Artificial intelligence tool detects sex-related differences in brain structure


A recent study published in Scientific Reports reveals that artificial intelligence (AI) computer programs analyzing MRI results can detect differences in how the brains of men and women are organized at a cellular level. Specifically, these variations were observed in white matter, a tissue primarily located in the innermost layer of the human brain responsible for facilitating communication between different regions.

Led by researchers at NYU Langone Health, the study aimed to enhance our understanding of how biological sex influences brain structure, with implications for improving diagnostic tools and treatments for conditions such as multiple sclerosis, autism spectrum disorder, migraines, and other brain-related issues.

Using machine learning, an AI technique, the researchers analyzed thousands of MRI brain scans from 471 men and 560 women. The results revealed that the AI programs could accurately distinguish between male and female brains by identifying patterns in structure and complexity not visible to the human eye. These findings were validated by three different AI models, each leveraging its strengths in analyzing white matter.

Dr. Yvonne Lui, the senior author of the study and a neuroradiologist at NYU Langone Health, emphasized the significance of these findings in providing a clearer understanding of how the human brain is structured. This understanding could offer new insights into the development of psychiatric and neurological disorders and why they manifest differently in men and women.

Unlike previous studies that relied on animal models or human tissue samples, this research utilized machine learning to analyze entire groups of images, minimizing human biases. By training AI models with existing data and genetic information, the programs learned to distinguish biological sex independently, achieving high accuracy rates.

The researchers underscored the importance of diversity in studying brain-related diseases, cautioning against using men as the standard model, which may overlook critical insights. They noted that while AI tools could detect differences in brain-cell organization, they could not determine which sex was more likely to exhibit specific features.

Moving forward, the research team plans to explore the development of sex-related brain structure differences over time, considering environmental, hormonal, and social factors. The study represents a significant step forward in understanding the complexities of brain biology and its implications for health and disease.

In addition to Dr. Lui, the study involved researchers Junbo Chen, Vara Lakshmi Bayanagari, Sohae Chung, and Yao Wang from NYU Langone Health and NYU.