MedGEN-Bench: Contextually entangled benchmark for open-ended multimodal medical generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Junjie, Yan, Yuhao, Wu, Gang, Wang, Yuxuan, Liang, Ruoyu, Jiang, Xinjie, Wan, Xiang, Fan, Fenglei, Zhang, Yongquan, Qin, Feiwei, Wang, Changmiao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908661650030592
author Yang, Junjie
Yan, Yuhao
Wu, Gang
Wang, Yuxuan
Liang, Ruoyu
Jiang, Xinjie
Wan, Xiang
Fan, Fenglei
Zhang, Yongquan
Qin, Feiwei
Wang, Changmiao
author_facet Yang, Junjie
Yan, Yuhao
Wu, Gang
Wang, Yuxuan
Liang, Ruoyu
Jiang, Xinjie
Wan, Xiang
Fan, Fenglei
Zhang, Yongquan
Qin, Feiwei
Wang, Changmiao
contents As Vision-Language Models (VLMs) increasingly gain traction in medical applications, clinicians are progressively expecting AI systems not only to generate textual diagnoses but also to produce corresponding medical images that integrate seamlessly into authentic clinical workflows. Despite the growing interest, existing medical visual benchmarks present notable limitations. They often rely on ambiguous queries that lack sufficient relevance to image content, oversimplify complex diagnostic reasoning into closed-ended shortcuts, and adopt a text-centric evaluation paradigm that overlooks the importance of image generation capabilities. To address these challenges, we introduce MedGEN-Bench, a comprehensive multimodal benchmark designed to advance medical AI research. MedGEN-Bench comprises 6,422 expert-validated image-text pairs spanning six imaging modalities, 16 clinical tasks, and 28 subtasks. It is structured into three distinct formats: Visual Question Answering, Image Editing, and Contextual Multimodal Generation. What sets MedGEN-Bench apart is its focus on contextually intertwined instructions that necessitate sophisticated cross-modal reasoning and open-ended generative outputs, moving beyond the constraints of multiple-choice formats. To evaluate the performance of existing systems, we employ a novel three-tier assessment framework that integrates pixel-level metrics, semantic text analysis, and expert-guided clinical relevance scoring. Using this framework, we systematically assess 10 compositional frameworks, 3 unified models, and 5 VLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2511_13135
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MedGEN-Bench: Contextually entangled benchmark for open-ended multimodal medical generation
Yang, Junjie
Yan, Yuhao
Wu, Gang
Wang, Yuxuan
Liang, Ruoyu
Jiang, Xinjie
Wan, Xiang
Fan, Fenglei
Zhang, Yongquan
Qin, Feiwei
Wang, Changmiao
Computer Vision and Pattern Recognition
As Vision-Language Models (VLMs) increasingly gain traction in medical applications, clinicians are progressively expecting AI systems not only to generate textual diagnoses but also to produce corresponding medical images that integrate seamlessly into authentic clinical workflows. Despite the growing interest, existing medical visual benchmarks present notable limitations. They often rely on ambiguous queries that lack sufficient relevance to image content, oversimplify complex diagnostic reasoning into closed-ended shortcuts, and adopt a text-centric evaluation paradigm that overlooks the importance of image generation capabilities. To address these challenges, we introduce MedGEN-Bench, a comprehensive multimodal benchmark designed to advance medical AI research. MedGEN-Bench comprises 6,422 expert-validated image-text pairs spanning six imaging modalities, 16 clinical tasks, and 28 subtasks. It is structured into three distinct formats: Visual Question Answering, Image Editing, and Contextual Multimodal Generation. What sets MedGEN-Bench apart is its focus on contextually intertwined instructions that necessitate sophisticated cross-modal reasoning and open-ended generative outputs, moving beyond the constraints of multiple-choice formats. To evaluate the performance of existing systems, we employ a novel three-tier assessment framework that integrates pixel-level metrics, semantic text analysis, and expert-guided clinical relevance scoring. Using this framework, we systematically assess 10 compositional frameworks, 3 unified models, and 5 VLMs.
title MedGEN-Bench: Contextually entangled benchmark for open-ended multimodal medical generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.13135