用3D面部结构识别罕见病表型，支持临床诊断。
Hierarchical Classification via Cascading Feature Elimination: Application to Human Phenotype Ontology-Aligned Facial Phenotyping (FaceMesh2HPO)
- 分层分类+逐步剔除特征，结合3D面部网格与人口统计信息
- 在10种疾病上达到0.55~0.89的AUROC，父节点表现优于末端术语
- 适合医学影像分析、遗传病筛查及可解释性要求高的场景
FaceMesh2HPO 是一个用于将面部表型描述符与人类表型本体（HPO）对齐以支持临床诊断的框架。基于124名临床医生对10种疾病（共107个HPO术语）及非综合征对照组的标注，从2D图像生成包含478个关键点的3D面部网格，并训练了一个基于PointNet的分层级联分类与特征剔除管道。最佳模型结合3D网格、面部轮廓和人口统计学信息，在父节点上的性能优于末端术语，AUROC范围为0.55至0.89。外部验证显示不同疾病的泛化能力存在差异。结果表明，基于3D面部几何的分层建模可实现可解释且与本体对齐的表型分类，但稀有末端术语的表现仍受限。需提升数据多样性与特征选择策略以增强鲁棒性和临床实用性。
原文摘要 · Abstract (English)
FaceMesh2HPO is a framework for classifying facial phenotypic descriptors aligned with the Human Phenotype Ontology (HPO) to support clinical diagnosis. Using annotations from 124 clinicians across 10 disorders (107 HPO terms) combined with non-syndromic controls, we generated 3D facial meshes (478 landmarks) from 2D images and trained a hierarchical PointNet-based pipeline with cascading classification and feature elimination. The best models, incorporating 3D meshes, facial outline, and demographic metadata, achieved AUROCs between ~0.55 and ~0.89, with higher performance at parent nodes than leaf terms. External validation showed variable generalizability across disorders. Results demonstrate that hierarchical modeling of 3D facial geometry enables interpretable, ontology-linked phenotype classification, though performance on rare leaf terms remains limited. Improved data diversity and feature selection strategies are needed to enhance robustness and clinical utility.
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。