Shape-aware Semi-supervised 3D Semantic Segmentation for Medical Images

TL;DR

This paper introduces a shape-aware semi-supervised learning method for 3D medical image segmentation that jointly predicts segmentation and shape information, improving shape accuracy and leveraging unlabeled data effectively.

Contribution

It proposes a novel multi-task network that predicts both segmentation and signed distance maps, incorporating shape constraints via adversarial training to enhance segmentation quality.

Findings

Outperforms state-of-the-art methods on atrial segmentation dataset

Improves shape estimation accuracy in segmentation results

Effectively leverages unlabeled data through adversarial loss

Abstract

Semi-supervised learning has attracted much attention in medical image segmentation due to challenges in acquiring pixel-wise image annotations, which is a crucial step for building high-performance deep learning methods. Most existing semi-supervised segmentation approaches either tend to neglect geometric constraint in object segments, leading to incomplete object coverage, or impose strong shape prior that requires extra alignment. In this work, we propose a novel shapeaware semi-supervised segmentation strategy to leverage abundant unlabeled data and to enforce a geometric shape constraint on the segmentation output. To achieve this, we develop a multi-task deep network that jointly predicts semantic segmentation and signed distance map(SDM) of object surfaces. During training, we introduce an adversarial loss between the predicted SDMs of labeled and unlabeled data so that our network is able to capture shape-aware features more effectively. Experiments on the Atrial Segmentation Challenge dataset show that our method outperforms current state-of-the-art approaches with improved shape estimation, which validates its efficacy. Code is available at https://github.com/kleinzcy/SASSnet.