Xi Ma1, Yu-Rui Wang2, Li-Yong Zhuo1, Xiao-Ping Yin1, Jia-Liang Ren3, Cai-Ying Li4, Li-Hong Xing1, Tong-Tong Zheng4. 1. CT/MRI Room, Affiliated Hospital of Hebei University, Baoding, Hebei Province, 071000, People's Republic of China. 2. Department of Computed Tomography, Tangshan Gongren Hospital, Tangshan, Hebei Province, 063000, People's Republic of China. 3. GE Healthcare[Shanghai] Co Ltd, Shanghai, 210000, People's Republic of China. 4. Department of Radiology, The Second Hospital of Hebei Medical University, Shijiazhuang, Hebei Province, 050000, People's Republic of China.
Abstract
PURPOSE: To investigate the feasibility of enhanced computed tomography (CT) radiomics analysis to differentiate between pancreatic cancer (PC) and chronic pancreatitis. METHODS AND MATERIALS: The CT images of 151 PCs and 24 chronic pancreatitis were retrospectively analyzed in the three-dimensional regions of interest on arterial phase (AP) and venous phase (VP) and segmented by MITK software. A multivariable logistic regression model was established based on the selected radiomics features. The radiomics score was calculated, and the nomogram was established. The discrimination of each model was analyzed by the receiver operating characteristic curve (ROC). Decision curve analysis (DCA) was used to evaluate clinical utility. The precision recall curve (PRC) was used to evaluate whether the model is affected by data imbalance. The Delong test was adopted to compare the diagnostic efficiency of each model. RESULTS: Significant differences were observed in the distribution of gender (P = 0.034), carbohydrate antigen 19-9 (P < 0.001), and carcinoembryonic antigen (P < 0.001) in patients with PC and chronic pancreatitis. The area under the ROC curve (AUC) value of AP multivariate regression model, VP multivariate regression model, AP combined with VP features model (Radiomics), clinical feature model, and radiomics combined with clinical feature model (COMB) was 0.905, 0.941, 0.941, 0.822, and 0.980, respectively. The sensitivity and specificity of the COMB model were 0.947 and 0.917, respectively. The results of DCA showed that the COMB model exhibited net clinical benefits and PRC shows that COMB model have good precision and recall (sensitivity). CONCLUSION: The COMB model could be a potential tool to distinguish PC from chronic pancreatitis and aid in clinical decisions.
PURPOSE: To investigate the feasibility of enhanced computed tomography (CT) radiomics analysis to differentiate between pancreatic cancer (PC) and chronic pancreatitis. METHODS AND MATERIALS: The CT images of 151 PCs and 24 chronic pancreatitis were retrospectively analyzed in the three-dimensional regions of interest on arterial phase (AP) and venous phase (VP) and segmented by MITK software. A multivariable logistic regression model was established based on the selected radiomics features. The radiomics score was calculated, and the nomogram was established. The discrimination of each model was analyzed by the receiver operating characteristic curve (ROC). Decision curve analysis (DCA) was used to evaluate clinical utility. The precision recall curve (PRC) was used to evaluate whether the model is affected by data imbalance. The Delong test was adopted to compare the diagnostic efficiency of each model. RESULTS: Significant differences were observed in the distribution of gender (P = 0.034), carbohydrate antigen 19-9 (P < 0.001), and carcinoembryonic antigen (P < 0.001) in patients with PC and chronic pancreatitis. The area under the ROC curve (AUC) value of AP multivariate regression model, VP multivariate regression model, AP combined with VP features model (Radiomics), clinical feature model, and radiomics combined with clinical feature model (COMB) was 0.905, 0.941, 0.941, 0.822, and 0.980, respectively. The sensitivity and specificity of the COMB model were 0.947 and 0.917, respectively. The results of DCA showed that the COMB model exhibited net clinical benefits and PRC shows that COMB model have good precision and recall (sensitivity). CONCLUSION: The COMB model could be a potential tool to distinguish PC from chronic pancreatitis and aid in clinical decisions.
Authors: Labrinus van Manen; Jesse V Groen; Hein Putter; Alexander L Vahrmeijer; Rutger-Jan Swijnenburg; Bert A Bonsing; J Sven D Mieog Journal: Biomarkers Date: 2020-02-13 Impact factor: 2.658
Authors: Thomas Aparicio; Christine Hoeffel; Anthony Dohan; Benoit Gallix; Boris Guiu; Karine Le Malicot; Caroline Reinhold; Philippe Soyer; Jaafar Bennouna; Francois Ghiringhelli; Emilie Barbier; Valérie Boige; Julien Taieb; Olivier Bouché; Eric François; Jean-Marc Phelip; Christian Borel; Roger Faroux; Jean-Francois Seitz; Stéphane Jacquot; Meher Ben Abdelghani; Faiza Khemissa-Akouz; Dominique Genet; Jean Louis Jouve; Yves Rinaldi; Françoise Desseigne; Patrick Texereau; Etienne Suc; Come Lepage Journal: Gut Date: 2019-05-17 Impact factor: 23.059
Authors: Julia Mayerle; Holger Kalthoff; Regina Reszka; Beate Kamlage; Erik Peter; Bodo Schniewind; Sandra González Maldonado; Christian Pilarsky; Claus-Dieter Heidecke; Philipp Schatz; Marius Distler; Jonas A Scheiber; Ujjwal M Mahajan; F Ulrich Weiss; Robert Grützmann; Markus M Lerch Journal: Gut Date: 2017-01-20 Impact factor: 23.059
Authors: Alexander N Hanania; Leonidas E Bantis; Ziding Feng; Huamin Wang; Eric P Tamm; Matthew H Katz; Anirban Maitra; Eugene J Koay Journal: Oncotarget Date: 2016-12-27
Authors: Andrew McGuigan; Paul Kelly; Richard C Turkington; Claire Jones; Helen G Coleman; R Stephen McCain Journal: World J Gastroenterol Date: 2018-11-21 Impact factor: 5.742