Semi-Supervised Medical Image Segmentation with Co-Distribution Alignment

TL;DR

This paper introduces Co-Distribution Alignment, a semi-supervised learning method for medical image segmentation that effectively utilizes unlabeled data and addresses class imbalance, achieving state-of-the-art results on multiple datasets.

Contribution

The paper proposes Co-DA, a novel class-wise alignment approach with an over-expectation loss, improving semi-supervised segmentation performance on medical images.

Findings

Outperforms existing methods on three datasets.

Achieves high mIoU and Dice scores with limited labeled data.

Effectively handles class imbalance in medical images.

Abstract

Medical image segmentation has made significant progress when a large amount of labeled data are available. However, annotating medical image segmentation datasets is expensive due to the requirement of professional skills. Additionally, classes are often unevenly distributed in medical images, which severely affects the classification performance on minority classes. To address these problems, this paper proposes Co-Distribution Alignment (Co-DA) for semi-supervised medical image segmentation. Specifically, Co-DA aligns marginal predictions on unlabeled data to marginal predictions on labeled data in a class-wise manner with two differently initialized models before using the pseudo-labels generated by one model to supervise the other. Besides, we design an over-expectation cross-entropy loss for filtering the unlabeled pixels to reduce noise in their pseudo-labels. Quantitative and qualitative experiments on three public datasets demonstrate that the proposed approach outperforms existing state-of-the-art semi-supervised medical image segmentation methods on both the 2D CaDIS dataset and the 3D LGE-MRI and ACDC datasets, achieving an mIoU of 0.8515 with only 24% labeled data on CaDIS, and a Dice score of 0.8824 and 0.8773 with only 20% data on LGE-MRI and ACDC, respectively.