Smart MRI

Currently, Alzheimer's disease has no cure, however, diagnosis at an early stage allows patients to access social care, start symptomatic treatment and plan for the future. Identifying patients at an early stage of the disease will also help researchers study pathological processes in the brain, develop and test new treatments.

Alzheimer's disease is the most common form of dementia, affecting about half a million people in the UK. In most cases, Alzheimer's disease develops after the age of 65, but it also occurs in younger people. The most common symptoms are memory impairment and difficulty thinking and speaking.

Currently, doctors use various methods to diagnose Alzheimer's disease, including memory and cognitive ability tests and brain tomography to assess the accumulation of pathological proteins in the brain and reduce the volume of the hippocampus. The organization, execution and processing of the results of such a survey may take several weeks.

Researchers from Imperial College London have created an algorithm that allows using standard magnetic resonance imaging (MRI) of the brain to quickly and at an early stage diagnose Alzheimer's disease. To do this, they divided the brain into 115 conditional zones and identified 660 different features (size, shape, texture, etc.) to evaluate each of the zones. The researchers then "trained" the algorithm to determine which changes in these signs could accurately indicate the presence of Alzheimer's disease.

Using data from the Alzheimer's Disease Neuroimaging Initiative (ADNI), the team tested the algorithm on brain scans of more than 400 patients with early and late-stage Alzheimer's disease, healthy volunteers and patients with other neurological diseases, including frontotemporal dementia and Parkinson's disease.

The researchers found that in 98% of cases, a machine learning system based on a single MRI can accurately determine the presence or absence of Alzheimer's disease in a patient, and also distinguish the early and late stages of Alzheimer's disease in 79% of patients with fairly high accuracy.

The new algorithm detected changes in areas of the brain not previously associated with Alzheimer's disease, including the cerebellum and the intermediate brain. This opens up new potential opportunities for research on these parts of the brain and their connection with Alzheimer's disease.

Article by Inglese et al. A predictive model using the mesoscopic architecture of the living brain to detect Alzheimer's disease is published in the journal.Communications Medicine.

Aminat Adzhieva, portal "Eternal Youth" http://vechnayamolodost.ru based on the materials of Imperial College London: Single brain scan can diagnose Alzheimer's disease.