Single Brain Scan Can Diagnose Alzheimer’s Disease

Single Brain Scan Can Diagnose Alzheimer’s Disease

New research breakthrough uses machine learning technology to view structural features inside the brain, including in areas that weren’t previously associated with Alzheimer’s. The technique’s advantage is its simplicity and the fact that it can detect the disease early when it can be too difficult to diagnose.

Although there is no cure for Alzheimer’s disease, obtaining early diagnosis can help patients. This allows them to access help and assistance, discipline their symptoms and plan for the future. Being able to accurately identify patients in the early stages of disease will also help researchers understand the brain changes that trigger disease, and support new treatment development and trials.

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

Alzheimer’s Disease is the most common form of dementia, affecting more than half a million people in the UK. Although most people with Alzheimer’s disease develop it after age 65, people younger than that age can develop it too. The most common symptoms of dementia are memory loss and difficulties in thinking, problem solving and language.

Doctors currently use a fleet of tests to diagnose Alzheimer’s disease, including memory and scientific tests and brain scans. Scans are used to test protein reserves in the brain and contraction of hippocampus, the area of the brain connected to memory. All these tests could take several weeks, both to be arranged and processed.
The new perspective requires just one of them – magnetic resonance imaging (MRI) brain scans taken on a standard 1.5 Tesla machine, commonly found in most hospitals.

Researchers have shaped an algorithm developed for use in classifying cancer tumors and applied it to the brain. They divided the brain into 115 regions and allocated 660 different features, such as size, shape and texture, to assess each region. They then trained an algorithm to identify if changes in these characteristics could accurately predict the existence of Alzheimer’s disease.

Using data from Alzheimer’s Disease Neuroming Initiative, the team tested their perspectives on brain scans from more than 400 patients with early and post-stage Alzheimer’s, health control and other neurological conditions, Frontotty Moral Including dementia and Parkinson’s disease. He also experimented with statistics of more than 80 patients undergoing diagnostic tests for Alzheimer’s at the Imperial College Healthcare NHS Trust.
They found that in 98 percent of cases, MRI -based machine learning system could only accurately predict whether a patient has Alzheimer’s disease or not. It managed to distinguish with significant accuracy, even between early and late-stage Alzheimer’s, in 79 percent of patients.

Professor Eric Abugai, from Imperial’s Department of Surgery and Cancer, who led the research, said: “No other simple and widely available method currently can predict Alzheimer’s disease with this level of accuracy, so our research.” This is an important step to move forward. Many patients who are present in memory clinics with Alzheimer’s also have neurological conditions, but even within this group our system can pick up patients who had Alzheimer’s who didn’t.

“Waiting for a diagnosis can be a terrifying experience for patients and their families.” If we could decrease the time needed to wait for them, make a diagnosis a simpler process, and ease some of the uncertainty, that would be a huge help. Our new approach can also identify early-early patients for clinical trials of drug treatment or lifestyle changes, which is currently too difficult to do

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

Doctor. Advisor neurologist at the Imperial College Healthcare NHS Trust and researcher at the Imperial College of Healthcare NHS Trust, Parish Malhotra said: “While neuroradiologists already interpret MRI scans to help diagnose Alzheimer’s, even for experts,” Scan done There are qualities that are not visible. Using algorithms capable of selecting structural and fine-tactical features in the brain affected by Alzheimer’s could truly expand the information we can obtain from standard imaging techniques

Reference: “A predictive model using mesoscopic architecture of a living brain to detect Alemeria’s disease” Mariana Anglesey, Neva Patel, Christopher Linton-Red, Flavia Loretto, Zernie One, Richard J. Perry, Christopher Carswell, Matthew Greech Solars, William R. Grace, Hanan Lo, Parish A. Malhotra, Alzheimer’s Disease Neurovimaging Initiative and Eric O’Abogai, June 20, 2022, Communication Medicine.

Leave a Comment