Deep Learning-Driven Estimation of Centiloid Scales from Amyloid PET Images with C-PiB and F-Labeled Tracers in Alzheimer's Disease.

Background: Standard methods for deriving Centiloid scales from amyloid PET images are time-consuming and require considerable expert knowledge. We aimed to develop a deep learning method of automating Centiloid scale calculations from amyloid PET images with C-Pittsburgh Compound-B (PiB) tracer and assess its applicability to F-labeled tracers without retraining.

Methods: We trained models on 231 C-PiB amyloid PET images using a 50-layer 3D ResNet architecture. The models predicted the Centiloid scale, and accuracy was assessed using mean absolute error (MAE), linear regression analysis, and Bland-Altman plots.

Results: The MAEs for Alzheimer's disease (AD) and young controls (YC) were 8.54 and 2.61, respectively, using C-PiB, and 8.66 and 3.56, respectively, using F-NAV4694. The MAEs for AD and YC were higher with F-florbetaben (39.8 and 7.13, respectively) and F-florbetapir (40.5 and 12.4, respectively), and the error rate was moderate for F-flutemetamol (21.3 and 4.03, respectively). Linear regression yielded a slope of 1.00, intercept of 1.26, and R of 0.956, with a mean bias of -1.31 in the Centiloid scale prediction.

Conclusions: We propose a deep learning means of directly predicting the Centiloid scale from amyloid PET images in a native space. Transferring the model trained on C-PiB directly to F-NAV4694 without retraining was feasible.