by
Christina Hwang, Contributing Reporter | July 09, 2016
Accuracy from 82 to 90 percent
With the use of artificial intelligence and an MR technique known as aerial spin labeling (ASL), physicians may be able to diagnose Alzheimer’s at a highly accurate rate, new research from the Netherlands has shown.
ASL, which measures the tissue absorption rate of the blood that flows in the brain, is used to detect early forms of dementia such as a mild cognitive impairment (MCI), but physicians have no concrete way of identifying who has early dementia or which cases of MCI would turn into Alzheimer’s disease, according to the announcement.
In the study, the researchers used the information of 260 participants from the Alzheimer Center of the VU University Medical Center who had undergone ASL MR between October 2010 and November 2012, and they applied the artificial intelligence system to the images.
Ad Statistics
Times Displayed: 121569
Times Visited: 7007 MIT labs, experts in Multi-Vendor component level repair of: MRI Coils, RF amplifiers, Gradient Amplifiers Contrast Media Injectors. System repairs, sub-assembly repairs, component level repairs, refurbish/calibrate. info@mitlabsusa.com/+1 (305) 470-8013
The system was built to recognize the patterns in the brain “maps”, and it was able to distinguish between the patients with Alzheimer’s, mild cognitive impairment, and subjective cognitive decline (SCD). According to the announcement, the researchers were then able to predict the Alzheimer’s diagnosis or progression with an accuracy of 82 to 90 percent.
“Training accuracies and prediction rates were high for the AD versus SCD, and AD versus MCI contrasts, but not for MCI versus SCD,” principal investigator Meije Wink, Ph.D., from the VU Medical Center in Amsterdam, told HCB News.
The study included 100 patients diagnosed with Alzheimer’s, 60 patients with mild cognitive impairment and 100 patients with subjective cognitive decline, as well as 26 healthy controls.
“The main limitation at this point is that we do not know enough about how to control the way these classifiers use the imaging data internally, so it is not possible to use classification outcomes at face value without review by an expert neuroradiologist,” Wink said.
“ASL MRI can identify brain changes that appear early in disease process, when there’s a window of opportunity for intervention,” he said. “If the disease process from SCD to MCI to Alzheimer’s could be intercepted or slowed, this technique could play a role in screening.”
