Hongyuan Shi1, Yun Wei1, Shenhao Cheng1, Zipeng Lu2, Kai Zhang2, Kuirong Jiang3, Qing Xu4. 1. Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, No 300, Guangzhou Road, Nanjing, 210009, Jiangsu Province, China. 2. Pancreas Center, The First Affiliated Hospital of Nanjing Medical University, No 300, Guangzhou Road, Nanjing, 210009, Jiangsu Province, China. 3. Pancreas Center, The First Affiliated Hospital of Nanjing Medical University, No 300, Guangzhou Road, Nanjing, 210009, Jiangsu Province, China. Electronic address: jiangkuirong@njmu.edu.cn. 4. Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, No 300, Guangzhou Road, Nanjing, 210009, Jiangsu Province, China. Electronic address: xuqing_jsph@163.com.
Abstract
OBJECTIVE: To investigate the value of radiomic features at contrast-enhanced CT integrated with clinic-pathologic features and body composition measures for predicting survival after upfront surgery in patients with pancreatic ductal adenocarcinoma (PDAC). METHODS: Two hundred and ninety-nine patients with PDAC who underwent surgical resection were included and allocated to training set (210 patients) and validation set (89 patients). The radiomics signature for predicting survival was constructed by using the least absolute shrinkage and selection operator Cox regression. Multivariable Cox regression analysis was used to construct a radiomics model based on radiomics signature, clinic-pathologic features and body composition measures. A clinical model without radiomics signature was also developed. Model performance was analyzed by Harrell's concordance index (C-index) and time-independent receiver operating characteristic (ROC) analysis. The Kaplan-Meier (KM) method was used for survival analysis. RESULTS: Five independent variables were selected for the radiomics model: radiomics signature, carbohydrate antigen 19-9, skeletal muscle index, histologic grade and postoperative chemotherapy. The radiomics-based model provided better predictive performance (C-index = 0.73; all p < 0.05) than the clinical model without radiomics signature and American Joint Committee on Cancer (AJCC) TNM staging system. Patients were stratified as high-risk and low-risk group by the radiomics model. The KM analysis showed a significant difference between two groups (p < 0.05). CONCLUSION: The radiovdmics-based model integrating with clinic-pathologic features and body composition measures could predict survival after surgical resection in PDAC patients.
OBJECTIVE: To investigate the value of radiomic features at contrast-enhanced CT integrated with clinic-pathologic features and body composition measures for predicting survival after upfront surgery in patients with pancreatic ductal adenocarcinoma (PDAC). METHODS: Two hundred and ninety-nine patients with PDAC who underwent surgical resection were included and allocated to training set (210 patients) and validation set (89 patients). The radiomics signature for predicting survival was constructed by using the least absolute shrinkage and selection operator Cox regression. Multivariable Cox regression analysis was used to construct a radiomics model based on radiomics signature, clinic-pathologic features and body composition measures. A clinical model without radiomics signature was also developed. Model performance was analyzed by Harrell's concordance index (C-index) and time-independent receiver operating characteristic (ROC) analysis. The Kaplan-Meier (KM) method was used for survival analysis. RESULTS: Five independent variables were selected for the radiomics model: radiomics signature, carbohydrate antigen 19-9, skeletal muscle index, histologic grade and postoperative chemotherapy. The radiomics-based model provided better predictive performance (C-index = 0.73; all p < 0.05) than the clinical model without radiomics signature and American Joint Committee on Cancer (AJCC) TNM staging system. Patients were stratified as high-risk and low-risk group by the radiomics model. The KM analysis showed a significant difference between two groups (p < 0.05). CONCLUSION: The radiovdmics-based model integrating with clinic-pathologic features and body composition measures could predict survival after surgical resection in PDAC patients.