DeepTumorVQA: A Hierarchical 3D CT Benchmark for Stage-Wise Evaluation of Medical VLMs and Tool-Augmented Agents

• URL: http://arxiv.org/abs/2605.09679v1
• Date: Sun, 10 May 2026 17:57:57 GMT
• Title: DeepTumorVQA: A Hierarchical 3D CT Benchmark for Stage-Wise Evaluation of Medical VLMs and Tool-Augmented Agents
• Abstract summary: We propose a hierarchical benchmark that decomposes 3D CT reasoning into four stages: recognition, measurement, visual reasoning, and medical reasoning.<n>The benchmark contains 476K questions across 42 clinical subtypes on 9,262 3D CT volumes.
• Score: 15.131996289027926
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Medical vision-language models (VLMs) and AI agents have made significant progress in learning to analyze and reason about clinical images. However, existing medical visual question answering (VQA) benchmarks collapse model capabilities into a single accuracy score, obscuring where and why models fail. We propose DeepTumorVQA, a hierarchical benchmark that follows the multi-stage evidence chain in tumor diagnosis and decomposes 3D CT reasoning into four stages: recognition, measurement, visual reasoning, and medical reasoning. Higher-level questions remain independently scorable, while their ground-truth evidence chains are defined over lower-level primitives. The benchmark contains 476K questions across 42 clinical subtypes on 9,262 3D CT volumes. In addition to a direct reasoning mode for VLMs, DeepTumorVQA provides tool-interaction environments for agent evaluation, where a model can call external tools, including segmentation models, measurement programs, and medical knowledge modules, before answering the question. Evaluating over 30 model configurations, we find that reliable quantitative measurement is the primary bottleneck, making later-stage visual and medical reasoning harder for VLMs, while tool augmentation substantially mitigates this issue. When tools are available, leveraging medical knowledge and tools to reason about medical images becomes a new challenge. We further show that ground-truth step-by-step tool-use traces from DeepTumorVQA can supervise agents and reduce tool-use and reasoning failures. This stage-wise progression from recognition to measurement to visual and medical reasoning provides a concrete roadmap for future medical VLM and AI agent studies. All data and code are released at https://github.com/Schuture/DeepTumorVQA.

