Foundation Model-Based One-Shot Anatomical Landmark Detection with Mamba and Graph Refinement
Open Access
- 2 June 2026
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 15 (11) , 2414
Abstract
Accurate anatomical landmark detection is important for orthodontic analysis, surgical planning, and morphometric measurement, but fully supervised methods usually require large expert-annotated datasets. This work studies a one-shot setting, where only a single annotated template image is used for training. We propose a foundation-model-based landmark detection framework using a frozen DINO Vision Transformer (ViT) backbone. The proposed framework integrates three complementary components: a Multi-Layer Multi-Facet (MLMF) module that adaptively fuses key and value features from multiple ViT layers through global source-wise reweighting; a Mamba-Based Long-Range Context Aggregation (MLCA) module that injects global anatomical context into fused patch descriptors with linear complexity; and a Topology-Constrained Graph Refinement (TCGR) module that refines the predicted landmark configuration using anatomical graph constraints. Experiments on the Cephalometric dataset and the Hand X-ray dataset demonstrate that the proposed method achieves strong performance. Overall, the results show that jointly exploiting multi-source foundation-model representations, efficient long-range context aggregation, and topology-aware refinement improves annotation-efficient anatomical landmark detection.Keywords
Funding Information
- Key Research and Development Program of Hainan Province (ZDYF2025(LALH)002)
- Natural Science Foundation of Beijing Municipality (L232039)
This publication has 28 references indexed in Scilit:
- VM-UNet: Vision Mamba UNet for Medical Image SegmentationACM Transactions on Multimedia Computing, Communications, and Applications, 2025
- FM-OSD: Foundation Model-Enabled One-Shot Detection of Anatomical Landmarks2024
- PDC-Net+: Enhanced Probabilistic Dense Correspondence NetworkIEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
- Landmark Localization for Cephalometric Analysis Using Multiscale Image Patch-Based Graph Convolutional NetworksIEEE Journal of Biomedical and Health Informatics, 2022
- Automated cephalometric landmark detection with confidence regions using Bayesian convolutional neural networksBMC Oral Health, 2020
- Integrating spatial configuration into heatmap regression based CNNs for landmark localizationMedical Image Analysis, 2019
- Integrating geometric configuration and appearance information into a unified framework for anatomical landmark localizationMedical Image Analysis, 2018
- Detecting Anatomical Landmarks From Limited Medical Imaging Data Using Two-Stage Task-Oriented Deep Neural NetworksIEEE Transactions on Image Processing, 2017
- A benchmark for comparison of dental radiography analysis algorithmsMedical Image Analysis, 2016
- Active appearance modelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2001