Contrastive Pretraining for Echocardiography Segmentation with Limited Data
Authors:
- Mohamed SaeedMSMohamed Saeed
- Rand MuhtasebRMRand Muhtaseb
- Mohammad YaqubMYMohammad Yaqub
Preprint
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).Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- ResDUnet: A Deep Learning-Based Left Ventricle Segmentation Method for EchocardiographyIEEE Access, 2021
- nnU-Net: a self-configuring method for deep learning-based biomedical image segmentationNature Methods, 2020
- Video-based AI for beat-to-beat assessment of cardiac functionNature, 2020
- MFP-Unet: A novel deep learning based approach for left ventricle segmentation in echocardiographyPhysica Medica, 2019
- Utilization of Artificial Intelligence in EchocardiographyCirculation Journal, 2019
- Deep Learning for Segmentation Using an Open Large-Scale Dataset in 2D EchocardiographyIEEE Transactions on Medical Imaging, 2019
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017