Bridging Vision and Language: Optimal Transport-Driven Radiology Report Generation via LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Haifeng, Zhang, Yufei, Ma, Leilei, Xu, Shuo, Sun, Dengdi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916826602012672
author Zhao, Haifeng
Zhang, Yufei
Ma, Leilei
Xu, Shuo
Sun, Dengdi
author_facet Zhao, Haifeng
Zhang, Yufei
Ma, Leilei
Xu, Shuo
Sun, Dengdi
contents Radiology report generation represents a significant application within medical AI, and has achieved impressive results. Concurrently, large language models (LLMs) have demonstrated remarkable performance across various domains. However, empirical validation indicates that general LLMs tend to focus more on linguistic fluency rather than clinical effectiveness, and lack the ability to effectively capture the relationship between X-ray images and their corresponding texts, thus resulting in poor clinical practicability. To address these challenges, we propose Optimal Transport-Driven Radiology Report Generation (OTDRG), a novel framework that leverages Optimal Transport (OT) to align image features with disease labels extracted from reports, effectively bridging the cross-modal gap. The core component of OTDRG is Alignment \& Fine-Tuning, where OT utilizes results from the encoding of label features and image visual features to minimize cross-modal distances, then integrating image and text features for LLMs fine-tuning. Additionally, we design a novel disease prediction module to predict disease labels contained in X-ray images during validation and testing. Evaluated on the MIMIC-CXR and IU X-Ray datasets, OTDRG achieves state-of-the-art performance in both natural language generation (NLG) and clinical efficacy (CE) metrics, delivering reports that are not only linguistically coherent but also clinically accurate.
format Preprint
id arxiv_https___arxiv_org_abs_2507_03908
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bridging Vision and Language: Optimal Transport-Driven Radiology Report Generation via LLMs
Zhao, Haifeng
Zhang, Yufei
Ma, Leilei
Xu, Shuo
Sun, Dengdi
Computer Vision and Pattern Recognition
Radiology report generation represents a significant application within medical AI, and has achieved impressive results. Concurrently, large language models (LLMs) have demonstrated remarkable performance across various domains. However, empirical validation indicates that general LLMs tend to focus more on linguistic fluency rather than clinical effectiveness, and lack the ability to effectively capture the relationship between X-ray images and their corresponding texts, thus resulting in poor clinical practicability. To address these challenges, we propose Optimal Transport-Driven Radiology Report Generation (OTDRG), a novel framework that leverages Optimal Transport (OT) to align image features with disease labels extracted from reports, effectively bridging the cross-modal gap. The core component of OTDRG is Alignment \& Fine-Tuning, where OT utilizes results from the encoding of label features and image visual features to minimize cross-modal distances, then integrating image and text features for LLMs fine-tuning. Additionally, we design a novel disease prediction module to predict disease labels contained in X-ray images during validation and testing. Evaluated on the MIMIC-CXR and IU X-Ray datasets, OTDRG achieves state-of-the-art performance in both natural language generation (NLG) and clinical efficacy (CE) metrics, delivering reports that are not only linguistically coherent but also clinically accurate.
title Bridging Vision and Language: Optimal Transport-Driven Radiology Report Generation via LLMs
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.03908