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

Image credit: Shuailin Li

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 shape-aware 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.

Publication
In Medical Image Computing and Computer Assisted Intervention Society 2020
Shuailin Li
Shuailin Li
Master Student

My research interests include image segmentation, medical image analysis and weak-supervised learning.

Chuyu Zhang
Chuyu Zhang
Master Student

My research interests include semi-supervised learning, and video understanding.

Xuming He
Xuming He
Associate Professor

My research interests include few/low-shot learning, graph neural networks and video understanding.

Related