Differentiating hypovascular pancreatic neuroendocrine tumors from pancreatic ductal adenocarcinoma based on CT texture analysis. (May 2020)

• Record Type: Journal Article
• Authors: Wang, Zhonglan; Chen, Xiao; Wang, Jianhua; Cui, Wenjing; Ren, Shuai; Wang, Zhongqiu
• Is Part Of: Acta radiologica. Volume 61:Number 5(2020)
• Page Start: 595
• Page End: 604
• Publication Date: 2020-05
• Subjects: Pancreatic ductal adenocarcinoma -- pancreatic neuroendocrine tumor -- computed tomography -- texture analysis -- hypovascular; Radiology, Medical -- Periodicals; Radiography, Medical -- Periodicals; Radiotherapy -- Periodicals; 616.0757
• DOI: 10.1177/0284185119875023
• Languages: English
• ISSNs: 0284-1851

Abstract

Background: Hypovascular pancreatic neuroendocrine tumor is usually misdiagnosed as pancreatic ductal adenocarcinoma. Purpose: To investigate the value of texture analysis in differentiating hypovascular pancreatic neuroendocrine tumors from pancreatic ductal adenocarcinoma on contrast-enhanced computed tomography (CT) images. Material and Methods: Twenty-one patients with hypovascular pancreatic neuroendocrine tumors and 63 patients with pancreatic ductal adenocarcinomas were included in this study. All patients underwent preoperative unenhanced and dynamic contrast-enhanced CT examinations. Two radiologists independently and manually contoured the region of interest of each lesion using texture analysis software on pancreatic parenchymal and portal phase CT images. Multivariate logistic regression analysis was performed to identify significant features to differentiate hypovascular pancreatic neuroendocrine tumors from pancreatic ductal adenocarcinomas. Receiver operating characteristic curve analysis was performed to ascertain diagnostic ability. Results: The following CT texture features were obtained to differentiate hypovascular pancreatic neuroendocrine tumors from pancreatic ductal adenocarcinomas: RMS (root mean square) (odds ratio [OR] = 0.50, P <0.001), Quantile50 (OR = 1.83, P <0.001), and sumAverage (OR = 0.92, P =0.007) in parenchymal images and "contrast" in portal phase images (OR = 6.08, P <0.001). The areas under the curves were 0.76 for RMS (sensitivity = 0.75, specificity = 0.67), 0.73 for Quantile50 (sensitivity = 0.60, specificity = 0.77), 0.70 for sumAverage (sensitivity = 0.65, specificity = 0.82), 0.85 for the combined texture features (sensitivity = 0.77, specificity = 0.85). Conclusion: CT texture analysis may be helpful to differentiate hypovascular pancreatic neuroendocrine tumors from pancreatic ductal adenocarcinomas. The three combined texture features showed acceptable diagnostic performance.