# Towards Enhancing 3D Spatial Reasoning in Medical Multimodal Large Language Models

arXiv: https://arxiv.org/abs/2607.13860 · HTML: https://mlsanity.com/paper/2607.13860/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 28 of its 33 references that are in the map.
- First posted on arXiv 15 Jul 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)
- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 28 of 28)

- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs](https://mlsanity.com/paper/2303.00915/) (2023)
- [PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering](https://mlsanity.com/paper/2305.10415/) (2023)
- [Segment Anything Model for Medical Image Analysis: an Experimental Study](https://mlsanity.com/paper/2304.10517/) (2023)
- [Towards Generalist Biomedical AI](https://mlsanity.com/paper/2307.14334/) (2023)
- [Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning](https://mlsanity.com/paper/2506.07044/) (2025)
- [Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomography](https://mlsanity.com/paper/2403.17834/) (2024)
- [Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey](https://mlsanity.com/paper/2503.12605/) (2025)
- [M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models](https://mlsanity.com/paper/2404.00578/) (2024)
- [Hulu-Med: A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding](https://mlsanity.com/paper/2510.08668/) (2025)
- [MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine](https://mlsanity.com/paper/2408.02900/) (2024)
- [VISTA3D: A Unified Segmentation Foundation Model For 3D Medical Imaging](https://mlsanity.com/paper/2406.05285/) (2024)
- [MedCoT: Medical Chain of Thought via Hierarchical Expert](https://mlsanity.com/paper/2412.13736/) (2024)
- [Med3DVLM: An Efficient Vision-Language Model for 3D Medical Image Analysis](https://mlsanity.com/paper/2503.20047/) (2025)
- [RadGenome-Chest CT: A Grounded Vision-Language Dataset for Chest CT Analysis](https://mlsanity.com/paper/2404.16754/) (2024)
- [Towards a Holistic Framework for Multimodal Large Language Models in Three-dimensional Brain CT Report Generation](https://mlsanity.com/paper/2407.02235/) (2024)
- [Biomedical Visual Instruction Tuning with Clinician Preference Alignment](https://mlsanity.com/paper/2406.13173/) (2024)
- [MC-CoT: A Modular Collaborative CoT Framework for Zero-shot Medical-VQA with LLM and MLLM Integration](https://mlsanity.com/paper/2410.04521/) (2024)
- [Med-2E3: A 2D-Enhanced 3D Medical Multimodal Large Language Model](https://mlsanity.com/paper/2411.12783/) (2024)
- [UMIT: Unifying Medical Imaging Tasks via Vision-Language Models](https://mlsanity.com/paper/2503.15892/) (2025)
- [Fleming-VL: Towards Universal Medical Visual Reasoning with Multimodal LLMs](https://mlsanity.com/paper/2511.00916/) (2025)
- [Fleming-R1: Toward Expert-Level Medical Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2509.15279/) (2025)
- [TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation](https://mlsanity.com/paper/2603.19039/) (2026)
- [M3CoTBench: Benchmark Chain-of-Thought of MLLMs in Medical Image Understanding](https://mlsanity.com/paper/2601.08758/) (2026)
- [Beyond Medical Diagnostics: How Medical Multimodal Large Language Models Think in Space](https://mlsanity.com/paper/2603.13800/) (2026)
- [UniReason-Med: A Shared Grounded Reasoning Interface for 2D-to-3D Transfer in Medical VQA](https://mlsanity.com/paper/2606.11740/) (2026)
- [ClinCoT: Clinical-Aware Visual Chain-of-Thought for Medical Vision Language Models](https://mlsanity.com/paper/2603.01124/) (2026)
- [DyCo-RL: Dynamic Cross-Modal Coordination for Visual Reasoning](https://mlsanity.com/paper/2606.08035/) (2026)

## Abstract (arXiv)

While Multimodal Large Language Models (MLLMs) have demonstrated remarkable success in 2D medical image understanding, their extension to 3D volumetric imaging remains hindered by prohibitive annotation costs and dataset opacity. Current data formats, predominantly consisting of rigid Visual Question Answering (VQA) pairs or unstructured final clinical reports, typically fail to capture explicit clinical reasoning. To address this limitation, we introduce a large-scale structured reasoning dataset constructed via a novel slice-wise data synthesis paradigm. Inspired by the genuine diagnostic workflow of radiologists, this paradigm models visual cognition by decomposing the complex 3D reading process, translating global clinical priors into fine-grained, per-slice observations that are subsequently synthesized into an interpretable Chain-of-Thought (CoT). Crucially, this synthesized reasoning framework enforces essential clinical principles: sequential spatial tracking, multi-slice spatial awareness for artifact mitigation, and differential exclusion. To validate this approach, we instruction-tune a standard 2D-pretrained MLLM baseline using the synthesized data to enhance its volumetric comprehension. Comprehensive evaluations across multiple 3D medical benchmarks demonstrate that our method yields significant performance improvements over the 2D baseline. Furthermore, the resulting model exhibits robust spatial reasoning capabilities and rivals resource-intensive native 3D architectures, effectively bridging the performance gap. Ultimately, this data-centric strategy unlocks deep volumetric understanding and highly interpretable clinical logic without requiring computationally expensive 3D-specific pre-training. The complete repository, including datasets and training workflows, is publicly available at https://github.com/2020420145009/hounsfield.