Séminaire Image: Shouhei Hanaoka et Rie Tanaka

Nous aurons le plaisir d’écouter Shouhei Hanaoka, Associate Professor (Graduate School of Medicine, The University of Tokyo) et Rie Tanaka (Pharmaceutical and Health Sciences, Kanazawa University).
Il donneront un séminaire IMAGE le jeudi 21 mai 2026 à 14h en salle de séminaire F-200.

Titre (Shouhei Hanaoka) : « Clinical importance of trees and graphs: An example of HoTPiG for cerebral aneurysm detection »

Résumé : 

TBA

Titre (Rie Tanaka) : « From Static X-ray to Functional Imaging: AI-driven Advances in Thoracic Radiography »

Résumé : 

Chest radiography is the most widely used imaging modality for screening and follow-up. Dynamic chest radiography (DCR) extends conventional radiography by enabling functional assessment using flat-panel detector (FPD)-based systems. Quantitative and time-series analysis of DCR allows evaluation of respiratory and circulatory dynamics through lung density changes, diaphragm motion, and tracheal diameter. However, these approaches remain limited by the two-dimensional projection nature of X-ray imaging, motivating the integration of artificial intelligence and in silico–based strategies to enable higher-dimensional understanding of spatiotemporal patterns.
We present a unified framework integrating DCR, artificial intelligence, and in silico–based training strategies. We first enhance two-dimensional projections via image decomposition, then estimate lung volume and respiratory function, and finally reconstruct four-dimensional (4D) representations from dynamic X-ray time-series data using deep learning. Developed using large-scale virtual datasets and validated on clinical cases, these approaches may enable functional and quantitative chest radiography, bridging the gap between low-cost X-ray imaging and advanced modalities such as CT.