Scholarlink

Background <p>There is no consensus on managing patients with endoscopic suspicion of early esophageal squamous cell carcinoma (ESCC) but biopsy-confirmed low-grade intraepithelial neoplasia (LGIN). The aim of this study is to evaluate the utility of an endoscopic ultrasound (EUS)-based radiomics nomogram for predicting esophageal LGIN pathological progression before diagnostic endoscopic submucosal dissection (ESD).</p> Methods <p>In the development phase, EUS images of&#xa0;535 patients who had biopsy-confirmed LGIN and were undergoing ESD&#xa0;were retrospectively included. Concurrently, 251 patients were prospectively included for independent model validation. A radiomics signature (RS) was constructed using Pearson test and the least absolute shrinkage and selection operator (LASSO) algorithm. A radiomics nomogram was then developed with multivariate&#xa0;logistic regression to predict pathologic upgrade before ESD. Model performance was assessed with receiver operating characteristic (ROC) analysis, calibration curves, and decision curve analysis (DCA).</p> Results <p>Following stepwise multivariate logistic regression analysis, statistically significant clinical features were incorporated into the clinical predictive model. From EUS images, 105 radiomic features were extracted, with 11 key features selected for RS development. The RS showed strong predictive performance in identifying pathologic upgrade (AUC = 0.786). Moreover, when integrated with the clinical model (AUC = 0.648), the RS performance remarkably improved (AUC = 0.818). These results were subsequently validated in the prospective test cohort (RS: AUC = 0.792; Clinical model: AUC = 0.669; Combined model: AUC = 0.821). The combined model presented as a nomogram also excelled in calibration tests and DCA, underlining its potential for clinical application.</p> Conclusion <p>The EUS-based radiomics nomogram showed potential for predicting pathologic upgrade in esophageal LGIN, which helps to distinguish high-risk from low-risk cases and assists clinicians in assessing the necessity of diagnostic ESD.</p> Graphical Abstract <p></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

Endoscopic ultrasound-based radiomics for predicting pathologic upgrade in esophageal low-grade intraepithelial neoplasia

  • 期刊论文

  • 发表日期：

    2025年2月10日

查看全文
  • Yajing Chen,
  • Shuhan Sun,
  • Shumei Miao,
  • Han Chen,
  • Xiaoying Zhou,
  • Feihong Yu

摘要

Background

There is no consensus on managing patients with endoscopic suspicion of early esophageal squamous cell carcinoma (ESCC) but biopsy-confirmed low-grade intraepithelial neoplasia (LGIN). The aim of this study is to evaluate the utility of an endoscopic ultrasound (EUS)-based radiomics nomogram for predicting esophageal LGIN pathological progression before diagnostic endoscopic submucosal dissection (ESD).

Methods

In the development phase, EUS images of 535 patients who had biopsy-confirmed LGIN and were undergoing ESD were retrospectively included. Concurrently, 251 patients were prospectively included for independent model validation. A radiomics signature (RS) was constructed using Pearson test and the least absolute shrinkage and selection operator (LASSO) algorithm. A radiomics nomogram was then developed with multivariate logistic regression to predict pathologic upgrade before ESD. Model performance was assessed with receiver operating characteristic (ROC) analysis, calibration curves, and decision curve analysis (DCA).

Results

Following stepwise multivariate logistic regression analysis, statistically significant clinical features were incorporated into the clinical predictive model. From EUS images, 105 radiomic features were extracted, with 11 key features selected for RS development. The RS showed strong predictive performance in identifying pathologic upgrade (AUC = 0.786). Moreover, when integrated with the clinical model (AUC = 0.648), the RS performance remarkably improved (AUC = 0.818). These results were subsequently validated in the prospective test cohort (RS: AUC = 0.792; Clinical model: AUC = 0.669; Combined model: AUC = 0.821). The combined model presented as a nomogram also excelled in calibration tests and DCA, underlining its potential for clinical application.

Conclusion

The EUS-based radiomics nomogram showed potential for predicting pathologic upgrade in esophageal LGIN, which helps to distinguish high-risk from low-risk cases and assists clinicians in assessing the necessity of diagnostic ESD.

Graphical Abstract