Performance of 18F-FDG PET/CT Radiomics for Predicting EGFR Mutation Status in Patients With Non-Small Cell Lung Cancer

Frontiers in Oncology

卷:10

Min Zhang¹  Xinyun Huang¹  Xiaozhu Lin¹  Hongping Meng¹  Jiajun Liu¹  Qian Qu¹  Biao Li¹  Miao Zhang¹  Yilei Zhou¹  Chengfang Shangguan²  Weiwei Rui³  Yiming Bao⁴  Jianwei Xu⁴  Dahong Qian⁴ 

[1] Department of Nuclear Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China;

[2] Department of Oncology, Rujin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China;

[3] Department of Pathology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China;

[4] Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai, China;

关键词: positron emission tomography/computed tomography;    radiomics;    lung cancer;    epidermal growth factor receptor;    18F-fluorodeoxyglucose;   

DOI  :  10.3389/fonc.2020.568857

来源: DOAJ

【 摘 要 】

ObjectiveTo assess the performance of pretreatment 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) radiomics features for predicting EGFR mutation status in patients with non-small cell lung cancer (NSCLC).Patients and MethodsWe enrolled total 173 patients with histologically proven NSCLC who underwent preoperative 18F-FDG PET/CT. Tumor tissues of all patients were tested for EGFR mutation status. A PET/CT radiomics prediction model was established through multi-step feature selection. The predictive performances of radiomics model, clinical features and conventional PET-derived semi-quantitative parameters were compared using receiver operating curves (ROCs) analysis.ResultsFour CT and two PET radiomics features were finally selected to build the PET/CT radiomics model. Compared with area under the ROC curve (AUC) equal to 0.664, 0.683 and 0.662 for clinical features, maximum standardized uptake values (SUVmax) and total lesion glycolysis (TLG), the PET/CT radiomics model showed better performance to discriminate between EGFR positive and negative mutations with the AUC of 0.769 and the accuracy of 67.06% after 10-fold cross-validation. The combined model, based on the PET/CT radiomics and clinical feature (gender) further improved the AUC to 0.827 and the accuracy to 75.29%. Only one PET radiomics feature demonstrated significant but low predictive ability (AUC = 0.661) for differentiating 19 Del from 21 L858R mutation subtypes.ConclusionsEGFR mutations status in patients with NSCLC could be well predicted by the combined model based on 18F-FDG PET/CT radiomics and clinical feature, providing an alternative useful method for the selection of targeted therapy.

【 授权许可】

Unknown