Classification of 18F-Flutemetamol Scans in Cognitively Normal Older Adults Using Machine Learning Trained with Neuropathology as Groundtruth

PURPOSE: End-of-life studies have validated the binary visual reads of 18F-labeled amyloid PET tracers as an accurate tool for the presence or absence of increased neuritic amyloid plaque density. In this study, the performance of a support vector machine (SVM) based classifier will be tested against pathological groundtruths and its performance determined in cognitively healthy older adults.METHODS: We applied SVM with a linear kernel to an 18F-Flutemetamol end-of-life dataset to determine the regions with the highest feature weights in a data-driven manner and to compare between two different pathological groundtruths: based on neuritic amyloid plaque density or on amyloid phases, respectively. We also trained and tested classifiers based on the 10% voxels with the highest feature weights for each of the two neuropathological groundtruths. Next, we tested the classifiers’ diagnostic performance in the asymptomatic Alzheimer’s disease (AD) phase, a phase of interest for future drug development, in an independent dataset of cognitively intact older adults, the Flemish Prevent AD Cohort-KU Leuven (F-PACK). A regression analysis was conducted between the Centiloid (CL) value in a composite volume of interest (VOI), as index for amyloid load, and the distance to the hyperplane for each of the two classifiers, based on the two pathological groundtruths. A Receiver-Operating-Characteristic analysis was also performed to determine the CL threshold that optimally discriminates between neuritic amyloid plaque positivity versus negativity, or amyloid phase positivity versus negativity, within F-PACK.RESULTS: The classifiers yielded adequate sensitivity and specificity within the end-of-life dataset (neuritic amyloid plaque density classifier: specificity of 90.2% and sensitivity of 83.7%; amyloid phase classifier: specificity of 98.4% and sensitivity of 84.0%). The regions with the highest feature weights corresponded to precuneus, caudate, anteromedial prefrontal, and also posterior inferior temporal and inferior parietal cortex. In the cognitively normal cohort, the correlation coefficient between CL and distance to the hyperplane was -0.66 for the classifier trained with neuritic amyloid plaque density, and -0.88 for the classifier trained with amyloid phases. This difference was significant. The optimal CL cut-off for discriminating positive versus negative scans was CL = 48-51 for the different classifiers (area under the curve (AUC) = 99.9%), except for the classifier trained with amyloid phases and based on the 10% voxels with highest feature weights. There the cut-off was CL = 26 (AUC = 99.5%).DISCUSSION: A neuropathologically validated classifier applied in cognitively normal older adults reveals that amyloid PET values (Centiloids) correlate best with amyloid phases. A CL cut-off of 26 reliably discriminated between amyloid phase 0-2 and 3-5 while only a CL around 50 discriminated between no or sparse and moderate to severe neuritic amyloid plaque density.