AI has determined that male and female brains are structured differently

An artificial intelligence (AI)-based study has helped resolve one of the debates among scientists about whether gender influences the organization and functioning of the brain, revealing clear patterns between men and women.

A team led by Stanford University (USA) published a study in the journal PNAS based on a new artificial intelligence model that determined with more than 90% accuracy whether images of brain activity came from a woman or a man.

The discovery helps resolve a long-standing debate about whether reliable sex differences exist in the human brain and suggests that understanding these differences may have important implications for addressing neuropsychiatric conditions that affect women and men differently, the university said.

Identifying consistent and reproducible sex differences in the healthy adult brain is an important step toward a better understanding of gender-based vulnerabilities in mental and neurological disorders, the institute said in a statement.

“A key motivation for this study is that gender plays a critical role in human brain development, aging, and the expression of psychiatric and neurological disorders,” said Vinod Menon of Stanford University and lead author of the study.

The work did not take into account whether sex differences emerge early in life or whether they may be due to hormonal differences or different social circumstances that men and women are more likely to face.

The hot spots that most helped the model distinguish male brains from female brains included the default mode network (a brain system that helps process self-referential information), the striatum, and the limbic network, which are involved in learning and how people respond to awards.

The team took advantage of advances in artificial intelligence and access to multiple large data sets to conduct complex analyses.

The first step was to create a deep neural network model that would learn to classify brain imaging data. When the researchers told the model whether they were looking at a male or female brain, they began to notice subtle patterns that could help them differentiate between the two.

This deep neural network model analyzed dynamic MRI images, thereby capturing the complex interactions between different brain regions.

When the researchers tested the model using about 1,500 brain scans, they were almost always able to determine whether the scan was from a woman or a man.

The model’s success suggests that there are marked differences in the brain between the sexes, but until now these have not been reliably detected, the institution said in a statement.

The team also turned to explainable artificial intelligence, which analyzes large amounts of data to explain how the model’s decisions are made, to understand which brain networks are most important to the model to judge whether a brain scan came from a man or a woman.

Thus, they found that the model most frequently searched for the default mode network, the striatum, and the limbic network.

Menon emphasized that these models worked “very well” because they were able to separate brain structures between the sexes, which suggests that “ignoring sex differences in brain organization may lead to ignoring key factors underlying neuropsychiatric disorders.”

While the team applied their deep neural network model to questions related to sex differences, Menon emphasized that the model will be used to answer questions about the relationship between any aspect of brain connectivity and any type of cognitive or behavioral ability.