The classifiers can be represented as discrimination maps, where a red color indicates that the intensity at that location contributes to the likelihood of the images belonging to the more advanced stage, and a blue color to the likelihood of belonging to the less advanced stage. Weights are shown inside the mask that resulted in the highest accuracies for each classification: A: Alzheimer’s disease (AD) vs. subjective cognitive decline (SCD); B: AD vs. mild cognitive impairment (MCI); C: MCI vs. SCD.
At the VU University Medical Center Amsterdam researchers are harnessing the power of artificial intelligence to be able to detect early signs of Alzheimer’s on MRI scans. The parenchyma exhibits small incremental changes on the scan as the disease develops, but these are difficult to spot in new patients. Only once the disease is at a later stage clinicians are able to identify the disease from the scans, but by then it’s usually already exhibiting well known symptoms.
To help identify these easy to miss characteristics, the team used a computer to analyze hundreds of existing patient scans to point characteristics that repeatedly come up in Alzheimer’s patients. Specifically, machine learning was applied to arterial spin labeling (ASL) scans that produce perfusion maps of the brain. The team used these to review patient scans without knowing the actual state of the patients in order to evaluate the capability of the system.
The computer application was able to pretty accurately distinguish between patients with Alzheimer’s, mild cognitive impairment, and subjective cognitive decline. Moreover, it accurately predicted the diagnosis of Alzheimer’s, or its progression, in individual patients with an accuracy between 82% and 90%.
Study in journal Radiology: Application of Machine Learning to Arterial Spin Labeling in Mild Cognitive Impairment and Alzheimer Disease…