Saved in:
Bibliographic Details
Main Authors: Monon, Mashrafi, Rahman, Umaima, Hanif, Asif, Saeed, Numan, Yaqub, Mohammad
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.08787
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917476596449280
author Monon, Mashrafi
Rahman, Umaima
Hanif, Asif
Saeed, Numan
Yaqub, Mohammad
author_facet Monon, Mashrafi
Rahman, Umaima
Hanif, Asif
Saeed, Numan
Yaqub, Mohammad
contents Recent advances in 3D medical vision-language models have enabled joint reasoning over volumetric images and text, showing strong performance in medical visual question-answering (VQA) and report generation. Despite this progress, it remains unclear whether these models learn spatially grounded anatomy from 3D volumes or rely primarily on learned priors and language correlations. This uncertainty stems from the lack of systematic evaluation of semantic-spatial reasoning in volumetric medical VLMs for clinically reliable decision support. To address this gap, we introduce CT-SpatialVQA, a benchmark designed to evaluate semantic-spatial reasoning in 3D CT data. The benchmark comprises 9077 clinically grounded question-answer (QA) pairs derived directly from 1601 radiology reports and CT volumes, which are validated via a robust LLM-assisted pipeline with a 95% human consensus agreement rate. Our dataset requires explicit anatomical localization, laterality awareness, structural comparison, and 3D inter-structure relational reasoning. We also introduce a standardized evaluation protocol and benchmark eight 3D medical VLMs, finding severe degradation on semantic-spatial reasoning tasks, averaging 34% accuracy and often below random, highlighting the need for deeper integration of volumetric evidence for trustworthy clinical use.
format Preprint
id arxiv_https___arxiv_org_abs_2605_08787
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Lost in Volume: The CT-SpatialVQA Benchmark for Evaluating Semantic-Spatial Understanding of 3D Medical Vision-Language Models
Monon, Mashrafi
Rahman, Umaima
Hanif, Asif
Saeed, Numan
Yaqub, Mohammad
Computer Vision and Pattern Recognition
Recent advances in 3D medical vision-language models have enabled joint reasoning over volumetric images and text, showing strong performance in medical visual question-answering (VQA) and report generation. Despite this progress, it remains unclear whether these models learn spatially grounded anatomy from 3D volumes or rely primarily on learned priors and language correlations. This uncertainty stems from the lack of systematic evaluation of semantic-spatial reasoning in volumetric medical VLMs for clinically reliable decision support. To address this gap, we introduce CT-SpatialVQA, a benchmark designed to evaluate semantic-spatial reasoning in 3D CT data. The benchmark comprises 9077 clinically grounded question-answer (QA) pairs derived directly from 1601 radiology reports and CT volumes, which are validated via a robust LLM-assisted pipeline with a 95% human consensus agreement rate. Our dataset requires explicit anatomical localization, laterality awareness, structural comparison, and 3D inter-structure relational reasoning. We also introduce a standardized evaluation protocol and benchmark eight 3D medical VLMs, finding severe degradation on semantic-spatial reasoning tasks, averaging 34% accuracy and often below random, highlighting the need for deeper integration of volumetric evidence for trustworthy clinical use.
title Lost in Volume: The CT-SpatialVQA Benchmark for Evaluating Semantic-Spatial Understanding of 3D Medical Vision-Language Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.08787