Browse > Article
http://dx.doi.org/10.5624/isd.20200324

A pilot study of an automated personal identification process: Applying machine learning to panoramic radiographs  

Ortiz, Adrielly Garcia (Department of Community Dentistry, School of Dentistry, University of de Sao Paulo)
Soares, Gustavo Hermes (Department of Community Dentistry, School of Dentistry, University of de Sao Paulo)
da Rosa, Gabriela Cauduro (Department of Community Dentistry, School of Dentistry, University of de Sao Paulo)
Biazevic, Maria Gabriela Haye (Department of Community Dentistry, School of Dentistry, University of de Sao Paulo)
Michel-Crosato, Edgard (Department of Community Dentistry, School of Dentistry, University of de Sao Paulo)
Publication Information
Imaging Science in Dentistry / v.51, no.2, 2021 , pp. 187-193 More about this Journal
Abstract
Purpose: This study aimed to assess the usefulness of machine learning and automation techniques to match pairs of panoramic radiographs for personal identification. Materials and Methods: Two hundred panoramic radiographs from 100 patients (50 males and 50 females) were randomly selected from a private radiological service database. Initially, 14 linear and angular measurements of the radiographs were made by an expert. Eight ratio indices derived from the original measurements were applied to a statistical algorithm to match radiographs from the same patients, simulating a semi-automated personal identification process. Subsequently, measurements were automatically generated using a deep neural network for image recognition, simulating a fully automated personal identification process. Results: Approximately 85% of the radiographs were correctly matched by the automated personal identification process. In a limited number of cases, the image recognition algorithm identified 2 potential matches for the same individual. No statistically significant differences were found between measurements performed by the expert on panoramic radiographs from the same patients. Conclusion: Personal identification might be performed with the aid of image recognition algorithms and machine learning techniques. This approach will likely facilitate the complex task of personal identification by performing an initial screening of radiographs and matching ante-mortem and post-mortem images from the same individuals.
Keywords
Machine Learning; Radiography, Panoramic; Forensic Dentistry; Neural Networks, Computer; Forensic Anthropology;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Lundberg E, Mihajlovic NS, Sjostrom M, Ahlqvist J. The use of panoramic images for identification of edentulous persons. J Forensic Odontostomatol 2019; 37: 18-24.
2 Zhou J, Abdel-Mottaleb M. A content-based system for human identification based on bitewing dental X-ray images. Pattern Recognit 2005; 38: 2132-42.   DOI
3 O'Toole A, Abdi H, Jiang F, Phillips PJ. Fusing face-recognition algorithms and humans. IEEE Trans Syst Man Cybern B Cybern 2007; 37: 1149-55.   DOI
4 Kumar A, Ghosh S, Logani A. Occurrence of diversity in dental pattern and their role in identification in Indian population: an orthopantomogram based pilot study. J Forensic Dent Sci 2014; 6: 42-5.   DOI
5 Lee C, Lim SH, Huh KH, Han SS, Kim JE, Heo MS, et al. Performance of dental pattern analysis system with treatment chronology on panoramic radiography. Forensic Sci Int 2019; 299: 229-34.   DOI
6 DeLisi M. The big data potential of epidemiological studies for criminology and forensics. J Forensic Leg Med 2018; 57: 24-7.   DOI
7 Carvalho SP, Brito LM, Paiva LA, Bicudo LA, Crosato EM, Oliveira RN. Validation of a physical anthropology methodology using mandibles for gender estimation in a Brazilian population. J Appl Oral Sci 2013; 21: 358-62.   DOI
8 Schneider CA, Rasband WS, Eliceiri KW. NIH Image to ImageJ: 25 years of image analysis. Nat Methods 2012; 9: 671-5.   DOI
9 Miki Y, Muramatsu C, Hayashi T, Zhou X, Hara T, Katsumata A, et al. Classification of teeth in cone-beam CT using deep convolutional neural network. Comput Biol Med 2017; 80: 24-9.   DOI
10 Wood JD. Forensic dental identification in mass disasters: the current status. J Calif Dent Assoc 2014; 42: 379-83.
11 Fujimoto H, Hayashi T, Iino M. A novel method for land-mark-based personal identification on panoramic dental radiographic and computed tomographic images. J Forensic Radiol Imaging 2016; 7: 21-7.   DOI
12 Tohnak S, Mehnert A, Mahoney M, Crozier S. Dental identification system based on unwrapped CT images. Annu Int Conf IEEE Eng Med Biol Soc 2009; 2009: 3549-52.
