DataSheet_1.doc

Abstract

Purpose: The intent of this study was to develop and verify a multi-phase (MP) CT-based radiomics nomogram to differentiate pancreatic serous cystic neoplasms (SCNs) from mucinous cystic neoplasms (MCNs), and to compare the diagnostic efficacy of radiomics models for different phases of CT scans. Materials and Methods: A total of 170 patients who had surgical resection between January 2011 and December 2018, with pathologically confirmed pancreatic cystic neoplasms (SCN=115, MCN=55) were included in this single-center retrospective study. Radiomics features were extracted from plain scan (PS), arterial phase (AP), and venous phase (VP) CT scans. Algorithms were performed to identify the optimal features to build a radiomics signature (Radscore) for each phase. All features from the three phases were analyzed to develop the MP-Radscore. A combined model was then constructed, consisting of the MP-Radscore and imaging features from which a nomogram was developed. The accuracy of the nomogram was evaluated utilizing ROC curves, calibration test and decision curve analysis. Results: For each scan phase, 1218 features were extracted, the optimal features were selected to construct the PS-Radscore (11 features), AP-Radscore (11 features) and VP-Radscore (12 features), respectively. The MP-Radscore (14 features) achieved better performance by ROC curves (AUC: area under the curve) than any single phase (AUC, training cohort: MP-Radscore 0.89, PS-Radscore 0.78, AP-Radscore 0.83, VP-Radscore 0.85; validation cohort: MP-Radscore 0.88, PS-Radscore 0.77, AP-Radscore 0.83, VP-Radscore 0.84). The combination nomogram performance was excellent, surpassing all others in both the training cohort (AUC, 0.91) and validation cohort (AUC, 0.90). The nomogram also performed well in calibration test and decision curve analysis. Conclusions: The radiomics for arterial and venous single-phase models outperformed the plain scan model. The combination nomogram that incorporates the MP-Radscore, tumor location and cystic number had the best discriminatory performance, and showed excellent accuracy for differentiating SCN from MCN.