# Structure-Guided Self-Supervised Matching for One-Shot Medical Landmark Detection

arXiv: https://arxiv.org/abs/2203.01687 · HTML: https://mlsanity.com/paper/2203.01687/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 33 references that are in the map.
- First posted on arXiv 3 Mar 2022.

## Builds on (most cited first, 20 of 20)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [Contrastive learning of global and local features for medical image segmentation with limited annotations](https://mlsanity.com/paper/2006.10511/) (2020)
- [A Survey on Deep Semi-supervised Learning](https://mlsanity.com/paper/2103.00550/) (2021)
- [Models Genesis: Generic Autodidactic Models for 3D Medical Image Analysis](https://mlsanity.com/paper/1908.06912/) (2019)
- [Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotation](https://mlsanity.com/paper/2007.09886/) (2020)
- [Integrating Spatial Configuration into Heatmap Regression Based CNNs for Landmark Localization](https://mlsanity.com/paper/1908.00748/) (2019)
- [SAM: Self-supervised Learning of Pixel-wise Anatomical Embeddings in Radiological Images](https://mlsanity.com/paper/2012.02383/) (2020)
- [Structured Landmark Detection via Topology-Adapting Deep Graph Learning](https://mlsanity.com/paper/2004.08190/) (2020)
- [Cephalometric Landmark Detection by AttentiveFeature Pyramid Fusion and Regression-Voting](https://mlsanity.com/paper/1908.08841/) (2019)
- [One-Shot Medical Landmark Detection](https://mlsanity.com/paper/2103.04527/) (2021)
- [You Only Learn Once: Universal Anatomical Landmark Detection](https://mlsanity.com/paper/2103.04657/) (2021)
- [An Attention-Guided Deep Regression Model for Landmark Detection in Cephalograms](https://mlsanity.com/paper/1906.07549/) (2019)
- [Models Genesis](https://mlsanity.com/paper/2004.07882/) (2020)
- [Contrastive Learning of Relative Position Regression for One-Shot Object Localization in 3D Medical Images](https://mlsanity.com/paper/2012.07043/) (2020)
- [Which images to label for few-shot medical landmark detection?](https://mlsanity.com/paper/2112.04386/) (2021)
- [Semi-supervised Anatomical Landmark Detection via Shape-regulated Self-training](https://mlsanity.com/paper/2105.13593/) (2021)

## Built on by (most cited first, 5 of 5)

- [SAM++: Enhancing Anatomic Matching using Semantic Information and Structural Inference](https://mlsanity.com/paper/2306.13988/) (2023)
- [FM-OSD: Foundation Model-Enabled One-Shot Detection of Anatomical Landmarks](https://mlsanity.com/paper/2407.05412/) (2024)
- [Matching in the Wild: Learning Anatomical Embeddings for Multi-Modality Images](https://mlsanity.com/paper/2307.03535/) (2023)
- [MedSapiens: Taking a Pose to Rethink Medical Imaging Landmark Detection](https://mlsanity.com/paper/2511.04255/) (2025)
- [UAE: Universal Anatomical Embedding on Multi-modality Medical Images](https://mlsanity.com/paper/2311.15111/) (2023)

## Abstract (arXiv)

Medical landmark detection usually requires accurate expert annotations, which are laborious and difficult to scale across anatomical regions. In this work, we study an extreme annotation-efficient setting where only a single annotated template image is available. We propose SGB-Match, a structure-guided coarse-to-fine self-supervised matching framework for one-shot medical landmark detection. The framework first learns dense anatomical correspondence from unlabeled augmented image pairs, and then transfers the landmark definition from the annotated template to each target image through feature matching. Different from standard contrastive correspondence learning, where negative candidates are penalized by a structure-agnostic rule, we introduce a structure-guided bias into the contrastive objective. The bias is constructed from relative distance and edge-aware anatomical cues, and explicitly reweights the negative gradients: nearby structure-relevant candidates are weakly repelled, while distant or structure-irrelevant negatives are strongly suppressed. As a result, the learned feature space better preserves local anatomical structures around template landmarks and reduces confusing responses from repeated textures. We further adopt a global-to-local design, where a global encoder provides coarse landmark localization and a local encoder refines the prediction in a cropped region. Extensive experiments on four 2D radiological landmark datasets demonstrate that SGB-Match achieves strong one-shot performance across both public and newly collected datasets and consistently benefits from both structure-guided bias and two-stage refinement.