Artificial intelligence can help individualize Wilms tumor treatment by predicting tumor response to preoperative chemotherapy.

PURPOSE

To create a computer-aided prediction (CAP) system to predict Wilms tumor (WT) responsiveness to preoperative chemotherapy (PC) using pre-therapy contrast-enhanced computed tomography (CECT).

MATERIALS AND METHODS

A single-center database was reviewed for children <18 years diagnosed with WT and received PC between 2001 and 2021. Patients were excluded if pre- and post-PC CECT were not retrievable. According to the Response Evaluation Criteria in Solid Tumors criteria, volumetric response was considered favorable if PC resulted in ≥30% tumor volume reduction. Histological response was considered favorable if post-nephrectomy specimens had ≥66% necrosis. Four steps were used to create the prediction model: tumor delineation; extraction of shape, texture and functionality-based features; integration of the extracted features and selection of the prediction model with the highest diagnostic performance. K-fold cross-validation allowed the presentation of all data in the training and testing phases.

RESULTS

A total of 63 tumors in 54 patients were used to train and test the prediction model. Patients were treated with 4-8 weeks of vincristine/actinomycin-D combination. Favorable volumetric and histologic responses were achieved in 46 tumors (73.0%) and 38 tumors (60.3%), respectively. Among machine learning classifiers, support vector machine had the best diagnostic performance with an accuracy, sensitivity, and specificity of 95.24%, 95.65%, and 94.12% for volumetric and 84.13%, 89.47%, 88% for histologic response prediction.

CONCLUSIONS

Based on pre-therapy CECT, CAP systems can help identify WT that are less likely to respond to PC with excellent accuracy. These tumors can be offered upfront surgery, avoiding the cons of PC.