A Deep Learning-Based Model for Classification of Different Subtypes of Subcortical Vascular Cognitive Impairment With FLAIR

• Published in: Frontiers in neuroscience Vol. 14; p. 557
• Main Authors: Chen, Qi, Wang, Yao, Qiu, Yage, Wu, Xiaowei, Zhou, Yan, Zhai, Guangtao
• Format: Journal Article
• Language: English
• Published: Lausanne Frontiers Research Foundation 18-06-2020; Frontiers Media S.A
• Subjects: Accuracy; Atrophy; Classification; Cognitive ability; cognitive impairment; convolutional neural network; Deep learning; Dementia; Diagnosis; magnetic resonance imaging; Medical imaging; Neural networks; Neuroscience; Patients; Studies; subcortical ischemic vascular disease
• ISSN: 1662-453X; 1662-4548; 1662-453X
• DOI: 10.3389/fnins.2020.00557

Deep learning methods have shown their great capability of extracting high-level features from image and have been used for effective medical imaging classification recently. However, training samples of medical images are restricted by the amount of patients as well as medical ethics issues, making it hard to train the neural networks. In this paper, we propose a novel end-to-end 3D attention-based Resnet network architecture to classify different subtypes of Subcortical Vascular Cognitive Impairment (SVCI) with single T2-weighted FLAIR sequence. Our aim is to develop a convolutional neural network to provide a convenient and effective way to assist doctors in diagnosis and early treatment of the different subtypes of SVCI. The experiment data in this paper are collected from 242 patients from the Neurology Department of Renji Hospital, including 78 a-MCI, 70 na-MCI and 94 NCI. The accuracy of our proposed model has reached 98.6% on training set and 97.3% on validation set. The test accuracy on untrained testing set reaches 93.8% with robustness. Our proposed method can provides a convenient and effective way to assist doctors in diagnosis and early treatment.