Cognitive signature of brain FDG PET based on deep learning: domain transfer from Alzheimer’s disease to Parkinson’s disease

• Published in: European journal of nuclear medicine and molecular imaging Vol. 47; no. 2; pp. 403 - 412
• Main Authors: Choi, Hongyoon, Kim, Yu Kyeong, Yoon, Eun Jin, Lee, Jee-Young, Lee, Dong Soo
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.02.2020; Springer Nature B.V
• Subjects: Advanced Image Analyses (Radiomics and Artificial Intelligence); Alzheimer Disease - diagnostic imaging; Alzheimer's disease; Biomarkers; Brain; Brain - diagnostic imaging; Brain mapping; Cardiology; Cognition; Cognitive ability; Cognitive Dysfunction - diagnostic imaging; Deep Learning; Dementia; Dementia disorders; Disorders; Domains; Evaluation; Feature maps; Fluorodeoxyglucose F18; Forecasting; Humans; Imaging; Machine learning; Mapping; Medical imaging; Medicine; Medicine & Public Health; Model accuracy; Movement disorders; Neurodegenerative diseases; Neuroimaging; Nuclear Medicine; Oncology; Original Article; Orthopedics; Parkinson Disease - diagnostic imaging; Parkinson's disease; Positron emission tomography; Radiology; Transfer learning; Two dimensional models; Deep learning; Parkinson disease; Transfer learning; FDG PET; Dementia

Purpose Although functional brain imaging has been used for the early and objective assessment of cognitive dysfunction, there is a lack of generalized image-based biomarker which can evaluate individual’s cognitive dysfunction in various disorders. To this end, we developed a deep learning-based co...