FDG-PET, and new radiopharmaceuticals such as prostate-specific membrane antigen (PSMA) and fibroblast activation protein inhibitor (FAPI) have emerged. Nuclear medicine therapy using agents such as [177Lu]-dotatate surpasses conventional treatments in terms of efficacy and side effects. This article reviews recently established evidence of FDG and non-FDG drugs and anticipates the future trajectory of nuclear medicine.

    DOI: 10.1007/s12149-023-01865-6

    PubMed

  • Chest radiography as a biomarker of ageing: artificial intelligence-based, multi-institutional model development and validation in Japan Reviewed

    Yasuhito Mitsuyama, Toshimasa Matsumoto, Hiroyuki Tatekawa, Shannon L Walston, Tatsuo Kimura, Akira Yamamoto, Toshio Watanabe, Yukio Miki, Daiju Ueda

    The Lancet Healthy Longevity   4 ( 9 )   e478 - e486   2023.09( ISSN:2666-7568

     More details

    Authorship:Last author, Corresponding author   Publishing type:Research paper (scientific journal)   International / domestic magazine:International journal  

    DOI: 10.1016/s2666-7568(23)00133-2

    PubMed

  • Comparison of the Diagnostic Performance from Patient’s Medical History and Imaging Findings between GPT-4 based ChatGPT and Radiologists in Challenging Neuroradiology Cases

    Daisuke Horiuchi, Hiroyuki Tatekawa, Tatsushi Oura, Satoshi Oue, Shannon L Walston, Hirotaka Takita, Shu Matsushita, Yasuhito Mitsuyama, Taro Shimono, Yukio Miki, Daiju Ueda

    medRxiv   2023.08

     More details

    Authorship:Last author, Corresponding author  

    Abstract

    Purpose

    To compare the diagnostic performance between Chat Generative Pre-trained Transformer (ChatGPT), based on the GPT-4 architecture, and radiologists from patient’s medical history and imaging findings in challenging neuroradiology cases.

    Methods

    We collected 30 consecutive “Freiburg Neuropathology Case Conference” cases from the journal Clinical Neuroradiology between March 2016 and June 2023. GPT-4 based ChatGPT generated diagnoses from the patient’s provided medical history and imaging findings for each case, and the diagnostic accuracy rate was determined based on the published ground truth. Three radiologists with different levels of experience (2, 4, and 7 years of experience, respectively) independently reviewed all the cases based on the patient’s provided medical history and imaging findings, and the diagnostic accuracy rates were evaluated. The Chi-square tests were performed to compare the diagnostic accuracy rates between ChatGPT and each radiologist.

    Results

    ChatGPT achieved an accuracy rate of 23% (7/30 cases). Radiologists achieved the following accuracy rates: a junior radiology resident had 27% (8/30) accuracy, a senior radiology resident had 30% (9/30) accuracy, and a board-certified radiologist had 47% (14/30) accuracy. ChatGPT’s diagnostic accuracy rate was lower than that of each radiologist, although the difference was not significant (p= 0.99, 0.77, and 0.10, respectively).

    Conclusion

    The diagnostic performance of GPT-4 based ChatGPT did not reach the performance level of either junior/senior radiology residents or board-certified radiologists in challenging neuroradiology cases. While ChatGPT holds great promise in the field of neuroradiology, radiologists should be aware of its current performance and limitations for optimal utilization.

    DOI: 10.1101/2023.08.28.23294607

  • Fairness of artificial intelligence in healthcare: review and recommendations. Invited Reviewed

    Daiju Ueda, Taichi Kakinuma, Shohei Fujita, Koji Kamagata, Yasutaka Fushimi, Rintaro Ito, Yusuke Matsui, Taiki Nozaki, Takeshi Nakaura, Noriyuki Fujima, Fuminari Tatsugami, Masahiro Yanagawa, Kenji Hirata, Akira Yamada, Takahiro Tsuboyama, Mariko Kawamura, Tomoyuki Fujioka, Shinji Naganawa

    Japanese journal of radiology   42 ( 1 )   3 - 15   2023.08( ISSN:18671071

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Research paper (scientific journal)   International / domestic magazine:Domestic journal  

    In this review, we address the issue of fairness in the clinical integration of artificial intelligence (AI) in the medical field. As the clinical adoption of deep learning algorithms, a subfield of AI, progresses, concerns have arisen regarding the impact of AI biases and discrimination on patient health. This review aims to provide a comprehensive overview of concerns associated with AI fairness; discuss strategies to mitigate AI biases; and emphasize the need for cooperation among physicians, AI researchers, AI developers, policymakers, and patients to ensure equitable AI integration. First, we define and introduce the concept of fairness in AI applications in healthcare and radiology, emphasizing the benefits and challenges of incorporating AI into clinical practice. Next, we delve into concerns regarding fairness in healthcare, addressing the various causes of biases in AI and potential concerns such as misdiagnosis, unequal access to treatment, and ethical considerations. We then outline strategies for addressing fairness, such as the importance of diverse and representative data and algorithm audits. Additionally, we discuss ethical and legal considerations such as data privacy, responsibility, accountability, transparency, and explainability in AI. Finally, we present the Fairness of Artificial Intelligence Recommendations in healthcare (FAIR) statement to offer best practices. Through these efforts, we aim to provide a foundation for discussing the responsible and equitable implementation and deployment of AI in healthcare.

    DOI: 10.1007/s11604-023-01474-3

    PubMed

  • AI-based Virtual Synthesis of Methionine PET from Contrast-enhanced MRI: Development and External Validation Study. Reviewed

    Hirotaka Takita, Toshimasa Matsumoto, Hiroyuki Tatekawa, Yutaka Katayama, Kosuke Nakajo, Takehiro Uda, Yasuhito Mitsuyama, Shannon L Walston, Yukio Miki, Daiju Ueda

    Radiology   308 ( 2 )   e223016   2023.08( ISSN:00338419

     More details

    Authorship:Last author, Corresponding author   Publishing type:Research paper (scientific journal)   International / domestic magazine:International journal  

    Background Carbon 11 (11C)-methionine is a useful PET radiotracer for the management of patients with glioma, but radiation exposure and lack of molecular imaging facilities limit its use. Purpose To generate synthetic methionine PET images from contrast-enhanced (CE) MRI through an artificial intelligence (AI)-based image-to-image translation model and to compare its performance for grading and prognosis of gliomas with that of real PET. Materials and Methods An AI-based model to generate synthetic methionine PET images from CE MRI was developed and validated from patients who underwent both methionine PET and CE MRI at a university hospital from January 2007 to December 2018 (institutional data set). Pearson correlation coefficients for the maximum and mean tumor to background ratio (TBRmax and TBRmean, respectively) of methionine uptake and the lesion volume between synthetic and real PET were calculated. Two additional open-source glioma databases of preoperative CE MRI without methionine PET were used as the external test set. Using the TBRs, the area under the receiver operating characteristic curve (AUC) for classifying high-grade and low-grade gliomas and overall survival were evaluated. Results The institutional data set included 362 patients (mean age, 49 years ± 19 [SD]; 195 female, 167 male; training, n = 294; validation, n = 34; test, n = 34). In the internal test set, Pearson correlation coefficients were 0.68 (95% CI: 0.47, 0.81), 0.76 (95% CI: 0.59, 0.86), and 0.92 (95% CI: 0.85, 0.95) for TBRmax, TBRmean, and lesion volume, respectively. The external test set included 344 patients with gliomas (mean age, 53 years ± 15; 192 male, 152 female; high grade, n = 269). The AUC for TBRmax was 0.81 (95% CI: 0.75, 0.86) and the overall survival analysis showed a significant difference between the high (2-year survival rate, 27%) and low (2-year survival rate, 71%; P < .001) TBRmax groups. Conclusion The AI-based model-generated synthetic methionine PET images strongly correlated with real PET images and showed good performance for glioma grading and prognostication. Published under a CC BY 4.0 license. Supplemental material is available for this article.

