By accessing more than 1.6 million brain scans collected from patients across Scotland, scientists hope it can help predict people’s risk of dementia. A team of 20 researchers from the Universities of Edinburgh and Dundee have been granted unprecedented permission to anonymise the vast number of brain scans collected over a decade from across the Scottish population.
This is the first time that scientists in the UK have access to such a large amount of valuable data. They will use artificial intelligence (AI) to analyze these scans to identify patterns or signs associated with dementia. Dementia occurs due to the accumulation of different types of proteins in the brain, which damages the brain tissue and causes a decrease in cognitive level. These molecular and cellular changes in the brain usually begin years before symptoms appear.
By studying a large number of brain scans, the researchers hope to develop tools to help radiologists diagnose dementia early. NHS Scotland has given scientists permission to use 1.6 million CT and MRI images collected between 2008 and 2018 during routine clinical care. Previous studies were limited due to limited access to a smaller number of scans. Access to large and quality data is one of the main pillars in the development of artificial intelligence models.
The decision to grant permission to review this huge volume of scans was made by the Public Interest and Privacy Commission (NHS) Scotland. The committee is responsible for ensuring that applicants have carefully considered the public interest and privacy implications. All scans will be anonymous so that the researchers do not have any information about the patients. Informing patients about their risk of developing diseases such as Alzheimer’s can help them make changes to slow the progression of the disease.
“If you know you’re at risk, you can make lifestyle changes that improve your brain health,” says Willie Gilder, a former journalist who was diagnosed with Alzheimer’s three years ago. The 71-year-old, from Edinburgh, added: “Since I was diagnosed early, I know that staying mentally active will help me.” He also pointed out: “Alzheimer’s treatments are being developed that look very promising, but these treatments are more effective in the early stages of the disease, which is why early detection is so critical.”
The latest research project is called Scan-Dan (Scottish Artificial Intelligence in Neuroimaging to Predict Dementia and Neurodegenerative Diseases) and is part of a global research collaboration called NEURii. “Scotland and the UK are leading the way in clinical data research,” says Professor Emanuele Treco, an expert in artificial intelligence and medical imaging at the University of Dundee. “This new data set will be invaluable to neuroscientists,” he adds.
Professor Turko added that the scientists did not know exactly what they were looking for, but given the large volume of brain scans, they were confident they could identify patterns associated with dementia. “Even if we don’t know exactly what we’re looking for at the outset, we can still predict whether someone is at risk,” he said.
The research team expects to gain a better understanding of the technology’s potential by early next year, but developing a practical product will take several more years. Professor Will Whiteley of the University of Edinburgh’s Center for Clinical Brain Sciences, who is co-leading the project, said: “Currently, treatments for dementia are expensive, rare and of uncertain value.” “If we can collect data from a large group of high-risk people who then consent to participate in trials, we can really start to develop new treatments,” he added.
He continued: “Using these images requires multiple permissions; Therefore, in collaboration with Public Health Scotland, we have gone through a thorough process to comply with all necessary confidentiality and legal arrangements.”
source
RCO NEWS