Three-Dimensional Dental Analysis for Sex Estimation in the Italian Population: A Pilot Study Based on a Geometric Morphometric and Artificial Neural Network Approach.

Giorgio Oliva,Ilenia Bianchi,Martina Focardi,Domenico Dalessandri,Vilma Pinchi,Rinaldo Zotti,Corrado Paganelli

doi:10.3390/healthcare10010009

Giorgio Oliva, Ilenia Bianchi + Show 5 more

Open Access

https://doi.org/10.3390/healthcare10010009

Copy DOI

Journal: Healthcare	Publication Date: Dec 22, 2021
Citations: 13	License type: CC BY 4.0

Affiliation: University of Brescia, University of Florence

Abstract

Dental dimorphism can be used for discriminating sex in forensic contexts. Geometric morphometric analysis (GMA) allows the evaluation of the shape and size, separately, of uneven 3D objects. This study presents experiments using a novel combination of GMA and an artificial neural network (ANN) for sex classification, applied to premolars of Caucasian Italian adults (50 females and 50 males). General Procrustes superimposition (GPS) and the partial least square (PLS) method were performed, respectively, to study the shape variance between sexes and to eliminate landmark variations. The “set-aside” approach was used to assess the accuracy of the proposed neural networks. As the main findings of the pilot study, the proposed method applied to the first upper premolar correctly classified 90% of females and 73% of males of the test sample. The accuracy was 0.84 and 0.80 for the training and test samples, respectively. The sexual dimorphism resulting from GMA was low, although statistically significant. GMA combined with the ANN demonstrated better sex classification ability than previous odontometric or dental morphometric methods. Future research could overcome some limitations by considering a larger sample of subjects and other kinds of teeth and experimenting with the use of computer vision for automatic landmark positioning.

Highlights

The sexual dimorphism of human dentition can be useful in a variety of forensic settings, such as mass disasters, the identification of bodies, and the classification of skull fragments [1]
In this study we aimed to test a new approach based on the combination of geometric morphometric analysis (GMA) and artificial neural network (ANN) applied to human premolars for detecting sexual dimorphism and for classifying subjects by sex
This study tested whether a method based on geometric morphometric analysis (GMA) combined with an ANN for studying the sexual dimorphism of teeth could overcome some of the limitations discussed in the previous literature, while yielding an accurate identification of sex

Summary

Introduction

The sexual dimorphism of human dentition can be useful in a variety of forensic settings, such as mass disasters, the identification of bodies, and the classification of skull fragments [1] Several methods, such as genetic and skeletal morphology analysis, can be effectively used for sex estimation, but in some cases, the available evidence is insufficient for conclusive sex identification. In forensic contexts, an intraoral scanner is seldom available during the post-mortem examination of the body; analysis and measurements are frequently performed later on casts In this sense, methods tested using dental casts, rather than real dentition, produce results that are more implementable in the current practice of forensic odontologists, and the evidence gained is not biased with the use of methods originally tested in vivo

Objectives

Methods

Results

Discussion

Conclusion