Abstract
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 three-dimensional (3D) attention-based residual neural network (ResNet) architecture to classify different subtypes of subcortical vascular cognitive impairment (SVCI) with single-shot T2-weighted fluid-attenuated inversion recovery (FLAIR) sequence. Our aim is to develop a convolutional neural network to provide a convenient and effective way to assist doctors in the 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 amnestic mild cognitive impairment (a-MCI), 70 nonamnestic MCI (na-MCI), and 94 no cognitive impairment (NCI). The accuracy of our proposed model has reached 98.6% on a training set and 97.3% on a validation set. The test accuracy on an untrained testing set reaches 93.8% with robustness. Our proposed method can provide a convenient and effective way to assist doctors in the diagnosis and early treatment.
Highlights
Vascular cognitive impairment (VCI) is a broad term that includes a group of cognitive disorders with various degrees of severity, from mild to severe attributable to pathological damage of the cerebral vascular system (Barbay et al, 2017)
Cerebral microbleeds, and atrophy are the other common signs shown in conventional MRI sequences that are associated with subcortical vascular cognitive impairment (SVCI) (Jee and Lee, 2014)
Because there are no relative pretrained models in our classification of different subtypes of SVCI with fluid-attenuated inversion recovery (FLAIR) MR image, we train our model with random initialization
Summary
Vascular cognitive impairment (VCI) is a broad term that includes a group of cognitive disorders with various degrees of severity, from mild to severe attributable to pathological damage of the cerebral vascular system (Barbay et al, 2017). SVCI is defined as a clinical continuum of cognitive impairments due to cerebral small vessel disease (Olivia et al, 2018). Voxel-based morphometry and lesionsymptom mapping studies have shown extensive brain damages in SVCI patients, the relationship between these damages and clinical cognitive impairments is still controversial among different studies (Marco et al, 2011; Biesbroek et al, 2013, 2017). The International Society for Vascular Behavior and Cognitive Disorders suggested that a strategic infarct or hemorrhage, multiple lacunes, one large infarct or hemorrhage, and extensive and confluent WMH of vascular origin may be helpful in the diagnosis of SVCI (Perminder et al, 2014). More effective methods to classify and evaluate the cognitive impairments of SVCI are needed
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
