Latent Representation Learning for Alzheimer's Disease Diagnosis With Incomplete Multi-Modality Neuroimaging and Genetic Data

• Published in: IEEE transactions on medical imaging Vol. 38; no. 10; pp. 2411 - 2422
• Main Authors: Zhou, Tao, Liu, Mingxia, Thung, Kim-Han, Shen, Dinggang
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.10.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Aged; Aged, 80 and over; Algorithms; Alzheimer Disease - diagnostic imaging; Alzheimer Disease - genetics; Alzheimer's disease; Brain - diagnostic imaging; Classification; Databases, Factual; Diagnosis; Diagnosis, Computer-Assisted - methods; Diagnostic systems; Feature extraction; Female; Genetic Association Studies; Genetics; Humans; incomplete multi-modality data; latent representation space; Learning; Machine Learning; Magnetic resonance imaging; Male; Medical diagnosis; Medical imaging; Missing data; multi-modality data; Multimodal Imaging - methods; Neuroimaging; Neuroimaging - methods; Neurology; NMR; Nuclear magnetic resonance; Polymorphism, Single Nucleotide - genetics; Positron emission; Positron emission tomography; Representations; Tomography

The fusion of complementary information contained in multi-modality data [e.g., magnetic resonance imaging (MRI), positron emission tomography (PET), and genetic data] has advanced the progress of automated Alzheimer's disease (AD) diagnosis. However, multi-modality based AD diagnostic models a...