Wilms tumor versus others with radiomics
| Article DOI | https://dx.doi.org/10.1007/s00330-024-10589-8 |
| Objective | To build a classifier for the preoperative differentiation of Wilms tumor vs adrenal neuroblastoma in pediatric abdominal CT |
| AI Approach | SVM, RF |
| Data Source(s) | Single institutional series (147 patients) |
| Model Input | 1218 features from contrast-enhanced abdominal CT, Age, gender, symptoms/signs, metastasis |
| Model Outcome | Wilms tumor vs. neuroblastoma |
| Model Metrics | Combined (radiomics + clinical) model, mean F1 0.94, AUC 0.96 |
| Model Usability | Code publicly available at https://github.com/ozgurkoska78/wt_nb. Dataset not publicly available. |
AI = Artificial intelligence, CT = Computed tomography, AUC = Area under the receiver operator characteristic
AIPEDURO 
Leave a comment