CycleMix: A Holistic Strategy for Medical Image Segmentation from Scribble Supervision

TL;DR

CycleMix introduces a novel framework combining mix augmentation and cycle consistency to improve medical image segmentation from scribble supervision, achieving performance comparable to fully-supervised methods.

Contribution

It proposes a new holistic approach for scribble-based medical image segmentation using mix augmentation and cycle consistency, enhancing performance with limited supervision.

Findings

Achieved comparable or better accuracy than fully-supervised methods.

Demonstrated effectiveness on ACDC and MSCMRseg datasets.

Code and annotations are publicly available.

Abstract

Curating a large set of fully annotated training data can be costly, especially for the tasks of medical image segmentation. Scribble, a weaker form of annotation, is more obtainable in practice, but training segmentation models from limited supervision of scribbles is still challenging. To address the difficulties, we propose a new framework for scribble learning-based medical image segmentation, which is composed of mix augmentation and cycle consistency and thus is referred to as CycleMix. For augmentation of supervision, CycleMix adopts the mixup strategy with a dedicated design of random occlusion, to perform increments and decrements of scribbles. For regularization of supervision, CycleMix intensifies the training objective with consistency losses to penalize inconsistent segmentation, which results in significant improvement of segmentation performance. Results on two open datasets, i.e., ACDC and MSCMRseg, showed that the proposed method achieved exhilarating performance, demonstrating comparable or even better accuracy than the fully-supervised methods. The code and expert-made scribble annotations for MSCMRseg are publicly available at https://github.com/BWGZK/CycleMix.