Wenjuan Zhang1, Mengjie Fang2, Di Dong2, Xiaoxiao Wang3, Xiaoai Ke4, Liwen Zhang2, Chaoen Hu2, Lingyun Guo5, Xiaoying Guan6, Junlin Zhou7, Xiuhong Shan8, Jie Tian9. 1. Department of Radiology, Lanzhou University Second Hospital, PR China; Second Clinical School, Lanzhou University, PR China; Key Laboratory of Medical Imaging of Gansu Province, PR China; CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, PR China. 2. CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, PR China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, PR China. 3. Department of Radiology, Affiliated People's Hospital of Jiangsu University, Zhenjiang, PR China. 4. Department of Radiology, Lanzhou University Second Hospital, PR China; Second Clinical School, Lanzhou University, PR China; Key Laboratory of Medical Imaging of Gansu Province, PR China. 5. Second Clinical School, Lanzhou University, PR China; Department of General Surgery, Lanzhou University Second Hospital, PR China. 6. Second Clinical School, Lanzhou University, PR China; Department of Pathology, Lanzhou University Second Hospital, PR China. 7. Department of Radiology, Lanzhou University Second Hospital, PR China; Second Clinical School, Lanzhou University, PR China; Key Laboratory of Medical Imaging of Gansu Province, PR China. Electronic address: ery_zhoujl@lzu.edu.cn. 8. Department of Radiology, Affiliated People's Hospital of Jiangsu University, Zhenjiang, PR China. Electronic address: xhongshan@hotmail.com. 9. CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, PR China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, PR China; Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, Beihang University, Beijing, PR China. Electronic address: tian@ieee.org.
Abstract
BACKGROUND: In the clinical management of advanced gastric cancer (AGC), preoperative identification of early recurrence after curative resection is essential. Thus, we aimed to create a CT-based radiomic model to predict early recurrence in AGC patients preoperatively. MATERIALS AND METHODS: We enrolled 669 consecutive patients (302 in the training set, 219 in the internal test set and 148 in the external test set) with clinicopathologically confirmed AGC from two centers. Radiomic features were extracted from preoperative diagnostic CT images. Machine learning methods were applied to shrink feature size and build a predictive radiomic signature. We incorporated the radiomic signature and clinical risk factors into a nomogram using multivariable logistic regression analysis. The area under the curve (AUC) of operating characteristics (ROC), accuracy, and calibration curves were assessed to evaluate the nomogram's performance in discriminating early recurrence. RESULTS: A radiomic signature, including three hand crafted features and six deep learning features, was significantly associated with early recurrence (p-value <0.0001 for all sets). In addition, clinical N stage, carbohydrate antigen 199 levels, carcinoembryonic antigen levels, and Borrmann type were considered useful predictors for early recurrence. The nomogram, combining all these predictors, showed powerful prognostic ability in the training set and two test sets with AUCs of 0.831 (95% CI, 0.786-0.876), 0.826 (0.772-0.880) and 0.806 (0.732-0.881), respectively. The predicted risk yielded good agreement with the observed recurrence probability. CONCLUSIONS: By incorporating a radiomic signature and clinical risk factors, we created a radiomic nomogram to predict early recurrence in patients with AGC, preoperatively, which may serve as a potential tool to guide personalized treatment.
BACKGROUND: In the clinical management of advanced gastric cancer (AGC), preoperative identification of early recurrence after curative resection is essential. Thus, we aimed to create a CT-based radiomic model to predict early recurrence in AGC patients preoperatively. MATERIALS AND METHODS: We enrolled 669 consecutive patients (302 in the training set, 219 in the internal test set and 148 in the external test set) with clinicopathologically confirmed AGC from two centers. Radiomic features were extracted from preoperative diagnostic CT images. Machine learning methods were applied to shrink feature size and build a predictive radiomic signature. We incorporated the radiomic signature and clinical risk factors into a nomogram using multivariable logistic regression analysis. The area under the curve (AUC) of operating characteristics (ROC), accuracy, and calibration curves were assessed to evaluate the nomogram's performance in discriminating early recurrence. RESULTS: A radiomic signature, including three hand crafted features and six deep learning features, was significantly associated with early recurrence (p-value <0.0001 for all sets). In addition, clinical N stage, carbohydrate antigen 199 levels, carcinoembryonic antigen levels, and Borrmann type were considered useful predictors for early recurrence. The nomogram, combining all these predictors, showed powerful prognostic ability in the training set and two test sets with AUCs of 0.831 (95% CI, 0.786-0.876), 0.826 (0.772-0.880) and 0.806 (0.732-0.881), respectively. The predicted risk yielded good agreement with the observed recurrence probability. CONCLUSIONS: By incorporating a radiomic signature and clinical risk factors, we created a radiomic nomogram to predict early recurrence in patients with AGC, preoperatively, which may serve as a potential tool to guide personalized treatment.