Related Experiment Video
Updated: Feb 28, 2026
08:03
Midface Hypoplasia and Cranial Base Morphology in Syndromic Craniosynostosis: A Comparative Analysis Study Using a Predictive Regression Model
Published on: November 4, 2025
313
Gender estimation using machine learning algorithms and artificial neural networks based on parameters obtained from
Oguzhan Harmandaoglu1, Yusuf Secgin2, Seren Kaya3
1Department of Therapy And Rehabilitation, Çatalzeytin Vocational School, Kastamonu University, Kastamonu.
Cirugia Y Cirujanos
|February 26, 2026
Summary
Gender estimation is possible using sphenoid sinus dimensions from CT scans. Machine learning models accurately predict sex based on sphenoid sinus size, offering reliable forensic and anthropological data.
Area of Science:
- Radiology
- Forensic Anthropology
- Medical Imaging Analysis
Background:
- Sex estimation is crucial in forensic and anthropological investigations.
- Craniofacial structures, including the sphenoid sinus, exhibit sexual dimorphism.
- Computed tomography (CT) provides detailed anatomical information for morphometric analysis.
Purpose of the Study:
- To determine gender using sphenoid sinus parameters from CT images.
- To evaluate the efficacy of various Machine Learning (ML) algorithms and Artificial Neural Networks (ANNs) for sex estimation.
- To assess the reliability of sphenoid sinus morphometry in gender determination.
Main Methods:
- CT images from 300 individuals (150 male, 150 female) aged 18-65 were analyzed.
- Measurements of sphenoid sinus length, width, and volume were taken.
- Gender prediction was performed using Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis, Logistic Regression (LR), Extra Tree Classifier, Random Forest, Decision Tree (DT), Gaussian Naive Bayes (GaussianNB), K-Nearest Neighbors (k-NN), and ANN models.
Main Results:
- Males exhibited significantly larger sphenoid sinus dimensions (length, width, volume) on both sides compared to females (p < 0.05).
- ML algorithms achieved notable performance: LDA (0.82), k-NN (0.80), LR (0.84), GaussianNB (0.80), DT (0.82), and ANN (0.82).
- Logistic Regression demonstrated the highest accuracy in gender prediction among the tested algorithms.
Conclusions:
- Morphometric analysis of the sphenoid sinus is a viable method for sex estimation.
- LDA, LR, DT, and ANN algorithms provide accurate and reliable data for gender determination.
- Sphenoid sinus dimensions are significant indicators of sex in CT-based analyses.
Keywords:
Algoritmos de aprendizaje automáticoArtificial neural networksGender estimationMachine learning algorithmsPredicción del sexoRedes neuronales artificialesSeno esfenoidalSphenoid sinus
