Related Experiment Video
Updated: Dec 12, 2025
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
Automated identification of retinopathy of prematurity by image-based deep learning
Yan Tong1, Wei Lu1, Qin-Qin Deng1
1Eye Center, Renmin Hospital of Wuhan University, Wuhan, 430060 Hubei China.
Insights
This study developed an AI system for diagnosing retinopathy of prematurity (ROP) from fundus images, achieving high accuracy comparable to human experts. The system aids in early detection and treatment of this leading cause of childhood blindness.
Area of Science:
- Ophthalmology
- Medical Imaging
- Artificial Intelligence
Background:
- Retinopathy of prematurity (ROP) is a significant cause of childhood blindness globally.
- Timely diagnosis and treatment are crucial for managing ROP.
- Automated systems can aid in ROP diagnosis and treatment planning.
Purpose of the Study:
- To develop a deep learning-based intelligent system for automated ROP diagnosis.
- To classify ROP severity, detect ROP stage, and identify plus disease from fundus images.
- To enable automated diagnosis and support clinical decisions for ROP.
Main Methods:
- Utilized a dataset of 36,231 fundus images labeled by 13 retinal experts.
- Trained a 101-layer ResNet and a Faster R-CNN for image classification and object detection.
- Employed 10-fold cross-validation and evaluated performance using accuracy, sensitivity, and specificity.
Main Results:
- The system achieved 0.903 accuracy for ROP severity classification.
- Accuracies for normal, mild, semi-urgent, and urgent ROP were 0.883, 0.900, 0.957, and 0.870.
- Achieved 0.957 accuracy for ROP stage detection and 0.896 for plus disease detection.
Conclusions:
- The developed system accurately detects ROP and classifies its severity from fundus images.
- The system's performance is comparable to or exceeds that of human experts.
- This intelligent system can serve as a valuable tool for supporting clinical decisions in ROP management.
Background:
Retinopathy of prematurity (ROP) is a leading cause of childhood blindness worldwide but can be a treatable retinal disease with appropriate and timely diagnosis. This study was performed to develop a robust intelligent system based on deep learning to automatically classify the severity of ROP from fundus images and detect the stage of ROP and presence of plus disease to enable automated diagnosis and further treatment.
Methods:
A total of 36,231 fundus images were labeled by 13 licensed retinal experts. A 101-layer convolutional neural network (ResNet) and a faster region-based convolutional neural network (Faster-RCNN) were trained for image classification and identification. We applied a 10-fold cross-validation method to train and optimize our algorithms. The accuracy, sensitivity, and specificity were assessed in a four-degree classification task to evaluate the performance of the intelligent system. The performance of the system was compared with results obtained by two retinal experts. Moreover, the system was designed to detect the stage of ROP and presence of plus disease as well as to highlight lesion regions based on an object detection network using Faster-RCNN.
Results:
The system achieved an accuracy of 0.903 for the ROP severity classification. Specifically, the accuracies in discriminating normal, mild, semi-urgent, and urgent were 0.883, 0.900, 0.957, and 0.870, respectively; the corresponding accuracies of the two experts were 0.902 and 0.898. Furthermore, our model achieved an accuracy of 0.957 for detecting the stage of ROP and 0.896 for detecting plus disease; the accuracies in discriminating stage I to stage V were 0.876, 0.942, 0.968, 0.998 and 0.999, respectively.
Conclusions:
Our system was able to detect ROP and differentiate four-level classification fundus images with high accuracy and specificity. The performance of the system was comparable to or better than that of human experts, demonstrating that this system could be used to support clinical decisions.
