发表机构
National Library of Medicine; National Institutes of Health（美国国家医学图书馆; 美国国立卫生研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出CephViT模型，在公开数据集上实现头影测量标志点自动定位，基于CBCT生成的DRR进行骨性错颌分类，性能与手动标注相当，验证了自动分析的可行性。
AI 中文摘要
手动头影测量标志点标注对于颅面评估十分重要，但该过程耗时且难以规模化。我们提出了CephViT，一种基于Vision Transformer的自动二维侧向头影测量标志点定位模型，并评估其在下游骨性错颌分类中的应用。CephViT在公开侧向头影测量片数据集上进行训练和基准测试，平均径向误差为1.28±1.42mm，在3.0mm阈值下的成功检测率为92.0%。由于私人评估队列包含三维CBCT扫描，我们从每个扫描体生成类似侧向头影测量片的数字重建放射影像（DRR），并将其作为二维输入送入标志点定位模型。将标志点坐标归一化到共同坐标系后，利用参考流程与DRR流程共享的标志点进行骨性错颌分类。使用DRR定位标志点的分类性能与手动标注参考标志点的结果相当，准确率分别为70.0%和68.3%。这些结果表明，基于CBCT生成的DRR进行自动头影测量分析用于骨性错颌评估具有可行性。
英文摘要
Manual cephalometric landmark annotation is important for craniofacial assessment but is labor-intensive and difficult to scale. We introduce CephViT, a Vision Transformer-based model for automated 2D lateral cephalometric landmark localization, and evaluate its use in downstream skeletal malocclusion classification. CephViT was trained and benchmarked on a public lateral cephalogram dataset, achieving a mean radial error of 1.28 +/- 1.42 mm and a successful detection rate of 92.0% at 3.0 mm. Because the private evaluation cohort consisted of 3D CBCT scans, lateral cephalogram-like digitally reconstructed radiographs (DRRs) were generated from each volume and used as 2D inputs to the landmark localization model. Landmark coordinates were normalized into a common coordinate frame, and skeletal malocclusion classification was performed using landmarks shared between the reference and DRR-based pipelines. Classification performance using DRR-localized landmarks was comparable to that obtained using manually annotated reference landmarks, with accuracies of 70.0% and 68.3%, respectively. These results support the feasibility of automated cephalometric analysis on CBCT-derived DRRs for skeletal malocclusion assessment.
CommentsAccepted for presentation at the ODIN 2026 Workshop, held in conjunction with MICCAI 2026
