基于T1WI增强影像组学在鉴别高级别胶质瘤复发与假性进展中的应用价值
DOI:
作者:
作者单位:

南京医科大学第一附属医院放射科

作者简介:

通讯作者:

中图分类号:

基金项目:


The value of contrast enhanced T1WI radiomics in differentiating high-grade glioma recurrence from pseudoprogression
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    摘 要: 目的:探讨基于T1WI增强影像组学在术前无创地鉴别高级别胶质瘤术后复发与假性进展的应用价值。方法:回顾性分析经病理证实为高级别胶质瘤的104例患者临床及MRI资料,根据二次手术病理或神经肿瘤疗效评估标准(response assessment in neuro-oncology,RANO)将其分为复发组71例,假性进展组33例。按7:3比例随机分为训练组和验证组。在T1WI增强图像上手动勾画肿瘤实质区的体积作为感兴趣区,用FeAture Explorer软件提取共1648个组学特征。采用主成分分析(principal component analysis,PCA)及最小绝对收缩和选择算子(least absolute shrinkage and selection operator,LASSO)进行特征处理及筛选,采用支持向量机(Support Vector Machine,SVM)构建影像组学模型。通过受试者工作曲线下面积(area under curve,AUC)及校准曲线评估模型的效能。 结果:训练组鉴别高级别胶质瘤复发与假性进展AUC为0.929,准确率为0.889,敏感度为72.7%,特异度为100%。验证组的AUC为0.853,准确率为0.813,敏感度为90.9%,特异度为71.4%。校准曲线显示模型预测值与实际值一致性较好。结论:基于T1WI增强影像组学模型具有较好的诊断效能,有助于鉴别高级别胶质瘤术后复发与假性进展。

    Abstract:

    Abstract: Objective: To explore the value of using radiomics based on contrast enhanced T1 weighted imaging(T1WI) in differentiating high-grade glioma recurrence from pseudoprogression. Methods: 104 patients with pathologically confirmed high-grade glioma were enrolled in this retrospective study, and they were divided into 71 cases in the recurrence group and 33 cases in the pseudoprogression group according to the secondary surgical pathology or response assessment in neuro-oncology (RANO). The cases were divided randomly into a training cohort and a validation cohort at a ratio of 7:3. Volume of interest (VOI) were delineated manually on contrast enhanced T1 weighted imaging. A total of 1648 radiomics features were extracted by FeAture Explorer software. Principal component analysis (PCA) and least absolute shrinkage and selection operator (LASSO) were used to process and select features. Support Vector Machine (SVM) was used to conduct the radiomics model. Area under the curve (AUC) and calibration curve were used to assess the efficacy of the model. Results: The radiomics model had an AUC of 0.929, accuracy of 0.889, sensitivity 72.7%, and specificity 100% in the training cohort to differentiate high-grade glioma recurrence from pseudoprogression. The validation cohort had an AUC of 0.853, accuracy of 0.813, sensitivity 90.9%, and specificity 71.4%. Calibration curve showed a good agreement between predicted and actual probabilities. Conclusion: The radiomics model based on contrast enhanced T1 weighted imaging showed great diagnostic performance and was promising in differentiating high-grade glioma recurrence from pseudoprogression.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2022-12-29
  • 最后修改日期:2023-03-16
  • 录用日期:2023-08-29
  • 在线发布日期:
  • 出版日期: