According to new research from Imperial College London, a single MRI scan of the brain might be enough to treat Alzheimers disease.
The study uses machine learning technology to evaluate key features inside the brain, especially in regions that weren''t previously associated with Alzheimers. The advantage of the technique is its simplicity and the fact that it can detect the disease at an early stage when it is quite difficult to diagnose.
Although there is no cure for Alzheimers disease, getting a diagnosis early at an early stage is beneficial to patients. It allows them to access help and support, and provide treatment to manage their symptoms and prepare for the future. Being able to accurately identify patients at an early stage of the disease will also assist researchers in establishing the brain changes that trigger the disease. The development and testing of new therapies.
Common form of dementia
The research is published in the Nature Portfolio Journal, Communications Medicine, and funded by the National Institute for Health and Care Research (NIHR) Imperial Biomedical Research Centre, as well as the Medical Research Council.
Alzheimers disease is a common form of dementia, which affects over half a million people in the United Kingdom. Despite the fact that most people with Alzheimers disease develop it after the age of 65, people under this age may develop it. Memory loss and difficulties with thinking, problem solving, and communication are among the most common symptoms of dementia.
The majority of Alzheimers disease diagnoses are performed using memory and cognitive tests and brain scans. These tests are used to detect protein deposits in the brain and shrinkage of the hippocampus, which is linked to memory. All of these tests may take several weeks, both to arrange and to process.
A magnetic resonance imaging (MRI) brain scan based on a 1.5 Tesla machine is required for the new approach, which is most commonly found in hospitals.
Researchers adapted an algorithm for estimating cancer tumours and applied it to the brain. They divided the brain into 115 areas and allocated 660 different features to assess each region, such as size, shape, and texture. They then trained the algorithm to identify areas in which changes to these features would accurately predict the existence of Alzheimers disease.
The team, which has been partnered with Alzheimers Disease Neuroimaging, tested their treatment using brain scans from over 400 patients with early and later stage Alzheimers, healthy controls, and patients with other neurological illnesses, including frontotemporal dementia and Parkinsons disease.
In 98 percent of cases, the MRI-based machine learning system merely could accurately predict whether the patient had Alzheimers disease or not. It was also capable of distinguishing between early and late-stage Alzheimers with fairly high accuracy, according to 79 percent of patients.
Professor Eric Aboagye, who led the research, said: "Currently, no other simple and widespread methods can predict Alzheimers disease with this level of accuracy, thus our research is a significant step forward. Many people who present with Alzheimers at memory clinics also have neurological disorders, but even within this group our system may select those who did not.
Waiting for a diagnosis can be a horrifying experience for patients and their families. We may reduce the length of time they have to wait, make diagnosis a simpler process, and reduce some of the uncertainty, that could, in turn, help a lot. We may also identify early-stage patients for clinical trials of new medication therapies or lifestyle changes, which is currently very difficult to do.
Changes in areas of the brain that were previously associated with Alzheimers disease have been detected by the new system, including the cerebellum (the brain''s focal structure that regulates physical activity) and the ventral diencephalon (linked to the senses, sight, and hearing). This opens up potential new avenues for research into these areas and their implications for Alzheimers disease.
According to Dr Paresh Malhotra, a consultant neurologist at Imperial College Healthcare NHS Trust and a researcher at the Imperials Department of Brain Sciences, MRI scans would be useful for Alzheimers patients. Even specialists might benefit from these scans, thanks to an algorithm able to select texture and subtle structural features in the brain that are affected by Alzheimers.