Development of AI for Supporting Image Diagnosis of Cerebral Infarction

Cerebral infarction requires urgent diagnosis, as early treatment following onset can significantly improve patient outcomes. Among diagnostic methods, imaging plays a critical role, with diffusion-weighted imaging (DWI) from MRI being widely utilized. Typically, specialists visually evaluate and diagnose using DWI, however, artifacts and other factors can sometimes complicate the diagnosis. Additionally, specialists are not always present at emergency sites.

Given these circumstances, this project aims to develop an AI model that highlights areas of cerebral infarction on diffusion-weighted images, assisting physicians in their diagnosis.

Development Section in Charge

AI Development for Diagnostic Imaging Assistant Section

Principal Investigator

KUDO Kohsuke, Professor, Department of Diagnostic Imaging, Hokkaido University Graduate School of Medicine

University-Affiliated Researchers

TAKAHASHI Bunya, PhD Student, Department of Diagnostic Imaging, Hokkaido University Graduate School of Medicine
HIRATA Kenji, Associate Professor, Department of Diagnostic Imaging, Hokkaido University Graduate School of Medicine
KAWAUCHI Keisuke, School of Biomedical Science and Engineering, Hokkaido University Graduate School of Medicine