We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Enhancing representation in radiography-reports foundation model: a granular alignment algorithm using masked contrastive learning.
- Authors
Huang, Weijian; Li, Cheng; Zhou, Hong-Yu; Yang, Hao; Liu, Jiarun; Liang, Yong; Zheng, Hairong; Zhang, Shaoting; Wang, Shanshan
- 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. Multi-modal foundation models are increasingly important in medical applications. Here, authors show a masked contrastive chest X-ray model that achieves fine-grained image understanding and zero-shot capabilities, outperforming existing methods
- Subjects
COMPUTER-aided diagnosis; X-ray imaging; IMAGE analysis; TASK analysis; DIAGNOSTIC imaging; X-rays
- Publication
Nature Communications, 2024, Vol 15, Issue 1, p1
- ISSN
2041-1723
- Publication type
Article
- DOI
10.1038/s41467-024-51749-0