Yuta Nakamura’s Curriculum Vitae
Contact
yutanakamura [hyphen] tky [at] umin.ac.jp
About me
I am a biomedical natural language processing (NLP) researcher and a board-certified diagnostic radiologist at the University of Tokyo Hospital.
My ambition is to introduce NLP to enhance clinical workflows and improve the quality of care. A particular area of interest is addressing the shortage of open-access Japanese language resources in the biomedical field.
To this end, I have created approximately 400 Japanese radiology reports that are devoid of personal information and made them publicly available. Using these resources, I have organized two shared tasks during NTCIR-16 and NTCIR-17, with the aim of fostering innovation and enhancing collaboration between the NLP and medical communities.
Publications
Capability of GPT-4V(ision) in the Japanese National Medical Licensing Examination: Evaluation Study
Takahiro Nakao, Soichiro Miki, Yuta Nakamura, Tomohiro Kikuchi, Yukihiro Nomura, Shouhei Hanaoka, Takeharu Yoshikawa, Osamu Abe. Capability of GPT-4V(ision) in the Japanese National Medical Licensing Examination: Evaluation Study. JMIR Med Edu 2024;10:e54393.
Axillary Lymphadenopathy after COVID-19 Vaccination: Follow-up for Enlarged Lymph Nodes on MR Imaging
Noriko Kanemaru, Takeharu Yoshikawa, Soichiro Miki, Takahiro Nakao, Yuta Nakamura, Kotaro Fujimoto, Osamu Abe. Axillary Lymphadenopathy after COVID-19 Vaccination: Follow-up for Enlarged Lymph Nodes on MR Imaging. Magn Reson Med Sci 2024. doi: 10.2463/mrms.mp.2023-0147.
ChatGPT for automating lung cancer staging: feasibility study on open radiology report dataset
Yuta Nakamura, Tomohiro Kikuchi, Yosuke Yamagishi, Shouhei Hanaoka, Takahiro Nakao, Soichiro Miki, Takeharu Yoshikawa, Osamu Abe. ChatGPT for automating lung cancer staging: feasibility study on open radiology report dataset. medRxiv preprint 2023. doi: 10.1101/2023.12.11.23299107.
Medical Visual Textual Entailment for Numerical Understanding of Vision-and-Language Models
Hitomi Yanaka, Yuta Nakamura (co-first), Yuki Chida, and Tomoya Kurosawa. Medical Visual Textual Entailment for Numerical Understanding of Vision-and-Language Models. Proceedings of the 5th Clinical Natural Language Processing Workshop 2023:8–18.
Playing the Werewolf game with artificial intelligence for language understanding
Hisaichi Shibata, Soichiro Miki, Yuta Nakamura. Playing the Werewolf game with artificial intelligence for language understanding. arXiv preprint arXiv:2302.10646.
Clinical Comparable Corpus Describing the Same Subjects with Different Expressions
Yuta Nakamura, Shouhei Hanaoka, Yukihiro Nomura, Naoto Hayashi, Osamu Abe, Shunrato Yada, Shoko Wakamiya, Eiji Aramaki. Clinical Comparable Corpus Describing the Same Subjects with Different Expressions. Stud Health Technol Inform 2022;290:253-257.
Natural Language Processing: from Bedside to Everywhere
Eiji Aramaki, Shoko Wakamiya, Shuntaro Yada, Yuta Nakamura. Natural Language Processing: from Bedside to Everywhere. Yearb Med Inform 2022;31(1):243-253.
Automatic detection of actionable radiology reports using bidirectional encoder representations from transformers
Yuta Nakamura, Shouhei Hanaoka, Yukihiro Nomura, Takahiro Nakao, Soichiro Miki, Takeyuki Watadani, Takeharu Yoshikawa, Naoto Hayashi, Osamu Abe. Automatic detection of actionable radiology reports using bidirectional encoder representations from transformers. BMC Med Inform Decis Mak 2021;21:262.
Computer-aided detection of cerebral aneurysms with magnetic resonance angiography: usefulness of volume rendering to display lesion candidates
Soichiro Miki, Takahiro Nakao, Yukihiro Nomura, Naomasa Okimoto, Keisuke Nyunoya, Yuta Nakamura, Ryo Kurokawa, Shiori Amemiya, Takeharu Yoshikawa, Shouhei Hanaoka, Naoto Hayashi, Osamu Abe. Computer-aided detection of cerebral aneurysms with magnetic resonance angiography: usefulness of volume rendering to display lesion candidates. Jpn J Radiol 2021;39:652–658.
Computer-aided detection of cerebral aneurysms with magnetic resonance angiography: usefulness of volume rendering to display lesion candidates
Soichiro Miki, Takahiro Nakao, Yukihiro Nomura, Naomasa Okimoto, Keisuke Nyunoya, Yuta Nakamura, Ryo Kurokawa, Shiori Amemiya, Takeharu Yoshikawa, Shouhei Hanaoka, Naoto Hayashi, Osamu Abe
KART: Privacy Leakage Framework of Language Models Pre-trained with Clinical Records
Yuta Nakamura, Shouhei Hanaoka, Yukihiro Nomura, Naoto Hayashi, Osamu Abe, Shuntaro Yada, Shoko Wakamiya, Eiji Aramaki. KART: Parameterization of Privacy Leakage Scenarios from Pre-trained Language Models. arXiv preprint arXiv:2101.00036.
Education
- Ph.D. in Medicine, 2023
- Division of Radiology and Biomedical Engineering, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
- Supervisor: Professor Osamu Abe
- Special Research Student, 2020
- NARA Institute of Science and Technology (NAIST), Nara, Japan
- Duties included: Building open biomedical corpus, analysing privacy risk of sharing AI models
- Supervisor: Professor Eiji Aramaki
- B.S. in Medicine, 2015
- Department of Medicine, The University of Tokyo, Tokyo, Japan
Work experience
- Department of Computational Diagnostic Radiology and Preventive Medicine, the University of Tokyo Hospital, 2023–
- Department of Radiology, the University of Tokyo Hospital, 2021–2022
- Department of Radiology, Toranomon Hospital, 2019–2020
- Department of Radiology, SHOWA University Northern Yokohama Hospital, 2018
- Department of Radiology, SHOWA University Hospital, 2018
- Department of Radiology, SHOWA University Fujigaoka Hospital, 2017
- Department of Radiology, SHOWA University Hospital, 2017