UPJO from ultrasounds images, Hydronephrosis.
| Article DOI | http://dx.doi.org/10.1109/CRV.2018.00021 |
| Objective | To diagnose and grade ureteropelvic junction obstruction from ultrasound images |
| AI Approach | Segmentation and CNN |
| Data Source(s) | Single institutional series (229 patients, 3289 ultrasound images) |
| Model Input | 810 x 608 pixels transverse and coronal section renal US images |
| Model Outcome | Hydronephrosis from UPJO SFU Grade |
| Model Metrics | AUC grade 0-2: 0.98 AUC grade 3: 0.90 AUC grade 4: 0.97 |
| Model Usability | NA |
AI = Artificial intelligence, SFU = Society for Fetal Urology, CNN = Convolutional Neural Network
AIPEDURO 
Leave a comment