Lost in Volume: The CT-SpatialVQA Benchmark for Evaluating Semantic-Spatial Understanding of 3D Medical Vision-Language Models
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 ...
| Authors | Mashrafi Monon, Umaima Rahman, Asif Hanif et al. |
|---|---|
| Primary category | cs.CV |
| Published | 9 May 2026 |
| Last updated at source | 19 June 2026 |
Connected in the knowledge graph
- Mashrafi2827/CT-SpatialVQADataset · cited by
Models and datasets referencing this paper
- Mashrafi2827/CT-SpatialVQADataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.