Related papers

• ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning [59.558706734431276]
  Current evaluations of spatial intelligence can be systematically invalid under modern vision-language model (VLM) settings.<n>We introduce ReVSI, a benchmark and protocol that ensures each QA pair is answerable and correct under the model's actual inputs.
  arXiv  Detail & Related papers  (2026-04-27T10:45:51Z)
• MedForget: Hierarchy-Aware Multimodal Unlearning Testbed for Medical AI [66.0701326117134]
  MedForget is a hierarchy-aware multimodal unlearning testbed for building compliant medical AI systems.<n>We show that existing methods struggle to achieve complete, hierarchy-aware forgetting without reducing diagnostic performance.<n>We introduce a reconstruction attack that progressively adds hierarchical level context to prompts.
  arXiv  Detail & Related papers  (2025-12-10T17:55:06Z)
• MedVision: Dataset and Benchmark for Quantitative Medical Image Analysis [29.537915199171547]
  We introduce MedVision, a dataset and benchmark designed to evaluate and improve vision-language models (VLMs) on medical image analysis.<n>MedVision spans 22 public datasets covering diverse anatomies and modalities, with 30.8 million image-annotation pairs.<n>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.<n>With supervised fine-tuning on MedVision, we significantly enhance their performance across detection, T/L estimation, and A/D measurement
  arXiv  Detail & Related papers  (2025-11-24T01:26:07Z)
• Hulu-Med: A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding [112.46150793476603]
  We introduce Hulu-Med, a transparent, generalist medical Vision-Language Model (VLM)<n>Hulu-Med is trained on a curated corpus of 16.7 million samples, spanning 12 major anatomical systems and 14 medical imaging modalities.<n>Hulu-Med surpasses existing open-source models on 27 of 30 benchmarks and outperforms proprietary systems such as GPT-4o on 16 benchmarks.
  arXiv  Detail & Related papers  (2025-10-09T17:06:42Z)
• TemMed-Bench: Evaluating Temporal Medical Image Reasoning in Vision-Language Models [54.48710348910535]
  Existing medical reasoning benchmarks primarily focus on analyzing a patient's condition based on an image from a single visit.<n>We introduce TemMed-Bench, the first benchmark designed for analyzing changes in patients' conditions between different clinical visits.
  arXiv  Detail & Related papers  (2025-09-29T17:51:26Z)
• MedGemma Technical Report [75.88152277443179]
  We introduce MedGemma, a collection of medical vision-language foundation models based on Gemma 3 4B and 27B.<n>MedGemma demonstrates advanced medical understanding and reasoning on images and text.<n>We additionally introduce MedSigLIP, a medically-tuned vision encoder derived from SigLIP.
  arXiv  Detail & Related papers  (2025-07-07T17:01:44Z)
• MedErr-CT: A Visual Question Answering Benchmark for Identifying and Correcting Errors in CT Reports [4.769418278782809]
  We introduce MedErr-CT, a novel benchmark for evaluating medical MLLMs' ability to identify and correct errors in CT reports.<n>The benchmark includes six error categories - four vision-centric errors (Omission, Insertion, Direction, Size) and two lexical error types (Unit, Typo)
  arXiv  Detail & Related papers  (2025-06-24T00:51:03Z)
• Are Vision Language Models Ready for Clinical Diagnosis? A 3D Medical Benchmark for Tumor-centric Visual Question Answering [8.185551155349241]
  Vision-Language Models (VLMs) have shown promise in various 2D visual tasks, yet their readiness for 3D clinical diagnosis remains unclear.<n>We present DeepTumorVQA, a diagnostic visual question answering benchmark targeting abdominal tumors in CT scans.<n>It comprises 9,262 CT volumes (3.7M slices) from 17 public datasets, with 395K expert-level questions spanning four categories: Recognition, Measurement, Visual Reasoning, and Medical Reasoning.
  arXiv  Detail & Related papers  (2025-05-25T00:50:15Z)
• GMAI-MMBench: A Comprehensive Multimodal Evaluation Benchmark Towards General Medical AI [67.09501109871351]
  Large Vision-Language Models (LVLMs) are capable of handling diverse data types such as imaging, text, and physiological signals. GMAI-MMBench is the most comprehensive general medical AI benchmark with well-categorized data structure and multi-perceptual granularity to date. It is constructed from 284 datasets across 38 medical image modalities, 18 clinical-related tasks, 18 departments, and 4 perceptual granularities in a Visual Question Answering (VQA) format.
  arXiv  Detail & Related papers  (2024-08-06T17:59:21Z)
• Visual Question Answering in the Medical Domain [13.673890873313354]
  We present a novel contrastive learning pretraining method to mitigate the problem of small datasets for the Med-VQA task. Our proposed model obtained an accuracy of 60% on the VQA-Med 2019 test set, giving comparable results to other state-of-the-art Med-VQA models.
  arXiv  Detail & Related papers  (2023-09-20T06:06:10Z)
• LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching [59.01894976615714]
  We introduce LVM-Med, the first family of deep networks trained on large-scale medical datasets. We have collected approximately 1.3 million medical images from 55 publicly available datasets. LVM-Med empirically outperforms a number of state-of-the-art supervised, self-supervised, and foundation models.
  arXiv  Detail & Related papers  (2023-06-20T22:21:34Z)
• PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering [56.25766322554655]
  Medical Visual Question Answering (MedVQA) presents a significant opportunity to enhance diagnostic accuracy and healthcare delivery. We propose a generative-based model for medical visual understanding by aligning visual information from a pre-trained vision encoder with a large language model. We train the proposed model on PMC-VQA and then fine-tune it on multiple public benchmarks, e.g., VQA-RAD, SLAKE, and Image-Clef 2019.
  arXiv  Detail & Related papers  (2023-05-17T17:50:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.