    DOI: 10.1148/radiol.223016

    PubMed

  • Artificial intelligence-based model to classify cardiac functions from chest radiographs: a multi-institutional, retrospective model development and validation study Reviewed

    Daiju Ueda, Toshimasa Matsumoto, Shoichi Ehara, Akira Yamamoto, Shannon L Walston, Asahiro Ito, Taro Shimono, Masatsugu Shiba, Tohru Takeshita, Daiju Fukuda, Yukio Miki

    The Lancet Digital Health   5 ( 8 )   e525 - e533   2023.08( ISSN:2589-7500

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Research paper (scientific journal)   International / domestic magazine:International journal  

    DOI: 10.1016/s2589-7500(23)00107-3

    PubMed

  • The Association of Metabolic Brain MRI, Amyloid PET, and Clinical Factors: A Study of Alzheimer's Disease and Normal Controls From the Open Access Series of Imaging Studies Dataset Reviewed

    Shu Matsushita, Hiroyuki Tatekawa, Daiju Ueda, Hirotaka Takita, Daisuke Horiuchi, Taro Tsukamoto, Taro Shimono, Yukio Miki

    Journal of Magnetic Resonance Imaging   59 ( 4 )   1341 - 1348   2023.07( ISSN:1053-1807 ( eISSN:1522-2586

     More details

    Publishing type:Research paper (scientific journal)  

    DOI: 10.1002/jmri.28892

    PubMed

  • Recent advances in artificial intelligence for cardiac CT: Enhancing diagnosis and prognosis prediction Reviewed

    Fuminari Tatsugami, Takeshi Nakaura, Masahiro Yanagawa, Shohei Fujita, Koji Kamagata, Rintaro Ito, Mariko Kawamura, Yasutaka Fushimi, Daiju Ueda, Yusuke Matsui, Akira Yamada, Noriyuki Fujima, Tomoyuki Fujioka, Taiki Nozaki, Takahiro Tsuboyama, Kenji Hirata, Shinji Naganawa

    Diagnostic and Interventional Imaging   104 ( 11 )   521 - 528   2023.07( ISSN:2211-5684

     More details

    Publishing type:Research paper (scientific journal)  

    DOI: 10.1016/j.diii.2023.06.011

    PubMed

  • ChatGPT's Diagnostic Performance from Patient History and Imaging Findings on the Diagnosis Please Quizzes. Reviewed

    Daiju Ueda, Yasuhito Mitsuyama, Hirotaka Takita, Daisuke Horiuchi, Shannon L Walston, Hiroyuki Tatekawa, Yukio Miki

    Radiology   308 ( 1 )   e231040   2023.07( ISSN:00338419

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Research paper (scientific journal)   International / domestic magazine:International journal  

    DOI: 10.1148/radiol.231040

    PubMed

  • Deep learning for pneumothorax diagnosis: a systematic review and meta-analysis Reviewed

    Takahiro Sugibayashi, Shannon L. Walston, Toshimasa Matsumoto, Yasuhito Mitsuyama, Yukio Miki, Daiju Ueda

    European Respiratory Review   32 ( 168 )   220259 - 220259   2023.06( ISSN:0905-9180 ( eISSN:1600-0617

     More details

    Authorship:Last author, Corresponding author   Publishing type:Research paper (scientific journal)  

    Background

    Deep learning (DL), a subset of artificial intelligence (AI), has been applied to pneumothorax diagnosis to aid physician diagnosis, but no meta-analysis has been performed.

    Methods

    A search of multiple electronic databases through September 2022 was performed to identify studies that applied DL for pneumothorax diagnosis using imaging. Meta-analysisviaa hierarchical model to calculate the summary area under the curve (AUC) and pooled sensitivity and specificity for both DL and physicians was performed. Risk of bias was assessed using a modified Prediction Model Study Risk of Bias Assessment Tool.

    Results

    In 56 of the 63 primary studies, pneumothorax was identified from chest radiography. The total AUC was 0.97 (95% CI 0.96–0.98) for both DL and physicians. The total pooled sensitivity was 84% (95% CI 79–89%) for DL and 85% (95% CI 73–92%) for physicians and the pooled specificity was 96% (95% CI 94–98%) for DL and 98% (95% CI 95–99%) for physicians. More than half of the original studies (57%) had a high risk of bias.

    Conclusions

    Our review found the diagnostic performance of DL models was similar to that of physicians, although the majority of studies had a high risk of bias. Further pneumothorax AI research is needed.

    DOI: 10.1183/16000617.0259-2022

    PubMed

  • Clinical applications of artificial intelligence in liver imaging Reviewed

    Akira Yamada, Koji Kamagata, Kenji Hirata, Rintaro Ito, Takeshi Nakaura, Daiju Ueda, Shohei Fujita, Yasutaka Fushimi, Noriyuki Fujima, Yusuke Matsui, Fuminari Tatsugami, Taiki Nozaki, Tomoyuki Fujioka, Masahiro Yanagawa, Takahiro Tsuboyama, Mariko Kawamura, Shinji Naganawa

    La radiologia medica   128 ( 6 )   655 - 667   2023.05( ISSN:00338362 ( eISSN:1826-6983

     More details

    Publishing type:Research paper (scientific journal)  

    DOI: 10.1007/s11547-023-01638-1

    PubMed

    Other URL: https://link.springer.com/article/10.1007/s11547-023-01638-1/fulltext.html

  • Evaluating GPT-4-based ChatGPT's Clinical Potential on the NEJM Quiz

    Daiju Ueda, Shannon Walston, Toshimasa Matsumoto, Ryo Deguchi, Hiroyuki Tatekawa, Yukio Miki

    medRxiv   2023.05

     More details

    Authorship:Lead author, Corresponding author  

    Background GPT-4-based ChatGPT demonstrates significant potential in various industries; however, its potential clinical applications remain largely unexplored. Methods We employed the New England Journal of Medicine (NEJM) quiz "Image Challenge" from October 2021 to March 2023 to assess ChatGPT's clinical capabilities. The quiz, designed for healthcare professionals, tests the ability to analyze clinical scenarios and make appropriate decisions. We evaluated ChatGPT's performance on the NEJM quiz, analyzing its accuracy rate by questioning type and specialty after excluding quizzes which were impossible to answer without images. The NEJM quiz has five multiple-choice options, but ChatGPT was first asked to answer without choices, and then given the choices to answer afterwards, in order to evaluate the accuracy in both scenarios. Results ChatGPT achieved an 87% accuracy without choices and a 97% accuracy with choices, after excluding 16 image-based quizzes. Upon analyzing performance by quiz type, ChatGPT excelled in the Diagnosis category, attaining 89% accuracy without choices and 98% with choices. Although other categories featured fewer cases, ChatGPT's performance remained consistent. It demonstrated strong performance across the majority of medical specialties; however, Genetics had the lowest accuracy at 67%. Conclusion ChatGPT demonstrates potential for clinical application, suggesting its usefulness in supporting healthcare professionals and enhancing AI-driven healthcare.

    DOI: 10.1101/2023.05.04.23289493

  • Deep learning-based screening tool for rotator cuff tears on shoulder radiography Reviewed

    Ryosuke Iio, Daiju Ueda, Toshimasa Matsumoto, Tomoya Manaka, Katsumasa Nakazawa, Yoichi Ito, Yoshihiro Hirakawa, Akira Yamamoto, Masatsugu Shiba, Hiroaki Nakamura

    Journal of Orthopaedic Science   29 ( 3 )   828 - 834   2023.05( ISSN:0949-2658

     More details

    Publishing type:Research paper (scientific journal)  

    DOI: 10.1016/j.jos.2023.05.004

    PubMed

  • Deep Learning Model Based on Contrast-Enhanced Computed Tomography Imaging to Predict Postoperative Early Recurrence after the Curative Resection of a Solitary Hepatocellular Carcinoma Reviewed

    Masahiko Kinoshita, Daiju Ueda, Toshimasa Matsumoto, Hiroji Shinkawa, Akira Yamamoto, Masatsugu Shiba, Takuma Okada, Naoki Tani, Shogo Tanaka, Kenjiro Kimura, Go Ohira, Kohei Nishio, Jun Tauchi, Shoji Kubo, Takeaki Ishizawa

    Cancers   15 ( 7 )   2140 - 2140   2023.04( ISSN:2072-6694 ( eISSN:2072-6694

     More details

    Publishing type:Research paper (scientific journal)  

    We aimed to develop the deep learning (DL) predictive model for postoperative early recurrence (within 2 years) of hepatocellular carcinoma (HCC) based on contrast-enhanced computed tomography (CECT) imaging. This study included 543 patients who underwent initial hepatectomy for HCC and were randomly classified into training, validation, and test datasets at a ratio of 8:1:1. Several clinical variables and arterial CECT images were used to create predictive models for early recurrence. Artificial intelligence models were implemented using convolutional neural networks and multilayer perceptron as a classifier. Furthermore, the Youden index was used to discriminate between high- and low-risk groups. The importance values of each explanatory variable for early recurrence were calculated using permutation importance. The DL predictive model for postoperative early recurrence was developed with the area under the curve values of 0.71 (test datasets) and 0.73 (validation datasets). Postoperative early recurrence incidences in the high- and low-risk groups were 73% and 30%, respectively (p = 0.0057). Permutation importance demonstrated that among the explanatory variables, the variable with the highest importance value was CECT imaging analysis. We developed a DL model to predict postoperative early HCC recurrence. DL-based analysis is effective for determining the treatment strategies in patients with HCC.

