MoCo-CXR: MoCo Pretraining Improves Representation and Transferability of Chest X-ray Models

Abstract

Contrastive learning is a form of self-supervision that can leverage unlabeled data to produce pretrained models. While contrastive learning has demonstrated promising results on natural image classification tasks, its application to medical imaging tasks like chest X-ray interpretation has been limited. In this work, we propose MoCo-CXR, which is an adaptation of the contrastive learning method Momentum Contrast (MoCo), to produce models with better representations and initializations for the detection of pathologies in chest X-rays. In detecting pleural effusion, we find that linear models trained on MoCo-CXR-pretrained representations outperform those without MoCo-CXR-pretrained representations, indicating that MoCo-CXR-pretrained representations are of higher-quality. End-to-end fine-tuning experiments reveal that a model initialized via MoCo-CXR-pretraining outperforms its non-MoCo-CXR-pretrained counterpart. We find that MoCo-CXR-pretraining provides the most benefit with limited labeled training data. Finally, we demonstrate similar results on a target Tuberculosis dataset unseen during pretraining, indicating that MoCo-CXR-pretraining endows models with representations and transferability that can be applied across chest X-ray datasets and tasks.

Accepted at Medical Imaging with Deep Learning (MIDL) Conference 2021

References in corpus (4)

• CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning
• Unsupervised Domain Adaptation through Self-Supervision
• Self-Supervised Learning for Cardiac MR Image Segmentation by Anatomical Position Prediction
• CheXternal: Generalization of Deep Learning Models for Chest X-ray Interpretation to Photos of Chest X-rays and External Clinical Settings

Cited by in corpus (15)

• Recent advances and clinical applications of deep learning in medical image analysis
• CheXtransfer: Performance and Parameter Efficiency of ImageNet Models for Chest X-Ray Interpretation
• Self-supervised deep convolutional neural network for chest X-ray classification
• MedAug: Contrastive learning leveraging patient metadata improves representations for chest X-ray interpretation
• Clinically Labeled Contrastive Learning for OCT Biomarker Classification
• CheXternal: Generalization of Deep Learning Models for Chest X-ray Interpretation to Photos of Chest X-rays and External Clinical Settings
• Using Radiomics as Prior Knowledge for Thorax Disease Classification and Localization in Chest X-rays
• CheXseg: Combining Expert Annotations with DNN-generated Saliency Maps for X-ray Segmentation
• Tips and Tricks to Improve CNN-based Chest X-ray Diagnosis: A Survey
• Contrastive Learning with Temporal Correlated Medical Images: A Case Study using Lung Segmentation in Chest X-Rays
• On the Robustness of Pretraining and Self-Supervision for a Deep Learning-based Analysis of Diabetic Retinopathy
• SCALP -- Supervised Contrastive Learning for Cardiopulmonary Disease Classification and Localization in Chest X-rays using Patient Metadata
• Unsupervised Local Discrimination for Medical Images
• Domain Generalization for Mammography Detection via Multi-style and Multi-view Contrastive Learning
• Federated Contrastive Learning for Decentralized Unlabeled Medical Images