Related Experiment Video
Updated: Jan 6, 2026
Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla
Published on: February 19, 2021
Nomograms integrating cortical morphometric metrics with 3D multi-parametric MRI radiomics for predicting disability
Zhuo Wang1,2, Shihang Li3, Jinrui Liu1,2
1Department of Magnetic Resonance, The Second Hospital & Clinical Medical School, Lanzhou University, No. 82 Cuiyingmen, Chengguan District, Lanzhou, 730030, China.
Objective:
To develop individualized nomograms integrating cortical morphometric measures with 3D multi-parametric MRI radiomics to predict disability progression (DP) and cognitive worsening (CW) in patients with relapsing-remitting multiple sclerosis (RRMS).
Materials And Methods:
In this multicenter study, 191 RRMS patients from two centers were divided into internal (training and validation sets, n = 158) and external validation (n = 33) sets. All patients underwent clinical and neuropsychological evaluations at both baseline and 2-year follow-up visits. Cortical morphometric metrics were extracted from 3D T1W images, with radiomics features were assessed within MS plaques on 3D DIR, 3D FLAIR, and 3D T1W images. Four models-clinical-only, radiomics-only, cortical morphometric-only, and a combined model-were developed. A nomogram was developed based on a multivariable logistic regression model to provide individualized probability estimates of DP and CW. Predictive performance was evaluated using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis.
Results:
The combined nomogram outperformed models using clinical, radiomic, or cortical morphometric features alone in predicting DP, achieving an area under the curve (AUC) (95% confidence interval [CI]) of 0.950 (0.878-0.994) in the internal cohort and 0.904 (0.781-0.987) in the external cohort. Similarly, the nomogram for CW demonstrated excellent performance, with AUCs of 0.916 (0.831-0.984) and 0.889 (0.752-0.981) in the respective cohorts. Decision curve analysis confirmed the clinical utility of the nomograms.
Conclusion:
Cortical atrophy, reduced morphological complexity, and high heterogeneity of MS lesions play significant roles in explaining DP and CW in MS. Nomograms integrating clinical indicators, cortical morphometric features, and 3D multi-parametric MRI radiomics, shows potential as a clinical tool for predicting disease progression, facilitating individualized management in RRMS patients.