13 Ruder TD, Thali YA, Rashid SN, Mund MT, Thali MJ, Hatch GM, et al. Validation of post mortem dental CT for disaster victim identification. J Forensic Radiol Imaging 2016; 5: 25-30.   DOI
14 Adams BJ. The diversity of adult dental patterns in the United States and the implications for personal identification. J Forensic Sci 2003; 48: 497-503.
15 Matsuda S, Miyamoto T, Yoshimura H, Hasegawa T. Personal identification with orthopantomography using simple convolutional neural networks: a preliminary study. Sci Rep 2020; 10: 13559.   DOI
16 Nino-Sandoval TC, Guevara Perez SV, Gonzalez FA, Jaque RA, Infante-Contreras C. Use of automated learning techniques for predicting mandibular morphology in skeletal class I, II and III. Forensic Sci Int 2017; 281: 187.e1-7.   DOI
17 Biazevic MG, de Almeida NH, Crosato E, Michel-Crosato E. Diversity of dental patterns: application on different ages using the Brazilian National Oral Health Survey. Forensic Sci Int 2011; 207: 240.e1-9.   DOI
18 Lee SS, Choi JH, Yoon CL, Kim CY, Shin KJ. The diversity of dental patterns in the orthopantomography and its significance in human identification. J Forensic Sci 2004; 49: 784-6.   DOI
19 Heinrich A, Guttler F, Wendt S, Schenkl S, Hubig M, Wagner R, et al. Forensic odontology: automatic identification of persons comparing antemortem and postmortem panoramic radiographs using computer vision. Rofo 2018; 190: 1152-8.   DOI
20 Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition; 2016 Jun 27-30; Las Vegas, USA. Piscataway: IEEE Computer Society; 2016. p. 2818-26.
21 Pereira CP, Santos JC. How to do identify single cases according to the quality assurance from IOFOS. The positive identification of an unidentified body by dental parameters: a case of homicide. J Forensic Leg Med 2013; 20: 169-73.   DOI
22 Solheim T. Quality assurance in forensic odontology. J Forensic Odontostomatol 2018; 36: 53-7.
23 Page M, Taylor J, Blenkin M. Uniqueness in the forensic identification sciences - fact or fiction? Forensic Sci Int 2011; 206: 12-8.   DOI
24 Hollis KF, Soualmia LF, Seroussi B. Artificial intelligence in health informatics: hype or reality? Yearb Med Inform 2019; 28: 3-4.   DOI
25 Lefevre T. Big data in forensic science and medicine. J Forensic Leg Med 2018; 57: 1-6.   DOI
26 Jain AK, Chen H. Matching of dental X-ray images for human identification. Pattern Recognit 2015; 37: 1295-305.
27 Khanagar SB, Vishwanathaiah S, Naik S, Al-Kheraif A, Devang Divakar D, Sarode SC, et al. Application and performance of artificial intelligence technology in forensic odontology - a systematic review. Leg Med (Tokyo) 2021; 48: 101826.   DOI
28 Bhateja S, Arora G, Katote R. Evaluation of adult dental patterns on orthopantomograms and its implication for personal identification: a retrospective observational study. J Forensic Dent Sci 2015; 7: 14-7.   DOI
29 Carvalho SP, Brito LM, Paiva LA, Bicudo LA, Crosato EM, Oliveira RN. Validation of a physical anthropology methodology using mandibles for gender estimation in a Brazilian population. J Appl Oral Sci 2013; 21: 358-62.   DOI
30 Phillips PJ, O'Toole AJ. Comparison of human and computer performance across face recognition experiments. Image Vis Comput 2014; 32: 74-85.   DOI
31 Phillips PJ, Yates AN, Hu Y, Hahn CA, Noyes E, Jackson K, et al. Face recognition accuracy of forensic examiners, super recognizers, and face recognition algorithms. Proc Natl Acad Sci U S A 2018; 115: 6171-6.   DOI
32 Dowsett AJ, Burton AM. Unfamiliar face matching: pairs outperform individuals and provide a route to training. Br J Psychol 2015; 106: 433-45.   DOI
33 Rothwell BR. Principles of dental identification. Dent Clin North Am 2001; 45: 253-70.   DOI
34 Du Chesne A, Benthaus S, Teige K, Brinkmann B. Post-mortem orthopantomography - an aid in screening for identification purposes. Int J Leg Med 2000; 113: 63-9.   DOI
35 Taroni F, Mangin P, Perrior M. Identification concept and the use of probabilities in forensic odontology - an approach by philosophical discussion. J Forensic Odontostomatol 2000; 18: 15-8.