Semi-weakly-supervised neural network training for medical image registration

arXiv:2402.10728v1 Announce Type: cross
Abstract: For training registration networks, weak supervision from segmented corresponding regions-of-interest (ROIs) have been proven effective for (a) supplementing unsupervised methods, and (b) being used independently in registration tasks in which unsupervised losses are unavailable or ineffective. This correspondence-informing supervision entails cost in annotation that requires significant specialised effort. This paper describes a semi-weakly-supervised registration pipeline that improves the model performance, when only a small corresponding-ROI-labelled dataset is available, by exploiting unlabelled image pairs. We examine …

abstract annotation arxiv cost cs.cv eess.iv image losses medical network networks network training neural network registration supervision tasks training type unsupervised weakly-supervised