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
• ISSN: 2168-2194; 2168-2208; 2168-2208
• DOI: 10.1109/JBHI.2018.2791863

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 defined by experts. Also, because of possibly heterogeneous property between the hand-crafted features and the subsequent model, existing methods may lead to sub-optimal performances in brain disease diagnosis. In this paper, we propose a landmark-based deep feature learning (LDFL) framework to automatically extract patch-based representation from MRI for automatic diagnosis of Alzheimer's disease. We first identify discriminative anatomical landmarks from MR images in a data-driven manner, and then propose a convolutional neural network for patch-based deep feature learning. We have evaluated the proposed method on subjects from three public datasets, including the Alzheimer's disease neuroimaging initiative (ADNI-1), ADNI-2, and the minimal interval resonance imaging in alzheimer's disease (MIRIAD) dataset. Experimental results of both tasks of brain disease classification and MR image retrieval demonstrate that the proposed LDFL method improves the performance of disease classification and MR image retrieval.