The human brain comprises hundreds of interconnected regions that drive our thoughts, emotions, and behaviours. Existing brain atlases can identify major structures in MRI scans - such as the hippocampus, which supports memory and learning - but their finer sub-regions remain hard to detect. These distinctions matter because sub-regions of areas like the hippocampus, for example, are affected differently during Alzheimer’s disease progression.
Examining the brain at the cellular level is achievable using microscopy (histology), but cannot be done in living individuals, limiting its potential for understanding how the human brain changes during development, ageing and disease.
Published in Nature , the new study introduces NextBrain, an atlas of the entire adult human brain that can be used to analyse MRI scans of living patients in a matter of minutes and at a level of detail not possible until now.
The creators of the atlas, which is freely available, hope it will ultimately help to accelerate discovery in brain science and its translation into better diagnosis and treatment of conditions such as Alzheimer’s.
How the AI-assisted brain atlas was developed
The atlas took the research team six years to build through a painstaking process akin to completing a jigsaw puzzle - albeit one made using post-mortem tissue from five human brains.Each brain was painstakingly dissected and sectioned into 10,000 pieces, stained to help identify brain structures, photographed under a microscope, then reassembled into a 3D digital model. Before they began this process, the team conducted MRI scans of the brains so they would know how to put them back together, not unlike the picture on the front of a jigsaw box.
AI was used to help align the microscope images and the MRI scans, accounting for the differences between the two techniques and ensuring that the pieces did not overlap or have gaps in between them.
A total of 333 brain regions were then labelled on the digital 3D models of each of the five brains, a process greatly accelerated by AI. Done manually, the researchers say it would have taken decades.
Dr Juan Eugenio Iglesias, senior author of the study from UCL Medical Physics & Biomedical Engineering and Massachusetts General Hospital/Harvard Medical School, said: "NextBrain is the culmination of years of effort to bridge the gap between microscope imaging and MRI. By combining high-resolution tissue data with advanced AI techniques, we’ve created a tool that allows researchers to analyse brain scans in a level of detail that was previously unattainable. This opens up new possibilities for studying neurodegenerative diseases and ageing."
The resulting atlas, which is an ’average’ of the five brain models, is generalisable to all’adult humans - meaning it can be used to automatically infer detail from MRI scans of living or deceased subjects.
