Learning and encoding semantics for multimodal deformable image registration with weak supervision

Housheng Xie

doi:10.1016/j.bspc.2025.108280

Learning and encoding semantics for multimodal deformable image registration with weak supervision

2025-07-11

0

PRE

AI

DOI：10.1016/j.bspc.2025.108280

Original

Original request for help

Save

Abstract

En 中文

• An end-to-end trainable semantics learning and encoding network called SLENet is proposed. • SLENet only relies on additional label maps of CT data for training. • SLENet can boost the performance of both intra-subject and inter-subject multimodal deformable image registration. • Extensive experiments on three datasets of different anatomical structures demonstrate the efficacy of our method.

Learning and encoding semantics for multimodal deformable image registration with weak supervision

Abstract

Journal

Organization