Summary: Researchers are using AI to reveal distinct differences at the cellular level in the brains of men and women, focusing on white matter. These results show that AI can accurately identify gender-based brain patterns invisible to the human eye.
The study suggests that understanding these differences can improve diagnostic tools and treatments for brain disorders. This research highlights the need to diversify brain studies to ensure a comprehensive understanding of neurological diseases.
Highlights:
- AI accuracy: AI models identified biological sex in MRI scans with 92-98% accuracy.
- Focus on white matter: Differences were found in the white matter of the brain, crucial for interregional communication.
- Improved diagnostics: Understanding sex-based brain differences can improve diagnoses and treatments of disorders like multiple sclerosis and autism.
Source: NYU Langone
Artificial intelligence (AI) computer programs that process MRI results show differences in how men’s and women’s brains are organized at the cellular level, a new study suggests. These variations were spotted in white matter, a tissue mainly located in the innermost layer of the human brain, which promotes communication between regions.
Men and women are known to experience multiple sclerosis, autism spectrum disorders, migraines and other brain problems at different rates and with varying symptoms.
A detailed understanding of the impact of biological sex on the brain is therefore seen as a way to improve diagnostic tools and treatments.
However, although the size, shape and weight of the brain have been studied, researchers only have a partial picture of the brain’s layout at the cellular level.
Led by researchers at NYU Langone Health, the new study used an AI technique called machine learning to analyze thousands of brain MRI scans from 471 men and 560 women.
The results revealed that computer programs could accurately distinguish between male and female biological brains by spotting patterns of structure and complexity invisible to the human eye.
The results were validated by three different AI models designed to identify biological sex using their relative strengths either by focusing on small parts of white matter or by analyzing relationships between larger regions of the brain.
“Our findings provide a clearer picture of how a living human brain is structured, which in turn could offer new insights into how many psychiatric and neurological disorders develop and why they may present differently in people. men and women,” said the study’s lead author and neuroradiologist. Yvonne Lui, MD.
Lui, a professor and vice chair for research in the Department of Radiology at NYU Grossman School of Medicine, notes that previous studies of brain microstructure relied largely on animal models and human tissue samples.
Additionally, the validity of some of these earlier findings was called into question because they relied on statistical analyzes of “hand-drawn” regions of interest, which meant that researchers had to make many subjective decisions about shape. , size and location of regions. they choose. Such choices can potentially distort the results, explains Lui.
The new study results, published online May 14 in the journal Scientific reportsavoided this problem by using machine learning to analyze entire groups of images without asking the computer to inspect a specific location, which helped eliminate human bias, the authors say.
For the research, the team began by feeding the AI programs with example data from brain scans of healthy men and women and also telling the machine programs the biological sex of each scan cerebral.
Since these models were designed to use complex statistical and mathematical methods to become “smarter” over time as they accumulated more data, they eventually “learned” to distinguish biological sex by them -themselves. It’s important to note that the programs couldn’t use the overall size and shape of the brain to make their decisions, Lui explains.
According to the results, all models correctly identified the gender of scanned subjects between 92% and 98% of the time. Several features in particular helped the machines determine how easily and in which direction water could move through brain tissue.
“These results highlight the importance of diversity when studying diseases that arise in the human brain,” said study co-senior author Junbo Chen, MS, a doctoral student at the NYU Tandon School of Engineering.
“If, as has always been the case, men are used as the standard model for various disorders, researchers risk missing critical information,” added Vara Lakshmi Bayanagari, MS, co-senior author of the study and graduate research assistant at the NYU Tandon School. of engineering.
Bayanagari cautions that even if AI tools could point to differences in the organization of brain cells, they could not reveal which sex was more likely to exhibit which characteristics. She adds that the study classified gender based on genetic information and only included MRIs from cis gender men and women.
According to the authors, the team next plans to explore how sex-related differences in brain structure evolve over time to better understand the environmental, hormonal and social factors that might play a role in these changes.
Funding: Funding for the study was provided by National Institutes of Health grants R01NS119767, R01NS131458, and P41EB017183, as well as grant W81XWH2010699 from the United States Department of Defense.
Besides Lui, Chen and Bayanagari, other NYU Langone Health and NYU researchers involved in the study were Sohae Chung, PhD, and Yao Wang, PhD.
About this research news in AI and neuroscience
Author: Shira Polan
Source: NYU Langone
Contact: Shira Polan – NYU Langone
Picture: Image is credited to Neuroscience News
Original research: Free access.
“Deep learning with diffusion MRI as an in vivo microscope reveals sex-related differences in human white matter microstructure” by Yvonne Lui et al. Scientific reports
Abstract
Deep learning with diffusion MRI as an in vivo microscope reveals sex differences in human white matter microstructure
Biological sex is a crucial variable in neuroscience studies where sex differences have been documented in cognitive functions and neuropsychiatric disorders.
While gross statistical differences have already been documented in the macroscopic structure of the brain, such as cortical thickness or region size, less is known about sex-related microstructural differences at the cellular level, which could provide insight of brain health and diseases.
Studying these microstructural differences between men and women opens the way to understanding brain disorders and diseases that manifest differently depending on the sex.
Diffusion MRI is an important non-invasive in vivo methodology that provides a window into the microstructure of brain tissues.
Our study develops multiple end-to-end classification models that accurately estimate a subject’s gender using volumetric diffusion MRI data and uses these models to identify white matter regions that differ most between subjects. men and women. 471 healthy male and 560 female subjects (age range 22 to 37 years) from the Human Connectome project are included.
Fractional anisotropy, mean diffusivity, and mean kurtosis are used to capture the microstructural features of brain tissue.
Parametric diffusion maps are registered to a standard template to reduce bias that may arise from macroscopic anatomical differences such as brain size and contour.
This study uses three major model architectures: 2D convolutional neural networks, 3D convolutional neural networks and Vision Transformer (with corresponding self-supervised).
Our results show that all 3 models achieve high sex classification performance (AUC test 0.92–0.98) for all diffusion measures, indicating definitive differences in white matter tissue microstructure between males. and women.
We further use complementary model architectures to inform the pattern of detected microstructural differences and the influence of short- and long-range interactions.
Occlusion analysis along with the Wilcoxon signed-rank test is used to determine which white matter regions contribute most to sex classification.
The results indicate that sex-related differences are manifested in both local features and global features/longer range interactions of tissue microstructure.
Our highly consistent results between models provide new information supporting differences between tissue organization at the cellular level of male and female brains, particularly in central white matter.
News Source : neurosciencenews.com
Gn Health
