Label-Efficient Multi-Task Segmentation using Contrastive Learning

TL;DR

This paper introduces a contrastive learning-based multi-task segmentation model that effectively utilizes limited labeled data and unlabeled data, outperforming existing methods in 3D medical image segmentation.

Contribution

It presents a novel contrastive learning approach for multi-task segmentation and extends it to semi-supervised learning, improving performance with scarce annotations.

Findings

Outperforms state-of-the-art fully supervised models with limited labeled data.

Effectively utilizes unlabeled data through a regularization branch.

Demonstrates significant improvements in 3D medical image segmentation accuracy.

Abstract

Obtaining annotations for 3D medical images is expensive and time-consuming, despite its importance for automating segmentation tasks. Although multi-task learning is considered an effective method for training segmentation models using small amounts of annotated data, a systematic understanding of various subtasks is still lacking. In this study, we propose a multi-task segmentation model with a contrastive learning based subtask and compare its performance with other multi-task models, varying the number of labeled data for training. We further extend our model so that it can utilize unlabeled data through the regularization branch in a semi-supervised manner. We experimentally show that our proposed method outperforms other multi-task methods including the state-of-the-art fully supervised model when the amount of annotated data is limited.