MTBI-DSANet: A deep self-attention model for diagnosing mild traumatic brain injury using multi-level functional connectivity networks. (January 2023)

• Record Type: Journal Article
• Authors: Teng, Jing; Mi, Chunlin; Liu, Wuyi; Shi, Jian; Li, Na
• Is Part Of: Computers in biology and medicine. Volume 152(2023)
• Publication Date: 2023-01
• Subjects: Mild traumatic brain injury -- Self-attention -- Multi-level functional connectivity networks -- Deep learning; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2022.106354
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: The main approach for analyzing resting-state functional magnetic resonance imaging (rs-fMRI) is the low-order functional connectivity network (LoFCN) based on the correlation between two brain regions. Based on LoFCN, researchers recently proposed the topographical high-order FCN (tHoFCN) and the associated high-order FCN (aHoFCN) to explore the high-order interactions among brain regions. In this work, we designed a Deep Self-Attention (DSA) framework called mTBI-DSANet to diagnose mild traumatic brain injury (mTBI) using multi-level FCNs, including LoFCN, tHoFCN, and aHoFCN. The multilayer perceptron and self-attention mechanism in mTBI-DSANet were designed to capture important features for the mTBI diagnosis. We evaluated the mTBI-DSANet's performance on the real rs-fMRI dataset, which was collected by Third Xiangya Hospital of Central South University from April 2014 to February 2021. We compared the performance of mTBI-DSANet with distinct FCNs and their combinations under 10-fold cross-validation. Based on the LoFCN+aHoFCN combination, the average performance of mTBI-DSANet achieved the best accuracy of 0.834, which is significantly better than peer methods. The experiments demonstrated the potential of the mTBI-DSANet in assisting mTBI diagnosis. Highlights: A deep self-attention framework named mTBI-DSANet is proposed to assist mTBI diagnosis. The HoFCNs outperform the LoFCN in mTBI diagnosis, verified by 10-fold cross-validation. The combination of LoFCN and aHoFCN could further improve the accuracy of diagnosis.