Accurate age classification using manual method and deep convolutional neural network based on orthopantomogram images

Age estimation is an important challenge in many fields, including immigrant identification, legal requirements, and clinical treatments. Deep learning techniques have been applied for age estimation recently but lacking performance comparison between manual and machine learning methods based on a l...

Full description

Saved in:
Bibliographic Details
Published in:International journal of legal medicine 2021-07, Vol.135 (4), p.1589-1597
Main Authors: Guo, Yu-cheng, Han, Mengqi, Chi, Yuting, Long, Hong, Zhang, Dong, Yang, Jing, Yang, Yang, Chen, Teng, Du, Shaoyi
Format: Article
Language:English
Subjects:
Adolescent
Age
Age Determination by Teeth - methods
Artificial neural networks
Child
Child, Preschool
Chronology
Classification
Deep learning
Feature extraction
Female
Forensic Medicine
Forensic odontology
Human growth
Humans
Machine Learning
Male
Medical Law
Medicine
Medicine & Public Health
Neural networks
Neural Networks, Computer
Original Article
Radiography, Panoramic
Teenagers
Thresholds
Young Adult
Young adults
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Age estimation is an important challenge in many fields, including immigrant identification, legal requirements, and clinical treatments. Deep learning techniques have been applied for age estimation recently but lacking performance comparison between manual and machine learning methods based on a large sample of dental orthopantomograms (OPGs). In total, we collected 10,257 orthopantomograms for the study. We derived logistic regression linear models for each legal age threshold (14, 16, and 18 years old) for manual method and developed the end-to-end convolutional neural network (CNN) which classified the dental age directly to compare with the manual method. Both methods are based on left mandibular eight permanent teeth or the third molar separately. Our results show that compared with the manual methods (92.5%, 91.3%, and 91.8% for age thresholds of 14, 16, and 18, respectively), the end-to-end CNN models perform better (95.9%, 95.4%, and 92.3% for age thresholds of 14, 16, and 18, respectively). This work proves that CNN models can surpass humans in age classification, and the features extracted by machines may be different from that defined by human.
ISSN:0937-9827
1437-1596
DOI:10.1007/s00414-021-02542-x