Automated detection of early-stage ROP using a deep convolutional neural network.
Journal:
The British journal of ophthalmology
PMID:
32830123
Abstract
BACKGROUND/AIM: To automatically detect and classify the early stages of retinopathy of prematurity (ROP) using a deep convolutional neural network (CNN).
Authors
Keywords
Algorithms
Birth Weight
Cross-Sectional Studies
Diagnosis, Computer-Assisted
Female
Gestational Age
Humans
Image Processing, Computer-Assisted
Infant, Low Birth Weight
Infant, Newborn
Infant, Premature
Male
Neural Networks, Computer
Retinopathy of Prematurity
Retrospective Studies
ROC Curve
Sensitivity and Specificity