Scholarlink

Purpose <p>Radiation proctitis (RP) is a frequent and clinically relevant complication of radiotherapy (RT) in cervical cancer (CC). However, effective tools for individualized RP risk prediction remain limited. This study aimed to develop and validate an MRI-based radiomic risk score for early RP prediction in CC patients.</p> Methods <p>This retrospective study included 375 CC patients who underwent radical RT. Patients were randomly assigned to training (80%) and validation (20%) cohorts. Radiomics features were extracted from pre-treatment MRI and screened using Mann–Whitney U test, intraclass correlation coefficient, and least absolute shrinkage and selection operator regression. Logistic regression analyses identified independent predictors of RP, and a clinical-radiomics nomogram was constructed. Model performance was assessed by the area under the curve (AUC), calibration, and decision curve analysis (DCA).</p> Results <p>Of 1,906 extracted features, 9 were selected to construct the radiomics risk score. Independent predictors of RP included lymphocyte counts ≥ 2.6 × 10⁹/L, platelet–lymphocyte ratio ≥ 196, rectal mean dose ≥ 47.22&#xa0;Gy, and radiomics risk score≥-0.4. The nomogram incorporating these factors achieved AUCs of 0.810 (training) and 0.730 (validation), with good calibration and clinical utility demonstrated by DCA.</p> Conclusion <p>The proposed MRI-based radiomic risk score enables accurate, noninvasive prediction of RP in CC patients and provides a practical tool to optimize individualized RT planning and toxicity management.</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

Construction of a predictive model for radiation proctitis after radical radiotherapy for cervical cancer based on MRI radiomics

  • 期刊论文

  • 发表日期：

    2025年12月19日

查看全文
  • Sufang Deng,
  • Linying Liu,
  • Jie Lin,
  • Zhuang Xiong,
  • Zhihua Cai,
  • Haijuan Yu,
  • Ning Xie,
  • Yixin Fu,
  • Yang Sun

摘要

Purpose

Radiation proctitis (RP) is a frequent and clinically relevant complication of radiotherapy (RT) in cervical cancer (CC). However, effective tools for individualized RP risk prediction remain limited. This study aimed to develop and validate an MRI-based radiomic risk score for early RP prediction in CC patients.

Methods

This retrospective study included 375 CC patients who underwent radical RT. Patients were randomly assigned to training (80%) and validation (20%) cohorts. Radiomics features were extracted from pre-treatment MRI and screened using Mann–Whitney U test, intraclass correlation coefficient, and least absolute shrinkage and selection operator regression. Logistic regression analyses identified independent predictors of RP, and a clinical-radiomics nomogram was constructed. Model performance was assessed by the area under the curve (AUC), calibration, and decision curve analysis (DCA).

Results

Of 1,906 extracted features, 9 were selected to construct the radiomics risk score. Independent predictors of RP included lymphocyte counts ≥ 2.6 × 10⁹/L, platelet–lymphocyte ratio ≥ 196, rectal mean dose ≥ 47.22 Gy, and radiomics risk score≥-0.4. The nomogram incorporating these factors achieved AUCs of 0.810 (training) and 0.730 (validation), with good calibration and clinical utility demonstrated by DCA.

Conclusion

The proposed MRI-based radiomic risk score enables accurate, noninvasive prediction of RP in CC patients and provides a practical tool to optimize individualized RT planning and toxicity management.