Predicting Your Brain Age From MRI Scans

Researchers from King’s College London developed a deep learning system to measure brain age using raw data from an MRI scanner that can help reveal the onset of conditions such as dementia.

Using CUDA, TITAN X GPUs and cuDNN with the Torch deep learning framework, the researchers trained their models on 1,600 MRI brain scans from healthy people between the age of 18 and 90 years old. They then used another 200 images to validate the process and tested the neural network on 200 other images it had never seen to determine how well it could measure the brain. Their deep learning method is able to give the correct age in seconds with a mean error of nearly 4.5 years – this analysis would typically take a neuroscientist more than 24 hours.

MRI data has to be heavily processed before it is suitable for automated aging. This pre-processing includes the removal from the image of non-brain tissue such as the skull, the classification of white matter, gray matter, and other tissue, and the removal of image artefacts along with various data-smoothing techniques.


The development has the potential to significantly influence the way clinicians come to a diagnosis. There is considerable evidence that conditions such as diabetes, schizophrenia, and traumatic brain injury are correlated with faster brain aging. So a way to measure brain aging quickly and accurately could have an important impact on the way clinicians deal with these conditions in the future. “Brain-predicted age represents an accurate, highly reliable, and genetically valid phenotype that has potential to be used as a biomarker of brain aging,” mentions Giovanni Montana of King’s College London in their research paper.

Read more >