Ph.D. Professor Megumi Nakao
Our lab is engaged in research and education on artificial intelligence (AI), machine learning methods and data science for biomedical imaging, and their application to imaging, diagnosis, and clinical treatment. We aim to create medical machine intelligence for a wide range of clinical applications such as next-generation surgery and radiotherapy.
Research and Education
[Research] In order to address limitations of medical imaging during treatment, we are exploring a framework for deep imaging and statistical modeling technology that enable inference of high-dimensional biological information beyond observations. We focus on generality and sparsity in our organs and image measurement, and aim to directly generate information related to diagnosis and treatment. Through development of advanced information techniques, we design the automated, higher-level treatment process, and to realize sustainable medical care with low burden for both physicians and patients.
[Education] Based on the theory of machine learning and programming skills related to image processing, graphics, and computer vision, we aim to foster advanced medical professionals who can explore and solve various problems in clinical and health medicine by building and verifying theories. Through problem settings and research activities based on individual interests, we cultivate the research and development skills needed to become researchers in medical engineering and informatics and experts in advanced medical devices that will lead the future of medicine and health science.
Recent Publications
- R. Miura, M. Nakamura, M. Nakao, Image-to-Volume Deformable Registration by Learning Displacement Vector Fields, IEEE Trans. on Radiation and Plasma Medical Sciences, Vol. 9, No. 1, pp. 69-82, 2025.
- T. Oya, Y. Kadomatsu, T. F. Chen-Yoshikawa, M. Nakao, 2D/3D deformable registration for endoscopic camera images using self-supervised offline learning of intraoperative pneumothorax deformation, Computerized Medical Imaging and Graphics, 102418, 2024.
- K. Masui, N. Kume, M. Nakao, T. Magaribuchi, A. Hamada, T. Kobayashi, A. Sawada, Vision-based estimation of manipulation forces by deep learning of laparoscopic surgical images obtained in a porcine excised kidney experiment, Scientific Reports, Vol.14, Art no. 9686, 2024.
- S. Okado, Y. Kadomatsu, M. Nakao, H. Ueno, K. Fukumoto, S. Nakamura, T. F. Chen-Yoshikawa, New method for delineation of the intersegmental line in a deflated lung, Journal of Thoracic Disease, Vol. 15, No.9 pp. 4736-4744, 2023.
- M. Nakao, M. Nakamura, T. Matsuda, Image-to-graph convolutional network for 2D/3D deformable model registration of low-contrast organs, IEEE Trans. on Medical Imaging, Vol. 41, No. 12, pp. 3747-3761, 2022.
Laboratory
Ph.D. Professor:Megumi Nakao
Ph.D. Assistant Professor:Sho Mitarai
Lab HP:https://ibme.hs.med.kyoto-u.ac.jp/
E-mail: nakao.megumi.6x (at) kyoto-u.ac.jp