Self-semantic contour adaptation for cross modality brain tumor segmentation

TL;DR

This paper introduces a multi-task framework leveraging low-level edge information and self-entropy minimization to improve cross-modality brain tumor segmentation, demonstrating superior results on BraTS2018.

Contribution

It proposes a novel multi-task approach combining contour and semantic adaptation with adversarial learning and self-entropy minimization for unsupervised domain adaptation in medical imaging.

Findings

Outperforms existing methods on BraTS2018 dataset

Effective cross-modality segmentation of brain tumors

Enhanced domain alignment through edge-guided adaptation

Abstract

Unsupervised domain adaptation (UDA) between two significantly disparate domains to learn high-level semantic alignment is a crucial yet challenging task.~To this end, in this work, we propose exploiting low-level edge information to facilitate the adaptation as a precursor task, which has a small cross-domain gap, compared with semantic segmentation.~The precise contour then provides spatial information to guide the semantic adaptation. More specifically, we propose a multi-task framework to learn a contouring adaptation network along with a semantic segmentation adaptation network, which takes both magnetic resonance imaging (MRI) slice and its initial edge map as input.~These two networks are jointly trained with source domain labels, and the feature and edge map level adversarial learning is carried out for cross-domain alignment. In addition, self-entropy minimization is incorporated to further enhance segmentation performance. We evaluated our framework on the BraTS2018 database for cross-modality segmentation of brain tumors, showing the validity and superiority of our approach, compared with competing methods.