Multi-task Cross-modal Learning for Chest X-ray Image Retrieval

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liang, Zhaohui, Rajaraman, Sivaramakrishnan, Marini, Niccolo, Xue, Zhiyun, Antani, Sameer
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909985509736448
author Liang, Zhaohui
Rajaraman, Sivaramakrishnan
Marini, Niccolo
Xue, Zhiyun
Antani, Sameer
author_facet Liang, Zhaohui
Rajaraman, Sivaramakrishnan
Marini, Niccolo
Xue, Zhiyun
Antani, Sameer
contents CLIP and BiomedCLIP are examples of vision-language foundation models and offer strong cross-modal embeddings; however, they are not optimized for fine-grained medical retrieval tasks, such as retrieving clinically relevant radiology reports using chest X-ray (CXR) image queries. To address this shortcoming, we propose a multi-task learning framework to fine-tune BiomedCLIP and evaluate improvements to CXR image-text retrieval. Using BiomedCLIP as the backbone, we incorporate a lightweight MLP projector head trained with a multi-task composite loss function that includes: (1) a binary cross-entropy loss to distinguish normal from abnormal CXR studies, (2) a supervised contrastive loss to reinforce intra-class consistency, and (3) a CLIP loss to maintain cross-modal alignment. Experimental results demonstrate that the fine-tuned model achieves more balanced and clinically meaningful performance across both image-to-text and text-to-image retrieval tasks compared to the pretrained BiomedCLIP and general-purpose CLIP models. Furthermore, t-SNE visualizations reveal clearer semantic clustering of normal and abnormal cases, demonstrating the model's enhanced diagnostic sensitivity. These findings highlight the value of domain-adaptive, multi-task learning for advancing cross-modal retrieval in biomedical applications.
format Preprint
id arxiv_https___arxiv_org_abs_2601_05399
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Multi-task Cross-modal Learning for Chest X-ray Image Retrieval
Liang, Zhaohui
Rajaraman, Sivaramakrishnan
Marini, Niccolo
Xue, Zhiyun
Antani, Sameer
Computer Vision and Pattern Recognition
Artificial Intelligence
Information Retrieval
CLIP and BiomedCLIP are examples of vision-language foundation models and offer strong cross-modal embeddings; however, they are not optimized for fine-grained medical retrieval tasks, such as retrieving clinically relevant radiology reports using chest X-ray (CXR) image queries. To address this shortcoming, we propose a multi-task learning framework to fine-tune BiomedCLIP and evaluate improvements to CXR image-text retrieval. Using BiomedCLIP as the backbone, we incorporate a lightweight MLP projector head trained with a multi-task composite loss function that includes: (1) a binary cross-entropy loss to distinguish normal from abnormal CXR studies, (2) a supervised contrastive loss to reinforce intra-class consistency, and (3) a CLIP loss to maintain cross-modal alignment. Experimental results demonstrate that the fine-tuned model achieves more balanced and clinically meaningful performance across both image-to-text and text-to-image retrieval tasks compared to the pretrained BiomedCLIP and general-purpose CLIP models. Furthermore, t-SNE visualizations reveal clearer semantic clustering of normal and abnormal cases, demonstrating the model's enhanced diagnostic sensitivity. These findings highlight the value of domain-adaptive, multi-task learning for advancing cross-modal retrieval in biomedical applications.
title Multi-task Cross-modal Learning for Chest X-ray Image Retrieval
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2601.05399