Identification of subclinical cardiac amyloidosis in aortic stenosis patients undergoing transaortic valve replacement using radiomic analysis of computed tomography myocardial texture

Background: Cardiac amyloidosis (CA) is an increasingly diagnosed pathology sharing several phenotypical features with aortic stenosis (AS). As diagnosing the two diseases has important prognostic and therapeutic implications, this study aims to identify a set of stable and discriminative radiomic features derived from cardiac computed tomography (CCT) to differentiate them. Methods: Forty-two patients were included in the study. For each patient, 107 radiomics features were extracted and evaluated by means of geometrical transformations (translations) to the region of interests (ROIs), and ICC (intra class correlation coefficient) computation. A stratified 7-fold cross validation (k=7) was performed to split data into learning, validation and test set. Three features selection methods (Wilcoxon signed rank- based method and/or LASSO regression) and five machine learning classifiers (k-nearest neighbors, support vector classifier, decision tree, logistic regression and gradient boosting) were tested. Results: Ninety radiomic features satisfied the robustness criteria and 10 were kept after feature selection. The best results were obtained using the logistic regression classifier, combined with Wilcoxon signed rank and LASSO regression, obtaining an accuracy of 95%  7% and sensitivity and specificity both equal to 95%  12% in the test set. Conclusions: In this study, radiomics has shown promising results in distinguishing left ventricle hypertrophy caused by CA from AS and might be used as non-invasive tool able to support clinical decision making