Multimodal Fusion Model for Diagnosing Mild Cognitive Impairment in Unilateral Middle Cerebral Artery Steno-occlusive Disease

Ziyi Yuan ¹ Zhaodi Huang ² Chaojun Li ³ Shengrong Li ³ Qingguo Ren ⁴ Xiaona Xia ⁵ Qingjun Jiang ⁵ Daoqiang Zhang ³ Qi Zhu ^3* Xiangshui Meng ^5,6*

• ¹ School of Medicine, Cheeloo College of Medicine, Shandong University, Jinan, China
• ² Meng Chao Hepatobiliary Hospital of Fujian Medical University, Dapartment of Radiology, Fuzhou, fujian, China
• ³ College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics, Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education, nanjing, China
• ⁴ Qilu Hospital of Shandong University (Qingdao), Qingdao, China
• ⁵ Department of Radiology, Qilu Hospital (Qingdao), Cheeloo College of Medicine, Shandong University, qingdao, China
• ⁶ Medical lmaging and Engineering Intersection Key Laboratory of Qingdao, qingdao, China

Objectives: To propose a multimodal functional brain network (FBN) and structural brain network (SBN) topological feature fusion technique based on resting-state functional magnetic resonance imaging (rs-fMRI), diffusion tensor imaging (DTI), 3D-T1-weighted imaging (3D-T1WI), and demographic characteristics to diagnose mild cognitive impairment (MCI) in patients with unilateral middle cerebral artery (MCA) steno-occlusive disease. Methods: The performances of different algorithms on the MCI dataset were evaluated using 5-fold cross-validation. The diagnostic results of the multimodal performance were evaluated using t-distributed stochastic neighbour embedding (t-SNE) analysis. The four-modal analysis method proposed in this study was applied to identify brain regions and connections associated with MCI, thus confirming its validity. Results: Based on the fusion of the topological features of the multimodal FBN and SBN, the accuracy for the diagnosis of MCI in patients with unilateral MCA steno-occlusive disease reached 90%. The accuracy, recall, sensitivity, and F1-score were higher than those of the other methods, as was the diagnostic efficacy (AUC=0.9149). Conclusions: The multimodal FBN and SBN topological feature fusion technique, which incorporates rs-fMRI, DTI, 3D-T1WI, and demographic characteristics, obtains the most discriminative features of MCI in patients with unilateral MCA steno-occlusive disease and can effectively identify disease-related brain areas and connections. Efficient automated diagnosis facilitates the early and accurate detection of MCI and timely intervention and treatment to delay or prevent disease progression.