Related Experiment Video
Updated: Jan 5, 2026
An Acute Retinal Model for Evaluating Blood Retinal Barrier Breach and Potential Drugs for Treatment
Published on: September 13, 2016
New grading criterion for retinal haemorrhages in term newborns based on deep convolutional neural networks
Jianbo Mao1, Yuhao Luo2, Kun Chen2
1Eye Hospital of Wenzhou Medical University, Wenzhou Medical University, Wenzhou, China.
Background:
To define a new quantitative grading criterion for retinal haemorrhages in term newborns based on the segmentation results of a deep convolutional neural network.
Methods:
We constructed a dataset of 1543 retina images acquired from 847 term newborns, and developed a deep convolutional neural network to segment retinal haemorrhages, blood vessels and optic discs and locate the macular region. Based on the ratio of areas of retinal haemorrhage to optic disc, and the location of retinal haemorrhages relative to the macular region, we defined a new criterion to grade the degree of retinal haemorrhages in term newborns.
Results:
The F1 scores of the proposed network for segmenting retinal haemorrhages, blood vessels and optic discs were 0.84, 0.73 and 0.94, respectively. Compared with two commonly used retinal haemorrhage grading criteria, this new method is more accurate, objective and quantitative, with the relative location of the retinal haemorrhages to the macula as an important factor.
Conclusions:
Based on a deep convolutional neural network, we can segment retinal haemorrhages, blood vessels and optic disc with high accuracy. The proposed grading criterion considers not only the area of the haemorrhages but also the locations relative to the macular region. It provides a more objective and comprehensive evaluation criterion. The developed deep convolutional neural network offers an end-to-end solution that can assist doctors to grade retinal haemorrhages in term newborns.