    DOI: 10.3390/cancers15072140

    PubMed

  • diffusion tensor image analysis along the perivascular space(DTI-ALPS) indexで再現性の改善 OASIS-3データセットを用いた再構成技術による解析法(Improved reproducibility of diffusion tensor image analysis along the perivascular space(DTI-ALPS) index: an analysis of reorientation technique of the OASIS-3 dataset)

    Tatekawa Hiroyuki, Matsushita Shu, Ueda Daiju, Takita Hirotaka, Horiuchi Daisuke, Atsukawa Natsuko, Morishita Yuka, Tsukamoto Taro, Shimono Taro, Miki Yukio

    Japanese Journal of Radiology   41 ( 4 )   393 - 400   2023.04( ISSN:1867-1071

     More details

    拡散テンソルイメージング(DTI)データの画像再構成により、analysis along the perivascular space(ALPS) indexにおいて再現性の改善を試みた。なお、本報では脳MRI画像データが登録されたオープンデータベースOASIS-3データセットから、認知機能が正常な234名(男性123名、女性111名、年齢42~92歳)の画像データを用いて実施した。また、DTIのベクトル情報を他の血管周囲腔に位置合わせする画像再構成技術を適用し、元データのALPS indexと再構成したALPS indexを新たに求め、再構成処理したdiffusivity mapを作成した。これらデータ間を比較した結果、再構成処理したALPS indexの変動は元データのALPS indexに比べ有意に小さく、再構成技術により、頭部回転を有する被験者でも良好ないし優れたALPS index数値の再現性が得られた。特にx軸で頭部回転が観察された被験者では、元データALPS indexと再構成したALPS indexを比較したBland-Altmanプロットにより、広範囲に及ぶ95%一致限界が認められたことから、x軸の頭部回転はALPS indexの算出に著しく影響を及ぼすことが示唆された。以上より、本法による再構成技術を適用したDTI-ALPS index算出によりALPSの再現性が改善され、再構成処理したdiffusivity mapも作成可能となった。

  • Deep Learning-Based Time-to-Death Prediction Model for COVID-19 Patients Using Clinical Data and Chest Radiographs. Reviewed

    Toshimasa Matsumoto, Shannon Leigh Walston, Michael Walston, Daijiro Kabata, Yukio Miki, Masatsugu Shiba, Daiju Ueda

    Journal of digital imaging   36 ( 1 )   178 - 188   2023.02( ISSN:0897-1889 ( eISSN:1618-727X

     More details

    Authorship:Last author, Corresponding author   Publishing type:Research paper (scientific journal)   International / domestic magazine:International journal  

    Accurate estimation of mortality and time to death at admission for COVID-19 patients is important and several deep learning models have been created for this task. However, there are currently no prognostic models which use end-to-end deep learning to predict time to event for admitted COVID-19 patients using chest radiographs and clinical data. We retrospectively implemented a new artificial intelligence model combining DeepSurv (a multiple-perceptron implementation of the Cox proportional hazards model) and a convolutional neural network (CNN) using 1356 COVID-19 inpatients. For comparison, we also prepared DeepSurv only with clinical data, DeepSurv only with images (CNNSurv), and Cox proportional hazards models. Clinical data and chest radiographs at admission were used to estimate patient outcome (death or discharge) and duration to the outcome. The Harrel's concordance index (c-index) of the DeepSurv with CNN model was 0.82 (0.75-0.88) and this was significantly higher than the DeepSurv only with clinical data model (c-index = 0.77 (0.69-0.84), p = 0.011), CNNSurv (c-index = 0.70 (0.63-0.79), p = 0.001), and the Cox proportional hazards model (c-index = 0.71 (0.63-0.79), p = 0.001). These results suggest that the time-to-event prognosis model became more accurate when chest radiographs and clinical data were used together.

    DOI: 10.1007/s10278-022-00691-y

    PubMed

    Other URL: https://link.springer.com/article/10.1007/s10278-022-00691-y/fulltext.html

  • Response: Evaluating Diagnostic Performance of ChatGPT in Radiology: Delving into Methods

    Ueda D.

    Radiology   308 ( 3 )   1 - 2   2023( ISSN:00338419

     More details

  • Application of AI-driven Image to Image Translation Techniques in Neuroradiology

    Takita Hirotaka, Ueda Daiju

    Medical Imaging and Information Sciences   40 ( 4 )   66 - 74   2023( ISSN:09101543 ( eISSN:18804977

     More details

    <p>In recent years, the rapid evolution of artificial intelligence (AI) has brought about a revolution in medical research. In particular, the application of AI technology to medical imaging is expanding rapidly, with image-to-image translation technique gaining significant attention. Image-to-image translation technique allows for a wide range of applications, such as converting between different imaging modalities and removing artifacts. It is expected to open up new perspectives that go beyond the traditional framework of medical imaging. Using image-to-image translation models, it’s possible to generate synthetic PET from MRI images, or convert images with artifacts to those without, potentially contributing to improved diagnostic accuracy and optimization of treatment plans. In this article, we introduce two papers we published applying image-to-image translation technique in the field of neuroradiology: a study on generating synthetic methionine PET using MRI, and a study on producing Digital Subtraction Angiography (DSA) without misregistration artifacts.</p>

    DOI: 10.11318/mii.40.66

  • Current State of Artificial Intelligence in Clinical Applications for Head and Neck MR Imaging Reviewed

    Noriyuki Fujima, Koji Kamagata, Daiju Ueda, Shohei Fujita, Yasutaka Fushimi, Masahiro Yanagawa, Rintaro Ito, Takahiro Tsuboyama, Mariko Kawamura, Takeshi Nakaura, Akira Yamada, Taiki Nozaki, Tomoyuki Fujioka, Yusuke Matsui, Kenji Hirata, Fuminari Tatsugami, Shinji Naganawa

    Magnetic Resonance in Medical Sciences   22 ( 4 )   401 - 414   2023( ISSN:1347-3182 ( eISSN:1880-2206

     More details

    Publishing type:Research paper (scientific journal)   International / domestic magazine:Domestic journal  

    DOI: 10.2463/mrms.rev.2023-0047

  • Nervus: A Comprehensive Deep Learning Classification, Regression, and Prognostication Tool for both Medical Image and Clinical Data Analysis

    Toshimasa Matsumoto, Shannon L Walston, Yukio Miki, Daiju Ueda

    arXiv   2022.12

     More details

    Authorship:Last author, Corresponding author  

    DOI: 10.48550/arXiv.2212.11113

  • Improved reproducibility of diffusion tensor image analysis along the perivascular space (DTI-ALPS) index: an analysis of reorientation technique of the OASIS-3 dataset Reviewed

    Hiroyuki Tatekawa, Shu Matsushita, Daiju Ueda, Hirotaka Takita, Daisuke Horiuchi, Natsuko Atsukawa, Yuka Morishita, Taro Tsukamoto, Taro Shimono, Yukio Miki

    Japanese Journal of Radiology   41 ( 4 )   393 - 400   2022.12( ISSN:1867-1071 ( eISSN:1867-108X

     More details

    Publishing type:Research paper (scientific journal)  

    Abstract

    Purpose

    Diffusion tensor image analysis along the perivascular space (DTI-ALPS) index is intended to reflect the glymphatic function of the brain; however, head rotation may reduce reproducibility and reliability. This study aimed to evaluate whether reorientation of DTI data improves the reproducibility of the ALPS index using the OASIS-3 dataset.

