Xiheng Wang1, Zhaoyong Sun1, Huadan Xue2, Taiping Qu3, Sihang Cheng1, Juan Li1, Yatong Li1, Li Mao3, Xiuli Li3, Liang Zhu1, Xiao Li4, Longjing Zhang4, Zhengyu Jin5, Yizhou Yu3. 1. Department of Radiology, Peking Union Medical College Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences, Shuaifuyuan No.1, Wangfujing Street, Dongcheng District, Beijing, 100730, People's Republic of China. 2. Department of Radiology, Peking Union Medical College Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences, Shuaifuyuan No.1, Wangfujing Street, Dongcheng District, Beijing, 100730, People's Republic of China. bjdanna95@hotmail.com. 3. Deepwise AI Lab, Deepwise Inc., Beijing, 100080, People's Republic of China. 4. Department of Diagnostic Radiology, Jinling Hospital, Medical School of Nanjing University, Nanjing, Jiangsu, 210002, People's Republic of China. 5. Department of Radiology, Peking Union Medical College Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences, Shuaifuyuan No.1, Wangfujing Street, Dongcheng District, Beijing, 100730, People's Republic of China. jinzy@pumch.cn.
Abstract
PURPOSE: To develop a deep learning model (DLM) to improve readers' interpretation and speed in the differentiation of pancreatic cystic lesions (PCLs) on dual-phase enhanced CT, and a low contrast media dose, external testing set validated the model. MATERIALS AND METHODS: Dual-phase enhanced CT images of 363 patients with 368 PCLs obtained from two centers were retrospectively assessed. Based on the examination date, a training and validation set of 266 PCLs, an internal testing set of 52 PCLs were designated from center 1. An external testing set included 50 PCLs from center 2. Clinical and radiological characteristics were compared. The DLM was developed using 3D specially designed densely connected convolutional networks for PCL differentiation. Radiomic features were extracted to build a traditional radiomics model (RM). Performance of the DLM, traditional RM, and three readers was compared. RESULTS: The accuracy for differential diagnosis was 0.904 with DLM, which was the highest in the internal testing set. Accuracy differences between the DLM and senior radiologist were not significant both in the internal and external testing set (both p > 0.05). With the help of the DLM, the accuracy and specificity of the junior radiologist were significantly improved (all p < 0.05), and all readers' diagnostic time was shortened (all p < 0.05). CONCLUSION: The DLM achieved senior radiologist-level performance in differentiating benign and malignant PCLs which could improve the junior radiologist's interpretation and speed of PCLs on CT.
PURPOSE: To develop a deep learning model (DLM) to improve readers' interpretation and speed in the differentiation of pancreatic cystic lesions (PCLs) on dual-phase enhanced CT, and a low contrast media dose, external testing set validated the model. MATERIALS AND METHODS: Dual-phase enhanced CT images of 363 patients with 368 PCLs obtained from two centers were retrospectively assessed. Based on the examination date, a training and validation set of 266 PCLs, an internal testing set of 52 PCLs were designated from center 1. An external testing set included 50 PCLs from center 2. Clinical and radiological characteristics were compared. The DLM was developed using 3D specially designed densely connected convolutional networks for PCL differentiation. Radiomic features were extracted to build a traditional radiomics model (RM). Performance of the DLM, traditional RM, and three readers was compared. RESULTS: The accuracy for differential diagnosis was 0.904 with DLM, which was the highest in the internal testing set. Accuracy differences between the DLM and senior radiologist were not significant both in the internal and external testing set (both p > 0.05). With the help of the DLM, the accuracy and specificity of the junior radiologist were significantly improved (all p < 0.05), and all readers' diagnostic time was shortened (all p < 0.05). CONCLUSION: The DLM achieved senior radiologist-level performance in differentiating benign and malignant PCLs which could improve the junior radiologist's interpretation and speed of PCLs on CT.
Authors: Nakul P Valsangkar; Vicente Morales-Oyarvide; Sarah P Thayer; Cristina R Ferrone; Jennifer A Wargo; Andrew L Warshaw; Carlos Fernández-del Castillo Journal: Surgery Date: 2012-07-06 Impact factor: 3.982
Authors: Klaus Sahora; Mari Mino-Kenudson; William Brugge; Sarah P Thayer; Cristina R Ferrone; Dushyant Sahani; Martha B Pitman; Andrew L Warshaw; Keith D Lillemoe; Carlos F Fernandez-del Castillo Journal: Ann Surg Date: 2013-09 Impact factor: 12.969
Authors: Masao Tanaka; Carlos Fernández-Del Castillo; Terumi Kamisawa; Jin Young Jang; Philippe Levy; Takao Ohtsuka; Roberto Salvia; Yasuhiro Shimizu; Minoru Tada; Christopher L Wolfgang Journal: Pancreatology Date: 2017-07-13 Impact factor: 3.996
Authors: Johannes Boos; Alexander Brook; Christina M Chingkoe; Trevor Morrison; Koenraad Mortele; Vassilios Raptopoulos; Ivan Pedrosa; Olga R Brook Journal: Abdom Radiol (NY) Date: 2017-02
Authors: Thomas A Laffan; Karen M Horton; Alison P Klein; Bruce Berlanstein; Stanley S Siegelman; Satomi Kawamoto; Pamela T Johnson; Elliot K Fishman; Ralph H Hruban Journal: AJR Am J Roentgenol Date: 2008-09 Impact factor: 3.959