Gender estimation using machine learning algorithms from computed tomography images of clivus

Abstract

The clivus, which is involved in the formation of the skull base, is an important material in gender prediction with its fusion structure. The aim of this study is to predict the gender of adult individuals using Machine Learning (ML) algorithms and Artificial Neural Networks (ANN) with parameters obtained from Computed Tomography (CT) images. The study was performed on CT images of 349 individuals aged 18-65 years. Clivus length, 1/3 upper, middle, and lower 1/3 width were measured on CT images and used in ML entry. As a result of the study, it was found that the clivus length, 1/3 upper, middle, and lower width had a significant difference in terms of gender, and ML algorithms showed accuracy up to 0.74. An accuracy of 0.67 was obtained with the ANN model. The study shows that clivus is a bone material that is open to research in terms of gender estimation and can be obtained with high accuracy. In this respect, we believe that it will guide the studies in forensic sciences.