Semi-Supervised Medical Image Segmentation via Dual Networks

TL;DR

This paper presents a semi-supervised 3D medical image segmentation method using dual networks and contrastive learning to reduce reliance on large labeled datasets and improve pseudo-label reliability.

Contribution

It introduces a dual-network architecture combined with self-supervised contrastive learning to enhance segmentation accuracy with limited labeled data.

Findings

Outperforms state-of-the-art methods on MRI segmentation

Reduces prediction uncertainty with contrastive learning

Effective with limited annotated data

Abstract

Traditional supervised medical image segmentation models require large amounts of labeled data for training; however, obtaining such large-scale labeled datasets in the real world is extremely challenging. Recent semi-supervised segmentation models also suffer from noisy pseudo-label issue and limited supervision in feature space. To solve these challenges, we propose an innovative semi-supervised 3D medical image segmentation method to reduce the dependency on large, expert-labeled datasets. Furthermore, we introduce a dual-network architecture to address the limitations of existing methods in using contextual information and generating reliable pseudo-labels. In addition, a self-supervised contrastive learning strategy is used to enhance the representation of the network and reduce prediction uncertainty by distinguishing between reliable and unreliable predictions. Experiments on clinical magnetic resonance imaging demonstrate that our approach outperforms state-of-the-art techniques. Our code is available at https://github.com/AIPMLab/Semi-supervised-Segmentation.