CSIRO, Australia’s national science agency, has developed an advanced artificial intelligence (AI) tool for assisting in the estimation of biological sex from human skulls.
The AI tool has the potential to accelerate the accurate identification of skulls , supporting investigators when results are needed rapidly, for example, in criminal analysis and severe natural disasters.
RIGHT: A volume-rendered CT scan featuring the five cranial traits used in the study.
Results published in Scientific Reports show the AI tool achieved an accuracy of 97 per cent, significantly outperforming the 82 per cent accuracy achieved by conventional methods used by human assessors.
The tool was developed in collaboration with The University of Western Australia (UWA), whose forensic anthropology experts provided labelled data and domain knowledge to support model development.
CSIRO research scientist and joint first-author of the study, Dr Hollie Min, said imaging from a dataset of 200 computerised tomography – or CT scans – was analysed for sex-associated traits by the AI algorithm, with results then compared against human analysis.
“Our AI tool produces its results approximately five times faster than humans can, meaning families waiting for results of investigations can receive news about their loved ones more quickly,” Dr Min said.
“This AI tool has the potential to support forensic anthropologists to enhance the accuracy of sex estimations, while reducing the potential impact of human bias.”
Dr Min also emphasised the importance of accounting for population-specific variations in skull traits.
“This collaborative study allowed us to address some of the perceived limitations of traditional methods and better account for diversity in forensic data,” she said.
“Future research is needed, especially around expanding datasets to include diverse populations, enhancing the robustness and generalisability of the AI framework.
“Our goal is to provide forensic anthropologists with a reliable, interpretable tool to support their critical work, especially in cases involving individuals of unknown population backgrounds.”
This collaborative effort demonstrates the potential of AI to support forensic anthropology and advance the field with innovative and data-driven solutions.
“Our team is currently looking for industry collaborators to develop and translate this technology for real-life applications,” Dr Min added.
The CT database was collected at Dr Wahidin Sudirohusodo General Hospital (RSWS) at Hasanuddin University, Indonesia.
The paper, “Deep learning versus human assessors: forensic sex estimation from three-dimensional computed tomography scans” was published in Scientific Reports.