基于基线CT的影像组学特征有助于预测胰腺癌新辅助治疗后淋巴结阳性
本回顾性研究纳入54例接受放化疗后手术切除及淋巴结清扫的胰腺癌患者,在基线双能CT的70-keV胰腺实质期图像上提取影像组学特征,发现积分总量(∫T)低于507.85 HU·mL可预测ypN1-2分类(敏感度96%、特异度34%、AUC 0.61),且该阈值以下患者总生存期和无进展生存期均较短。
要点
- 基线CT胰腺实质期影像组学特征∫T(HU·mL)低于507.85可能有助于预测胰腺癌新辅助治疗后淋巴结阳性(ypN1-2)。
- 该阈值预测ypN1-2的敏感度为96%、特异度为34%、AUC为0.61。
- ∫T(HU·mL)低于507.85的患者总生存期(中位2.8年)和无进展生存期(中位1.5年)较短。
核心结论
- 基于CT的影像组学特征可能有助于预测胰腺癌患者的ypN分类。
研究设计与样本
- 回顾性研究,纳入54例胰腺癌患者(中位年龄62岁,范围40-88岁;32例男性),于2012年5月至2016年6月接受放化疗后手术切除及淋巴结清扫;在基线双能CT的70-keV胰腺实质期图像和碘物质密度图像上进行三维分割,分别提取15个和19个影像组学特征;采用弹性网络正则化逻辑回归筛选与结局相关的纹理特征,受试者工作特征分析评估特征性能,Kaplan-Meier法生成生存曲线。
诊断标准与关键数值
- 积分总量(∫T)代表胰腺实质期图像的平均强度(Hounsfield单位)乘以轮廓体积(毫升),即∫T(HU·mL)(PPP);∫T(HU·mL)(PPP)与治疗后病理淋巴结(ypN)分类呈负相关;阈值∫T(HU·mL)(PPP)低于507.85预测ypN1-2分类的敏感度为96%、特异度为34%、AUC为0.61。
临床应用与阅片要点
- 作者认为基于CT的影像组学特征可能有助于预测胰腺癌患者的ypN分类。
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)。
英文原文(摘要)· 点击展开
Purpose To study the association between CT-derived textural features of pancreatic cancer and patient outcome. Materials and Methods This retrospective study evaluated 54 patients (median age, 62 years [range, 40-88 years]; 32 men) with pancreatic cancer who underwent chemoradiation followed by surgical resection and lymph node dissection from May 2012 to June 2016. Three-dimensional segmentation of the pancreatic tumor was performed on baseline dual-energy CT images: 70-keV pancreatic parenchymal phase (PPP) images and iodine material density images. Then, 15 and 19 radiomic features were extracted from each phase, respectively. Logistic regression with elastic net regularization was used to select textural features associated with outcome, and receiver operating characteristic analysis evaluated feature performance. Survival curves were generated using the Kaplan-Meier method. Results The feature of integral total (∫ T), representing the mean intensity in Hounsfield units times the contour volume in milliliters of PPP imaging (hereafter, "∫ T (HU·mL) (PPP)"), is inversely associated with posttherapy pathologic lymph node (ypN) category. A threshold ∫ T (HU·mL) (PPP) less than 507.85 predicted ypN1-2 classification with 96% sensitivity, 34% specificity, and area under the curve of 0.61. Patients with an ∫ T (HU·mL) (PPP) of less than 507.85 had decreased overall survival (median, 2.8 years) compared with patients with an ∫ T (HU·mL) (PPP) of 507.85 or greater (one event at 3.4 years) (P = .006). Patients with an ∫ T (HU·mL) (PPP) of less than 507.85 had decreased progression-free survival (median, 1.5 years) compared with patients with an ∫ T (HU·mL) (PPP) of 507.85 or greater (median, 2.7 years) (P = .001). Conclusion A CT-based radiomic signature may help predict ypN category in patients with pancreatic cancer. Keywords: CT-Dual Energy, Abdomen/GI, Pancreas, Tumor Response, Outcomes Analysis © RSNA, 2022 Supplemental material is available for this article.
引用
- Elsherif SB, Javadi S, Le O, et al. Baseline CT-based Radiomic Features Aid Prediction of Nodal Positivity after Neoadjuvant Therapy in Pancreatic Cancer. Radiol Imaging Cancer. 2022. PMID: 35333131. doi:10.1148/rycan.210068
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。