Related Experiment Video
Updated: Aug 5, 2025
Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
Published on: May 19, 2023
CT-based identification of pediatric non-Wilms tumors using convolutional neural networks at a single center
Yupeng Zhu1,2, Hailin Li3,4, Yangyue Huang5
1Department of Radiology, MOE Key Laboratory of Major Diseases in Children, Beijing Children's Hospital, Capital Medical University, National Center for Children's Health, Beijing, 100045, China.
Background:
Deep learning (DL) is more and more widely used in children's medical treatment. In this study, we have developed a computed tomography (CT)-based DL model for identifying undiagnosed non-Wilms tumors (nWTs) from pediatric renal tumors.
Methods:
This study collected and analyzed the preoperative clinical data and CT images of pediatric renal tumor patients diagnosed by our center from 2008 to 2020, and established a DL model to identify nWTs noninvasively.
Results:
A total of 364 children who had been confirmed by histopathology with renal tumors from our center were enrolled, including 269 Wilms tumors (WTs) and 95 nWTs. For DL model development, all cases were randomly allocated to training set (218 cases), validation set (73 cases), and test set (73 cases). In the test set, the DL model achieved area under the curve of 0.831 (95% CI: 0.712-0.951) in discriminating WTs from nWTs, with the accuracy, sensitivity, and specificity of 0.781, 0.563, and 0.842, respectively. The sensitivity of our model was higher than a radiologist with 15 years of experience.
Conclusions:
We presented a DL model for identifying undiagnosed nWTs from pediatric renal tumors, with the potential to improve the image-based diagnosis.
Impact:
Deep learning model was used for the first time to identify pediatric renal tumors in this study. Deep learning model can identify non-Wilms tumors from pediatric renal tumors. Deep learning model based on computed tomography images can improve tumor diagnosis rate.
