A Single AI-Enhanced Brain Scan Can Diagnose Alzheimer's Disease (imperial.ac.uk) 10
Long-time Slashdot reader schwit1 shares an announcement from London's Imperial College of Science, Technology and Medicine:
A single MRI scan of the brain could be enough to diagnose Alzheimer's disease, according to new research by Imperial College London.
The research uses machine learning technology to look at structural features within the brain, including in regions not previously associated with 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. Although there is no cure for Alzheimer's disease, getting a diagnosis quickly at an early stage helps patients. It allows them to access help and support, get treatment to manage their symptoms and plan for the future. Being able to accurately identify patients at an early stage of the disease will also help researchers to understand the brain changes that trigger the disease, and support development and trials of new treatments....
The researchers adapted an algorithm developed for use in classifying cancer tumours, 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 the algorithm to identify where changes to these features could accurately predict the existence of Alzheimer's disease... They found that in 98 per cent of cases, the MRI-based machine learning system alone could accurately predict whether the patient had Alzheimer's disease or not. It was also able to distinguish between early and late-stage Alzheimer's with fairly high accuracy, in 79 per cent 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 methods can predict Alzheimer's disease with this level of accuracy, so our research is an important step forward...." The new system spotted changes in areas of the brain not previously associated with Alzheimer's disease, [which] opens up potential new avenues for research into these areas and their links to Alzheimer's disease.
Professor Aboagye adds that this new approach "could also identify early-stage patients for clinical trials of new drug treatments or lifestyle changes, which is currently very hard to do."
The research uses machine learning technology to look at structural features within the brain, including in regions not previously associated with 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. Although there is no cure for Alzheimer's disease, getting a diagnosis quickly at an early stage helps patients. It allows them to access help and support, get treatment to manage their symptoms and plan for the future. Being able to accurately identify patients at an early stage of the disease will also help researchers to understand the brain changes that trigger the disease, and support development and trials of new treatments....
The researchers adapted an algorithm developed for use in classifying cancer tumours, 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 the algorithm to identify where changes to these features could accurately predict the existence of Alzheimer's disease... They found that in 98 per cent of cases, the MRI-based machine learning system alone could accurately predict whether the patient had Alzheimer's disease or not. It was also able to distinguish between early and late-stage Alzheimer's with fairly high accuracy, in 79 per cent 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 methods can predict Alzheimer's disease with this level of accuracy, so our research is an important step forward...." The new system spotted changes in areas of the brain not previously associated with Alzheimer's disease, [which] opens up potential new avenues for research into these areas and their links to Alzheimer's disease.
Professor Aboagye adds that this new approach "could also identify early-stage patients for clinical trials of new drug treatments or lifestyle changes, which is currently very hard to do."
Open access paper (Score:5, Informative)
Re: (Score:2)
Good use of AI (Score:3)
would be nice if the AI could teach the doctors how to do it. But it sounds like a lot more solid results than some other other currently-being-used AI situations, like criminal sentence recommendations based on "risk factors" or some really sketchy things like that. (I'm not a big fan of depend-on-it-first, test-it-later, oops sorry about the mistakes)
Would be nice if the AI's could spot some potential causes of Alzheimer's, like testing prion interaction, which is a promising new line of research into the cause. (like mad-cow disease, except slower, more common, and therefore scarier)
Re: (Score:2)
Would be nice if the AI's could spot some potential causes of Alzheimer's, like testing prion interaction, which is a promising new line of research into the cause. (like mad-cow disease, except slower, more common, and therefore scarier)
These detection networks show correlation. However, correlation could be causation, so that's helpful to point researchers in specific directions to explore with further research.
Re: (Score:1)
There seems to be increasing evidence that lack of sleep has a long term effect including increasing the levels of certain proteins in the brani that are associated with Alzheimer's, and that the effect doesn't seem to be recovered from with "catch up sleep".
https://www.nih.gov/news-event... [nih.gov]
Unfortunately with the many late nighters I have done in my life I'm probably doomed to get it. If I do, I'd rather not know - just sit me down in front of a good movie I can enjoy over and over like it's the first time
This could help many people (Score:5, Insightful)
Not just for the patient, but for the family knowing what to watch for and how to deal with it in the future is a big positive step. Glad to see research like this happening, props to the people doing it.
For those that already (Score:3)
have a brain MRI, is the model open, or are they selling access to use it or what?
Clean data? (Score:2)
bad news and good news (Score:2)
The bad news is that you definitely have Alzheimer's. Its going to kill you in a horrible way in a few years and there's nothing much we can do for you. The good news is that you can now put your affairs into order and plan ahead for a place to slowly go braindead in whatever modicum of comfort you may be able to afford. Cheery!
AI technology (Score:1)