Linning E1, Yan Xu2, Zhifeng Wu1, Li Li3, Na Zhang1, Hao Yang4, Lawrence H Schwartz4, Lin Lu4, Binsheng Zhao4. 1. From the Department of Radiology, Shanxi DAYI Hospital, Taiyuan. 2. Department of Radiology, Beijing Friendship Hospital, Capital Medical University, Beijing. 3. Department of Pathology, Shanxi DAYI Hospital, Taiyuan, China. 4. Department of Radiology, Columbia University Medical Center, New York, NY.
Abstract
OBJECTIVES: The aim of this study was to develop a radiomics model for a differential diagnosis of focal-type autoimmune pancreatitis (AIP) from pancreatic ductal adenocarcinoma. METHODS: A total of 96 patients, 45 with AIP and 51 with pancreatic ductal adenocarcinoma, were retrospectively evaluated. All patients underwent pretreatment abdominal computed tomography imaging acquired at noncontrast, arterial, and venous phases. Furthermore, 1160 radiomics features were extracted from each phasic image to build radiomics models. The performance of radiomics model was evaluated by sensitivity, specificity, and accuracy. The results of radiomics model were also compared with those of radiologists' visual assessments. RESULTS: The sensitivity, specificity, and accuracy of the optimal radiomics model were 93.3%, 96.1%, and 94.8%, respectively. They were higher than those of the radiologists' assessments with sensitivity of 57.78% and 73.33%, specificity of 88.24% and 90.20%, and accuracy of 75.00% and 81.25%, respectively. CONCLUSION: Radiomics is helpful for a differential diagnosis of AIP in clinical practice as a noninvasive and quantitative method.
OBJECTIVES: The aim of this study was to develop a radiomics model for a differential diagnosis of focal-type autoimmune pancreatitis (AIP) from pancreatic ductal adenocarcinoma. METHODS: A total of 96 patients, 45 with AIP and 51 with pancreatic ductal adenocarcinoma, were retrospectively evaluated. All patients underwent pretreatment abdominal computed tomography imaging acquired at noncontrast, arterial, and venous phases. Furthermore, 1160 radiomics features were extracted from each phasic image to build radiomics models. The performance of radiomics model was evaluated by sensitivity, specificity, and accuracy. The results of radiomics model were also compared with those of radiologists' visual assessments. RESULTS: The sensitivity, specificity, and accuracy of the optimal radiomics model were 93.3%, 96.1%, and 94.8%, respectively. They were higher than those of the radiologists' assessments with sensitivity of 57.78% and 73.33%, specificity of 88.24% and 90.20%, and accuracy of 75.00% and 81.25%, respectively. CONCLUSION: Radiomics is helpful for a differential diagnosis of AIP in clinical practice as a noninvasive and quantitative method.
Authors: Stephanie A Lee-Felker; Ely R Felker; Barbara Kadell; James Farrell; Steven S Raman; James Sayre; David S Lu Journal: AJR Am J Roentgenol Date: 2015-07 Impact factor: 3.959
Authors: Dushyant V Sahani; Sanjeeva P Kalva; James Farrell; Michael M Maher; Sanjay Saini; Peter R Mueller; Gregory Y Lauwers; Carlos D Fernandez; Andrew L Warshaw; Joseph F Simeone Journal: Radiology Date: 2004-09-30 Impact factor: 11.105
Authors: Meghan G Lubner; Andrew D Smith; Kumar Sandrasegaran; Dushyant V Sahani; Perry J Pickhardt Journal: Radiographics Date: 2017 Sep-Oct Impact factor: 5.333
Authors: Dushyant V Sahani; Nisha I Sainani; Vikram Deshpande; Mehrine S Shaikh; Dmitry L Frinkelberg; Carlos Fernandez-del Castillo Journal: Radiology Date: 2008-11-18 Impact factor: 11.105
Authors: M J van Heerde; K Biermann; P E Zondervan; G Kazemier; C H J van Eijck; C Pek; E J Kuipers; H R van Buuren Journal: Dig Dis Sci Date: 2012-05-16 Impact factor: 3.199
Authors: Calogero Casà; Antonio Piras; Andrea D'Aviero; Francesco Preziosi; Silvia Mariani; Davide Cusumano; Angela Romano; Ivo Boskoski; Jacopo Lenkowicz; Nicola Dinapoli; Francesco Cellini; Maria Antonietta Gambacorta; Vincenzo Valentini; Gian Carlo Mattiucci; Luca Boldrini Journal: Ther Adv Gastrointest Endosc Date: 2022-03-16