    Materials and methods

    234 cognitively normal subjects from the OASIS-3 dataset were included. Original and reoriented ALPS indices were calculated using a technique that registered vector information of DTI to another space and created reoriented diffusivity maps. The F test was used to compare variances of the original and reoriented ALPS indices. Subsequently, subjects with head rotation around the z- (inferior-superior; n = 43) or x axis (right-left; n = 25) and matched subjects with neutral head position were selected for evaluation of intra- and inter-rater reliability. Intraclass correlation coefficients (ICCs) of the original and reoriented ALPS indices for participants with head rotation and neutral head position were calculated separately. The Bland–Altman plot comparing the original and reoriented ALPS indices was also evaluated.

    Results

    The reoriented ALPS index exhibited a significantly smaller variance than the original ALPS index (p &lt; 0.001). For intra- and inter-reliability, the reorientation technique showed good-to-excellent reproducibility in calculating the ALPS index even in subjects with head rotation (ICCs of original ALPS index: 0.52–0.81; ICCs of reoriented ALPS index: &gt; 0.85). A wider range of the 95% limit of agreement of the Bland–Altman plot for subjects with x axis rotation was identified, indicating that x axis rotation may remarkably affect calculation of the ALPS index.

    Conclusion

    The technique used in this study enabled the creation of reoriented diffusivity maps and improved reproducibility in calculating the ALPS index.

    DOI: 10.1007/s11604-022-01370-2

    PubMed

    Other URL: https://link.springer.com/article/10.1007/s11604-022-01370-2/fulltext.html

  • Artificial intelligence-based model for COVID-19 prognosis incorporating chest radiographs and clinical data; a retrospective model development and validation study. Reviewed

    Shannon L Walston, Toshimasa Matsumoto, Yukio Miki, Daiju Ueda

    The British journal of radiology   95 ( 1140 )   20220058 - 20220058   2022.12( ISSN:0007-1285 ( eISSN:1748-880X

     More details

    Authorship:Last author, Corresponding author   Publishing type:Research paper (scientific journal)   International / domestic magazine:International journal  

    Objectives:

    The purpose of this study was to develop an artificial intelligence-based model to prognosticate COVID-19 patients at admission by combining clinical data and chest radiographs.

    Methods:

    This retrospective study used the Stony Brook University COVID-19 dataset of 1384 inpatients. After exclusions 1356 patients were randomly divided into training (1083) and test datasets (273). We implemented three artificial intelligence models which classified mortality, ICU admission, or ventilation risk. Each model had three submodels with different inputs: clinical data, chest radiographs, and both. We showed the importance of the variables using SHAP values.

    Results:

    The mortality prediction model was best overall with area under the curve, sensitivity, specificity, and accuracy of 0.79 (0.72–0.86), 0.74 (0.68–0.79), 0.77 (0.61–0.88), and 0.74 (0.69–0.79) for the clinical data-based model; 0.77 (0.69–0.85), 0.67 (0.61–0.73), 0.81 (0.67–0.92), 0.70 (0.64–0.75) for the image-based model, and 0.86 (0.81–0.91), 0.76 (0.70–0.81), 0.77 (0.61–0.88), 0.76 (0.70–0.81) for the mixed model. The mixed model had the best performance (p value &lt; 0.05). The radiographs ranked fourth for prognostication overall, and first of the inpatient tests assessed.

    Conclusions:

    These results suggest that prognosis models become more accurate if AI-derived chest radiograph features and clinical data are used together.

    Advances in knowledge:

    This AI model evaluates chest radiographs together with clinical data in order to classify patients as having high or low mortality risk. This work shows that chest radiographs taken at admission have significant COVID-19 prognostic information compared to clinical data other than age and sex.

    DOI: 10.1259/bjr.20220058

    PubMed

  • 多列検出器コンピューター断層撮影により診断されたS状結腸間膜ヘルニアによる絞扼性小腸閉塞 症例報告(Strangulated Small-bowel Obstruction due to Transmesosigmoid Hernia Diagnosed with Multidetector Computed Tomography: A Case Report)

    Takeshita Tohru, Matsushima Hisakazu, Ikeda Kimimasa, Noma Toshiki, Goto Takuya, Ueda Daiju

    Osaka City Medical Journal   68 ( 2 )   91 - 98   2022.12( ISSN:0030-6096

     More details

    症例は79歳女性。50歳代時に虫垂炎のため虫垂切除を行った。75歳時に子宮頸部扁平上皮細胞癌と診断され、放射線療法と化学療法を行い、治療の42ヵ月後の経過観察では再発は認められなかった。診察により左下部に圧痛が認められた。上腹部レントゲン検査でニボーを伴う弛緩性ループが観察され、当初は癒着性の小腸閉塞と診断された。保存療法では症状が変化しなかったため、腹部と骨盤の造影多列検出器コンピューター断層撮影を行った。その結果、S状結腸間膜の欠如による腸間膜脂肪組織と腸間膜血管による小腸への陥入が観察され、絞扼性小腸閉塞(TMSH)と診断した。緊急開腹手術を行い、TMSHが確認された。小腸の壊死部分を切除し、術後9日目に退院した。

  • Deep learning-based algorithm for lung cancer detection on chest radiographs using the segmentation method Reviewed

    Akitoshi Shimazaki, Daiju Ueda, Antoine Choppin, Akira Yamamoto, Takashi Honjo, Yuki Shimahara, Yukio Miki

    Scientific Reports   12 ( 1 )   2022.12( eISSN:2045-2322

     More details

    Authorship:Corresponding author   Publishing type:Research paper (scientific journal)  

    <title>Abstract</title>We developed and validated a deep learning (DL)-based model using the segmentation method and assessed its ability to detect lung cancer on chest radiographs. Chest radiographs for use as a training dataset and a test dataset were collected separately from January 2006 to June 2018 at our hospital. The training dataset was used to train and validate the DL-based model with five-fold cross-validation. The model sensitivity and mean false positive indications per image (mFPI) were assessed with the independent test dataset. The training dataset included 629 radiographs with 652 nodules/masses and the test dataset included 151 radiographs with 159 nodules/masses. The DL-based model had a sensitivity of 0.73 with 0.13 mFPI in the test dataset. Sensitivity was lower in lung cancers that overlapped with blind spots such as pulmonary apices, pulmonary hila, chest wall, heart, and sub-diaphragmatic space (0.50–0.64) compared with those in non-overlapped locations (0.87). The dice coefficient for the 159 malignant lesions was on average 0.52. The DL-based model was able to detect lung cancers on chest radiographs, with low mFPI.

    DOI: 10.1038/s41598-021-04667-w

    Other URL: https://www.nature.com/articles/s41598-021-04667-w

  • Visual and quantitative evaluation of microcalcifications in mammograms with deep learning-based super-resolution. Reviewed

    Takashi Honjo, Daiju Ueda, Yutaka Katayama, Akitoshi Shimazaki, Atsushi Jogo, Ken Kageyama, Kazuki Murai, Hiroyuki Tatekawa, Shinya Fukumoto, Akira Yamamoto, Yukio Miki

    European journal of radiology   154   110433 - 110433   2022.09( ISSN:0720-048X

     More details

    Authorship:Corresponding author   Publishing type:Research paper (scientific journal)   International / domestic magazine:International journal  

    PURPOSE: To evaluate visually and quantitatively the performance of a deep-learning-based super-resolution (SR) model for microcalcifications in digital mammography. METHOD: Mammograms were consecutively collected from 5080 patients who underwent breast cancer screening from January 2015 to March 2017. Of these, 93 patients (136 breasts, mean age, 50 ± 7 years) had microcalcifications in their breasts on mammograms. We applied an artificial intelligence model known as a fast SR convolutional neural network to the mammograms. SR and original mammograms were visually evaluated by four breast radiologists using a 5-point scale (1: original mammograms are strongly preferred, 5: SR mammograms are strongly preferred) for the detection, diagnostic quality, contrast, sharpness, and noise of microcalcifications. Mammograms were quantitatively evaluated using a perception-based image-quality evaluator (PIQE). RESULTS: All radiologists rated the SR mammograms better than the original ones in terms of detection, diagnostic quality, contrast, and sharpness of microcalcifications. These ratings were significantly different according to the Wilcoxon signed-rank test (p <.001), while the noise score of the three radiologists was significantly lower (p <.001). According to PIQE, SR mammograms were rated better than the original mammograms, showing a significant difference by paired t-test (p <.001). CONCLUSION: An SR model based on deep learning can improve the visibility of microcalcifications in mammography and help detect and diagnose them in mammograms.

