Radiomics analysis for the differentiation of autoimmune pancreatitis and pancreatic ductal adenocarcinoma in 18 F-FDG PET/CT.

Abstract

PURPOSE\nTo perform a radiomics analysis with comparisons of multi-domain features and a variety of feature selection strategies and classifiers, with the goal of evaluating the value of quantified radiomics method for noninvasively differentiating autoimmune pancreatitis (AIP) from pancreatic ductal adenocarcinoma (PDAC) in 18 F FDG PET/CT images.\n\n\nMETHODS\nWe extracted 251 expert-designed features from 2D and 3D PET/CT images of 111 patients, and recombined these features into five feature sets according to their modalities and dimensions. Among the five feature sets, the optimal one was found leveraging four feature selection strategies and four machine learning classifiers based on the area under the receiver operating characteristic curve (AUC). The feature selection strategies include spearman s rank correlation coefficient, minimum redundancy maximum relevance, support vector machine recursive feature elimination (SVM-RFE) and no feature selection, while the classifiers are random forest, adaptive boosting, support vector machine (SVM) with the Gaussian radial basis function, and SVM with the linear kernel function, respectively. Based on the optimal feature set, these feature selection strategies and classifiers were comparatively studied to achieve the best differentiation. Finally, the quantified radiomics prediction model was developed based on the best combination of the feature selection strategy and classifier, and it was compared with two clinical factors based prediction models, and human doctors using nested cross-validation in terms of AUC, accuracy, sensitivity, and specificity.\n\n\nRESULTS\nComparison experiments demonstrated that CT features and 3D features performed better than PET features and 2D features respectively, and multi-domain features were superior to single domain features. In addition, the combination of SVM-RFE feature selection strategy and Linear SVM classifier had the highest diagnostic performance (i.e., AUC=0.93±0.01, ACC=0.85±0.02, SEN=0.86±0.03, SPE=0.84±0.03). The quantified radiomics model developed is significantly superior to both human doctors and clinical factors based prediction models in terms of accuracy and specificity.\n\n\nCONCLUSIONS\nOur preliminary results confirmed that the quantified radiomics method could aid the noninvasive differentiation of AIP and PDAC in 18 F FDG PET/CT images and the integration of multi-domain features is beneficial for the differentiation.