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

Journal: Journal of forensic and legal medicine
Published Date:

Abstract

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.

Authors

  • James Bewes
    Department of Radiology, Royal Adelaide Hospital, North Terrace, Adelaide, 5000, Australia. Electronic address: bewesj@gmail.com.
  • Andrew Low
    Department of Radiology, Royal Adelaide Hospital, North Terrace, Adelaide, 5000, Australia.
  • Antony Morphett
    Dr Jones and Partners, Medical Imaging, 270 Wakefield St, Adelaide, 5000, Australia.
  • F Donald Pate
    Archaeology, Flinders University, Adelaide, SA, 5001, Australia.
  • Maciej Henneberg
    Biological Anthropology and Comparative Anatomy Research Unit, School of Medical Sciences, University of Adelaide, Adelaide, 5005, Australia.