Scholarlink

Background <p>Adult diffuse low-grade glioma (DLGG) is a heterogeneous tumor, making accurate prognostic prediction challenging. This study aimed to develop and validate a clinical-radiomics model for predicting progression-free survival (PFS) in DLGG patients.</p> Methods <p>Patients from The Cancer Genome Atlas Low-Grade Glioma (TCGA-LGG) formed the training cohort. Radiomic features were extracted from tumor regions on preoperative MRI. A radiomics model was constructed using Least Absolute Shrinkage and Selection Operator (LASSO) regression. This was integrated with clinical factors to build a combined clinical-radiomics model. The model was externally validated using an independent cohort from the First Affiliated Hospital of Chongqing Medical University (CQMU). Performance was assessed using receiver operating characteristic (ROC) curves, calibration plots, and decision curve analysis (DCA).</p> Results <p>The radiomics-score (hazard ratio [HR]: 3.98, 95% confidence interval [CI]: 1.20–13.27, <i>P </i>= 0.024) and radiotherapy (HR: 0.07, 95% CI: 0.01–0.66, <i>P</i> = 0.021) were independent prognostic factors. The clinical-radiomics model demonstrated superior performance to the radiomics-only model. In the training set, the clinical-radiomics model achieved an area under the curve (AUC) of 0.97 compared to 0.86 for the radiomics model. This superior performance was maintained in external validation, with AUCs of 0.92 and 0.89 for the clinical-radiomics model versus 0.81 and 0.84 for the radiomics model.</p> Conclusions <p>The clinical-radiomics model demonstrated superior performance over the standalone radiomics model in predicting PFS in DLGGs, thus providing valuable insights for patient management strategies.</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

MRI-based clinical radiomics nomogram for the prognostic prediction of adult diffuse low-grade gliomas

  • 期刊论文

  • 发表日期：

    2026年2月7日

查看全文
  • Kanglin Xiong,
  • Dongjie Shi,
  • Lei Ao,
  • Wenjie Zhong,
  • Junjie Zhou,
  • Boyi Shi,
  • Xinlong Chen,
  • Yaning Sun,
  • Song Chen,
  • Gang Huo,
  • Xiaochuan Sun,
  • Gang Yang,
  • Haijian Xia

摘要

Background

Adult diffuse low-grade glioma (DLGG) is a heterogeneous tumor, making accurate prognostic prediction challenging. This study aimed to develop and validate a clinical-radiomics model for predicting progression-free survival (PFS) in DLGG patients.

Methods

Patients from The Cancer Genome Atlas Low-Grade Glioma (TCGA-LGG) formed the training cohort. Radiomic features were extracted from tumor regions on preoperative MRI. A radiomics model was constructed using Least Absolute Shrinkage and Selection Operator (LASSO) regression. This was integrated with clinical factors to build a combined clinical-radiomics model. The model was externally validated using an independent cohort from the First Affiliated Hospital of Chongqing Medical University (CQMU). Performance was assessed using receiver operating characteristic (ROC) curves, calibration plots, and decision curve analysis (DCA).

Results

The radiomics-score (hazard ratio [HR]: 3.98, 95% confidence interval [CI]: 1.20–13.27, P = 0.024) and radiotherapy (HR: 0.07, 95% CI: 0.01–0.66, P = 0.021) were independent prognostic factors. The clinical-radiomics model demonstrated superior performance to the radiomics-only model. In the training set, the clinical-radiomics model achieved an area under the curve (AUC) of 0.97 compared to 0.86 for the radiomics model. This superior performance was maintained in external validation, with AUCs of 0.92 and 0.89 for the clinical-radiomics model versus 0.81 and 0.84 for the radiomics model.

Conclusions

The clinical-radiomics model demonstrated superior performance over the standalone radiomics model in predicting PFS in DLGGs, thus providing valuable insights for patient management strategies.