Accurate gender estimation from skeletal remains is a critical component of forensic anthropology, bio archaeology,
and medico-legal identification. Conventional morphometric approaches largely depend on visual assessment and manual
measurements of sexually dimorphic cranial traits, which are often constrained by observer subjectivity, population variability,
and incomplete or damaged skeletal remains. To overcome these limitations, this study presents a deep learning–based
framework for automated gender classification from skull images, employing residual learning–based architectures. A curated
dataset of dental radiographs was preprocessed through normalization and data augmentation to improve feature consistency
and model generalizability. The proposed ResNet-50–based model was trained to learn discriminative dental features associated
with sexual dimorphism. Model performance was evaluated using standard classification metrics, including accuracy, precision,
recall, F1-score, and confusion matrix analysis. Experimental results demonstrate that the proposed deep learning framework
achieves reliable gender classification performance, outperforming traditional odontometric methods and classical machine
learning classifiers. These findings indicate that deep learning models provide a robust, objective, and scalable solution for
teeth-based gender estimation, with significant potential for application in forensic investigations and digital human
identification systems.
[1] Krogman, W. M., &İşcan, M. Y. (1986). The Human Skeleton in Forensic Medicine. Springfield, IL: Charles C. Thomas.
[2]
Franklin, D., Cardini, A., Flavel, A., &Kuliukas, A. (2012). Estimation of sex from cranial measurements in diverse
populations.Forensic Science International, 217(1–3), 238.e1–238.e8.
[3] Garn, S. M., Lewis, A. B., & Swindler, D. R. (1967). Metric dental variation.Journal of Dental Research, 46(5), 963–971.
[4] Acharya, A. B., &Mainali, S. (2008). Sex determination from odontometric analysis of permanent maxillary incisors and
canines.Journal of Forensic Sciences, 53(1), 129–132.
[5] Liao, C., et al. (2019). Sex determination using dental radiographs and machine learning approaches.Forensic Science
International, 298, 300–307.
[6]
Şenol, D., et al. (2020). Gender determination using panoramic dental radiographs with convolutional neural
networks.Journal of Forensic Radiology and Imaging, 21, 100358.
[7] Chen, Y., et al. (2021). Deep learning for sex determination based on dental panoramic radiographs. Oral Radiology, 37,
486–495.
[8] LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521, 436–444.
[9]
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural
networks.Advances in Neural Information Processing Systems, 25, 1097–1105.
[10] Simonyan, K., &Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition.ICLR.
[11] He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition.CVPR, 770–778.
[12] Ronneberger, O., Fischer, P., &Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation.
MICCAI, 234–241.
[13] Mazurowski, M. A., et al. (2019). Deep learning in radiology: An overview of the concepts and challenges.Radiology,
292(1), 24–34.
[14] Alqahtani, S. J., et al. (2022). Sex estimation using deep learning models on CBCT images of teeth.Applied Sciences,
12(3), 1289.
[15] Silva, A. M., et al. (2023). Automated sex estimation from skeletal remains using convolutional neural networks.Forensic
Science International: Digital Investigation, 45, 301533.
[16] Ubelaker, D. H. (2014). Advances in skeletal sex determination: A review. Journal of Forensic Sciences, 59(2), 343–349.
[17] Bigoni, L., et al. (2010). Craniofacial sexual dimorphism in a modern Italian population.Journal of Human Evolution,
59(5), 519–531.
[18] Kumar, A., et al. (2018). Gender determination using odontometric measurements: A machine learning approach.Forensic
Science International, 282, 70–76.
[19]
El-Din, A. S., & El-Bassyouni, H. T. (2016). Sex determination using odontometric measurements of permanent
teeth.Egyptian Journal of Forensic Sciences, 6(4), 341–346.
[20] Özden, B., et al. (2019). Sex determination using cone-beam computed tomography images of teeth.Dentomaxillofacial
Radiology, 48(5), 20180333.
[21] Alwakeel, S. S., &Shaaban, A. M. (2020). Face and skull-based gender classification using deep convolutional neural
networks.Applied Soft Computing, 91, 106229.
[22] Abdi, A. M., et al. (2021). A deep learning framework for sex classification using skull images.Pattern Recognition
Letters, 145, 138–145.
[23] Litjens, G., et al. (2017). A survey on deep learning in medical image analysis.Medical Image Analysis, 42, 60–88.
[24] Zhou, Z., et al. (2019). Learning deep features for forensic image analysis using convolutional neural networks. IEEE
Access, 7, 123456–123468.
[25] Kharat, M. U., et al. (2022). Deep learning-based gender classification from dental panoramic radiographs.Diagnostics,
12(9), 2214.
