Our brain age can now be predicted using MRI scanners, according to a recent study. This method can help patients that might be at an increased risk of developing poor health.
The human brain changes with age and the difference between brain age and chronological age can reveal the start of certain conditions such as dementia. Understanding these changes that are associated with brain ageing can help improve detection and even predict diseases.
In 2016, researchers from King’s College London developed a deep learning framework and trained it to measure brain age using raw data from MRI scans. This method takes seconds compared to the lengthy analysis (more than 24 hours) it would take a neuroscientist to process the imaging and data.
The processing includes the removal of non-brain tissue, the sorting of white and grey matter, the removal of image artefacts and other tissues. The deep-learning technique can give doctors an accurate idea of the patient’s brain age while they are still in the MRI scanner.
In the picture below you can see the grey matter in the first scan that had to be removed, the white matter in the second scan that also must be removed and finally the third scan is the raw MRI scan.
Picture from: https://arxiv.org/ftp/arxiv/papers/1612/1612.02572.pdf
The development of this deep-learning technique started by researchers training the framework on 1,600 MRI brain scans from healthy people between the age of 18 and 90 years old.
By training the framework on healthy brain scans, predictions can then be made in independent clinical samples. So, if the brain age prediction is greater than the individual’s chronological age, this will reflect some changes to the brain.
Next, 200 images were used to validate the process and lastly another 200 images were used- that the framework had never seen- to test how well it could measure the brains.
Giovanni Montana of King’s College London mentions in his research paper: “Our analysis showed the brain-predicted age is highly reliable and thus appropriate for use in both longitudinal and multi-centre studies. Brain-predicted age has the potential to be used as a biomarker to investigate the brain ageing process and how this relates to cognitive ageing, neurodegeneration and age associated brain disease”.
Conditions such as diabetes, dementia and schizophrenia are linked with faster brain ageing. Predicting a patient’s brain age can have a huge positive impact on the way clinicians deal with conditions and how they come to a diagnosis.
Read the full research here: Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker
Do you require the use of medical imaging equipment for a research paper? Please contact us if you’re interested in partnering on a research project. Newcastle Clinic offers open MRI scanning, ultrasound and image intensifying.