Contrastive Pretraining for Echocardiography Segmentation with Limited Data

Document Type

Conference Proceeding

Publication Title

26th Annual Conference on Medical Image Understanding and Analysis 2022


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 ). © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

First Page


Last Page




Publication Date



BYOL, Contrastive learning, Echocardiography, Segmentation, Self-supervised, SimCLR, Ultrasound, Image segmentation, Large dataset, Learning systems, Medical computing, Medical imaging


IR Deposit conditions: non-described