Related Experiment Video
Updated: Aug 14, 2025
09:10
Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures
Published on: August 5, 2021
1.8K
Implementation of a personal identification system using alveolar bone images.
Hideko Fujimoto1, Kaori Kimura-Kataoka2, Hidekazu Kanayama3
1Lab. 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.
Forensic Science International
|January 11, 2023
Summary
This study developed a personal identification method using alveolar bone from X-ray and CT images. The system demonstrated high accuracy, proving effective for screening and reducing errors in forensic identification.
Area of Science:
- Forensic Science
- Radiology
- Biometrics
Background:
- Personal identification commonly uses antemortem X-rays and postmortem CT scans.
- Alveolar bone offers a unique anatomical feature for identification.
Purpose of the Study:
- To evaluate a novel personal identification method based on alveolar bone.
- To implement a reproducible and efficient identification system.
Main Methods:
- Utilized 633 CT and panoramic X-ray images (160 same-person sets, 96,820 other-person sets).
- Employed Procrustes analysis with a landmark method to calculate alveolar bone image similarity.
- System implementation and validation were performed.
Main Results:
- Achieved an Area Under the Curve (AUC) of 0.9769 for distinguishing same-person from other-person groups.
- At a cutoff of 4.978, no false rejections occurred, with a slightly elevated false acceptance rate.
Conclusions:
- The alveolar bone method is effective for personal identification screening.
- System implementation enhanced efficiency and minimized human error.
- Future work includes using distortion-corrected images and deep learning for auto-detected landmarks.
