18F-FDG PET/CT 影像组学特征鉴别孤立性肺腺癌与肺结核的价值
本研究回顾性纳入 235 例经病理或随访确诊的孤立性肺腺癌(n=131)或肺结核(n=104)患者的 18F-FDG PET/CT 数据,随机分为训练组(n=163)和验证组(n=72)。从 92 个影像组学特征中筛选出 9 个最优预测因子构建影像组学模型,并与临床模型及复合模型比较。影像组学模型在训练组和验证组的 AUC 均显著高于临床模型,与复合模型无显著差异。
要点
- 影像组学模型在训练组 AUC 为 0.861,显著高于临床模型的 0.686(p<0.01)。
- 影像组学模型在验证组 AUC 为 0.889,显著高于临床模型的 0.644(p<0.01)。
- 影像组学模型与复合模型 AUC 无显著差异(训练组 0.861 vs 0.884,p>0.05;验证组 0.889 vs 0.909,p>0.05)。
核心结论
- 18F-FDG PET/CT 影像组学特征在鉴别孤立性肺腺癌与肺结核方面具有显著价值。
研究设计与样本
- 回顾性研究,共纳入 235 例经病理或随访确诊的孤立性肺腺癌(n=131)或肺结核(n=104)患者的 18F-FDG PET/CT 数据,随机分为训练组(n=163)和验证组(n=72)。
- 本研究按照 TRIPOD 声明属于 TRIPOD 2a 类研究。
主要发现
- 从 92 个 PET/CT 影像组学特征中通过 Mann-Whitney U 检验和 LASSO 算法筛选出 9 个最优预测因子构建影像组学模型。
- 训练组影像组学模型 AUC 为 0.861,显著高于临床模型的 0.686(p<0.01)。
- 验证组影像组学模型 AUC 为 0.889,显著高于临床模型的 0.644(p<0.01)。
- 训练组影像组学模型 AUC 略低于复合模型的 0.884(p>0.05),验证组影像组学模型 AUC 略低于复合模型的 0.909(p>0.05),均无显著差异。
关键数值与推荐
- 影像组学模型在训练组 AUC 0.861 vs 临床模型 0.686(p<0.01)。
- 影像组学模型在验证组 AUC 0.889 vs 临床模型 0.644(p<0.01)。
- 影像组学模型在训练组 AUC 0.861 vs 复合模型 0.884(p>0.05)。
- 影像组学模型在验证组 AUC 0.889 vs 复合模型 0.909(p>0.05)。
临床怎么用
- 原文未据此给出推荐。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
PURPOSE: To develop a predictive model by 18F-FDG PET/CT radiomic features and to validate the predictive value of the model for distinguishing solitary lung adenocarcinoma from tuberculosis. METHODS: A total of 235 18F-FDG PET/CT patients with pathologically or follow-up confirmed lung adenocarcinoma (n = 131) or tuberculosis (n = 104) were retrospectively and randomly divided into a training (n = 163) and validation (n = 72) cohort. Based on the Transparent Reporting of Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD), this work was belonged to TRIPOD type 2a study. The Mann-Whitney U test and least absolute shrinkage and selection operator (LASSO) algorithm were used to select the optimal predictors from 92 radiomic features that were extracted from PET/CT, and the optimal predictors were used to build the radiomic model in the training cohort. The meaningful clinical variables comprised the clinical model, and the combination of the radiomic model and clinical model was a complex model. The performances of the models were assessed by the area under the receiver operating characteristic curve (AUC) in the training and validation cohorts. RESULTS: In the training cohort, 9 radiomic features were selected as optimal predictors to build the radiomic model. The AUC of the radiomic model was significantly higher than that of the clinical model in the training cohort (0.861 versus 0.686, p < 0.01), and this was similar in the validation cohort (0.889 versus 0.644, p < 0.01). The AUC of the radiomic model was slightly lower than that of the complex model in the training cohort (0.861 versus 0.884, p > 0.05) and validation cohort (0.889 versus 0.909, p > 0.05), but there was no significant difference. CONCLUSION: 18F-FDG PET/CT radiomic features have a significant value in differentiating solitary lung adenocarcinoma from tuberculosis.
引用
- Hu Y, Zhao X, Zhang J, et al. Value of 18F-FDG PET/CT radiomic features to distinguish solitary lung adenocarcinoma from tuberculosis. Eur J Nucl Med Mol Imaging. 2020. PMID: 32588088. doi:10.1007/s00259-020-04924-6
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。