SCALP -- Supervised Contrastive Learning for Cardiopulmonary Disease Classification and Localization in Chest X-rays using Patient Metadata

TL;DR

This paper introduces SCALP, a supervised contrastive learning framework that uses patient metadata for clinically accurate data augmentation, improving cardiopulmonary disease classification and localization in chest X-rays.

Contribution

The paper presents a novel data augmentation method based on patient metadata and supervised knowledge, extending contrastive learning to a supervised setting for medical imaging.

Findings

SCALP achieves higher classification AUCs than state-of-the-art methods.

Localization accuracy improves by an average of 3.7% over various IoU thresholds.

SCALP outperforms existing baselines in both classification and localization tasks.

Abstract

Computer-aided diagnosis plays a salient role in more accessible and accurate cardiopulmonary diseases classification and localization on chest radiography. Millions of people get affected and die due to these diseases without an accurate and timely diagnosis. Recently proposed contrastive learning heavily relies on data augmentation, especially positive data augmentation. However, generating clinically-accurate data augmentations for medical images is extremely difficult because the common data augmentation methods in computer vision, such as sharp, blur, and crop operations, can severely alter the clinical settings of medical images. In this paper, we proposed a novel and simple data augmentation method based on patient metadata and supervised knowledge to create clinically accurate positive and negative augmentations for chest X-rays. We introduce an end-to-end framework, SCALP, which extends the self-supervised contrastive approach to a supervised setting. Specifically, SCALP pulls together chest X-rays from the same patient (positive keys) and pushes apart chest X-rays from different patients (negative keys). In addition, it uses ResNet-50 along with the triplet-attention mechanism to identify cardiopulmonary diseases, and Grad-CAM++ to highlight the abnormal regions. Our extensive experiments demonstrate that SCALP outperforms existing baselines with significant margins in both classification and localization tasks. Specifically, the average classification AUCs improve from 82.8% (SOTA using DenseNet-121) to 83.9% (SCALP using ResNet-50), while the localization results improve on average by 3.7% over different IoU thresholds.