Enhancing Representation in Radiography-Reports Foundation Model: A Granular Alignment Algorithm Using Masked Contrastive Learning

TL;DR

MaCo is a novel masked contrastive learning model for chest X-ray analysis that improves fine-grained understanding and zero-shot capabilities, outperforming existing methods across multiple tasks.

Contribution

Introduces MaCo, a masked contrastive learning framework with a correlation weighting mechanism for enhanced representation in medical imaging.

Findings

MaCo outperforms 10 state-of-the-art methods in classification, segmentation, detection, and phrase grounding.

Demonstrates effectiveness in zero-shot learning for medical imaging tasks.

Achieves superior results across 6 open-source X-ray datasets.

Abstract

Recently, multi-modal vision-language foundation models have gained significant attention in the medical field. While these models offer great opportunities, they still face crucial challenges, such as the requirement for fine-grained knowledge understanding in computer-aided diagnosis and the capability of utilizing very limited or even no task-specific labeled data in real-world clinical applications. In this study, we present MaCo, a masked contrastive chest X-ray foundation model that tackles these challenges. MaCo explores masked contrastive learning to simultaneously achieve fine-grained image understanding and zero-shot learning for a variety of medical imaging tasks. It designs a correlation weighting mechanism to adjust the correlation between masked chest X-ray image patches and their corresponding reports, thereby enhancing the model's representation learning capabilities. To evaluate the performance of MaCo, we conducted extensive experiments using 6 well-known open-source X-ray datasets. The experimental results demonstrate the superiority of MaCo over 10 state-of-the-art approaches across tasks such as classification, segmentation, detection, and phrase grounding. These findings highlight the significant potential of MaCo in advancing a wide range of medical image analysis tasks.