    DOI: 10.1016/j.ejrad.2022.110433

    PubMed

  • Artificial intelligence-based detection of atrial fibrillation from chest radiographs. Reviewed

    Toshimasa Matsumoto, Shoichi Ehara, Shannon L Walston, Yasuhito Mitsuyama, Yukio Miki, Daiju Ueda

    European radiology   32 ( 9 )   5890 - 5897   2022.09( eISSN:1432-1084

     More details

    Authorship:Last author, Corresponding author   Publishing type:Research paper (scientific journal)   International / domestic magazine:International journal  

    OBJECTIVE: The purpose of this study was to develop an artificial intelligence (AI)-based model to detect features of atrial fibrillation (AF) on chest radiographs. METHODS: This retrospective study included consecutively collected chest radiographs of patients who had echocardiography at our institution from July 2016 to May 2019. Eligible radiographs had been acquired within 30 days of the echocardiography. These radiographs were labeled as AF-positive or AF-negative based on the associated electronic medical records; then, each patient was randomly divided into training, validation, and test datasets in an 8:1:1 ratio. A deep learning-based model to classify radiographs as with or without AF was trained on the training dataset, tuned with the validation dataset, and evaluated with the test dataset. RESULTS: The training dataset included 11,105 images (5637 patients; 3145 male, mean age ± standard deviation, 68 ± 14 years), the validation dataset included 1388 images (704 patients, 397 male, 67 ± 14 years), and the test dataset included 1375 images (706 patients, 395 male, 68 ± 15 years). Applying the model to the validation and test datasets gave a respective area under the curve of 0.81 (95% confidence interval, 0.78-0.85) and 0.80 (0.76-0.84), sensitivity of 0.76 (0.70-0.81) and 0.70 (0.64-0.76), specificity of 0.75 (0.72-0.77) and 0.74 (0.72-0.77), and accuracy of 0.75 (0.72-0.77) and 0.74 (0.71-0.76). CONCLUSION: Our AI can identify AF on chest radiographs, which provides a new way for radiologists to infer AF. KEY POINTS: • A deep learning-based model was trained to detect atrial fibrillation in chest radiographs, showing that there are indicators of atrial fibrillation visible even on static images. • The validation and test datasets each gave a solid performance with area under the curve, sensitivity, and specificity of 0.81, 0.76, and 0.75, respectively, for the validation dataset, and 0.80, 0.70, and 0.74, respectively, for the test dataset. • The saliency maps highlighted anatomical areas consistent with those reported for atrial fibrillation on chest radiographs, such as the atria.

    DOI: 10.1007/s00330-022-08752-0

    PubMed

    Other URL: https://link.springer.com/article/10.1007/s00330-022-08752-0/fulltext.html

  • Maskless 2-Dimensional Digital Subtraction Angiography Generation Model for Abdominal Vasculature using Deep Learning. Reviewed

    Hiroki Yonezawa, Daiju Ueda, Akira Yamamoto, Ken Kageyama, Shannon Leigh Walston, Takehito Nota, Kazuki Murai, Satoyuki Ogawa, Etsuji Sohgawa, Atsushi Jogo, Daijiro Kabata, Yukio Miki

    Journal of vascular and interventional radiology : JVIR   33 ( 7 )   845 - 851   2022.07( ISSN:1051-0443

     More details

    Authorship:Corresponding author   Publishing type:Research paper (scientific journal)   International / domestic magazine:International journal  

    PURPOSE: To develop a deep learning (DL) model to generate synthetic, 2-dimensional subtraction angiograms free of artifacts from native abdominal angiograms. MATERIALS AND METHODS: In this retrospective study, 2-dimensional digital subtraction angiography (2D-DSA) images and native angiograms were consecutively collected from July 2019 to March 2020. Images were divided into motion-free (training, validation, and motion-free test datasets) and motion-artifact (motion-artifact test dataset) sets. A total of 3,185, 393, 383, and 345 images from 87 patients (mean age, 71 years ± 10; 64 men and 23 women) were included in the training, validation, motion-free, and motion-artifact test datasets, respectively. Native angiograms and 2D-DSA image pairs were used to train and validate an image-to-image translation model to generate synthetic DL-based subtraction angiography (DLSA) images. DLSA images were quantitatively evaluated by the peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) using the motion-free dataset and were qualitatively evaluated via visual assessments by radiologists with a numerical rating scale using the motion-artifact dataset. RESULTS: The DLSA images showed a mean PSNR (± standard deviation) of 43.05 dB ± 3.65 and mean SSIM of 0.98 ± 0.01, indicating high agreement with the original 2D-DSA images in the motion-free dataset. Qualitative visual evaluation by radiologists of the motion-artifact dataset showed that DLSA images contained fewer motion artifacts than 2D-DSA images. Additionally, DLSA images scored similar to or higher than 2D-DSA images for vascular visualization and clinical usefulness. CONCLUSIONS: The developed DL model generated synthetic, motion-free subtraction images from abdominal angiograms with similar imaging characteristics to 2D-DSA images.

    DOI: 10.1016/j.jvir.2022.03.010

    PubMed

  • 原発性副甲状腺機能亢進症患者への99mTc-MIBIシンチグラフィーによる副甲状腺腺腫の深層学習による検出(Deep learning-based detection of parathyroid adenoma by 99mTc-MIBI scintigraphy in patients with primary hyperparathyroidism)

    Yoshida Atsushi, Ueda Daiju, Higashiyama Shigeaki, Katayama Yutaka, Matsumoto Toshimasa, Yamanaga Takashi, Miki Yukio, Kawabe Joji

    Annals of Nuclear Medicine   36 ( 5 )   468 - 478   2022.05( ISSN:0914-7187

     More details

    副甲状腺機能亢進症患者の早期相ならびに後期相の99mTc-MIBIシンチグラフィー画像から副甲状腺腺腫を検出するため、深層学習(DL)をベースとしたモデルをそれぞれ開発し、検証した。DLモデルの学習データセットには患者192例(男性47例、女性145例、平均年齢64±13歳)から検出された165腺腫を選択し、検証データセットには、患者45例(男性8例、女性37例、平均年齢67±12歳)から検出された30腺腫とした。画像は2010年6月~2019年3月までの期間内に著者等の医療施設で、シンチグラフィーと超音波検査を受けた患者から収集し、試験データセットには、患者44例(男性6例、女性38例、平均年齢67±12歳)から検出された30腺腫を用いて解析した。その結果、初期相モデルによるシンチグラムでは病変をベースとした感度は82%[95%CI 72-92%]、1画像当りの平均偽陽性数(mFPI)は0.44で、後期相モデルではそれぞれ83%[95%CI 73-92%]、0.31であった。これらの所見から、99mTc-MIBIシンチグラフィー画像を用いて、本DLモデルを適用することにより、高感度に副甲状腺腺腫が検出されることが確認された。

  • Deep learning-based detection of parathyroid adenoma by 99mTc-MIBI scintigraphy in patients with primary hyperparathyroidism. Reviewed

    Atsushi Yoshida, Daiju Ueda, Shigeaki Higashiyama, Yutaka Katayama, Toshimasa Matsumoto, Takashi Yamanaga, Yukio Miki, Joji Kawabe

    Annals of nuclear medicine   36 ( 5 )   468 - 478   2022.05( ISSN:0914-7187 ( eISSN:1864-6433

     More details

    Authorship:Corresponding author   Publishing type:Research paper (scientific journal)   International / domestic magazine:Domestic journal  

    OBJECTIVE: It is important to detect parathyroid adenomas by parathyroid scintigraphy with 99m-technetium sestamibi (99mTc-MIBI) before surgery. This study aimed to develop and validate deep learning (DL)-based models to detect parathyroid adenoma in patients with primary hyperparathyroidism, from parathyroid scintigrams with 99mTc-MIBI. METHODS: DL-based models for detecting parathyroid adenoma in early- and late-phase parathyroid scintigrams were, respectively, developed and evaluated. The training dataset used to train the models was collected from 192 patients (165 adenoma cases, mean age: 64 years ± 13, 145 women) and the validation dataset used to tune the models was collected from 45 patients (30 adenoma cases, mean age: 67 years ± 12, 37 women). The images were collected from patients who were pathologically diagnosed with parathyroid adenomas or in whom no lesions could be detected by either parathyroid scintigraphy or ultrasonography at our institution from June 2010 to March 2019. The models were tested on a dataset collected from 44 patients (30 adenoma cases, mean age: 67 years ± 12, 38 women) who took scintigraphy from April 2019 to March 2020. The models' lesion-based sensitivity and mean false positive indications per image (mFPI) were assessed with the test dataset. RESULTS: The sensitivity was 82% [95% confidence interval 72-92%] with mFPI of 0.44 for the scintigrams of the early-phase model and 83% [73-92%] with mFPI of 0.31 for the scintigrams of the delayed-phase model in the test dataset, respectively. CONCLUSIONS: The DL-based models were able to detect parathyroid adenomas with a high sensitivity using parathyroid scintigraphy with 99m-technetium sestamibi.

