Anatomical Landmark Based Deep Feature Representation for MR Images in Brain Disease Diagnosis

• Published in: IEEE journal of biomedical and health informatics Vol. 22; no. 5; pp. 1476 - 1485
• Main Authors: Liu, Mingxia, Zhang, Jun, Nie, Dong, Yap, Pew-Thian, Shen, Dinggang
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.09.2018; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Aged; Aged, 80 and over; Algorithms; Alzheimer's disease; Anatomic Landmarks - diagnostic imaging; Anatomical landmarks; Artificial neural networks; Automation; Biomarkers; Brain; Brain - diagnostic imaging; brain disease diagnosis; Brain diseases; Brain Diseases - diagnostic imaging; Classification; convolutional neural network; Dementia; Diagnosis; Feature extraction; Female; Humans; Image classification; Image Interpretation, Computer-Assisted - methods; Image management; Image retrieval; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Male; Medical diagnosis; Medical imaging; Middle Aged; Neural networks; Neurodegenerative diseases; Neuroimaging; Neuroimaging - methods; Neurology; Performance enhancement; Representations; Resonance; Testing; Training

Most automated techniques for brain disease diagnosis utilize hand-crafted (e.g., voxel-based or region-based) biomarkers from structural magnetic resonance (MR) images as feature representations. However, these hand-crafted features are usually high-dimensional or require regions-of-interest define...