Scholarlink

Objective <p>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).</p> Materials and methods <p>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.</p> Results <p>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.</p> Conclusion <p>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.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Nomograms integrating cortical morphometric metrics with 3D multi-parametric MRI radiomics for predicting disability progression and cognitive worsening in relapsing–remitting multiple sclerosis: a multi-center validation study

  • 期刊论文

  • 发表日期：

    2025年11月29日

查看全文
  • Zhuo Wang,
  • Shihang Li,
  • Jinrui Liu,
  • Yujing Li,
  • Mingsong Tang,
  • Jun Wang,
  • Wenjing Ren,
  • Jia Guo,
  • Zhuo Shao,
  • Jingqi Jiang,
  • Fei Jia,
  • Hao Li,
  • Xia Xu,
  • Guangyao Liu,
  • Yanli Jiang,
  • Yucheng Ding,
  • Kai Ai,
  • Jing Zhang

摘要

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.