    DOI: 10.1007/s12149-022-01726-8

    PubMed

    Other URL: https://link.springer.com/article/10.1007/s12149-022-01726-8/fulltext.html

  • Development and validation of a deep learning model for detection of breast cancers in mammography from multi-institutional datasets Reviewed

    Daiju Ueda, Akira Yamamoto, Naoyoshi Onoda, Tsutomu Takashima, Satoru Noda, Shinichiro Kashiwagi, Tamami Morisaki, Shinya Fukumoto, Masatsugu Shiba, Mina Morimura, Taro Shimono, Ken Kageyama, Hiroyuki Tatekawa, Kazuki Murai, Takashi Honjo, Akitoshi Shimazaki, Daijiro Kabata, Yukio Miki

    PLOS ONE   17 ( 3 )   e0265751 - e0265751   2022.03( ISSN:1932-6203 ( eISSN:1932-6203

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Research paper (scientific journal)  

    Objectives

    The objective of this study was to develop and validate a state-of-the-art, deep learning (DL)-based model for detecting breast cancers on mammography.

    Methods

    Mammograms in a hospital development dataset, a hospital test dataset, and a clinic test dataset were retrospectively collected from January 2006 through December 2017 in Osaka City University Hospital and Medcity21 Clinic. The hospital development dataset and a publicly available digital database for screening mammography (DDSM) dataset were used to train and to validate the RetinaNet, one type of DL-based model, with five-fold cross-validation. The model’s sensitivity and mean false positive indications per image (mFPI) and partial area under the curve (AUC) with 1.0 mFPI for both test datasets were externally assessed with the test datasets.

    Results

    The hospital development dataset, hospital test dataset, clinic test dataset, and DDSM development dataset included a total of 3179 images (1448 malignant images), 491 images (225 malignant images), 2821 images (37 malignant images), and 1457 malignant images, respectively. The proposed model detected all cancers with a 0.45–0.47 mFPI and had partial AUCs of 0.93 in both test datasets.

    Conclusions

    The DL-based model developed for this study was able to detect all breast cancers with a very low mFPI. Our DL-based model achieved the highest performance to date, which might lead to improved diagnosis for breast cancer.

    DOI: 10.1371/journal.pone.0265751

  • Development and Validation of Artificial Intelligence–based Method for Diagnosis of Mitral Regurgitation from Chest Radiographs Reviewed

    Daiju Ueda, Shoichi Ehara, Akira Yamamoto, Shinichi Iwata, Koji Abo, Shannon L. Walston, Toshimasa Matsumoto, Akitoshi Shimazaki, Minoru Yoshiyama, Yukio Miki

    Radiology: Artificial Intelligence   4 ( 2 )   2022.03( eISSN:2638-6100

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Research paper (scientific journal)  

    DOI: 10.1148/ryai.210221

  • Artificial intelligence-based detection of aortic stenosis from chest radiographs Reviewed

    Daiju Ueda, Akira Yamamoto, Shoichi Ehara, Shinichi Iwata, Koji Abo, Shannon L Walston, Toshimasa Matsumoto, Akitoshi Shimazaki, Minoru Yoshiyama, Yukio Miki

    European Heart Journal - Digital Health   3 ( 1 )   20 - 28   2021.12( eISSN:2634-3916

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Research paper (scientific journal)  

    Abstract

    Aims

    We aimed to develop models to detect aortic stenosis (AS) from chest radiographs—one of the most basic imaging tests—with artificial intelligence.

    Methods and results

    We used 10 433 retrospectively collected digital chest radiographs from 5638 patients to train, validate, and test three deep learning models. Chest radiographs were collected from patients who had also undergone echocardiography at a single institution between July 2016 and May 2019. These were labelled from the corresponding echocardiography assessments as AS-positive or AS-negative. The radiographs were separated on a patient basis into training [8327 images from 4512 patients, mean age 65 ±  (standard deviation) 15 years], validation (1041 images from 563 patients, mean age 65 ± 14 years), and test (1065 images from 563 patients, mean age 65 ± 14 years) datasets. The soft voting-based ensemble of the three developed models had the best overall performance for predicting AS with an area under the receiver operating characteristic curve, sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of 0.83 (95% confidence interval 0.77–0.88), 0.78 (0.67–0.86), 0.71 (0.68–0.73), 0.71 (0.68–0.74), 0.18 (0.14–0.23), and 0.97 (0.96–0.98), respectively, in the validation dataset and 0.83 (0.78–0.88), 0.83 (0.74–0.90), 0.69 (0.66–0.72), 0.71 (0.68–0.73), 0.23 (0.19–0.28), and 0.97 (0.96–0.98), respectively, in the test dataset.

    Conclusion

    Deep learning models using chest radiographs have the potential to differentiate between radiographs of patients with and without AS.

    Lay Summary

    We created artificial intelligence (AI) models using deep learning to identify aortic stenosis (AS) from chest radiographs. Three AI models were developed and evaluated with 10 433 retrospectively collected radiographs and labelled from echocardiography reports. The ensemble AI model could detect AS in a test dataset with an area under the receiver operating characteristic curve of 0.83 (95% confidence interval 0.78–0.88). Since chest radiography is a cost-effective and widely available imaging test, our model can provide an additive resource for the detection of AS.

    DOI: 10.1093/ehjdh/ztab102

    Other URL: https://academic.oup.com/ehjdh/article-pdf/3/1/20/47116703/ztab102.pdf

  • Training, Validation, and Test of Deep Learning Models for Classification of Receptor Expressions in Breast Cancers From Mammograms. Reviewed

    Daiju Ueda, Akira Yamamoto, Tsutomu Takashima, Naoyoshi Onoda, Satoru Noda, Shinichiro Kashiwagi, Tamami Morisaki, Takashi Honjo, Akitoshi Shimazaki, Yukio Miki

    JCO precision oncology   5 ( 5 )   543 - 551   2021.11( eISSN:2473-4284

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Research paper (scientific journal)   International / domestic magazine:International journal  

    <sec><title>PURPOSE</title> The molecular subtype of breast cancer is an important component of establishing the appropriate treatment strategy. In clinical practice, molecular subtypes are determined by receptor expressions. In this study, we developed a model using deep learning to determine receptor expressions from mammograms.

    </sec><sec><title>METHODS</title> A developing data set and a test data set were generated from mammograms from the affected side of patients who were pathologically diagnosed with breast cancer from January 2006 through December 2016 and from January 2017 through December 2017, respectively. The developing data sets were used to train and validate the DL-based model with five-fold cross-validation for classifying expression of estrogen receptor (ER), progesterone receptor (PgR), and human epidermal growth factor receptor 2-neu (HER2). The area under the curves (AUCs) for each receptor were evaluated with the independent test data set.

    </sec><sec><title>RESULTS</title> The developing data set and the test data set included 1,448 images (997 ER-positive and 386 ER-negative, 641 PgR-positive and 695 PgR-negative, and 220 HER2-enriched and 1,109 non–HER2-enriched) and 225 images (176 ER-positive and 40 ER-negative, 101 PgR-positive and 117 PgR-negative, and 53 HER2-enriched and 165 non–HER2-enriched), respectively. The AUC of ER-positive or -negative in the test data set was 0.67 (0.58-0.76), the AUC of PgR-positive or -negative was 0.61 (0.53-0.68), and the AUC of HER2-enriched or non–HER2-enriched was 0.75 (0.68-0.82).

    </sec><sec><title>CONCLUSION</title> The DL-based model effectively classified the receptor expressions from the mammograms. Applying the DL-based model to predict breast cancer classification with a noninvasive approach would have additive value to patients.

