Comprehensive Radiomics Analysis for Predicting Benign and Malignant Intraductal Papillary Mucinous Neoplasms (IPMNs) of the Pancreas: Integrating Clinical and Imaging Data

Abstract Purpose:The primary aim of this investigation was to leverage radiomics derived from contrast-enhanced abdominal computed tomography (CT) scans to devise a predictive model adept at discerning the benign and malignant of IPMNs. Material and Methods: Radiomic signatures were meticulously crafted to delineate benign from malignant IPMNs by extracting pertinent features from contrast-enhanced CT images within a designated training cohort (n = 84). Subsequent validation was conducted on an independent test cohort (n = 37). The efficacy of the model's discriminative capability was quantitatively evaluated through receiver operating characteristic (ROC) analysis, with an integration of carefully selected clinical features to enhance comparative analysis. Results:The arterial phase images were utilized to construct a model comprising 8 features for distinguishing between benign and malignant cases. The model achieved an accuracy of 0.891 [95% confidence interval (95% CI), 0.816–0.996] in the cross-validation set and 0.553 (95% CI, 0.360-0.745) in the test set. Conversely, employing 9 features from the venous phase resulted in a model with a cross-validation accuracy of 0.862 (95%CI, 0.777-0.946) and a test set accuracy of 0.801 (95% CI, 0.653-0.950).Integrating the identified clinical features with image features yielded a model with a cross-validation accuracy of 0.934 (95% CI, 0.879-0.990) and a test set accuracy of 0.904 (95% CI, 0.808-0.999), thereby further enhancing its discriminatory capability. Conclusion:Our findings distinctly illustrate that venous phase radiomics eclipses arterial phase radiomics in terms of predictive accuracy regarding the nature of IPMN. Furthermore, the synthesis and meticulous screening of clinical features with radiomic data significantly amplify the diagnostic efficacy of our model, underscoring the pivotal importance of a comprehensive and integrated approach for accurate risk stratification in IPMN management.