Cross-adversarial local distribution regularization for semi-supervised medical image segmentation

TL;DR

This paper introduces Cross-ALD, a novel regularization method that enhances semi-supervised medical image segmentation by improving model smoothness, achieving state-of-the-art results on public datasets.

Contribution

The paper proposes a new cross-adversarial local distribution regularization technique to strengthen the smoothness assumption in semi-supervised segmentation.

Findings

Achieves state-of-the-art performance on LA and ACDC datasets.

Outperforms recent semi-supervised segmentation methods.

Enhances model robustness through cross-adversarial regularization.

Abstract

Medical semi-supervised segmentation is a technique where a model is trained to segment objects of interest in medical images with limited annotated data. Existing semi-supervised segmentation methods are usually based on the smoothness assumption. This assumption implies that the model output distributions of two similar data samples are encouraged to be invariant. In other words, the smoothness assumption states that similar samples (e.g., adding small perturbations to an image) should have similar outputs. In this paper, we introduce a novel cross-adversarial local distribution (Cross-ALD) regularization to further enhance the smoothness assumption for semi-supervised medical image segmentation task. We conducted comprehensive experiments that the Cross-ALD archives state-of-the-art performance against many recent methods on the public LA and ACDC datasets.