Development and Validation of a Radiomics Nomogram Based on 18F-Fluorodeoxyglucose Positron Emission Tomography/Computed Tomography and Clinicopathological Factors to Predict the Survival Outcomes of Patients With Non-Small Cell Lung Cancer

Bin Yang; Jian Zhong; Jing Zhong; Lu Ma; Ang Li; Hengshan Ji; Changsheng Zhou; Shaofeng Duan; Qinggen Wang; Chaohui Zhu; Jiahe Tian; Longjiang Zhang; Feng Wang; Hong Zhu; Guangming Lu

doi:10.3389/fonc.2020.01042

Development and Validation of a Radiomics Nomogram Based on ¹⁸F-Fluorodeoxyglucose Positron Emission Tomography/Computed Tomography and Clinicopathological Factors to Predict the Survival Outcomes of Patients With Non-Small Cell Lung Cancer

Front Oncol. 2020 Jul 17:10:1042. doi: 10.3389/fonc.2020.01042. eCollection 2020.

Authors

Bin Yang¹, Jian Zhong¹, Jing Zhong¹, Lu Ma¹, Ang Li¹, Hengshan Ji², Changsheng Zhou¹, Shaofeng Duan³, Qinggen Wang⁴, Chaohui Zhu⁵, Jiahe Tian⁶, Longjiang Zhang¹, Feng Wang⁷, Hong Zhu², Guangming Lu¹

Affiliations

¹ Department of Medical Imaging, Affiliated Jinling Hospital, Medical School of Nanjing University, Nanjing, China.
² Department of Nuclear Medicine, Affiliated Jinling Hospital, Medical School of Nanjing University, Nanjing, China.
³ GE Healthcare China, Shanghai, China.
⁴ Department of Medical Imaging, Jinling Hospital, The First School of Clinical Medicine, Southern Medical University, Nanjing, China.
⁵ Department of Nuclear Medicine, Peking Union Medical College Hospital, Beijing, China.
⁶ Department of Nuclear Medicine, The Chinese PLA General Hospital, Beijing, China.
⁷ Department of Nuclear Medicine, First People's Hospital of Nanjing, Nanjing, China.

Abstract

Purpose: In this study, we developed and validated a radiomics nomogram by combining the radiomic features extracted from ¹⁸F-fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) images and clinicopathological factors to evaluate the overall survival (OS) of patients with non-small cell lung cancer (NSCLC). Patients and Methods: A total of 315 consecutive patients with NSCLC (221 in the training cohort and 94 in the validation cohort) were enrolled in this study. A total of 840 radiomic features were extracted from the CT and PET images. Three radiomic scores (rad-scores) were calculated using the least absolute shrinkage and selection operator (LASSO) Cox regression based on subsets of CT, PET, and PET/CT radiomic features. A multivariate Cox regression analysis was performed for each rad-score combined with clinicopathological factors to determine the independent risk factors. The OS nomogram was constructed based on the PET/CT rad-score and independent clinicopathological factors. Validation and calibration were conducted to evaluate the performance of the model in the training and validation cohorts, respectively. Results: A total of 144 (45.71%) women and 171 (54.29%) men with NSCLC were enrolled in this study. The PET/CT rad-score combined with the clinical model had the best C-index (0.776 and 0.789 for the training and validation cohorts, respectively). Distant metastasis, stage, carcinoembryonic antigen (CEA), and targeted therapy were independent risk factors for patients with NSCLC. The validation curve showed that the OS nomogram had a strong predictive power in patients' survival. The calibration curve showed that the predicted survival time was significantly close to the observed one. Conclusion: A radiomic nomogram based on ¹⁸F-FDG PET/CT rad-score and clinicopathological factors had good predictive performance for the survival outcome, offering feasible, and practical guidance for individualized management of patients with NSCLC.

Keywords: PET/CT; non-small cell lung cancer; radiomics; risk stratification; survival outcome.