Deep Learning for Fast MRI

This talk explains the concept of the deep learning-based methods for accelerating magnetic resonance imaging, from the basics to the up-to-date methods. It covers image-domain deep learning, k-space-domain deep learning, cross-domain deep learning, and direct mapping for MR image reconstruction. The pros and cons of each approaches are explained. Parallel imaging and parameter mapping are also included in the line of deep learning-based MR image reconstruction. Deep-learning based contrast conversion is also briefly introduced in the context of the fast MR imaging

§  시간: 2022년 11월16일 (수요일) 오후4:00~5:00

§  장소: 공학관 A102호

§  연사: 황도식 교수 (연세대학교 전기전자공학부)

§  초청: 신태훈 교수 (휴먼기계바이오공학부, taehoons@ewha.ac.kr)