Saved in:
Bibliographic Details
Main Authors: Liu, Minghao, He, Zhitao, Fan, Zhiyuan, Wang, Qingyun, Fung, Yi R.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.01921
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918154237640704
author Liu, Minghao
He, Zhitao
Fan, Zhiyuan
Wang, Qingyun
Fung, Yi R.
author_facet Liu, Minghao
He, Zhitao
Fan, Zhiyuan
Wang, Qingyun
Fung, Yi R.
contents Text-guided image editing has seen significant progress in natural image domains, but its application in medical imaging remains limited and lacks standardized evaluation frameworks. Such editing could revolutionize clinical practices by enabling personalized surgical planning, enhancing medical education, and improving patient communication. To bridge this gap, we introduce MedEBench1, a robust benchmark designed to diagnose reliability in text-guided medical image editing. MedEBench consists of 1,182 clinically curated image-prompt pairs covering 70 distinct editing tasks and 13 anatomical regions. It contributes in three key areas: (1) a clinically grounded evaluation framework that measures Editing Accuracy, Context Preservation, and Visual Quality, complemented by detailed descriptions of intended edits and corresponding Region-of-Interest (ROI) masks; (2) a comprehensive comparison of seven state-of-theart models, revealing consistent patterns of failure; and (3) a diagnostic error analysis technique that leverages attention alignment, using Intersection-over-Union (IoU) between model attention maps and ROI masks to identify mislocalization issues, where models erroneously focus on incorrect anatomical regions. MedEBench sets the stage for developing more reliable and clinically effective text-guided medical image editing tools.
format Preprint
id arxiv_https___arxiv_org_abs_2506_01921
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MedEBench: Diagnosing Reliability in Text-Guided Medical Image Editing
Liu, Minghao
He, Zhitao
Fan, Zhiyuan
Wang, Qingyun
Fung, Yi R.
Computer Vision and Pattern Recognition
Artificial Intelligence
Text-guided image editing has seen significant progress in natural image domains, but its application in medical imaging remains limited and lacks standardized evaluation frameworks. Such editing could revolutionize clinical practices by enabling personalized surgical planning, enhancing medical education, and improving patient communication. To bridge this gap, we introduce MedEBench1, a robust benchmark designed to diagnose reliability in text-guided medical image editing. MedEBench consists of 1,182 clinically curated image-prompt pairs covering 70 distinct editing tasks and 13 anatomical regions. It contributes in three key areas: (1) a clinically grounded evaluation framework that measures Editing Accuracy, Context Preservation, and Visual Quality, complemented by detailed descriptions of intended edits and corresponding Region-of-Interest (ROI) masks; (2) a comprehensive comparison of seven state-of-theart models, revealing consistent patterns of failure; and (3) a diagnostic error analysis technique that leverages attention alignment, using Intersection-over-Union (IoU) between model attention maps and ROI masks to identify mislocalization issues, where models erroneously focus on incorrect anatomical regions. MedEBench sets the stage for developing more reliable and clinically effective text-guided medical image editing tools.
title MedEBench: Diagnosing Reliability in Text-Guided Medical Image Editing
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2506.01921