Scholarlink

Background <p>Cervical squamous cell carcinoma is a major global health burden, with many patients presenting with locally advanced disease requiring concurrent chemoradiotherapy (CCRT). Early assessment of treatment response (TR) is critical for optimizing therapeutic strategies and improving clinical outcomes; however, conventional imaging parameters provide limited predictive value. This study aimed to develop a PET radiomics model using machine learning (ML) to predict early TR after CCRT in patients with stage II–III locally advanced cervical squamous cell carcinoma (LACSC).</p> Methods <p>This retrospective study included 184 patients with LACSC who received CCRT (2018–2021) and underwent pre-treatment <sup>18</sup>F-FDG PET/CT within 1 week before CCRT initiation. The patients were randomly assigned to a training set (<i>n</i> = 128) or an internal test set (<i>n</i> = 56). The ROIs were delineated using ITK-SNAP. Radiomic features were extracted using Pyradiomics and selected using the least absolute shrinkage and selection operator. Five ML algorithms (random forest, logistic regression, light gradient boosting machine, extremely randomized trees, and multilayer perceptron) were evaluated in this study. The performance was assessed using the area under the curve (AUC), sensitivity, and specificity.</p> Results <p>Eight radiomic features were identified. The random forest model performed best, with AUCs of 0.877 (95% confidence interval [CI]: 0.810–0.943) in the training set and 0.783 (95% CI: 0.648–0.918) in the test set. The sensitivity was 0.833 in both sets, and the specificity was 0.783 (training) and 0.682 (test).</p> Conclusion <p>In this single-center retrospective cohort study, a pre-treatment <sup>18</sup>F-FDG PET radiomics model using random forest showed the best performance among the five evaluated ML algorithms for predicting early CCRT response (test-set AUC = 0.783). External validation is required before clinical implementation.</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

Machine learning-based radiomics analysis of PET imaging for early prediction of concurrent chemoradiotherapy response in stage II–III cervical squamous cell carcinoma

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月9日

查看全文
  • Dinghua Pang,
  • Hong Yang,
  • Shilai Zhang,
  • Wenming Qiu,
  • Weiwei Pu,
  • Ziya Liu,
  • Zhi Yang,
  • Ning Li,
  • Hai Liao,
  • Guoyou Xiao

摘要

Background

Cervical squamous cell carcinoma is a major global health burden, with many patients presenting with locally advanced disease requiring concurrent chemoradiotherapy (CCRT). Early assessment of treatment response (TR) is critical for optimizing therapeutic strategies and improving clinical outcomes; however, conventional imaging parameters provide limited predictive value. This study aimed to develop a PET radiomics model using machine learning (ML) to predict early TR after CCRT in patients with stage II–III locally advanced cervical squamous cell carcinoma (LACSC).

Methods

This retrospective study included 184 patients with LACSC who received CCRT (2018–2021) and underwent pre-treatment 18F-FDG PET/CT within 1 week before CCRT initiation. The patients were randomly assigned to a training set (n = 128) or an internal test set (n = 56). The ROIs were delineated using ITK-SNAP. Radiomic features were extracted using Pyradiomics and selected using the least absolute shrinkage and selection operator. Five ML algorithms (random forest, logistic regression, light gradient boosting machine, extremely randomized trees, and multilayer perceptron) were evaluated in this study. The performance was assessed using the area under the curve (AUC), sensitivity, and specificity.

Results

Eight radiomic features were identified. The random forest model performed best, with AUCs of 0.877 (95% confidence interval [CI]: 0.810–0.943) in the training set and 0.783 (95% CI: 0.648–0.918) in the test set. The sensitivity was 0.833 in both sets, and the specificity was 0.783 (training) and 0.682 (test).

Conclusion

In this single-center retrospective cohort study, a pre-treatment 18F-FDG PET radiomics model using random forest showed the best performance among the five evaluated ML algorithms for predicting early CCRT response (test-set AUC = 0.783). External validation is required before clinical implementation.