Lab. of Tissue Reconstruction Researcher, Institute for Life and Medical Sciences, Kyoto University, Japan; Division of Legal Medicine, Tottori University, Japan; Fujimoto Clinic for Oral and Maxillofacial Surgery, Japan.
Department of Legal Medicine, Shimane University Faculty of Medicine, Japan.
Forensic Sci Int. 2023 Feb;343:111548. doi: 10.1016/j.forsciint.2022.111548. Epub 2023 Jan 4.
In recent years, personal identification has been performed using antemortem panoramic X-ray images and postmortem-CT images. Using these, we have developed a personal identification method that focuses on the alveolar bone. This study examined the effectiveness of this method and aimed to implement a reproducible system.
For personal identification, a total of 633 CT images and panoramic X-ray images belonging to three groups with different conditions were used. These images were 160 sets in the same person group and 96,820 in the other groups. The similarity of alveolar bone images was calculated using the landmark method of Procrustes analysis. The processes were system implemented and the methodology was validated.
The ability to identify between the same person group and other person groups showed 0.9769 as the area under the curve (AUC: ROC curve). At the cutoff value of 4.978, there was no false rejection rate, but false acceptance rate was slightly higher.
This method was useful as a screening method for personal identification. In addition, system implementation was efficient and reduced human error. In the future, we aim to realize a more efficient personal identification method using distortion-corrected images and including auto-detective landmarks using deep learning.
近年来，个人身份识别采用了生前全景 X 射线图像和死后 CT 图像。在此基础上，我们开发了一种专注于牙槽骨的个人身份识别方法。本研究检验了该方法的有效性，并旨在实现一个可重复的系统。
为了进行个人身份识别，共使用了三组具有不同条件的 633 张 CT 图像和全景 X 射线图像。这些图像中，同个人组有 160 组，其他组有 96820 组。采用 Procrustes 分析的标志点法计算牙槽骨图像的相似性。对过程进行了系统实现，并对该方法进行了验证。
在相同人和其他人组之间进行身份识别的能力，曲线下面积（AUC：ROC 曲线）为 0.9769。在 4.978 的截断值处，没有假拒绝率，但假接受率略高。
该方法可作为个人身份识别的筛选方法。此外，系统实现效率高，减少了人为错误。未来，我们旨在使用经过失真校正的图像和包括使用深度学习的自动检测标志点来实现更有效的个人身份识别方法。
