Differentiation of early relapse and late relapse in intermediate- and high-risk neuroblastoma with an ¹⁸F-FDG PET/CT-based radiomics nomogram

To develop and validate an ¹⁸F-FDG PET/CT-based radiomics nomogram for differentiating early relapse and late relapse of intermediate- and high-risk neuroblastoma (NB).

A total of eighty-five patients with relapsed NB who underwent ¹⁸F-FDG PET/CT were retrospectively evaluated. All selected patients were randomly assigned to the training set and the validation set in a 7:3 ratio. Tumors were segmented using the 3D slicer, followed by radiomics features extraction. Features selection was performed using random forest, and the radiomics score was constructed by logistic regression analysis. Clinical risk factors were identified, and the clinical model was constructed using logistic regression analysis. A radiomics nomogram was constructed by combining the radiomics score and clinical risk factors, and its performance was evaluated by receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA).

Finally, the 12 most important radiomics features were used for modeling, with an area under the curve (AUC) of 0.835 and 0.824 in the training and validation sets, respectively. Age at diagnosis and International Neuroblastoma Pathology Classification were determined as clinical risk factors to construct the clinical model. In addition, the nomogram achieved an AUC of 0.902 and 0.889 for identifying early relapse in the training and validation sets, respectively, which is higher than the clinical model (AUC of 0.712 and 0.588, respectively). The predicted early relapse and actual early relapse in the calibration curves were in good agreement. The DCA showed that the radiomics nomogram was clinically useful.

Our ¹⁸F-FDG PET/CT-based radiomics nomogram can well predict early relapse and late relapse of intermediate- and high-risk NB, which contributes to follow-up and management in clinical practice.