AIPEDURO

Erdman et al. (2020)

April 28, 2024

Written by:

Hydronephrosis

Article DOI	https://doi.org/10.1007/978-3-030-59716-0_47
Objective	To predict obstructive hydronephrosis requiring surgery from renal ultrasounds in children with prenatal hydronephrosis
AI Approach	CNN
Data Source(s)	Institutional series (294 patients, 1645 sonographic images)
Model Input	256 x 256 pixel images of renal ultrasound
Model Outcome	Requiring surgery
Model Metrics	AUROC = 0.93, accuracy = 58%
Model Usability	NA

AI = Artificial Intelligence, AUROC = Area-under-the-receiver-operator-characteristic, CNN = Convolutional neural network