This repository contains the codes for our study involving an end-to-end deep machine learning framework developed to sequentially detect ultrasound regions of interest, segment kidneys from US images, and classify Antenatal or Prenatal Hydronephrosis (AHN) severity.
In this phase, we segment or localize the kidney regions from preprocessed Ultrasound (US) images using 2D-segmentation networks e.g., UNet.
In this phase, we classify the severity of AHN based on segmented kidney regions from Phase 1.