Alzheimer’s breakthrough as new algorithm 99% accurate at identifying brain changes

Alzheimer's: Dr Chris discusses the early signs of condition

We use your sign-up to provide content in ways you’ve consented to and to improve our understanding of you. This may include adverts from us and 3rd parties based on our understanding. You can unsubscribe at any time. More info

The new system completed an analysis of brain scan images from 130 people, where the newly developed algorithm operated with nearly 100 accuracy. It also proved to be more accurate, sensitive and specific than any other existing method. The new method can identify signs of mild cognitive impairment (MCI) which is the step that follows from cognitive decline, and the step the comes before Alzheimer’s.

This method will prove important as often, MCI goes undiagnosed as it can be symptomless.

MCI will not always necessarily develop into Alzheimer’s, but it is definitely a very important indicator that someone who has signs of MCI may develop Alzheimer’s in the future.

MRI scans can be done manually by humans, but deep learning techniques have proved a much faster and more accurate and reliable method.

Deep learning techniques take massive databases of training data, and can apply that knowledge to data in novel ways.

Rytis Maskeliūnas, an informatics professor from the Kaunas University of Technology (KTU) in Lithuania, said: “Modern signal processing allows delegating the image processing to the machine, which can complete it faster and accurately enough.

“Of course, we don’t dare to suggest that a medical professional should ever rely on any algorithm 100 percent.

“Think of a machine as a robot capable of doing the most tedious task of sorting the data and searching for features.”

Specialists work with the AI by confirming potential cases that the computer software has identified.

The earlier the diagnosis, the earlier a treatment plan can be made and this is an important step in the right direction towards one day finding a cure for the disease.

This study used the AI model based on an existing ResNet18 neural network.

This allowed a modified system to split brain scans into six categories, from normal healthy brains to the full development of Alzheimer’s disease.

Professer Maskeliūnas said: “Although this was not the first attempt to diagnose the early onset of Alzheimer’s from similar data, our main breakthrough is the accuracy of the algorithm.

DON’T MISS 
Covid cases and deaths are rising and a new risk factor has been found [INSIGHT] 
London: 3,500 seals found living in Thames [REVEAL] 
Yellowstone rocked by 97 earthquakes amid fears of overdue eruption [REPORT]

“Obviously, such high numbers are not indicators of true real-life performance, but we’re working with medical institutions to get more data.

“Medical professionals all over the world attempt to raise awareness of an early Alzheimer’s diagnosis, which provides the affected with a better chance of benefiting from treatment.”

Alzheimer’s disease is the most common cause of dementia and is responsible for 70 percent of cases globally.

Right now, there are around 850,000 people with dementia in the UK. This is projected to rise to 1.6 million by 2040 due to an ageing population.

The study was published in the journal Diagnostics.

Source: Read Full Article