Please use this identifier to cite or link to this item:
http://bura.brunel.ac.uk/handle/2438/27251
Title: | DEEP MULTI-MODAL SCHIZOPHRENIA DISORDER DIAGNOSIS VIA A GRU-CNN ARCHITECTURE |
Authors: | Masoudi, B Danishvar, S |
Keywords: | CNN;data fusion;deep learning;functional connectivity;GRU;multimodality analysis;schizophrenia |
Issue Date: | 30-Jun-2022 |
Publisher: | Czech Technical University in Prague |
Citation: | Masoudi, B. and Danishvar, S. (2022) 'DEEP MULTI-MODAL SCHIZOPHRENIA DISORDER DIAGNOSIS VIA A GRU-CNN ARCHITECTURE', Neural Network World, 32 (3), pp. 147 - 161. doi: 10.14311/NNW.2022.32.009. |
Abstract: | Schizophrenia is a complex mental disorder associated with a change in the functional and structural of the brain. Accurate automatic diagnosis of schizophrenia is crucial and still a challenge. In this paper, we propose an automatic diagnosis of schizophrenia disorder method based on the fusion of different neuroimaging features and a deep learning architecture. We propose a deep-multimodal fusion (DMMF) architecture based on gated recurrent unit (GRU) network and 2D-3D convolutional neural networks (CNN). The DMMF model combines functional connectivity (FC) measures extracted from functional magnetic resonance imaging (fMRI) data and low-level features obtained from fMRI, magnetic resonance imaging (MRI), or diffusion tensor imaging (DTI) data and creates latent and discriminative feature maps for classification. The fusion of ROI-based FC with fractional anisotropy (FA) derived from DTI images achieved state-of-theart diagnosis-accuracy of 99.50% and an area under the curve (AUC) of 99.7% on COBRE dataset. The results are promising for the combination of features. The high accuracy and AUC in our experiments show that the proposed deep learning architecture can extract latent patterns from neuroimaging data and can help to achieve accurate classification of schizophrenia and healthy groups. |
Description: | The file on this institutional repository is embargoed indefinitely due to licensing and copyright restrictions. Individuals may download a copy of this article from the publisher's website for personal, non-commercial use at: https://doi.org/10.14311/NNW.2022.32.009 . |
URI: | https://bura.brunel.ac.uk/handle/2438/27251 |
DOI: | https://doi.org/10.14311/NNW.2022.32.009 |
ISSN: | 1210-0552 |
Other Identifiers: | ORCID iD: Sebelan Danishvar https://orcid.org/0000-0002-8258-0437 |
Appears in Collections: | Dept of Computer Science Research Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
FullText.pdf | Copyright © CTU FTS 2022. Some rights reserved. See: http://nnw.cz/soubory/NNW_CopyrightForm.pdf. The file on this institutional repository is embargoed indefinitely due to licensing and copyright restrictions. Individuals may download a copy of this article from the publisher's website for personal, non-commercial use at: https://doi.org/10.14311/NNW.2022.32.009 . | 1.21 MB | Adobe PDF | View/Open |
Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.