Diagnostic Performance of convolutional neural networks for dental sexual dimorphism

Ademir Franco do Rosario Junior; Lucas Porto; Dennis Heng; Jared Murray; Anna Lygate; Raquel  Franco; Juliano  Bueno; Marilia Sobania; Márcio M. Costa; Luiz R. Paranhos; Scheila Manica; Andre Abade

doi:10.1038/s41598-022-21294-1

Diagnostic Performance of convolutional neural networks for dental sexual dimorphism

Ademir Franco do Rosario Junior (Lead / Corresponding author), Lucas Porto, Dennis Heng, Jared Murray, Anna Lygate, Raquel Franco, Juliano Bueno, Marilia Sobania, Márcio M. Costa, Luiz R. Paranhos (Lead / Corresponding author), Scheila Manica, Andre Abade

Dentistry

Research output: Contribution to journal › Article › peer-review

16 Citations (Scopus)

79 Downloads (Pure)

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 = 4,003) 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

Original language	English
Article number	17279
Number of pages	12
Journal	Scientific Reports
Volume	12
DOIs	https://doi.org/10.1038/s41598-022-21294-1
Publication status	Published - 14 Oct 2022

Keywords

CNN
Forensic dentistry
Human identification
Machine learning
Radiology
Dental anthropology
Dental radiology

ASJC Scopus subject areas

General

Access to Document

10.1038/s41598-022-21294-1Licence: CC BY

Final Published VersionFinal published version, 1.92 MBLicence: CC BY

Cite this

@article{398cba652ed74482a91f679651872d91,

title = "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 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 = 4,003) 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 ",

keywords = "CNN, Forensic dentistry, Human identification, Machine learning, Radiology, Dental anthropology, Dental radiology",

author = "{Franco do Rosario Junior}, Ademir and Lucas Porto and Dennis Heng and Jared Murray and Anna Lygate and Raquel Franco and Juliano Bueno and Marilia Sobania and Costa, {M{\'a}rcio M.} and Paranhos, {Luiz R.} and Scheila Manica and Andre Abade",

note = "Funding Information: This study was funded in part by the Coordination for the Improvement of Higher Education Personnel (CAPES—finance code 001), the National Council for Scientific and Technological Development (CNPq), and the ASFO-2022 Research Grant by the American Society of Forensic Odontology. The authors express their gratitude.",

year = "2022",

month = oct,

day = "14",

doi = "10.1038/s41598-022-21294-1",

language = "English",

volume = "12",

journal = "Scientific Reports",

issn = "2045-2322",

publisher = "Nature Publishing Group",

}

TY - JOUR

T1 - Diagnostic Performance of convolutional neural networks for dental sexual dimorphism

AU - Franco do Rosario Junior, Ademir

AU - Porto, Lucas

AU - Heng, Dennis

AU - Murray, Jared

AU - Lygate, Anna

AU - Franco, Raquel

AU - Bueno, Juliano

AU - Sobania, Marilia

AU - Costa, Márcio M.

AU - Paranhos, Luiz R.

AU - Manica, Scheila

AU - Abade, Andre

N1 - Funding Information: This study was funded in part by the Coordination for the Improvement of Higher Education Personnel (CAPES—finance code 001), the National Council for Scientific and Technological Development (CNPq), and the ASFO-2022 Research Grant by the American Society of Forensic Odontology. The authors express their gratitude.

PY - 2022/10/14

Y1 - 2022/10/14

N2 - 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 = 4,003) 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

AB - 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 = 4,003) 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

KW - CNN

KW - Forensic dentistry

KW - Human identification

KW - Machine learning

KW - Radiology

KW - Dental anthropology

KW - Dental radiology

UR - http://www.scopus.com/inward/record.url?scp=85139888813&partnerID=8YFLogxK

U2 - 10.1038/s41598-022-21294-1

DO - 10.1038/s41598-022-21294-1

M3 - Article

C2 - 36241670

SN - 2045-2322

VL - 12

JO - Scientific Reports

JF - Scientific Reports

M1 - 17279

ER -

Diagnostic Performance of convolutional neural networks for dental sexual dimorphism

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this