Effect of Denoising and Deblurring F-18-Fluorodeoxyglucose Positron Emission Tomography Images on a Deep Learning Model's Classification Performance for Alzheimer's Disease

Abstract

Alzheimer's disease (AD) is the most common progressive neurodegenerative disease. F-18-fluorodeoxyglucose positron emission tomography (F-18-FDG PET) is widely used to predict AD using a deep learning model. However, the effects of noise and blurring on 18 F-FDG PET images were not considered. The performance of a classification model trained using raw, deblurred (by the fast total variation deblurring method), or denoised (by the median modified Wiener filter) F-18-FDG PET images without or with cropping around the limbic system area using a 3D deep convolutional neural network was investigated. The classification model trained using denoised whole-brain F-18-FDG PET images achieved classification performance (0.75/0.65/0.79/0.39 for sensitivity/specificity/F1-score/Matthews correlation coefficient (MCC), respectively) higher than that with raw and deblurred F-18-FDG PET images. The classification model trained using cropped raw F-18-FDG PET images achieved higher performance (0.78/0.63/0.81/0.40 for sensitivity/specificity/F1-score/MCC) than the whole-brain F-18-FDG PET images (0.72/0.32/0.71/0.10 for sensitivity/specificity/F1-score/MCC, respectively). The F-18-FDG PET image deblurring and cropping (0.89/0.67/0.88/0.57 for sensitivity/specificity/F1-score/MCC) procedures were the most helpful for improving performance. For this model, the right middle frontal, middle temporal, insula, and hippocampus areas were the most predictive of AD using the class activation map. Our findings demonstrate that F-18-FDG PET image preprocessing and cropping improves the explainability and potential clinical applicability of deep learning models.