Preoperative Multidetector-Row Computed Tomography-Guided Prognostic Prediction for Disease-Free Survival: A Multicenter Study in Gastric Cancer

Abstract

Background: Preoperative noninvasive evaluation of clinical outcomes remains challenging for gastric cancer. Herein, we identified a multidetector-row computed tomography (MDCT)-guided prognostic radiomic signature for disease-free survival (DFS), with the purpose of constructing a convenient nomogram for clinical need. Methods: A retrospective dataset of 353 gastric cancer patients were enrolled from two centers totally and allocated to three cohorts: training cohort (n=166), internal validation cohort (n=83), and external validation cohort (n=104). Quantitative feature extraction was derived from portal venous phase MDCT images. The least absolute shrinkage and selection operator penalized Cox regression was adopted to construct a radiomic signature. A radiomic nomogram integrated radiomic signature and significant clinical risk factors. We also built a preoperative tumornode-metastasis staging model for comparison. All models were evaluated considering risk stratification, discrimination, calibration, and clinical use. Findings: In the two validation cohorts, the established four-feature radiomic signature showed robust risk stratification power (P=0.0260 and 0.0003, log-rank test). The radiomic nomogram incorporated radiomic signature, extramural vessel invasion, clinical T stage, and clinical N stage, outperforming the other models (concordance index = 0.720 and 0.727) with good calibration and decision curves. The 2-year DFS prediction was also most effective (time-dependent AUC = 0.771 and 0.765). Moreover, subgroup analysis indicated radiomic signature was more sensitive in stratifying patients with advanced clinical T/N stage. Interpretation: The proposed MDCT-guided radiomic signature was verified as a prognostic factor for gastric cancer. The radiomic nomogram provided a noninvasive model for individualized DFS prediction, holding potential in promoting preoperative clinical prognosis and treatment strategies. Funding Statement: This work was supported by the National Key R&D Program of China (2017YFC1308700, 2017YFA0205200, 2017YFC1309100), National Natural Science Foundation of China (81971776, 81771924, 81501616, 81227901, 81671851, 81527805, 81771912), the Beijing Natural Science Foundation (L182061), the Bureau of International Cooperation of Chinese Academy of Sciences (173211KYSB20160053), the Instrument Developing Project of the Chinese Academy of Sciences (YZ201502), and the Youth Innovation Promotion Association CAS (2017175). Declaration of Interests: The authors declare no conflicts of interest. Ethics Approval Statement: This retrospective analysis was ethically granted by the Institutional Review Board of Peking University People's Hospital (PKUPH) and Guangdong General Hospital (GDGH) in compliance with the Health Insurance Portability and Accountability. Informed consent was not required from patients.