Feature extraction and coalescence of medical imaging modalities of alzheimers diseases using deep learning

Abstract

The thesis considered three modalities, including PET, MRI, and DTI for AD classification. To extract statistical and textural features from brain scans, this work applied ML and DL techniques to classify AD and NC.A multi-modality fused image deep CNN architecture for early diagnosis of Alzheimer s is also proposed. Also, it examines the impact of hyper parameters on the performance of the considered networks. The latter part of thesis focuses on classifying AD from NC using machine learning-based multimodality feature fusion framework. newline