Contrastive Pretraining for Echocardiography Segmentation with Limited Data

TL;DR

This paper introduces a contrastive self-supervised learning approach for segmenting the left ventricle in echocardiography images, significantly reducing the need for annotated data while maintaining high accuracy.

Contribution

It proposes a novel contrastive pretraining method for medical image segmentation that improves performance with limited annotated data and demonstrates its effectiveness on multiple datasets.

Findings

Contrastive pretraining enhances segmentation accuracy with scarce labeled data.

Achieves comparable results to fully supervised models using only 5% labeled data.

Outperforms existing methods on the EchoNet-Dynamic dataset with a Dice score of 0.9252.

Abstract

Contrastive learning has proven useful in many applications where access to labelled data is limited. The lack of annotated data is particularly problematic in medical image segmentation as it is difficult to have clinical experts manually annotate large volumes of data such as cardiac structures in ultrasound images of the heart. In this paper, We propose a self supervised contrastive learning method to segment the left ventricle from echocardiography when limited annotated images exist. Furthermore, we study the effect of contrastive pretraining on two well-known segmentation networks, UNet and DeepLabV3. Our results show that contrastive pretraining helps improve the performance on left ventricle segmentation, particularly when annotated data is scarce. We show how to achieve comparable results to state-of-the-art fully supervised algorithms when we train our models in a self-supervised fashion followed by fine-tuning on just 5\% of the data. We show that our solution outperforms what is currently published on a large public dataset (EchoNet-Dynamic) achieving a Dice score of 0.9252. We also compare the performance of our solution on another smaller dataset (CAMUS) to demonstrate the generalizability of our proposed solution. The code is available at (https://github.com/BioMedIA-MBZUAI/contrastive-echo).