Artificial intelligence for sex determination of skeletal remains: Application of a deep learning artificial neural network to human skulls

• Published in: Journal of forensic and legal medicine Vol. 62; pp. 40 - 43
• Main Authors: Bewes, James, Low, Andrew, Morphett, Antony, Pate, F. Donald, Henneberg, Maciej
• Format: Journal Article
• Language: English
• Published: England Elsevier Ltd 01.02.2019
• Subjects: Adult; Artificial intelligence; Artificial neural network; Australia; Deep Learning; Female; Forensic Anthropology - methods; Humans; Imaging, Three-Dimensional; Male; Neural Networks (Computer); Sex determination; Sex Determination by Skeleton - methods; Skull - diagnostic imaging; Skull determination; Software; Tomography, X-Ray Computed; Australia; Deep learning; Artificial neural network; Sex determination; Artificial intelligence; Skull determination
• ISSN: 1752-928X; 1878-7487; 1878-7487
• DOI: 10.1016/j.jflm.2019.01.004

A deep learning artificial neural network was adapted to the task of sex determination of skeletal remains. The neural network was trained on images of 900 skulls virtually reconstructed from hospital CT scans. When tested on previously unseen images of skulls, the artificial neural network showed 95% accuracy at sex determination. Artificial intelligence methods require no significant expertise to implement once trained, are rapid to use, and have the potential to eliminate human bias from sex estimation of skeletal remains. •Artificial neural networks can be adapted to the task of sex classification of skeletal structures.•Artificial neural networks demonstrate 95% accuracy at sex classification of images of skulls.•Artificial neural networks perform equally well in classifying male and female skeletal structures.