# Zero-shot System for Automatic Body Region Detection for Volumetric CT and MR Images

arXiv: https://arxiv.org/abs/2602.08717 · HTML: https://mlsanity.com/paper/2602.08717/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 17 references that are in the map.
- First posted on arXiv 9 Feb 2026.

## Builds on (most cited first, 11 of 11)

- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [TotalSegmentator: robust segmentation of 104 anatomical structures in CT images](https://mlsanity.com/paper/2208.05868/) (2022)
- [Multi-organ Segmentation over Partially Labeled Datasets with Multi-scale Feature Abstraction](https://mlsanity.com/paper/2001.00208/) (2020)
- [SAM: Self-supervised Learning of Pixel-wise Anatomical Embeddings in Radiological Images](https://mlsanity.com/paper/2012.02383/) (2020)
- [TotalSegmentator MRI: Robust Sequence-independent Segmentation of Multiple Anatomic Structures in MRI](https://mlsanity.com/paper/2405.19492/) (2024)
- [You Only Learn Once: Universal Anatomical Landmark Detection](https://mlsanity.com/paper/2103.04657/) (2021)
- [Learn Fine-grained Adaptive Loss for Multiple Anatomical Landmark Detection in Medical Images](https://mlsanity.com/paper/2105.09124/) (2021)
- [Content-Based Image Retrieval for Multi-Class Volumetric Radiology Images: A Benchmark Study](https://mlsanity.com/paper/2405.09334/) (2024)
- [Deep Learning Body Region Classification of MRI and CT examinations](https://mlsanity.com/paper/2104.13826/) (2021)
- [A simple and effective approach for body part recognition on CT scans based on projection estimation](https://mlsanity.com/paper/2504.21810/) (2025)
- [Content-based 3D Image Retrieval and a ColBERT-inspired Re-ranking for Tumor Flagging and Staging](https://mlsanity.com/paper/2507.17412/) (2025)

## Abstract (arXiv)

Reliable identification of anatomical body regions is a prerequisite for many automated medical imaging workflows, yet existing solutions remain heavily dependent on unreliable DICOM metadata. Current solutions mainly use supervised learning, which limits their applicability in many real-world scenarios. In this work, we investigate whether body region detection in volumetric CT and MR images can be achieved in a fully zero-shot manner by using knowledge embedded in large pre-trained foundation models. We propose and systematically evaluate three training-free pipelines: (1) a segmentation-driven rule-based system leveraging pre-trained multi-organ segmentation models, (2) a Multimodal Large Language Model (MLLM) guided by radiologist-defined rules, and (3) a segmentation-aware MLLM that combines visual input with explicit anatomical evidence. All methods are evaluated on 887 heterogeneous CT and MR scans with manually verified anatomical region labels. The segmentation-driven rule-based approach achieves the strongest and most consistent performance, with weighted F1-scores of 0.947 (CT) and 0.914 (MR), demonstrating robustness across modalities and atypical scan coverage. The MLLM performs competitively in visually distinctive regions, while the segmentation-aware MLLM reveals fundamental limitations.