Han Xuejiao, Yang Jing, Luo Jingwen, Chen Pengan, Zhang Zilong, Alu Aqu, Xiao Yinan, Ma Xuelei
Department of Biotherapy, Cancer Center, West China Hospital, Sichuan University, Chengdu, China.
State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Sun Yat-sen University Cancer Center, Guangzhou, China.
Front Oncol. 2021 Jul 22;11:606677. doi: 10.3389/fonc.2021.606677. eCollection 2021.
The purpose of this study aimed at investigating the reliability of radiomics features extracted from contrast-enhanced CT in differentiating pancreatic cystadenomas from pancreatic neuroendocrine tumors (PNETs) using machine-learning methods.
In this study, a total number of 120 patients, including 66 pancreatic cystadenomas patients and 54 PNETs patients were enrolled. Forty-eight radiomic features were extracted from contrast-enhanced CT images using LIFEx software. Five feature selection methods were adopted to determine the appropriate features for classifiers. Then, nine machine learning classifiers were employed to build predictive models. The performance of the forty-five models was evaluated with area under the curve (AUC), accuracy, sensitivity, specificity, and F1 score in the testing group.
The predictive models exhibited reliable ability of differentiating pancreatic cystadenomas from PNETs when combined with suitable selection methods. A combination of DC as the selection method and RF as the classifier, as well as Xgboost+RF, demonstrated the best discriminative ability, with the highest AUC of 0.997 in the testing group.
Radiomics-based machine learning methods might be a noninvasive tool to assist in differentiating pancreatic cystadenomas and PNETs.
本研究旨在使用机器学习方法，调查从增强CT中提取的影像组学特征在鉴别胰腺囊腺瘤与胰腺神经内分泌肿瘤（PNETs）方面的可靠性。
本研究共纳入120例患者，其中包括66例胰腺囊腺瘤患者和54例PNETs患者。使用LIFEx软件从增强CT图像中提取48个影像组学特征。采用五种特征选择方法来确定适合分类器的特征。然后，使用九个机器学习分类器构建预测模型。在测试组中，用曲线下面积（AUC）、准确率、灵敏度、特异度和F1分数评估45个模型的性能。
当与合适的选择方法相结合时，预测模型表现出可靠的区分胰腺囊腺瘤与PNETs的能力。以DC作为选择方法、RF作为分类器，以及Xgboost+RF的组合表现出最佳的鉴别能力，测试组中最高AUC为0.997。
基于影像组学的机器学习方法可能是辅助鉴别胰腺囊腺瘤和PNETs的一种非侵入性工具。
