Multimodal Radiomics of Precisely Segmented Hippocampal Subfields: Iron Deposition and Structural Biomarkers for Early Diagnosis of Alzheimer's Disease

• A hippocampal-subfield multimodal radiomics framework integrating QSM and 3D-T1WI was developed for Alzheimer’s disease stage classification. • Super-resolution SR-T1 segmentation using an nnU-Net + nnFormer ensemble delineated 24 hippocampal subfields, and the ROI labels were propagated to native QSM space for feature extraction. • A leakage-controlled, training-only pipeline (preprocessing + Pearson→mRMR→RFE→LASSO with lambda.1se) yielded a sparse Rad-score that served as the sole predictor for all five classifiers. • The Rad-score–based SVM showed good generalization on an independent external cohort (AUC = 0.85; ACC = 0.83), and ablation analyses suggested the potential complementary value of combining QSM and T1 features. Profiling imaging biomarkers of prodromal Alzheimer’s disease (AD) against AD dementia may aid earlier diagnosis, yet approaches jointly capturing iron-related pathology and hippocampal subfield heterogeneity remain scarce. We developed a hippocampal-subfield multimodal radiomics framework integrating quantitative susceptibility mapping (QSM) and 3D T1-weighted MRI. A primary cohort of 92 participants (50 prodromal AD, 42 AD dementia) and an independent external cohort of 30 (15/15) were included. Twenty-four hippocampal subfields were segmented on super-resolution T1 images and propagated to co-registered QSM for feature extraction. Radiomic features were condensed into a radiomics score (Rad-score) via a training-only selection pipeline. Using the Rad-score as the sole predictor, a support vector machine (SVM) classifier was trained. On the external cohort, the SVM achieved an area under the receiver operating characteristic curve of 0.85 and an accuracy of 0.83. The predictive signature was dominated by QSM texture features in Cornu Ammonis 1 and the granule cell layer of the dentate gyrus, complemented by T1 first-order heterogeneity. Modality ablation suggested potential—but not definitive—complementarity of multimodal integration. This framework shows promise for AD stage classification and warrants further validation in larger independent cohorts.