Human gender estimation from CT images of skull using deep feature selection and feature fusion

• Published in: Scientific reports Vol. 14; no. 1; pp. 16879 - 14
• Main Authors: Çiftçi, Rukiye, Dönmez, Emrah, Kurtoğlu, Ahmet, Eken, Özgür, Samee, Nagwan Abdel, Alkanhel, Reem Ibrahim
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 23.07.2024; Nature Publishing Group; Nature Portfolio
• Subjects: 692/308; 692/700/1421; Adult; Aged; Algorithms; Computed tomography; Convolutional neural networks (CNN); Deep Learning; Deep learning algorithms; Feature selection; Female; Forensic Anthropology - methods; Gender; Gender prognostication; Humanities and Social Sciences; Humans; Learning algorithms; Machine learning; Male; Middle Aged; multidisciplinary; Neural networks; Neural Networks, Computer; Precision gender estimation; Radiography; Reproducibility of Results; Science; Science (multidisciplinary); Sex Characteristics; Skull; Skull - diagnostic imaging; Skull computed tomography; Tomography, X-Ray Computed - standards; Gender prognostication; Precision gender estimation; Skull computed tomography; Convolutional neural networks (CNN); Deep learning algorithms
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-024-65521-3

This research endeavors to prognosticate gender by harnessing the potential of skull computed tomography (CT) images, given the seminal role of gender identification in the realm of identification. The study encompasses a corpus of CT images of cranial structures derived from 218 male and 203 female subjects, constituting a total cohort of 421 individuals within the age bracket of 25 to 65 years. Employing deep learning, a prominent subset of machine learning algorithms, the study deploys convolutional neural network (CNN) models to excavate profound attributes inherent in the skull CT images. In pursuit of the research objective, the focal methodology involves the exclusive application of deep learning algorithms to image datasets, culminating in an accuracy rate of 96.4%. The gender estimation process exhibits a precision of 96.1% for male individuals and 96.8% for female individuals. The precision performance varies across different selections of feature numbers, namely 100, 300, and 500, alongside 1000 features without feature selection. The respective precision rates for these selections are recorded as 95.0%, 95.5%, 96.2%, and 96.4%. It is notable that gender estimation via visual radiography mitigates the discrepancy in measurements between experts, concurrently yielding an expedited estimation rate. Predicated on the empirical findings of this investigation, it is inferred that the efficacy of the CNN model, the configurational intricacies of the classifier, and the judicious selection of features collectively constitute pivotal determinants in shaping the performance attributes of the proposed methodology.