Computed Tomography-Based Radiomics Signature for the Preoperative Differentiation of Pancreatic Adenosquamous Carcinoma From Pancreatic Ductal Adenocarcinoma
Computed Tomography-Based Radiomics Signature for the Preoperative Differentiation of Pancreatic Adenosquamous Carcinoma From Pancreatic Ductal Adenocarcinoma
复制标题
基于计算机断层扫描的放射组学特征用于术前区分胰腺腺鳞癌和胰腺导管腺癌
DOI：
10.3389/fonc.2020.01618
复制
发表时间：
2020-08-25
影响因子：
4.7
通讯作者：
Chen, Rong
中科院分区：
文献类型：
--
作者：
Ren, Shuai;Zhao, Rui;Chen, Rong
目的评价CT放射组学特征在胰腺腺鳞癌（PASC）和胰腺导管腺癌（PDAC）鉴别诊断中的预测能力。资料与方法81例PDAC患者（63.6 ± 8.8岁）和31例PASC患者（64.7 ± 11.1岁）术前均行CE-CT检查。从每例病例的晚期动脉相（n= 396）和门静脉相（n= 396）中提取了总计792个放射组学特征。采用Mann-WhitneyU检验、单变量Logistic回归分析和最小冗余最大相关法选择显著不同的特征。采用随机森林方法构建放射组学特征，并采用10次留组交叉验证（LGOCV）方法验证其稳健性和可靠性。结果从动脉期晚期图像中筛选出7个放射组学特征，从门静脉期图像中筛选出3个放射组学特征。放射组学特征在PASC和PDAC之间的鉴别诊断中表现良好，准确性为94.5%，灵敏度为98.3%，特异性为90.1%，阳性预测值（PPV）为91.9%，阴性预测值（NPV）为97.8%。此外，使用LGOCV方法证明放射组学特征是稳健和可靠的，具有76.4%的准确性、91.1%的灵敏度、70.8%的特异性、56.7%的PPV和96.2%的NPV。结论基于CT的放射组学特征可作为鉴别PASC和PDAC的无创性诊断方法。
Purpose The purpose was to assess the predictive ability of computed tomography (CT)-based radiomics signature in differential diagnosis between pancreatic adenosquamous carcinoma (PASC) and pancreatic ductal adenocarcinoma (PDAC). Materials and Methods Eighty-one patients (63.6 +/- 8.8 years old) with PDAC and 31 patients (64.7 +/- 11.1 years old) with PASC who underwent preoperative CE-CT were included. A total of 792 radiomics features were extracted from the late arterial phase (n= 396) and portal venous phase (n= 396) for each case. Significantly different features were selected using Mann-WhitneyUtest, univariate logistic regression analysis, and minimum redundancy and maximum relevance method. A radiomics signature was constructed using random forest method, the robustness and the reliability of which was validated using 10-times leave group out cross-validation (LGOCV) method. Results Seven radiomics features from late arterial phase images and three from portal venous phase images were finally selected. The radiomics signature performed well in differential diagnosis between PASC and PDAC, with 94.5% accuracy, 98.3% sensitivity, 90.1% specificity, 91.9% positive predictive value (PPV), and 97.8% negative predictive value (NPV). Moreover, the radiomics signature was proved to be robust and reliable using the LGOCV method, with 76.4% accuracy, 91.1% sensitivity, 70.8% specificity, 56.7% PPV, and 96.2% NPV. Conclusion CT-based radiomics signature may serve as a promising non-invasive method in differential diagnosis between PASC and PDAC.