Deep model based research may advance FDG-PET analysis by demonstrating their potential as an effective imaging biomarker of AD by proposing novel methods that involve probabilistic principal component analysis on max-pooled data and mean-pooles for dimensionality reduction, and multilayer feed forward neural network which performs binary classification.
This thesis develops a classification method to investigate the performance of FDGPET as an effective biomarker for Alzheimer’s clinical group classification, and results indicate that the designed classifiers achieve competitive results, and better with the additional of demographic features.
This paper describes their synthetic dataset generation tool that enables scalable collection of such a synthetic dataset with realistic adversarial examples and demonstrates simulated attacks that undergo the same environmental transforms and processing as real-world images.