Rethinking Medical Landmark Localization with Prototype Learning-based Progressive Offset Correction
2026-08-10 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial IntelligenceMachine Learning
AI summaryⓘ
The authors created a new method called PPOC-LL to help pinpoint important spots (landmarks) in medical images like X-rays and ultrasounds more accurately and efficiently. They improved the process by making the system focus on details step-by-step, learn local patterns better, and manage mistakes more smartly during training. They tested their method on large sets of images from different body parts and found it works well without needing too much computing power. Overall, their approach balances accuracy and speed effectively.
landmark localizationmedical imagingprototype learningmulti-scale feature pyramidoffset correctionregularizationX-rayultrasoundmodel complexitycephalometric landmarks
Authors
Jingxian Xu, Yuhao Huang, Rusi Chen, Yanfeng Zhou, Dong Ni
Abstract
Accurate landmark localization in medical images is a fundamental step for quantitative clinical measurement and downstream analysis. Existing localization methods have advanced, among which multi-stage refinement is a superior solution. Although this strategy mitigates the anatomical ambiguity inherent in single-stage global predictions, its high computational cost limits practical applicability. In this work, we propose a parameter-economic model, PPOC-LL, which leverages Prototype learning-based Progressive Offset Correction for Landmark Localization. Our contribution is three-fold. First, to drive coarse-to-fine landmark optimization, we introduce a multi-scale dynamic perception strategy for patch-level feature pyramid modeling. Second, to effectively handle anatomically similar patterns, we design a similarity-driven prototype learning mechanism that captures informative local semantics for robust offset prediction. Last, to stabilize the model learning and improve the overall performance, we incorporate a novel error-aware reliability regularization via tolerance-based balancing. We collected a large validation cohort, including two public and one private datasets spanning X-ray and ultrasound modalities, covering cephalometric, symphysis-fetal head, and fetal heart landmarks. Extensive experiments demonstrate that PPOC-LL achieves satisfactory performance with a favorable trade-off between accuracy and model complexity.