Multiphasic CT fusion model aids differentiation of pediatric hepatoblastoma from focal nodular hyperplasia

Fusion model on multiphasic CT differentiated pediatric hepatoblastoma from focal nodular hyperplasia with AUC 0.980, accuracy 94.2%, sensitivity 94.9%, specificity 92.9% in 121 children. Model assistance improved junior radiologist accuracy from 88.4% to 95.0% (p=0.0078).

• The DL+QEF model combined the high hepatoblastoma sensitivity of DL-3Phase with the high FNH specificity of the QEF model.
• In reader-defined atypical cases, the model's accuracy was 90.2% vs junior radiologist's 68.3%.
• The model was temporally validated using a chronological split with a separate test set of 121 patients.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.