    </sec>

    DOI: 10.1200/PO.20.00176

    PubMed

  • Artificial intelligence-supported lung cancer detection by multi-institutional readers with multi-vendor chest radiographs: a retrospective clinical validation study. Reviewed

    Daiju Ueda, Akira Yamamoto, Akitoshi Shimazaki, Shannon Leigh Walston, Toshimasa Matsumoto, Nobuhiro Izumi, Takuma Tsukioka, Hiroaki Komatsu, Hidetoshi Inoue, Daijiro Kabata, Noritoshi Nishiyama, Yukio Miki

    BMC cancer   21 ( 1 )   1120 - 1120   2021.10( eISSN:1471-2407

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Research paper (scientific journal)   International / domestic magazine:International journal  

    <title>Abstract</title><sec>
    <title>Background</title>
    We investigated the performance improvement of physicians with varying levels of chest radiology experience when using a commercially available artificial intelligence (AI)-based computer-assisted detection (CAD) software to detect lung cancer nodules on chest radiographs from multiple vendors.


    </sec><sec>
    <title>Methods</title>
    Chest radiographs and their corresponding chest CT were retrospectively collected from one institution between July 2017 and June 2018. Two author radiologists annotated pathologically proven lung cancer nodules on the chest radiographs while referencing CT. Eighteen readers (nine general physicians and nine radiologists) from nine institutions interpreted the chest radiographs. The readers interpreted the radiographs alone and then reinterpreted them referencing the CAD output. Suspected nodules were enclosed with a bounding box. These bounding boxes were judged correct if there was significant overlap with the ground truth, specifically, if the intersection over union was 0.3 or higher. The sensitivity, specificity, accuracy, PPV, and NPV of the readers’ assessments were calculated.


    </sec><sec>
    <title>Results</title>
    In total, 312 chest radiographs were collected as a test dataset, including 59 malignant images (59 nodules of lung cancer) and 253 normal images. The model provided a modest boost to the reader’s sensitivity, particularly helping general physicians. The performance of general physicians was improved from 0.47 to 0.60 for sensitivity, from 0.96 to 0.97 for specificity, from 0.87 to 0.90 for accuracy, from 0.75 to 0.82 for PPV, and from 0.89 to 0.91 for NPV while the performance of radiologists was improved from 0.51 to 0.60 for sensitivity, from 0.96 to 0.96 for specificity, from 0.87 to 0.90 for accuracy, from 0.76 to 0.80 for PPV, and from 0.89 to 0.91 for NPV. The overall increase in the ratios of sensitivity, specificity, accuracy, PPV, and NPV were 1.22 (1.14–1.30), 1.00 (1.00–1.01), 1.03 (1.02–1.04), 1.07 (1.03–1.11), and 1.02 (1.01–1.03) by using the CAD, respectively.


    </sec><sec>
    <title>Conclusion</title>
    The AI-based CAD was able to improve the ability of physicians to detect nodules of lung cancer in chest radiographs. The use of a CAD model can indicate regions physicians may have overlooked during their initial assessment.


    </sec>

    DOI: 10.1186/s12885-021-08847-9

    PubMed

    Other URL: https://link.springer.com/article/10.1186/s12885-021-08847-9/fulltext.html

  • Automated classification of coronary atherosclerotic plaque in optical frequency domain imaging based on deep learning. Reviewed

    Hiroki Shibutani, Kenichi Fujii, Daiju Ueda, Rika Kawakami, Takahiro Imanaka, Kenji Kawai, Koichiro Matsumura, Kenta Hashimoto, Akira Yamamoto, Hiroyuki Hao, Seiichi Hirota, Yukio Miki, Ichiro Shiojima

    Atherosclerosis   328   100 - 105   2021.07( ISSN:0021-9150

     More details

    Publishing type:Research paper (scientific journal)   International / domestic magazine:International journal  

    BACKGROUND AND AIMS: We developed a deep learning (DL) model for automated atherosclerotic plaque categorization using optical frequency domain imaging (OFDI) and performed quantitative and visual evaluations. METHODS: A total of 1103 histological cross-sections from 45 autopsy hearts were examined to compare the ex vivo OFDI scans. The images were segmented and annotated considering four histological categories: pathological intimal thickening (PIT), fibrous cap atheroma (FA), fibrocalcific plaque (FC), and healed erosion/rupture (HER). The DL model was developed based on pyramid scene parsing network (PSPNet). Given an input image, a convolutional neural network (ResNet50) was used as an encoder to generate feature maps of the last convolutional layer. RESULTS: For the quantitative evaluation, the mean F-score and IoU values, which are used to evaluate how close the predicted results are to the ground truth, were used. The validation and test dataset had F-score and IoU values of 0.63, 0.49, and 0.66, 0.52, respectively. For the section-level diagnostic accuracy, the areas under the receiver-operating characteristic curve produced by the DL model for FC, PIT, FA, and HER were 0.91, 0.85, 0.86, and 0.86, respectively, and were comparable to those of an expert observer. CONCLUSIONS: DL semantic segmentation of coronary plaques in OFDI images was used as a tool to automatically categorize atherosclerotic plaques using histological findings as the gold standard. The proposed method can support interventional cardiologists in understanding histological properties of plaques.

    DOI: 10.1016/j.atherosclerosis.2021.06.003

    PubMed

  • Deep Learning-based Angiogram Generation Model for Cerebral Angiography without Misregistration Artifacts. Reviewed

    Daiju Ueda, Yutaka Katayama, Akira Yamamoto, Tsutomu Ichinose, Hironori Arima, Yusuke Watanabe, Shannon L Walston, Hiroyuki Tatekawa, Hirotaka Takita, Takashi Honjo, Akitoshi Shimazaki, Daijiro Kabata, Takao Ichida, Takeo Goto, Yukio Miki

    Radiology   299 ( 3 )   675 - 681   2021.06( ISSN:0033-8419 ( eISSN:1527-1315

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Research paper (scientific journal)   International / domestic magazine:International journal  

    Background Digital subtraction angiography (DSA) generates an image by subtracting a mask image from a dynamic angiogram. However, patient movement-caused misregistration artifacts can result in unclear DSA images that interrupt procedures. Purpose To train and to validate a deep learning (DL)-based model to produce DSA-like cerebral angiograms directly from dynamic angiograms and then quantitatively and visually evaluate these angiograms for clinical usefulness. Materials and Methods A retrospective model development and validation study was conducted on dynamic and DSA image pairs consecutively collected from January 2019 through April 2019. Angiograms showing misregistration were first separated per patient by two radiologists and sorted into the misregistration test data set. Nonmisregistration angiograms were divided into development and external test data sets at a ratio of 8:1 per patient. The development data set was divided into training and validation data sets at ratio of 3:1 per patient. The DL model was created by using the training data set, tuned with the validation data set, and then evaluated quantitatively with the external test data set and visually with the misregistration test data set. Quantitative evaluations used the peak signal-to-noise ratio (PSNR) and the structural similarity (SSIM) with mixed liner models. Visual evaluation was conducted by using a numerical rating scale. Results The training, validation, nonmisregistration test, and misregistration test data sets included 10 751, 2784, 1346, and 711 paired images collected from 40 patients (mean age, 62 years ± 11 [standard deviation]; 33 women). In the quantitative evaluation, DL-generated angiograms showed a mean PSNR value of 40.2 dB ± 4.05 and a mean SSIM value of 0.97 ± 0.02, indicating high coincidence with the paired DSA images. In the visual evaluation, the median ratings of the DL-generated angiograms were similar to or better than those of the original DSA images for all 24 sequences. Conclusion The deep learning-based model provided clinically useful cerebral angiograms free from clinically significant artifacts directly from dynamic angiograms. Published under a CC BY 4.0 license. Supplemental material is available for this article.

    DOI: 10.1148/radiol.2021203692

    PubMed

  • Visualizing "featureless" regions on mammograms classified as invasive ductal carcinomas by a deep learning algorithm: the promise of AI support in radiology. Reviewed

    Daiju Ueda, Akira Yamamoto, Tsutomu Takashima, Naoyoshi Onoda, Satoru Noda, Shinichiro Kashiwagi, Tamami Morisaki, Shinichi Tsutsumi, Takashi Honjo, Akitoshi Shimazaki, Takuya Goto, Yukio Miki

    Japanese journal of radiology   39 ( 4 )   333 - 340   2021.04( ISSN:1867-1071 ( eISSN:1867-108X

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Research paper (scientific journal)   International / domestic magazine:Domestic journal  

    PURPOSE: To demonstrate how artificial intelligence (AI) can expand radiologists' capacity, we visualized the features of invasive ductal carcinomas (IDCs) that our algorithm, developed and validated for basic pathological classification on mammograms, had focused on. MATERIALS AND METHODS: IDC datasets were built using mammograms from patients diagnosed with IDCs from January 2006 to December 2017. The developing dataset was used to train and validate a VGG-16 deep learning (DL) network. The true positives (TPs) and accuracy of the algorithm were externally evaluated using the test dataset. A visualization technique was applied to the algorithm to determine which malignant findings on mammograms were revealed. RESULTS: The datasets were split into a developing dataset (988 images) and a test dataset (131 images). The proposed algorithm diagnosed 62 TPs with an accuracy of 0.61-0.70. The visualization of features on the mammograms revealed that the tubule forming, solid, and scirrhous types of IDCs exhibited visible features on the surroundings, corners of the masses, and architectural distortions, respectively. CONCLUSION: We successfully showed that features isolated by a DL-based algorithm trained to classify IDCs were indeed those known to be associated with each pathology. Thus, using AI can expand the capacity of radiologists through the discovery of previously unknown findings.

