Effective feature learning and fusion of multimodality data using stage‐wise deep neural network for dementia diagnosis

• Published in: Human brain mapping Vol. 40; no. 3; pp. 1001 - 1016
• Main Authors: Zhou, Tao, Thung, Kim‐Han, Zhu, Xiaofeng, Shen, Dinggang
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 15.02.2019
• Subjects: Abnormalities; Aged; Aging; Alzheimer's disease; Alzheimer's disease (AD); Artificial neural networks; Brain; Cognitive ability; Cognitive Dysfunction - diagnostic imaging; Cognitive Dysfunction - genetics; Deep Learning; Dementia; Dementia - diagnostic imaging; Dementia - genetics; Dementia disorders; Diagnosis; Diagnostic systems; Female; Gene polymorphism; Heterogeneity; Humans; Machine learning; Magnetic resonance imaging; Male; Medical imaging; Middle Aged; mild cognitive impairment (MCI); Multimodal Imaging - methods; multimodality data fusion; Neurodegenerative diseases; Neuroimaging; Neuroimaging - methods; Neurology; Polymorphism; Polymorphism, Single Nucleotide; Positron emission tomography; Representations; Risk analysis; Risk factors; Single-nucleotide polymorphism; Training; mild cognitive impairment (MCI); deep learning; Alzheimer's disease (AD); multimodality data fusion

In this article, the authors aim to maximally utilize multimodality neuroimaging and genetic data for identifying Alzheimer's disease (AD) and its prodromal status, Mild Cognitive Impairment (MCI), from normal aging subjects. Multimodality neuroimaging data such as MRI and PET provide valuable...