AI Support Diagnostic System for Radiation Dose Reduction in PET

We provide a diagnostic support system that generates images in cancer treatment from patient data acquired with low doses of Positron Emission Tomography (PET) that possess image quality and quantification comparable to those obtained with standard doses. This system will present temporal changes based on historical patient data and suggest to physicians the need for follow-up examinations at standard doses when values exceed the reference range. Through the development of this diagnostic support AI, we aim to promote research and development focused on minimizing administered doses during PET examinations and reducing medical radiation exposure.

Development Section in Charge

AI Development for Diagnostic Imaging Assistant Section

Principal Investigator

YOSHIMURA Takaaki, Senior Lecturer, Department of Health Sciences and Technology, Faculty of Health Sciences

University-Affiliated Researchers

KUDO Kohsuke, Professor, Department of Diagnostic Imaging, Hokkaido University Graduate School of Medicine
HIRATA Kenji, Associate Professor, Department of Diagnostic Imaging, Hokkaido University Graduate School of Medicine
SUGIMORI Hiroyuki, Associate Professor, Department of Biomedical Science and Engineering, Faculty of Health Sciences
ENDO Hiroki, PhD Student, Department of Diagnostic Imaging, Hokkaido University Graduate School of Medicine

External Funding

This study was supported in part by Grants-in-Aid for Regional R&D Proposal-Based Program
from Northern Advancement Center for Science & Technology of Hokkaido Japan（2021）
The Akiyama Life Science Foundation（2023）
This research was supported by AMED under Grant Number JP24ym0126801（2024）