3DReasonKnee: Advancing Grounded Reasoning in Medical Vision Language Models

• URL: http://arxiv.org/abs/2510.20967v1
• Date: Thu, 23 Oct 2025 19:54:49 GMT
• Title: 3DReasonKnee: Advancing Grounded Reasoning in Medical Vision Language Models
• Abstract summary: Current Vision-Language Models (VLMs) struggle to ground anatomical regions in 3D medical images and reason about them in a step-by-step manner.<n>Existing 3D datasets provide localization labels, but none support this "grounded reasoning" ability.<n>We introduce 3DReasonKnee, the first 3D grounded reasoning dataset for medical images.
• Score: 8.67489471170441
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Current Vision-Language Models (VLMs) struggle to ground anatomical regions in 3D medical images and reason about them in a step-by-step manner, a key requirement of real-world diagnostic assessment. This ability is essential for aligning model outputs with the diagnostic workflows clinicians use in practice, enabling trustworthy clinician-AI collaboration. Existing 3D datasets provide localization labels, but none support this "grounded reasoning" ability. To address this gap, we introduce 3DReasonKnee, the first 3D grounded reasoning dataset for medical images, which provides 494k high-quality quintuples derived from 7,970 3D knee MRI volumes. Each quintuple includes: (1) the 3D MRI volume, (2) a diagnostic question targeting a specific anatomical region (3) a 3D bounding box localizing the relevant anatomical structures, (4) clinician-generated diagnostic reasoning steps that explicitly detail the 3D reasoning process, and (5) structured severity assessments for the relevant anatomical region. The creation and validation of 3DReasonKnee, involving over 450 hours of expert clinician time for manually segmenting MRIs and generating reasoning chains, ensures its superior quality and clinical relevance. We establish ReasonKnee-Bench to evaluate localization and diagnostic accuracy, providing insight into VLM ability to perform grounding and severity assessment across anatomical regions and diagnostic inquiries. We benchmark five state-of-the-art VLMs, providing baseline performance for ReasonKnee-Bench. By providing this unique resource of expert-annotated 3D reasoning pathways, 3DReasonKnee serves as a repository of orthopedic surgeons' diagnostic expertise and offers a vital testbed for advancing multimodal medical AI systems towards 3D, clinically aligned, localized decision-making capabilities. The dataset can be found in: https://huggingface.co/datasets/rajpurkarlab/3DReasonKnee