    DOI: 10.1007/s11604-020-01070-9

    PubMed

    Other URL: http://link.springer.com/article/10.1007/s11604-020-01070-9/fulltext.html

  • 深層学習アルゴリズムにより浸潤性乳管癌として分類されたマンモグラム上で「特徴のみられない」領域での可視化 放射線学的検査におけるAI支援の有用性について(Visualizing "featureless" regions on mammograms classified as invasive ductal carcinomas by a deep learning algorithm: the promise of AI support in radiology)

    Ueda Daiju, Yamamoto Akira, Takashima Tsutomu, Onoda Naoyoshi, Noda Satoru, Kashiwagi Shinichiro, Morisaki Tamami, Tsutsumi Shinichi, Honjo Takashi, Shimazaki Akitoshi, Goto Takuya, Miki Yukio

    Japanese Journal of Radiology   39 ( 4 )   333 - 340   2021.04( ISSN:1867-1071

     More details

    マンモグラム上での浸潤性乳管癌(IDC)の病理分類のため、深層学習(DL)をベースとしたアルゴリズムの開発と検証に人工知能(AI)を適用し、その有用性について検討した。なお、学習データセットは2006年1月~2016年12月までの期間内に、当院で乳癌と診断された患者529例(年齢25~97歳)から得たマンモグラフィ画像988画像を用いて作成した。VGG-16DLネットワークにより、学習データセットと検証データセットを作成し、テストデータセットには2017年1月~2017年12月までの期間内に、乳癌と診断された当院患者67例(年齢40~92歳)から得た131画像を用いて作成し、アルゴリズムの真陽性と正確さを判定した。可視化技術をアルゴリズムに適用し、マンモグラム上で判明した悪性所見を調査した結果、DLベースのアルゴリズムにより、62画像の真陽性が0.61~0.70の正確さで診断され、マンモグラム上で認められた特徴の可視化により、腺管形成型、充実型および硬性型のIDCが、それぞれ腫瘤の周囲組織や乳腺の歪み、構築の乱れ等、可視化される特徴で描出されることが確認された。以上の所見から、DLベースのアルゴリズムにより、各分類でIDC病理との関連性が指摘されている画像特徴が抽出され、AIの適用により、これまで不明であった所見が明らかにされた。

  • Deep Learning for MR Angiography: Automated Detection of Cerebral Aneurysms. Reviewed

    Daiju Ueda, Akira Yamamoto, Masataka Nishimori, Taro Shimono, Satoshi Doishita, Akitoshi Shimazaki, Yutaka Katayama, Shinya Fukumoto, Antoine Choppin, Yuki Shimahara, Yukio Miki

    Radiology   290 ( 1 )   187 - 194   2019.01

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Research paper (scientific journal)   International / domestic magazine:International journal  

    Purpose To develop and evaluate a supportive algorithm using deep learning for detecting cerebral aneurysms at time-of-flight MR angiography to provide a second assessment of images already interpreted by radiologists. Materials and Methods MR images reported by radiologists to contain aneurysms were extracted from four institutions for the period from November 2006 through October 2017. The images were divided into three data sets: training data set, internal test data set, and external test data set. The algorithm was constructed by deep learning with the training data set, and its sensitivity to detect aneurysms in the test data sets was evaluated. To find aneurysms that had been overlooked in the initial reports, two radiologists independently performed a blinded interpretation of aneurysm candidates detected by the algorithm. When there was disagreement, the final diagnosis was made in consensus. The number of newly detected aneurysms was also evaluated. Results The training data set, which provided training and validation data, included 748 aneurysms (mean size, 3.1 mm ± 2.0 [standard deviation]) from 683 examinations; 318 of these examinations were on male patients (mean age, 63 years ± 13) and 365 were on female patients (mean age, 64 years ± 13). Test data were provided by the internal test data set (649 aneurysms [mean size, 4.1 mm ± 3.2] in 521 examinations, including 177 male patients and 344 female patients with mean age of 66 years ± 12 and 67 years ± 13, respectively) and the external test data set (80 aneurysms [mean size, 4.1 mm ± 2.1] in 67 examinations, including 19 male patients and 48 female patients with mean age of 63 years ± 12 and 68 years ± 12, respectively). The sensitivity was 91% (592 of 649) and 93% (74 of 80) for the internal and external test data sets, respectively. The algorithm improved aneurysm detection in the internal and external test data sets by 4.8% (31 of 649) and 13% (10 of 80), respectively, compared with the initial reports. Conclusion A deep learning algorithm detected cerebral aneurysms in radiologic reports with high sensitivity and improved aneurysm detection compared with the initial reports. © RSNA, 2018 See also the editorial by Flanders in this issue.

    DOI: 10.1148/radiol.2018180901

    PubMed

  • Technical and clinical overview of deep learning in radiology Invited Reviewed

    Daiju Ueda, Akitoshi Shimazaki, Yukio Miki

    Japanese Journal of Radiology   37 ( 1 )   15 - 33   2019.01( ISSN:1867-1071 ( eISSN:1867-108X

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Research paper (scientific journal)   International / domestic magazine:Domestic journal  

    Deep learning has been applied to clinical applications in not only radiology, but also all other areas of medicine. This review provides a technical and clinical overview of deep learning in radiology. To gain a more practical understanding of deep learning, deep learning techniques are divided into five categories: classification, object detection, semantic segmentation, image processing, and natural language processing. After a brief overview of technical network evolutions, clinical applications based on deep learning are introduced. The clinical applications are then summarized to reveal the features of deep learning, which are highly dependent on training and test datasets. The core technology in deep learning is developed by image classification tasks. In the medical field, radiologists are specialists in such tasks. Using clinical applications based on deep learning would, therefore, be expected to contribute to substantial improvements in radiology. By gaining a better understanding of the features of deep learning, radiologists could be expected to lead medical development.

    DOI: 10.1007/s11604-018-0795-3

    PubMed

    Other URL: http://link.springer.com/content/pdf/10.1007/s11604-018-0795-3.pdf

▼display all

Books and Other Publications

  • 医療学総論

    大滝 純司, 武田 裕子, 榊原 千秋, 貝沼 茂三郎, 松下 明, 小﨑 真規子, 吉田 絵理子, 磯野 真穂, 棚瀬 裕文, 春田 淳志, 松村 真司, 山田 隆司, 市橋 亮一, 辻 喜久, 志水 太郎, 勝倉 真一, 水澤 桂, 新井 正美, 山本 亮, 平山 陽示, 植田 大樹, 中山 和弘, 近藤 克則, 千嶋 巌, 藤原 聡子, 長嶺 由衣子, 西岡 大輔, 熊倉 陽介, 村岡 亮, 沢田 貴志, 坂井 建雄, 大生 定義, 北村 聖, 廣瀬 清英, 森川 すいめい, 勝井 恵子, 大熊 由紀子

    メヂカルフレンド社  2020.12  ( ISBN:9784839233693

     More details

    Total pages:xi, 277p  

    CiNii Books

MISC

▼display all

Presentations

▼display all

Grant-in-Aid for Scientific Research

  • Multi-center validation of prognostic prediction of Xp-age by AI

    Grant-in-Aid for Early-Career Scientists  2025

  • Multi-center validation of prognostic prediction of Xp-age by AI

    Grant-in-Aid for Early-Career Scientists  2024

  • AIを用いたCTからの門脈圧亢進症の診断プログラムの開発-無侵襲診断へ

    Grant-in-Aid for Scientific Research(C)  2024