KCL and UCL scientists develop accurate AI brain imaging model for research

In the UK, there are an estimated 11 million people living with a neurological condition

Researchers from King’s College London have developed a new artificial intelligence (AI) brain imaging model in collaboration with University College London (UCL) which is realistic and accurate enough to use in medical research.

Published in Nature Medicine Intelligence, the three-dimensional, synthetic images of the human brain could help support research to predict, diagnose and treat brain diseases including dementia, stroke and multiple sclerosis.

According to Brain Research UK, there are an estimated 11 million people in the UK who are living with a neurological condition. Among the most common are Alzheimer’s disease, epilepsy and stroke.

In collaboration with the London Medical Imaging and AI Centre for Value-Based Healthcare and NVIDIA data scientists and engineers, researchers trained the AI model in weeks as opposed to months using the NVIDIA Cambridge-1 supercomputer.

The model is able to produce 3D, high-resolution images that have all the characteristics of real human brains, including correct folding patterns and regions of the risk size, while also accurately producing images that reflect clinical factors such as age, sex or disease status.

After looking at large volumes of data, the AI model learned how age and sex affect the brain, as well as how pathologies impact anatomy. When tested, the data produced by the model was realistic enough to replicate human anatomy.

Researchers believe this tool could help to make AI diagnosis more accurate and equitable and help neuroscientists better understand how brains change with age and with disease, which could lead to treatments for critical conditions.

Dr Jorge Cardoso, School of Biomedical Engineering and Imaging Sciences, KCL, commented: “With more development, the technology could help us understand which drugs are best for each patient, how certain conditions might evolve differently in different patients, and how a person’s brain might react to a specific treatment.”

Parashkev Nachev, professor of neurology, UCL, said: “The research is also being expanded to other organs like the heart and lungs, and even to complex multi-system diseases like cancer.”