Chinese researchers found that a deep-learning model, which analyzed PET and MRI scans, along with cognitive impairment test scores, yielded 96.6% sensitivity, 95.4% specificity and 98.5% accuracy in differentiating individuals with normal cognition from those with Alzheimer's disease. The model, described in the journal Neurocomputing, also had 90.1% sensitivity, 91.8% specificity and 85.7% accuracy in distinguishing those who were cognitively normal from those with mild cognitive impairment, as well as 97.4% sensitivity, 84.3% specificity and 88.2% accuracy in differentiating between those with MCI and those with Alzheimer's.
Study evaluates deep-learning model in Alzheimer's diagnosis
Sign up for SNMMI SmartBrief
Nuclear medicine and molecular imaging news
Get the intelligence you need: news and information that is changing your industry today, hand-curated by our professional editors from thousands of sources and delivered straight to your inbox.