用深度学习自动标注全身DXA图像关键点，提升体成分建模效率
Deep Learning Enables Large-Scale Shape and Appearance Modeling in Total-Body DXA Imaging
- 基于1683张人工标注图训练模型，实现99.5%关键点定位准确率
- 在35,928张图像上完成标注，发现体形与代谢、炎症等健康指标相关
- 适用于研究衰老、代谢病等人群的体成分与健康关系，开源可用
全身双能X射线吸收测定法（TBDXA）是一种低成本的全身成像技术，广泛用于体成分评估。本文开发并验证了一种深度学习方法，可在1,683张手动标注的TBDXA图像上自动标记关键点，外部测试集准确率达99.5%。为展示其在形态与外观建模（SAM）中的价值，该方法应用于35,928张不同成像模式的扫描图像，随后在两个未参与建模的队列中，通过两样本Kolmogorov-Smirnov检验分析特征分布与健康标志物的关系。结果显示，SAM特征分布与现有证据一致，并揭示了体成分与形态与虚弱、代谢、炎症及心血管代谢标志物之间的新关联。代码、模型权重、自动标注生成脚本及三角化文件已开源：https://github.com/hawaii-ai/dxa-pointplacement。
原文摘要 · Abstract (English)
Total-body dual X-ray absorptiometry (TBDXA) imaging is a relatively low-cost whole-body imaging modality, widely used for body composition assessment. We develop and validate a deep learning method for automatic fiducial point placement on TBDXA scans using 1,683 manually-annotated TBDXA scans. The method achieves 99.5% percentage correct keypoints in an external testing dataset. To demonstrate the value for shape and appearance modeling (SAM), our method is used to place keypoints on 35,928 scans for five different TBDXA imaging modes, then associations with health markers are tested in two cohorts not used for SAM model generation using two-sample Kolmogorov-Smirnov tests. SAM feature distributions associated with health biomarkers are shown to corroborate existing evidence and generate new hypotheses on body composition and shape's relationship to various frailty, metabolic, inflammation, and cardiometabolic health markers. Evaluation scripts, model weights, automatic point file generation code, and triangulation files are available at https://github.com/hawaii-ai/dxa-pointplacement.
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。