Enhanced prediction of mild cognitive impairment in type 2 diabetes mellitus using a structural MRI model
Ran-Chao Wang1, Jin-Xin Wang1, Yang Li1
1Department of Radiology, Affiliated People's Hospital of Jiangsu University, Zhenjiang Jiangsu, China.
Abstract:
BackgroundType 2 diabetes mellitus (T2DM) is associated with a higher risk of mild cognitive impairment (MCI), but conventional structural MRI (sMRI) metrics lack sensitivity for detecting early hippocampal alterations. Radiomic analysis of hippocampal subfields may capture diabetes-related microstructural abnormalities.ObjectiveTo develop and interpret a structural MRI-based model incorporating hippocampal subfield radiomic features for identifying MCI in T2DM patients.MethodsThis retrospective study included 149 T2DM patients. Based on Montreal Cognitive Assessment (MoCA) and Mini-Mental State Examination (MMSE) scores, participants were classified into T2DM-MCI and T2DM-NC groups. A total of 2232 radiomic features were extracted from 24 hippocampal subfields segmented by FreeSurfer. Maximum relevance minimum redundancy (mRMR) and least absolute shrinkage and selection operator (LASSO) were used to construct the hippocampal radiomics score (Hip-Radscore). Additional models were built using gray matter volume (sMRI-Radscore), subfield volumes (SFV-Score), and clinical variables. Model performance was evaluated by bootstrap resampling, ROC analysis, and SHapley Additive exPlanations (SHAP) interpretation.ResultsThe Hip-Radscore model achieved an AUC of 0.76 (95% CI: 0.68-0.84), outperforming the gray matter volume (0.62) and SFV-Score (0.63) models. The combined model integrating imaging and clinical variables reached the highest accuracy (AUC = 0.87, 95% CI: 0.81-0.93), significantly superior to the clinical-only model (AUC = 0.70, p < 0.05). The Hip-Radscore correlated positively with diabetes duration (ρ = 0.47) and HbA1c (ρ = 0.56), and negatively with MMSE (ρ = -0.63) and MoCA (ρ = -0.65) (all p < 0.001).ConclusionsHippocampal subfield radiomics significantly improves the detection of MCI in T2DM and reflects diabetes-specific structural alterations linked to metabolic status and cognitive decline.
Insights
Hippocampal radiomics using MRI can better detect mild cognitive impairment in type 2 diabetes patients. This advanced imaging technique reveals diabetes-related brain changes linked to cognitive decline and metabolic status.
Area of Science:
- Neuroimaging
- Radiology
- Endocrinology
Background:
- Type 2 diabetes mellitus (T2DM) increases the risk of mild cognitive impairment (MCI).
- Standard MRI lacks sensitivity for early hippocampal changes in T2DM.
- Radiomics may identify microstructural abnormalities in hippocampal subfields.
Purpose of the Study:
- Develop and interpret a structural MRI-based radiomics model.
- Incorporate hippocampal subfield features to identify MCI in T2DM patients.
Main Methods:
- Retrospective study of 149 T2DM patients classified as T2DM-MCI or T2DM-NC.
- Extracted 2232 radiomic features from 24 hippocampal subfields.
- Constructed Hip-Radscore using mRMR and LASSO; compared with sMRI-Radscore, SFV-Score, and clinical variables.
Main Results:
- Hip-Radscore model achieved AUC of 0.76, outperforming gray matter volume (0.62) and subfield volume (0.63) models.
- Combined imaging and clinical model reached highest accuracy (AUC=0.87), superior to clinical-only model (AUC=0.70).
- Hip-Radscore correlated with diabetes duration, HbA1c, MMSE, and MoCA scores.
Conclusions:
- Hippocampal subfield radiomics significantly enhances MCI detection in T2DM.
- Radiomics reflects diabetes-specific structural alterations.
- Findings link metabolic status and cognitive decline in T2DM via hippocampal changes.
