Scholarlink

<p>To evaluate the diagnostic performance of radiomics derived from abdominal non-contrast CT for identifying abdominal aortic syndrome (AS) in emergency patients. In this retrospective multicenter study, consecutive emergency patients who underwent both non-contrast and contrast-enhanced abdominal CT between August 2012 and March 2022 were included. Radiomic features were extracted from the abdominal aorta segmented on non-contrast CT images, and a radiomic model was developed after feature selection and dimensionality reduction. A clinical–radiomics model was further developed by integrating the radiomics score with independent clinical predictors. Model performance was assessed using ROC analysis and decision curve analysis (DCA). A total of 267 patients were included, of whom 83 had AS. The radiomic model achieved AUCs of 0.830 (95% CI: 0.761–0.892), 0.821 (95% CI: 0.698–0.924), and 0.808 (95% CI: 0.633–0.937) across the training, internal test, and external validation sets, respectively. DCA showed similar net benefit for the radiomic and clinical–radiomics models, both exceeding that of the clinical model. A radiomics model based on non-contrast abdominal CT demonstrated moderate performance for identifying abdominal AS and may have potential value in emergency settings, although further prospective validation is required.</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

Radiomic analysis of abdominal non-contrast CT for identifying aortic syndrome in emergency patients

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月1日

查看全文
  • Wenxiao Lin,
  • Yifan Guo,
  • Haonan Zhu,
  • MengYuan Shen,
  • Jiehui Su

摘要

To evaluate the diagnostic performance of radiomics derived from abdominal non-contrast CT for identifying abdominal aortic syndrome (AS) in emergency patients. In this retrospective multicenter study, consecutive emergency patients who underwent both non-contrast and contrast-enhanced abdominal CT between August 2012 and March 2022 were included. Radiomic features were extracted from the abdominal aorta segmented on non-contrast CT images, and a radiomic model was developed after feature selection and dimensionality reduction. A clinical–radiomics model was further developed by integrating the radiomics score with independent clinical predictors. Model performance was assessed using ROC analysis and decision curve analysis (DCA). A total of 267 patients were included, of whom 83 had AS. The radiomic model achieved AUCs of 0.830 (95% CI: 0.761–0.892), 0.821 (95% CI: 0.698–0.924), and 0.808 (95% CI: 0.633–0.937) across the training, internal test, and external validation sets, respectively. DCA showed similar net benefit for the radiomic and clinical–radiomics models, both exceeding that of the clinical model. A radiomics model based on non-contrast abdominal CT demonstrated moderate performance for identifying abdominal AS and may have potential value in emergency settings, although further prospective validation is required.