Brief

On 12/02/2025, the Commonwealth Scientific and Industrial Research Organisation (CSIRO) issued an update regarding "CSIRO develops AI tool for rapid identification in forensic investigations". The CSIRO has developed an advanced artificial intelligence (AI) tool to estimate biological sex from human skulls with a 97% accuracy rate.

12 February 2025
News Release

3 Photos

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.
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.

Images

A volume-rendered CT scan featuring the five cranial traits used in the study.

Download image

JPG 1MB

Imaging from a dataset of 200 CT scans was analysed for sex-associated traits by the AI algorithm.

Download image

JPG 1MB

CSIRO research scientist and joint first-author of the study, Dr Hollie Min.

Download image

PNG 3MB

Highlights content goes here...

Purpose

The primary objective behind the development of an advanced artificial intelligence (AI) tool by CSIRO, Australia’s national science agency, is to assist in the estimation of biological sex from human skulls. The AI tool has been designed to accelerate accurate identification of skulls, supporting investigators when results are needed rapidly, for example, in criminal analysis and severe natural disasters.

The development of this AI tool aims to provide a reliable and efficient solution for forensic anthropology, particularly in cases involving individuals of unknown population backgrounds. By leveraging the power of machine learning, CSIRO researchers have created an algorithm that can analyze imaging from computerized tomography (CT) scans to estimate sex-associated traits with high accuracy.

The AI tool has been shown to achieve an accuracy rate of 97%, significantly outperforming conventional methods used by human assessors, which only achieved an accuracy rate of 82%. This level of precision is crucial in forensic anthropology, where small variations can have significant implications for investigations and legal proceedings.

Effects on Industry

The development of this AI tool has the potential to disrupt traditional methods of sex estimation in forensic anthropology. By providing a more accurate and efficient solution, CSIRO’s AI tool can support investigators in their work, particularly in cases involving individuals with unknown population backgrounds.

The use of AI in forensic anthropology can also have significant implications for industries such as law enforcement, mortuary services, and medical institutions. In the long term, this technology has the potential to transform the field of forensic anthropology, enabling researchers and investigators to analyze data more quickly and accurately than ever before.

Moreover, the collaboration between CSIRO and The University of Western Australia (UWA) demonstrates the potential for industry-academia partnerships to drive innovation in key areas such as forensic science. This partnership has enabled the development of a cutting-edge technology that can have far-reaching implications for various industries and stakeholders.

Relevant Stakeholders

The relevant stakeholders affected by this update include:

  • Forensic anthropologists and investigators
  • Law enforcement agencies
  • Mortuary services
  • Medical institutions
  • Academia (particularly universities with forensic anthropology programs)
  • Industry partners (such as those involved in the development of AI technologies)

These stakeholders will be impacted by the use of this AI tool, which has the potential to transform traditional methods of sex estimation and analysis in forensic anthropology.

Next Steps

To comply with or respond to this update, the following actions are required:

  • Industry partners should consider collaborating with CSIRO and UWA to develop and refine this technology for real-life applications.
  • Forensic anthropologists and investigators should familiarize themselves with the capabilities and limitations of this AI tool and consider incorporating it into their workflows.
  • Law enforcement agencies, mortuary services, and medical institutions should explore the potential implications of this technology on their operations and procedures.

Any Other Relevant Information

Additional details that may be helpful to stakeholders include:

  • The need for future research to expand datasets to include diverse populations and enhance the robustness and generalizability of the AI framework.
  • The importance of accounting for population-specific variations in skull traits when using this technology.
  • The potential for industry-academia partnerships to drive innovation in key areas such as forensic science.

Commonwealth Scientific and Industrial Research Organisation (CSIRO)

Quick Insight
RADA.AI
RADA.AI
Hello! I'm RADA.AI - Regulatory Analysis and Decision Assistance. Your Intelligent guide for compliance and decision-making. How can i assist you today?
Suggested

Form successfully submitted. One of our GRI rep will contact you shortly

Thanking You!

Enter your Email

Enter your registered username/email id.

Enter your Email

Enter your email id below to signup.

Enter your Email

Enter your email id below to signup.
Individual Plan
$125 / month OR $1250 / year
Features
Best for: Researchers, Legal professionals, Academics
Enterprise Plan
Contact for Pricing
Features
Best for: Law Firms, Corporations, Government Bodies