Identification of voxel-based texture abnormalities as new biomarkers for schizophrenia and major depressive patients using layer-wise relevance propagation on deep learning decisions. (30th July 2021)

• Record Type: Journal Article
• Authors: Korda, A.I.; Ruef, A.; Neufang, S.; Davatzikos, C.; Borgwardt, S.; Meisenzahl, E.M.; Koutsouleris, N.
• Is Part Of: Psychiatry research. Volume 313(2021)
• Publication Date: 2021-07-30
• Subjects: Texture -- MRI -- Schizophrenia -- Depression -- Deep learning -- Layer-wise relevance propagation; Psychiatry -- Periodicals; Brain -- Imaging -- Periodicals; Psychiatry -- Periodicals; Diagnostic Imaging -- Periodicals; Psychiatrie -- Périodiques; Cerveau -- Imagerie pour le diagnostic -- Périodiques; 616.890754
• DOI: 10.1016/j.pscychresns.2021.111303
• Languages: English
• ISSNs: 0925-4927

Abstract

Highlights: Texture features extraction from non-segmented brain MRI. Deep learning classification decisions explained by the LRP algorithm. Affinity propagation algorithm clusters subject's positive relevance. Key regions identified for schizophrenia and major depressive patients. Abstract: Non-segmented MRI brain images are used for the identification of new Magnetic Resonance Imaging (MRI) biomarkers able to differentiate between schizophrenic patients (SCZ), major depressive patients (MD) and healthy controls (HC). Brain texture measures such as entropy and contrast, capturing the neighboring variation of MRI voxel intensities, were computed and fed into deep learning technique for group classification. Layer-wise relevance was applied for the localization of the classification results. Texture feature map of non-segmented brain MRI scans were extracted from 141 SCZ, 103 MD and 238 HC. The gray level co-occurrence matrix (GLCM) was calculated on a voxel-by-voxel basis in a cube of voxels. Deep learning tested if texture feature map could predict diagnostic group membership of three classes under a binary classification (SCZ vs. HC, MD vs. HC, SCZ vs. MD). The method was applied in a repeated nested cross-validation scheme and cross-validated feature selection. The regions with the highest relevance (positive/negative) are presented. The method was applied on non-segmented images reducing the computation complexity and the error associated with segmentation process.