MedVision: Dataset and Benchmark for Quantitative Medical Image Analysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yao, Yongcheng, Zong, Yongshuo, Dutt, Raman, Yang, Yongxin, Tsaftaris, Sotirios A, Hospedales, Timothy
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912726408757248
author Yao, Yongcheng
Zong, Yongshuo
Dutt, Raman
Yang, Yongxin
Tsaftaris, Sotirios A
Hospedales, Timothy
author_facet Yao, Yongcheng
Zong, Yongshuo
Dutt, Raman
Yang, Yongxin
Tsaftaris, Sotirios A
Hospedales, Timothy
contents Current vision-language models (VLMs) in medicine are primarily designed for categorical question answering (e.g., "Is this normal or abnormal?") or qualitative descriptive tasks. However, clinical decision-making often relies on quantitative assessments, such as measuring the size of a tumor or the angle of a joint, from which physicians draw their own diagnostic conclusions. This quantitative reasoning capability remains underexplored and poorly supported in existing VLMs. In this work, we introduce MedVision, a large-scale dataset and benchmark specifically designed to evaluate and improve VLMs on quantitative medical image analysis. MedVision spans 22 public datasets covering diverse anatomies and modalities, with 30.8 million image-annotation pairs. We focus on three representative quantitative tasks: (1) detection of anatomical structures and abnormalities, (2) tumor/lesion (T/L) size estimation, and (3) angle/distance (A/D) measurement. Our benchmarks show that current off-the-shelf VLMs perform poorly on these tasks. However, with supervised fine-tuning on MedVision, we significantly enhance their performance across detection, T/L estimation, and A/D measurement, demonstrating reduced error rates and improved precision. This work provides a foundation for developing VLMs with robust quantitative reasoning capabilities in medical imaging. Code and data are available at https://medvision-vlm.github.io.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18676
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MedVision: Dataset and Benchmark for Quantitative Medical Image Analysis
Yao, Yongcheng
Zong, Yongshuo
Dutt, Raman
Yang, Yongxin
Tsaftaris, Sotirios A
Hospedales, Timothy
Computer Vision and Pattern Recognition
Artificial Intelligence
N/A
I.2.10
Current vision-language models (VLMs) in medicine are primarily designed for categorical question answering (e.g., "Is this normal or abnormal?") or qualitative descriptive tasks. However, clinical decision-making often relies on quantitative assessments, such as measuring the size of a tumor or the angle of a joint, from which physicians draw their own diagnostic conclusions. This quantitative reasoning capability remains underexplored and poorly supported in existing VLMs. In this work, we introduce MedVision, a large-scale dataset and benchmark specifically designed to evaluate and improve VLMs on quantitative medical image analysis. MedVision spans 22 public datasets covering diverse anatomies and modalities, with 30.8 million image-annotation pairs. We focus on three representative quantitative tasks: (1) detection of anatomical structures and abnormalities, (2) tumor/lesion (T/L) size estimation, and (3) angle/distance (A/D) measurement. Our benchmarks show that current off-the-shelf VLMs perform poorly on these tasks. However, with supervised fine-tuning on MedVision, we significantly enhance their performance across detection, T/L estimation, and A/D measurement, demonstrating reduced error rates and improved precision. This work provides a foundation for developing VLMs with robust quantitative reasoning capabilities in medical imaging. Code and data are available at https://medvision-vlm.github.io.
title MedVision: Dataset and Benchmark for Quantitative Medical Image Analysis
topic Computer Vision and Pattern Recognition
Artificial Intelligence
N/A
I.2.10
url https://arxiv.org/abs/2511.18676