Shuai Ren1,2,3, Rui Zhao1, Jingjing Zhang1, Kai Guo1, Xiaoyu Gu1, Shaofeng Duan4, Zhongqiu Wang5, Rong Chen3. 1. Department of Radiology, Affiliated Hospital of Nanjing University of Chinese Medicine, No. 155 Hanzhong Road, Nanjing, 210029, Jiangsu Province, China. 2. The First Clinical Medical College, Nanjing University of Chinese Medicine, Nanjing, 210023, Jiangsu Province, China. 3. Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, MD, 21201, USA. 4. GE Healthcare China, Shanghai, 201203, China. 5. Department of Radiology, Affiliated Hospital of Nanjing University of Chinese Medicine, No. 155 Hanzhong Road, Nanjing, 210029, Jiangsu Province, China. zhongqiuwang0815@163.com.
Abstract
PURPOSE: To investigate the value of texture analysis on unenhanced computed tomography (CT) to potentially differentiate mass-forming pancreatitis (MFP) from pancreatic ductal adenocarcinoma (PDAC). METHODS: A retrospective study consisting of 109 patients (30 MFP patients vs 79 PDAC patients) who underwent preoperative unenhanced CT between January 2012 and December 2017 was performed. Synthetic minority oversampling technique (SMOTE) algorithm was adopted to reconstruct and balance MFP and PDAC samples. A total of 396 radiomic features were extracted from unenhanced CT images. Mann-Whitney U test and minimum redundancy maximum relevance (MRMR) methods were used for the purpose of dimension reduction. Predictive models were constructed using random forest (RF) method, and were validated using leave group out cross-validation (LGOCV) method. Diagnostic performance of the predictive model, including sensitivity, specificity, accuracy, positive predicting value (PPV), and negative predicting value (NPV), was recorded. RESULTS: We applied 200% of SMOTE to MFP and PDAC patients, resulting in 90 MFP patients compared with 120 PDAC patients. Dimension reduction steps yielded 30 radiomic features using Mann-Whitney U test and MRMR methods. Ten radiomic features were retained using RF method. Four most predictive parameters, including GreyLevelNonuniformity_angle90_offset1, VoxelValueSum, HaraVariance, and ClusterProminence_AllDirection_offset1_SD, were used to generate the predictive model with preferable 92.2% sensitivity, 94.2% specificity, 93.3% accuracy, 92.2% PPV, and 94.2% NPV. Finally, in LGOCV analysis, a high pooled mean sensitivity, specificity, and accuracy (82.6%, 80.8%, and 82.1%, respectively) indicate a relatively reliable and stable predictive model. CONCLUSIONS: Unenhanced CT texture analysis can be a promising noninvasive method in discriminating MFP from PDAC.
PURPOSE: To investigate the value of texture analysis on unenhanced computed tomography (CT) to potentially differentiate mass-forming pancreatitis (MFP) from pancreatic ductal adenocarcinoma (PDAC). METHODS: A retrospective study consisting of 109 patients (30 MFP patients vs 79 PDACpatients) who underwent preoperative unenhanced CT between January 2012 and December 2017 was performed. Synthetic minority oversampling technique (SMOTE) algorithm was adopted to reconstruct and balance MFP and PDAC samples. A total of 396 radiomic features were extracted from unenhanced CT images. Mann-Whitney U test and minimum redundancy maximum relevance (MRMR) methods were used for the purpose of dimension reduction. Predictive models were constructed using random forest (RF) method, and were validated using leave group out cross-validation (LGOCV) method. Diagnostic performance of the predictive model, including sensitivity, specificity, accuracy, positive predicting value (PPV), and negative predicting value (NPV), was recorded. RESULTS: We applied 200% of SMOTE to MFP and PDACpatients, resulting in 90 MFP patients compared with 120 PDACpatients. Dimension reduction steps yielded 30 radiomic features using Mann-Whitney U test and MRMR methods. Ten radiomic features were retained using RF method. Four most predictive parameters, including GreyLevelNonuniformity_angle90_offset1, VoxelValueSum, HaraVariance, and ClusterProminence_AllDirection_offset1_SD, were used to generate the predictive model with preferable 92.2% sensitivity, 94.2% specificity, 93.3% accuracy, 92.2% PPV, and 94.2% NPV. Finally, in LGOCV analysis, a high pooled mean sensitivity, specificity, and accuracy (82.6%, 80.8%, and 82.1%, respectively) indicate a relatively reliable and stable predictive model. CONCLUSIONS: Unenhanced CT texture analysis can be a promising noninvasive method in discriminating MFP from PDAC.
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