Improved interpretation of 18F-florzolotau PET in progressive supranuclear palsy using a normalization-free deep-learning classifier

While F-18-florzolotau tau PET is an emerging biomarker for progressive supranu-clear palsy (PSP), its interpretation has been hindered by a lack of consensus on visual reading and potential biases in conventional semi-quantitative analysis. As clinical manifestations and regions of elevated F-18-florzolotau binding are highly overlapping in PSP and the Parkinsonian type of multiple system atrophy (MSA-P), developing a reliable discriminative classifier for F-18-florzolotau PET is urgently needed. Herein, we developed a normalization-free deep-learning (NFDL) model for F-18-florzolotau PET, which achieved significantly higher accu-racy for both PSP and MSA-P compared to semi-quantitative classifiers. Regions driving the NFDL classifier's decision were consistent with disease-specific to-pographies. NFDL-guided radiomic features correlated with clinical severity of PSP. This suggests that the NFDL model has the potential for early and accurate differentiation of atypical parkinsonism and that it can be applied in various sce-narios due to not requiring subjective interpretation, MR-dependent, and refer-ence-based preprocessing.