IWAIT 2026 / IFMIA 2026

Generative AI for Medical Image Analysis

The rapid advancement of generative AI is profoundly transforming our society. Agentic AI systems are now capable of responding to complex questions with remarkable speed and accuracy. In the medical domain, generative AI is beginning to reshape assistive technologies for clinicians. Applications include automated generation of radiology reports, automatic annotation of endoscopic videos, and depth estimation from endoscopic images. In this talk, we present recent research activities on medical generative AI at Nagoya University. We introduce nation-wide Japanese medical image databases and the computational infrastructure that support these developments. As a demonstration, we showcase a system for automated report generation from longitudinal CT volumes, trained on large-scale CT datasets. We also describe a method for generating questionโ€“answer pairs for visionโ€“language models (VLMs) using radiological findings stored in DICOM files. Through these examples, we discuss how generative AI can advance medical image understanding and contribute to the next generation of intelligent medical assistance systems.

About the speaker

Kensaku Mori

Nagoya University, Japan

Kensaku Mori received his B.S. degree in Electronics Engineering, M.S. degree in Information Engineering, and Ph.D. in Information Engineering from Nagoya University, Japan, under the supervision of Prof. Jun-ichiro Toriwaki, in 1992, 1994, and 1996, respectively. In 2016, he began serving as the Director of the Information Technology Center at Nagoya University. In 2017, he was appointed Vice Chair of Information and Communication at Nagoya University. Since 2017, he has been a Professor at the Graduate School of Informatics, Nagoya University. He is also serving as the Director of the Research Center for Medical Big Data at the National Institute of Informatics in Tokyo, Japan. He served as the General Chair of MICCAI 2013, held in Nagoya, Japan. His current research interests include three-dimensional image processing, computer graphics, virtual reality, and their applications to medical imaging. Computer-aided diagnosis and surgery are his major active research fields. Recently, an AI-based colonoscope diagnosis system developed in his laboratory has obtained official certification as a medical device. He has received many awards, including the Award for Science and Technology from the Ministry of Education, Culture, Sports, Science and Technology (MEXT), and best paper awards from the Japanese Society of Medical Imaging Technology.

Copyright ยฉ 2025. IRIS Yuntech. All Right Reserved