Diagnostic performance of convolutional neural networks for dental sexual dimorphism
Abstract Convolutional neural networks (CNN) led to important solutions in the field of Computer Vision. More recently, forensic sciences benefited from the resources of artificial intelligence, especially in procedures that normally require operator-dependent steps. Forensic tools for sexual dimorp...
Main Authors: | , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2022-10-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-022-21294-1 |
_version_ | 1798029930525622272 |
---|---|
author | Ademir Franco Lucas Porto Dennis Heng Jared Murray Anna Lygate Raquel Franco Juliano Bueno Marilia Sobania Márcio M. Costa Luiz R. Paranhos Scheila Manica André Abade |
author_facet | Ademir Franco Lucas Porto Dennis Heng Jared Murray Anna Lygate Raquel Franco Juliano Bueno Marilia Sobania Márcio M. Costa Luiz R. Paranhos Scheila Manica André Abade |
author_sort | Ademir Franco |
collection | DOAJ |
description | Abstract Convolutional neural networks (CNN) led to important solutions in the field of Computer Vision. More recently, forensic sciences benefited from the resources of artificial intelligence, especially in procedures that normally require operator-dependent steps. Forensic tools for sexual dimorphism based on morphological dental traits are available but have limited performance. This study aimed to test the application of a machine learning setup to distinguish females and males using dentomaxillofacial features from a radiographic dataset. The sample consisted of panoramic radiographs (n = 4003) of individuals in the age interval of 6 and 22.9 years. Image annotation was performed with V7 software (V7labs, London, UK). From Scratch (FS) and Transfer Learning (TL) CNN architectures were compared, and diagnostic accuracy tests were used. TL (82%) performed better than FS (71%). The correct classifications of females and males aged ≥ 15 years were 87% and 84%, respectively. For females and males < 15 years, the correct classifications were 80% and 83%, respectively. The Area Under the Curve (AUC) from Receiver-operating Characteristic (ROC) curves showed high classification accuracy between 0.87 and 0.91. The radio-diagnostic use of CNN for sexual dimorphism showed positive outcomes and promising forensic applications to the field of dental human identification. |
first_indexed | 2024-04-11T19:31:51Z |
format | Article |
id | doaj.art-684ef85210694dbd884116b899d64d0d |
institution | Directory Open Access Journal |
issn | 2045-2322 |
language | English |
last_indexed | 2024-04-11T19:31:51Z |
publishDate | 2022-10-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Scientific Reports |
spelling | doaj.art-684ef85210694dbd884116b899d64d0d2022-12-22T04:06:58ZengNature PortfolioScientific Reports2045-23222022-10-0112111210.1038/s41598-022-21294-1Diagnostic performance of convolutional neural networks for dental sexual dimorphismAdemir Franco0Lucas Porto1Dennis Heng2Jared Murray3Anna Lygate4Raquel Franco5Juliano Bueno6Marilia Sobania7Márcio M. Costa8Luiz R. Paranhos9Scheila Manica10André Abade11Centre of Forensic and Legal Medicine and Dentistry, University of DundeeComputer Vision Solutions, Rumina S.ACentre of Forensic and Legal Medicine and Dentistry, University of DundeeCentre of Forensic and Legal Medicine and Dentistry, University of DundeeCentre of Forensic and Legal Medicine and Dentistry, University of DundeeDepartment of Preventive and Social Dentistry, Federal University of UberlandiaDivision of Oral Radiology, Faculdade Sao Leopoldo MandicDivision of Forensic Dentistry, Faculdade Sao Leopoldo MandicDepartment of Removable Prosthodontics, Federal University of UberlandiaDepartment of Preventive and Social Dentistry, Federal University of UberlandiaCentre of Forensic and Legal Medicine and Dentistry, University of DundeeComputer Science, Federal Institute of Science and TechnologyAbstract Convolutional neural networks (CNN) led to important solutions in the field of Computer Vision. More recently, forensic sciences benefited from the resources of artificial intelligence, especially in procedures that normally require operator-dependent steps. Forensic tools for sexual dimorphism based on morphological dental traits are available but have limited performance. This study aimed to test the application of a machine learning setup to distinguish females and males using dentomaxillofacial features from a radiographic dataset. The sample consisted of panoramic radiographs (n = 4003) of individuals in the age interval of 6 and 22.9 years. Image annotation was performed with V7 software (V7labs, London, UK). From Scratch (FS) and Transfer Learning (TL) CNN architectures were compared, and diagnostic accuracy tests were used. TL (82%) performed better than FS (71%). The correct classifications of females and males aged ≥ 15 years were 87% and 84%, respectively. For females and males < 15 years, the correct classifications were 80% and 83%, respectively. The Area Under the Curve (AUC) from Receiver-operating Characteristic (ROC) curves showed high classification accuracy between 0.87 and 0.91. The radio-diagnostic use of CNN for sexual dimorphism showed positive outcomes and promising forensic applications to the field of dental human identification.https://doi.org/10.1038/s41598-022-21294-1 |
spellingShingle | Ademir Franco Lucas Porto Dennis Heng Jared Murray Anna Lygate Raquel Franco Juliano Bueno Marilia Sobania Márcio M. Costa Luiz R. Paranhos Scheila Manica André Abade Diagnostic performance of convolutional neural networks for dental sexual dimorphism Scientific Reports |
title | Diagnostic performance of convolutional neural networks for dental sexual dimorphism |
title_full | Diagnostic performance of convolutional neural networks for dental sexual dimorphism |
title_fullStr | Diagnostic performance of convolutional neural networks for dental sexual dimorphism |
title_full_unstemmed | Diagnostic performance of convolutional neural networks for dental sexual dimorphism |
title_short | Diagnostic performance of convolutional neural networks for dental sexual dimorphism |
title_sort | diagnostic performance of convolutional neural networks for dental sexual dimorphism |
url | https://doi.org/10.1038/s41598-022-21294-1 |
work_keys_str_mv | AT ademirfranco diagnosticperformanceofconvolutionalneuralnetworksfordentalsexualdimorphism AT lucasporto diagnosticperformanceofconvolutionalneuralnetworksfordentalsexualdimorphism AT dennisheng diagnosticperformanceofconvolutionalneuralnetworksfordentalsexualdimorphism AT jaredmurray diagnosticperformanceofconvolutionalneuralnetworksfordentalsexualdimorphism AT annalygate diagnosticperformanceofconvolutionalneuralnetworksfordentalsexualdimorphism AT raquelfranco diagnosticperformanceofconvolutionalneuralnetworksfordentalsexualdimorphism AT julianobueno diagnosticperformanceofconvolutionalneuralnetworksfordentalsexualdimorphism AT mariliasobania diagnosticperformanceofconvolutionalneuralnetworksfordentalsexualdimorphism AT marciomcosta diagnosticperformanceofconvolutionalneuralnetworksfordentalsexualdimorphism AT luizrparanhos diagnosticperformanceofconvolutionalneuralnetworksfordentalsexualdimorphism AT scheilamanica diagnosticperformanceofconvolutionalneuralnetworksfordentalsexualdimorphism AT andreabade diagnosticperformanceofconvolutionalneuralnetworksfordentalsexualdimorphism |