Related Experiment Video
Updated: Jun 13, 2026
Assessing Iron Deposition in the Brains of 5xFAD Mice by Perls'/DAB Staining
Published on: May 23, 2025
Sub-voxel Susceptibility Mapping and Machine Learning to Detect Brain Iron Deposition and Its Cognitive Relevance in
Mingrui Yang1, Yugui Huang1, Chunxia Zhu1
1From the Department of Radiology (M.Y., Y.H., C.Z., G.C., C.T., Y.L., J.L., R.K., J.L., P. P.), The First Affiliated Hospital of Guangxi Medical University, Nanning, China; NHC Key Laboratory of Thalassemia Medicine (C.T., P.P.), Nanning, China; Binzhou Medical University Hospital (M.Y.), Binzhou, China; and MR Research Collaboration Team (H.Z.), Siemens Healthineers Ltd., Shenzhen, China.
Objective:
Brain iron dysregulation is increasingly recognized as a critical contributor to neurocognitive impairment in patients with beta-thalassemia major (β-TM). However, in-vivo characterization of region-specific iron accumulation and its relationship with cognitive function remains limited.
Methods:
Fifty β-TM patients and fifty age- and sex-matched healthy controls underwent 3T multi-echo gradient-echo MRI. Sub-voxel chi-separation decomposed magnetic susceptibility into paramagnetic (iron-related) and diamagnetic components. Regional paramagnetic susceptibility was extracted from anatomically defined regions of interest (ROIs). Group differences were assessed using FDR-corrected comparisons (q < 0.05). Partial Spearman correlations evaluated associations between regional susceptibility and Montreal Cognitive Assessment (MoCA) scores, controlling for age, sex, and education. Three classifiers-support vector machine (SVM), random forest (RF), and eXtreme Gradient Boosting (XGBoost)-were trained using ROI-based features. In each Monte Carlo cross-validation iteration, the data were divided into stratified 80/20 training/testing subsets. Preprocessing, feature selection, and hyperparameter optimization were performed using the training data only, and the held-out test subset was used exclusively for final evaluation. SHapley Additive exPlanations (SHAP) were used for model interpretability.
Results:
β-TM patients showed significantly higher paramagnetic susceptibility in the hippocampus, insula, and anterior cingulate cortex (q < 0.05). Among classifiers, SVM with an RBF kernel demonstrated the highest performance (mean AUC = 0.919 ± 0.054), outperforming RF and XGBoost. SHAP analysis identified hippocampal and insular susceptibility as key features, with higher susceptibility linked to lower MoCA scores.
Conclusion:
ROI-based chi-separation detected iron-related changes in β-TM, and exploratory machine-learning analysis highlighted regions associated with cognitive vulnerability, supporting the potential value of susceptibility-based imaging features for studying neurocognitive risk patterns in this population.
