Related Experiment Video
Updated: Dec 14, 2025
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
Plus Disease in Retinopathy of Prematurity: Convolutional Neural Network Performance Using a Combined Neural Network
Veysi M Yildiz1, Peng Tian1, Ilkay Yildiz1
1Cognitive Systems Laboratory, Northeastern University, Boston, MA, USA.
Insights
A new automated system, I-ROP ASSIST, accurately diagnoses plus disease in retinopathy of prematurity (ROP) using retinal images. This tool achieves performance comparable to convolutional neural networks (CNNs), aiding in early detection of a 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.
- Accurate diagnosis of ROP, particularly 'plus disease' (abnormal retinal vessel dilation and tortuosity), is crucial for timely treatment.
- Current diagnostic methods rely on manual ophthalmoscopic examination or image analysis.
Purpose of the Study:
- To develop and validate I-ROP ASSIST, a publicly available, feature-extraction-based pipeline for diagnosing plus disease in ROP.
- To achieve diagnostic performance comparable to convolutional neural networks (CNNs) using automated feature extraction.
- To provide an objective and automated tool for ROP diagnosis.
Main Methods:
- Development of two retinal image datasets (100 and 5512 images).
- Automated retinal vessel segmentation, centerline detection, and extraction of ROP-relevant features (tortuosity, dilation).
- Classification using logistic regression, support vector machines, and neural networks, evaluated with fivefold cross-validation and AUC.
Main Results:
- AUC of 99% and 94% for plus vs. not-plus prediction on the two datasets.
- AUC of 99% and 88% for pre-plus or worse vs. normal prediction on the two datasets.
- Comparable performance to CNNs (98% and 94% AUC for two categories on the second dataset).
Conclusions:
- The I-ROP ASSIST pipeline effectively diagnoses plus disease in ROP through automated vessel analysis and feature classification.
- The system demonstrates CNN-like performance, offering a reliable automated diagnostic solution.
- High performance indicates strong potential for automated, objective diagnosis of plus disease in clinical settings.
Purpose:
Retinopathy of prematurity (ROP), a leading cause of childhood blindness, is diagnosed by clinical ophthalmoscopic examinations or reading retinal images. Plus disease, defined as abnormal tortuosity and dilation of the posterior retinal blood vessels, is the most important feature to determine treatment-requiring ROP. We aimed to create a complete, publicly available and feature-extraction-based pipeline, I-ROP ASSIST, that achieves convolutional neural network (CNN)-like performance when diagnosing plus disease from retinal images.
Methods:
We developed two datasets containing 100 and 5512 posterior retinal images, respectively. After segmenting retinal vessels, we detected the vessel centerlines. Then, we extracted features relevant to ROP, including tortuosity and dilation measures, and used these features in the classifiers including logistic regression, support vector machine and neural networks to assess a severity score for the input. We tested our system with fivefold cross-validation and calculated the area under the curve (AUC) metric for each classifier and dataset.
Results:
For predicting plus versus not-plus categories, we achieved 99% and 94% AUC on the first and second datasets, respectively. For predicting pre-plus or worse versus normal categories, we achieved 99% and 88% AUC on the first and second datasets, respectively. The CNN method achieved 98% and 94% for predicting two categories on the second dataset.
Conclusions:
Our system combining automatic retinal vessel segmentation, tracing, feature extraction and classification is able to diagnose plus disease in ROP with CNN-like performance.
Translational Relevance:
The high performance of I-ROP ASSIST suggests potential applications in automated and objective diagnosis of plus disease.