arXiv cs.AI· Augustin Daridon, Sofiane Sifaoui, Ayman Assi, Mohamad Karam, Wafa Skalli, Elsa Angelini, Loic Le Folgoc·· 2 天前AI 评分18
用稠密表示学习与可微形状建模做脊柱关键点检测
Dense Representation Learning and Differentiable Shape Modeling for Spine Landmark Detection
AI 导读
研究将脊柱 X 光片的关键点检测重构为像素级对比表示学习问题，用稠密像素嵌入匹配关键点原型，即使搭配通用 U-Net 主干也能生成比传统热图回归更具判别性的热图，更好区分不同椎骨的椎角。方法再将热图与脊柱关键点全局配置的可学习形状先验结合以消解位置歧义，在公开 AASCE 数据集和两个私有脊柱 X 光数据集上，关键点精度与临床参数估计均达到与 SOTA 相当的水平，代码与预训练权重已公开。
正文 · 原文
Abstract:Spine landmark detection from spinal X-ray is a key step for estimating spine deformation severity, for building biomechanical models, and for pre-operative planning. We reframe anatomical landmark detection as a pixel-level contrastive representation learning problem, matching dense pixel embeddings with landmark prototypes. Surprisingly, even with a generic U-Net backbone, this formulation results in more discriminative heatmaps compared to the traditional heatmap regression paradigm, leading to improved discrimination between vertebral corners on distinct vertebra. Furthermore, we combine the resulting heatmaps with learnable shape priors over the global configuration of spinal landmarks to resolve ambiguities in landmark locations, yielding a simple and practical approach to spinal landmark detection. Our approach is competitive, in terms of landmark accuracy and clinical parameter estimation, with the state-of-the-art on the public AASCE dataset and on two private spinal X-ray datasets. Our code and pre-trained weights are available at this https URL.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.36951 [cs.CV] |
| (or arXiv:2610.36951v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.36951 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Sofiane Sifaoui [view email]
[v1]
Tue, 27 Oct 2026 10:11:18 UTC (7,726 KB)
来源：arXiv cs.AI · arxiv.org