With this new Algorithm, a Single MRI scan can detect early Alzheimer's

A new algorithm by a team from Imperial College, London, is trained to predict Alzheimer's in a single MRI scan.

According to World Health Organization, Dementia is the 7th reason of death worldwide. The most common form of dementia is Alzheimer's. It affects up to 70% of people diagnosed with dementia. People with suspected Alzheimer's usually undergo multiple tests to diagnose the condition, but all the diagnostic tests are inaccurate, have limited availability, and take much time.

A team from Imperial College, London, has developed an MRI-based machine learning system for quick and accurate diagnosis of Alzheimer's disease. Their study was published in Communications Medicine. They claim that the method could detect early and advanced Alzheimer's disease. The researchers developed an algorithm based on those used for classifying cancerous tumors. This algorithm can divide the brain into 115 regions. To each region, they allocated 660 features, such as size, shape, and texture. The algorithm is trained to predict Alzheimer's by identifying size, shape, and texture changes from a single, standard MRI scan.

They tested their method in the Alzheimer's disease Neuroimaging Initiative on brain scans from more than 400 patients. The patients had early or late-stage Alzheimer's and they are compared with patients with other neurological diseases. However, Dr. Rebecca Edelmayer, Senior Director of Scientific Engagement, Alzheimer's Association, said, "That being said, this research is in its early days, and it is not ready to be used as a stand-alone diagnostic tool."