کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
8841878 1615034 2018 7 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Predictive brain networks for major depression in a semi-multimodal fusion hierarchical feature reduction framework
ترجمه فارسی عنوان
شبکه های مغز پیش بینی شده برای افسردگی عمده در چارچوب کاهش قابلیت سلسله مراتبی نیمه مولتی مدلی
موضوعات مرتبط
علوم زیستی و بیوفناوری علم عصب شناسی علوم اعصاب (عمومی)
چکیده انگلیسی
Major depressive disorder (MDD) is characterized by dysregulation of distributed structural and functional networks. It is now recognized that structural and functional networks are related at multiple temporal scales. The recent emergence of multimodal fusion methods has made it possible to comprehensively and systematically investigate brain networks and thereby provide essential information for influencing disease diagnosis and prognosis. However, such investigations are hampered by the inconsistent dimensionality features between structural and functional networks. Thus, a semi-multimodal fusion hierarchical feature reduction framework is proposed. Feature reduction is a vital procedure in classification that can be used to eliminate irrelevant and redundant information and thereby improve the accuracy of disease diagnosis. Our proposed framework primarily consists of two steps. The first step considers the connection distances in both structural and functional networks between MDD and healthy control (HC) groups. By adding a constraint based on sparsity regularization, the second step fully utilizes the inter-relationship between the two modalities. However, in contrast to conventional multi-modality multi-task methods, the structural networks were considered to play only a subsidiary role in feature reduction and were not included in the following classification. The proposed method achieved a classification accuracy, specificity, sensitivity, and area under the curve of 84.91%, 88.6%, 81.29%, and 0.91, respectively. Moreover, the frontal-limbic system contributed the most to disease diagnosis. Importantly, by taking full advantage of the complementary information from multimodal neuroimaging data, the selected consensus connections may be highly reliable biomarkers of MDD.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Neuroscience Letters - Volume 665, 5 February 2018, Pages 163-169
نویسندگان
, , , , , , , , , ,