针对头影测量关键点检测，提出域对齐新方法提升跨域性能。
Optimising for the Unknown: Domain Alignment for Cephalometric Landmark Detection
- 通过区域面部提取与X光伪影增强实现域对齐。
- 在在线评测中达1.186mm的平均定位误差，2mm准确率82.04%。
- 适合医学影像关键点检测及跨域模型优化研究者参考。
头影测量关键点检测旨在识别临床医生标注的关键解剖点。每个关键点为一个真实标注点，机器学习模型通过热图预测其概率分布位置。本文针对2024年CL-Detection MICCAI挑战赛，提出一种域对齐策略，包含区域面部提取模块和X射线伪影增强流程。在在线验证排行榜上，该方法以1.186mm的平均定位误差（MRE）排名第一，2mm准确率（2mm SDR）为82.04%，位列第三。代码已公开于https://github.com/Julian-Wyatt/OptimisingfortheUnknown。
原文摘要 · Abstract (English)
Cephalometric Landmark Detection is the process of identifying key areas for cephalometry. Each landmark is a single GT point labelled by a clinician. A machine learning model predicts the probability locus of a landmark represented by a heatmap. This work, for the 2024 CL-Detection MICCAI Challenge, proposes a domain alignment strategy with a regional facial extraction module and an X-ray artefact augmentation procedure. The challenge ranks our method's results as the best in MRE of 1.186mm and third in the 2mm SDR of 82.04% on the online validation leaderboard. The code is available at https://github.com/Julian-Wyatt/OptimisingfortheUnknown.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。