An AI model developed by Stanford researchers determined individuals' sexes through brain scans with 90 per cent accuracy, raising likelihood that male-female brains are indeed different at the most fundamental level.
The research not only enhances our comprehension of brain development and ageing but also unveils potential pathways for addressing sex-specific vulnerabilities in psychiatric and neurological disorders, the study's authors said.
The study, published Tuesday in the Proceedings of the National Academy of Sciences, shed light on a longstanding debate regarding sex differences in the human brain's reliability.
Its lead authors are senior research scientist Srikanth Ryali and academic staff researcher Yuan Zhang, PhD. Vinod Menon is the study's senior author.
The model's proficiency in discerning between male and female brain scans underscores inherent sex disparities in brain organisation, they said.
"A key motivation for this study is that sex plays a crucial role in human brain development, in ageing, and in the manifestation of psychiatric and neurological disorders," said Vinod Menon, a professor of psychiatry and behavioural sciences and director of the Stanford Cognitive and Systems Neuroscience Laboratory.
He added, "Identifying consistent and replicable sex differences in the healthy adult brain is a critical step toward a deeper understanding of sex-specific vulnerabilities in psychiatric and neurological disorders."
The authors called the study "not only highly replicable and generalizable but also behaviorally relevant, challenging the notion of a continuum in male-female brain organization."
"Our findings underscore the crucial role of sex as a biological determinant in human brain organization, have significant implications for developing personalized sex-specific biomarkers in psychiatric and neurological disorders, and provide innovative AI-based computational tools for future research," they said.
The researchers highlighted that their findings do not address whether sex-related differences emerge early in life or are influenced by hormonal disparities or societal factors experienced more by men or women.
For the study, Menon and his team developed a deep neural network model that excelled in classifying brain imaging data, particularly dynamic MRI scans.
Testing on 1,500 brain scans from diverse locations yielded consistently accurate results in identifying gender differences.
"This is a very strong piece of evidence that sex is a robust determinant of human brain organisation," Menon said.
Researchers have harnessed a tool known as "explainable AI" to delve into vast data sets and understand the decision-making process of models.
Curious about whether they could predict cognitive abilities based on gender-specific brain features, they crafted sex-specific models.
One model accurately forecasted cognitive performance in men, and another did the same for women. These results underscore how differences in brain function between sexes can significantly impact behaviour.
Menon and his team aim to make the model accessible to all researchers, enabling investigations into various aspects of brain connectivity and their relationship to cognitive abilities or behaviours.
Menon claimed their AI models have very broad applicability.
"A researcher could use our models to look for brain differences linked to learning impairments or social functioning differences, for instance — aspects we are keen to understand better to aid individuals in adapting to and surmounting these challenges," he added.
Comments