Rationale and objectivesTo investigate whether computed tomography features can differentiate pancreatoblastoma (PB) from solid pseudopapillary tumor (SPN) in children. Materials and methodsClinical and imaging data of 18 cases of PB and 61 cases of SPN confirmed by surgery or biopsy were retrospectively analyzed. All enrolled patients underwent 3 phases (non-contrast, arterial, and portal venous phases) of CT scanning. Qualitative CT analysis (location, margin, solid/cystic component proportion, calcification, hemorrhage, peritumoral vascularity, bile duct dilatation, pancreatic duct dilatation, pancreatic atrophy, vascular invasion, peripancreatic invasion, and distant metastases) and quantitative analysis (maximum tumor diameter, interface between tumor and parenchyma [delta], arterial enhancement ratio [AER], and portal enhancement ratio [PER]) were performed. The general CT morphologic features, age and tumor markers were compared also compared between the groups. Univariate analysis and the F test were conducted to identify features of PB. Then logistic Regression classifier was trained using the top five features with the highest F-value. Moreover, we used 5-fold cross-validation techniques for the validation of our model. ResultsPB exhibited a significantly higher frequency of location in the body/tail, larger tumor size, poorly defined margins, calcification, peritumoral vascularity, pancreatic atrophy, and less hemorrhage. In addition, PB had higher AER, PER and lower delta relative to SPN (p < 0.05). PB presented a younger age and higher levels of AFP. Results of the F test indicated that AFP, AER, Age, calcification and pancreatic atrophy were the top five features included in the model that could differentiate pediatric PB from SPN. The combined model of CT and clinical features performed well in differentiating PB from SPN, with an AUC of 0.981 in the training cohort and 0.953 in the validation cohort. ConclusionsAFP, AER, age, calcification and pancreatic atrophy are robust CT and clinical features for differentiating pediatric PB from SPN. A combination of qualitative and quantitative CT features may provide good diagnostic accuracy in differentiating PB from SPN in children.
Read full abstract