# MedSapiens: Taking a Pose to Rethink Medical Imaging Landmark Detection

arXiv: https://arxiv.org/abs/2511.04255 · HTML: https://mlsanity.com/paper/2511.04255/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 40 references that are in the map.
- First posted on arXiv 6 Nov 2025.

## Builds on (most cited first, 25 of 25)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Customized Segment Anything Model for Medical Image Segmentation](https://mlsanity.com/paper/2304.13785/) (2023)
- [Sapiens: Foundation for Human Vision Models](https://mlsanity.com/paper/2408.12569/) (2024)
- [BiomedParse: a biomedical foundation model for image parsing of everything everywhere all at once](https://mlsanity.com/paper/2405.12971/) (2024)
- [Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding](https://mlsanity.com/paper/2204.08129/) (2022)
- [Integrating Spatial Configuration into Heatmap Regression Based CNNs for Landmark Localization](https://mlsanity.com/paper/1908.00748/) (2019)
- [ViTPose++: Vision Transformer for Generic Body Pose Estimation](https://mlsanity.com/paper/2212.04246/) (2022)
- [uniGradICON: A Foundation Model for Medical Image Registration](https://mlsanity.com/paper/2403.05780/) (2024)
- [Text-guided Foundation Model Adaptation for Pathological Image Classification](https://mlsanity.com/paper/2307.14901/) (2023)
- [High-Throughput Precision Phenotyping of Left Ventricular Hypertrophy with Cardiovascular Deep Learning](https://mlsanity.com/paper/2106.12511/) (2021)
- [MedCLIP-SAM: Bridging Text and Image Towards Universal Medical Image Segmentation](https://mlsanity.com/paper/2403.20253/) (2024)
- [Self-Prompting Large Vision Models for Few-Shot Medical Image Segmentation](https://mlsanity.com/paper/2308.07624/) (2023)
- [multiGradICON: A Foundation Model for Multimodal Medical Image Registration](https://mlsanity.com/paper/2408.00221/) (2024)
- [Cephalometric Landmark Detection across Ages with Prototypical Network](https://mlsanity.com/paper/2406.12577/) (2024)
- [UOD: Universal One-shot Detection of Anatomical Landmarks](https://mlsanity.com/paper/2306.07615/) (2023)
- [Depth-Driven Geometric Prompt Learning for Laparoscopic Liver Landmark Detection](https://mlsanity.com/paper/2406.17858/) (2024)
- [Structure-Guided Self-Supervised Matching for One-Shot Medical Landmark Detection](https://mlsanity.com/paper/2203.01687/) (2022)
- [Towards multi-modal anatomical landmark detection for ultrasound-guided brain tumor resection with contrastive learning](https://mlsanity.com/paper/2307.14523/) (2023)
- [FM-OSD: Foundation Model-Enabled One-Shot Detection of Anatomical Landmarks](https://mlsanity.com/paper/2407.05412/) (2024)
- [FD-SOS: Vision-Language Open-Set Detectors for Bone Fenestration and Dehiscence Detection from Intraoral Images](https://mlsanity.com/paper/2407.09088/) (2024)
- [Synthetic Augmentation for Anatomical Landmark Localization using DDPMs](https://mlsanity.com/paper/2410.12489/) (2024)
- [Topological GCN for Improving Detection of Hip Landmarks from B-Mode Ultrasound Images](https://mlsanity.com/paper/2408.13495/) (2024)
- [Geometric-Guided Few-Shot Dental Landmark Detection with Human-Centric Foundation Model](https://mlsanity.com/paper/2507.04710/) (2025)
- [WiseLVAM: A Novel Framework For Left Ventricle Automatic Measurements](https://mlsanity.com/paper/2508.12023/) (2025)

## Built on by (most cited first, 1 of 1)

- [CDPM-Align: Multi-Scale Guidance-Aligned Diffusion Pretraining for Robust Few-Shot Anatomical Landmark Detection](https://mlsanity.com/paper/2606.04898/) (2026)

## Abstract (arXiv)

This paper does not introduce a novel architecture; instead, it revisits a fundamental yet overlooked baseline: adapting human-centric foundation models for anatomical landmark detection in medical imaging. While landmark detection has traditionally relied on domain-specific models, the emergence of large-scale pre-trained vision models presents new opportunities. In this study, we investigate the adaptation of Sapiens, a human-centric foundation model designed for pose estimation, to medical imaging through multi-dataset pretraining, establishing a new state of the art across multiple datasets. Our proposed model, MedSapiens, demonstrates that human-centric foundation models, inherently optimized for spatial pose localization, provide strong priors for anatomical landmark detection, yet this potential has remained largely untapped. We benchmark MedSapiens against existing state-of-the-art models, achieving up to 5.26% improvement over generalist models and up to 21.81% improvement over specialist models in the average success detection rate (SDR). To further assess MedSapiens adaptability to novel downstream tasks with few annotations, we evaluate its performance in limited-data settings, achieving 2.69% improvement over the few-shot state of the art in SDR. Code and model weights are available at https://github.com/xmed-lab/MedSapiens .