New study finds unique brain organization patterns in males and females

A new study conducted by researchers at Stanford Medicine revealed an advanced artificial intelligence model that boasts over 90% accuracy in discerning whether brain activity scans belong to a woman or a man.

The findings published Feb. 19 2024 in the Proceedings of the National Academy of Sciences, helped resolve a long-term discussion about whether reliable sex differences exist in the human brain and suggest that understanding these differences may be critical to addressing neuropsychiatric conditions that affect women and men differently.While sex chromosomes determine hormone exposure, linking sex to distinct brain differences has been challenging. Brain structures appear similar in both genders and studies on brain region interactions have not consistently revealed sex-related indicators.

"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, PhD, professor of psychiatry and behavioural sciences and director of the Stanford Cognitive and Systems Neuroscience Laboratory. "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 "hotspots" crucial for distinguishing between male and female brains in the model include the default mode network, responsible for processing self-referential information, and the striatum and limbic network, associated with learning and reward response.

For the study, Menon and his team analysed recent AI advancements and extensive datasets. They developed a deep neural network model capable of classifying brain imaging data. By presenting brain scans as male or female to the model, it learned to discern subtle patterns for differentiation.The model employed a deep neural network to analyse dynamic MRI scans, capturing the complex interactions among various brain regions. During testing on approximately 1,500 brain scans, it consistently distinguished between scans from women and men with remarkable accuracy.

The model's success suggested that detectable sex differences do exist in the brain thathave not been studied previously. "This is a very strong piece of evidence that sex is a robust determinant of human brain organization," concluded Menon.

References: Srikanth Ryali, Yuan Zhang, Carlo de los Angeles, Kaustubh Supekar, Vinod Menon. Deep learning models reveal replicable, generalizable, and behaviorally relevant sex differences in human functional brain organization. Proceedings of the National Academy of Sciences, 2024; 121 (9) DOI: 10.1073/pnas.2310012121