Cerebellar MRI-Based Radiomics Models for Identifying Mild Cognitive Impairment：A Retrospectively Multicenter Study in Southeast of China

Jianping Lu¹Guoen Cai¹Naian Xiao²Kunmu Zheng³Qinyong Ye^1*Xiaochun Chen^1*

• ¹Fujian Medical University Union Hospital, Fuzhou, China
• ²Third Hospital of Xiamen, Xiamen, Fujian Province, China
• ³First Affiliated Hospital of Xiamen University, Xiamen, Fujian Province, China

Objective: To investigate the role of cerebellar magnetic resonance imaging (MRI) features in identifying mild cognitive impairment (MCI). Methods: This retrospective multicenter study enrolled MCI, Alzheimer's disease (AD) and healthy controls (HCs) from three tertiary hospitals in China (January 2022-December 2023). Cerebellar and hippocampal radiomics features were extracted from T1-, T2-, and T2-FLAIR-weighted MRI. A sparse representation classifier was developed using 10-fold cross validation and validated on independent datasets. Diagnostic performance was assessed via sensitivity, specificity, and ROC-AUC. Results: 87 patients with MCI, 109 patients with AD, and 55 healthy controls (HCs) with matched gender and age were included for model construction and validation. 13 patients with MCI and 26 patients with AD were included for external validation. The 10-fold cross-validation accuracy and ROC AUC for identifying CI in the training set based on combination of cerebellar T1, T2 and T2-FLAIR weighted images were better than hippocampal (91.0% vs 86.8%, 0.943 vs 0.931). Their accuracy and ROC AUC of independent test set were similar (89.3% vs 89.3%, 0.908 vs 0.906) . The 10-fold cross-validation accuracy and ROC AUC for identifying MCI in the training set based on combination of cerebellar T1, T2 and T2-FLAIR weighted images were similar with hippocampal (85.2% vs 83.7%, 0.877 vs 0.905) and the same to external validation set (89.7% vs 93.1%, 0.962 vs 0.974). Conclusions: Cerebellar MRI radiomics models exhibit diagnostic accuracy equivalent to hippocampal models for CI and MCI, supporting the cerebellum's role in early cognitive dysfunction detection. These findings provide novel insights into cerebellar contributions to AD pathophysiology and offer potential biomarkers for clinical application.