Medical images are widely used in clinical decision making and artificial intelligence (AI) technologies are commonly utilized in medical imaging and image analysis. In this talk, we address the aspect of medical imaging and present an overview of how AI facilitates the generation of medical image through recovery and synthesis. Medical image recovery attempts to recover the original image under adverse imaging conditions, such as metal artifacts, slow acquisition time, etc. Medical image synthesis attempts to synthesize, from an acquired image under current conditions, a novel image under different conditions. We will cover three neural approaches:
(i)   Dual domain network (DuDoNet) for metal artifact reduction in CT via joint learning in both sinogram and image domains and MR image reconstruction from undersampled k-space data via joint and recurrent learning in both frequency and image domains.
(ii)  Causal image synthesis (CIS) for counterfactually synthesizing MR brain images in 3D via a seamless, novel integration of a causal graph and 3D StyleGAN, which then form bases for better prediction of future brain conditions.
(iii)   Unified multimodal image synthesis (UMIS) for imputing missing MR images of multiple modalities from any combination of available ones with a single unified model.
Our recovery and synthesis approaches leverage deep neural networks as cores, integrate specific domain knowledge, achieve high quality images, and enable better clinical decision.

Speaker: Professor S. Kevin Zhou
Date: 11 April 2024 (Thursday)
Time: 10:00am – 11:00am
Poster: Click here