Related papers

• ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding [67.57715989349471]
  Multimodal large language models (MLLMs) hold immense potential to revolutionize clinical practice, yet deploying them in the medical domain is fundamentally a vision-centric challenge.<n>We introduce ClinFusion, a vision-centric MLLM designed for holistic medical understanding.<n>We show that ClinFusion sets a new state-of-the-art across a comprehensive suite of 2D and 3D multimodal medical benchmarks.
  arXiv  Detail & Related papers  (2026-07-27T17:59:49Z)
• Disease-Centric Vision-Language Pretraining with Hybrid Visual Encoding for 3D Computed Tomography [75.7789001619107]
  Vision-language pre-training holds great promise for general-purpose medical AI.<n>We propose a tailored framework featuring three key components.<n>A diagnosis-aware prompt strategy employs real clinical phrases and aggregated disease prototypes to bridge the pre-training-inference gap.
  arXiv  Detail & Related papers  (2026-06-24T08:24:45Z)
• A unified multi-task framework enables interpretable chest radiograph analysis [35.74517495754825]
  IMT-CXR is a framework that emulates radiologists' diagnostic workflow through three evidence-driven stages.<n>The framework employs a unified transformer architecture optimized via medical-domain instruction tuning.<n>Three radiologists rated 66% of AI-generated reports as comparable to or surpassing original clinical reports in diagnostic clarity.
  arXiv  Detail & Related papers  (2026-06-02T10:02:15Z)
• Lost in Volume: The CT-SpatialVQA Benchmark for Evaluating Semantic-Spatial Understanding of 3D Medical Vision-Language Models [3.6659638651482536]
  Recent advances in 3D medical vision-language models have enabled joint reasoning over volumetric images and text.<n>It remains unclear whether these models learn spatially grounded anatomy from 3D volumes or rely primarily on learned priors and language correlations.<n>We introduce CT-SpatialVQA, a benchmark designed to evaluate semantic-spatial reasoning in 3D CT data.
  arXiv  Detail & Related papers  (2026-05-09T08:16:00Z)
• Med3D-R1: Incentivizing Clinical Reasoning in 3D Medical Vision-Language Models for Abnormality Diagnosis [20.302134776419955]
  We propose a reinforcement learning framework with a two-stage training process: Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL)<n>In RL stage, we redesign the consistency reward to explicitly promote coherent, step-by-step diagnostic reasoning.<n>Our model attains state-of-the-art accuracies of 41.92% on CT-RATE and 44.99% on RAD-ChestCT.
  arXiv  Detail & Related papers  (2026-02-01T12:43:11Z)
• RAD: Towards Trustworthy Retrieval-Augmented Multi-modal Clinical Diagnosis [56.373297358647655]
  Retrieval-Augmented Diagnosis (RAD) is a novel framework that injects external knowledge into multimodal models directly on downstream tasks.<n>RAD operates through three key mechanisms: retrieval and refinement of disease-centered knowledge from multiple medical sources, a guideline-enhanced contrastive loss transformer, and a dual decoder.
  arXiv  Detail & Related papers  (2025-09-24T10:36:14Z)
• 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)
• Describe Anything in Medical Images [32.785523415007]
  We propose MedDAM, the first comprehensive framework leveraging large vision-language models for region-specific captioning in medical images.<n>MedDAM employs medical expert-designed prompts tailored to specific imaging modalities and establishes a robust evaluation benchmark.<n>This benchmark evaluates both MedDAM and other large vision-language models, focusing on clinical factuality through attribute-level verification tasks.
  arXiv  Detail & Related papers  (2025-05-09T05:45:31Z)
• Uncertainty-aware Medical Diagnostic Phrase Identification and Grounding [72.18719355481052]
  We introduce a novel task called Medical Report Grounding (MRG)<n>MRG aims to directly identify diagnostic phrases and their corresponding grounding boxes from medical reports in an end-to-end manner.<n>We propose uMedGround, a robust and reliable framework that leverages a multimodal large language model to predict diagnostic phrases.
  arXiv  Detail & Related papers  (2024-04-10T07:41:35Z)
• On the Localization of Ultrasound Image Slices within Point Distribution Models [84.27083443424408]
  Thyroid disorders are most commonly diagnosed using high-resolution Ultrasound (US) Longitudinal tracking is a pivotal diagnostic protocol for monitoring changes in pathological thyroid morphology. We present a framework for automated US image slice localization within a 3D shape representation.
  arXiv  Detail & Related papers  (2023-09-01T10:10:46Z)
• Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&3D Medical Data [66.9359934608229]
  This study aims to initiate the development of Radiology Foundation Model, termed as RadFM. To the best of our knowledge, this is the first large-scale, high-quality, medical visual-language dataset, with both 2D and 3D scans. We propose a new evaluation benchmark, RadBench, that comprises five tasks, including modality recognition, disease diagnosis, visual question answering, report generation and rationale diagnosis.
  arXiv  Detail & Related papers  (2023-08-04T17:00:38Z)
• Knowledge-enhanced Visual-Language Pre-training on Chest Radiology Images [40.52487429030841]
  We propose Knowledge-enhanced Auto Diagnosis (KAD) to guide vision-supervised pre-training using paired chest X-rays and radiology reports. We evaluate KAD on four external X-ray datasets and demonstrate that its zero-shot performance is superior to that of fully-language models.
  arXiv  Detail & Related papers  (2023-02-27T18:53:10Z)
• A unified 3D framework for Organs at Risk Localization and Segmentation for Radiation Therapy Planning [56.52933974838905]
  Current medical workflow requires manual delineation of organs-at-risk (OAR) In this work, we aim to introduce a unified 3D pipeline for OAR localization-segmentation. Our proposed framework fully enables the exploitation of 3D context information inherent in medical imaging.
  arXiv  Detail & Related papers  (2022-03-01T17:08:41Z)
• Simulating Realistic MRI variations to Improve Deep Learning model and visual explanations using GradCAM [0.0]
  We use a modified HighRes3DNet model for solving brain MRI volumetric landmark detection problem. Grad-CAM produces a coarse localization map highlighting the regions the model is focusing.
  arXiv  Detail & Related papers  (2021-11-01T11:14:23Z)
• SpineOne: A One-Stage Detection Framework for Degenerative Discs and Vertebrae [54.751251046196494]
  We propose a one-stage detection framework termed SpineOne to simultaneously localize and classify degenerative discs and vertebrae from MRI slices. SpineOne is built upon the following three key techniques: 1) a new design of the keypoint heatmap to facilitate simultaneous keypoint localization and classification; 2) the use of attention modules to better differentiate the representations between discs and vertebrae; and 3) a novel gradient-guided objective association mechanism to associate multiple learning objectives at the later training stage.
  arXiv  Detail & Related papers  (2021-10-28T12:59:06Z)

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.