Single brain scan can diagnose Alzheimer’s disease quickly and accurately

A new machine learning algorithm can diagnose Alzheimer’s disease from a single MRI brain scan, using a standard MRI machine available in most hospitals.

A new breakthrough in research uses machine learning technology to examine structural features within the brain, even in regions not previously associated Alzheimer’s

Alzheimer's disease is a disease that attacks the brain, causing a decline in mental ability that worsens over time. It is the most common form of dementia and accounts for 60 to 80 percent of dementia cases. There is no current cure for Alzheimer's disease, but there are medications that can help ease the symptoms.

” data-gt-translate-attributes=”[{” attribute=””>Alzheimer’s. The advantage of the technique is its simplicity and the fact that it can identify the disease at an early stage when it can be very difficult to diagnose.

While there is no cure for Alzheimer’s, getting a diagnosis quickly at an early stage helps patients. It allows them to access help and support, get treatment to manage symptoms, and plan for the future. Being able to accurately identify patients at an early stage of the disease will also help researchers understand the brain changes that trigger the disease and support the development and testing of new treatments.

The research was published today (June 20, 2022) in the Nature Portfolio JournalCommunications Medicine, and funded through the Imperial Biomedical Research Center of the National Institute for Health and Care Research (NIHR).

Alzheimer’s disease is the most common form of dementia, affecting over half a million people in the UK. Although most people with Alzheimer’s develop it after age 65, people under this age can develop it as well. The most frequent symptoms of dementia are memory loss and difficulties with thinking, problem solving and language.

Doctors currently use a number of tests to diagnose Alzheimer’s disease, including memory and cognitive tests and brain scans. The scans are used to check for protein deposits in the brain and for narrowing of the hippocampus, the area of ​​the brain connected to memory. All of these tests can take several weeks, both for organization and processing.

The new approach requires only one of these: a brain magnetic resonance imaging (MRI) performed on a standard 1.5 Tesla machine, commonly found in most hospitals.

The researchers adapted an algorithm developed for use in the classification of cancer tumors and applied it to the brain. They divided the brain into 115 regions and assigned 660 different characteristics, such as size, shape and texture, to evaluate each region. They then trained the algorithm to identify where changes to these characteristics could accurately predict the existence of Alzheimer’s disease.

Using data from the Alzheimer’s Disease Neuroimaging Initiative, the team tested their approach on brain scans of more than 400 early and late-stage Alzheimer’s patients, healthy controls, and patients with other neurological conditions, including frontotemporal dementia and Parkinson’s. They also tested it with data from more than 80 patients undergoing diagnostic tests for Alzheimer’s at the Imperial College Healthcare NHS Trust.

They found that in 98% of cases, the MRI-based machine learning system alone could accurately predict whether or not the patient had Alzheimer’s disease. He was also able to distinguish between early and advanced Alzheimer’s with fairly high levels accuracy

How close the measured value conforms to the correct value.

” data-gt-translate-attributes=”[{” attribute=””>precisionin 79% of patients.

Professor Eric Aboagye, from Imperial’s Department of Surgery and Cancer, who led the research, said: “Currently no other simple and widely available method can predict Alzheimer’s with this level of accuracy, so our research is a important step forward. Many patients presenting with Alzheimer’s in memory clinics also have other neurological conditions, but even within this group our system could distinguish those patients who had Alzheimer’s from those who didn’t.

“Waiting for a diagnosis can be a horrifying experience for patients and their families. If we could reduce the amount of time they have to wait, make diagnosis a simpler process, and reduce some of the uncertainty, that would be of great help. Our new approach could also identify early stage patients for clinical trials of new drug treatments or lifestyle changes, which is currently very difficult to do. “

The new system identified changes in areas of the brain not previously associated with Alzheimer’s disease, including the cerebellum (the part of the brain that coordinates and regulates physical activity) and the ventral diencephalon (related to senses, sight and hearing). This opens up potential new avenues for research in these areas and their links with Alzheimer’s disease.

Dr Paresh Malhotra, a consultant neurologist at the Imperial College Healthcare NHS Trust and a research fellow in the Imperial Department of Brain Sciences, said: “Although neuroradiologists already interpret MRI scans to help diagnose Alzheimer’s, it is likely that there are features of the scans that are not visible, even to specialists. The use of an algorithm capable of selecting the texture and subtle structural features of the brain that are affected by Alzheimer’s could really improve the information we can obtain from the techniques of standard imaging “.

Reference: “A Predictive Model Using Mesoscopic Architecture of the Living Brain to Detect Alzheimer’s Disease” by Marianna Inglese, Neva Patel, Kristofer Linton-Reid, Flavia Loreto, Zarni Win, Richard J. Perry, Christopher Carswell, Matthew Grech -Sollars, William R. Crum, Haonan Lu, Paresh A. Malhotra, Alzheimer’s Disease Neuroimaging Initiative and Eric O. Aboagye, June 20, 2022, Communications medicine.
DOI: 10.1038 / s43856-022-00133-4