Grading prenatal hydronephrosis severity
| Article DOI | https://doi.org/10.1016/j.eswa.2024.124594 |
| Objective | To automate the grading of prenatal hydronephrosis severity from kidney ultrasounds |
| AI Approach | CNN |
| Data Source(s) | Single institutional series (163 patients, 2062 images) |
| Model Input | Renal ultrasound images (512×512) |
| Model Outcome | Severity classification |
| Model Metrics | Accuracy 94%, precision 94%, recall 94%, specificity 89%, F1 0.94 |
| Model Usability | Dataset available upon request to authors. |
AI = Artificial intelligence, CNN = Convolutional Neural Network
AIPEDURO 
Leave a comment