Related Experiment Video
Updated: Jun 28, 2026
Using Retinal Imaging to Study Dementia
Published on: November 6, 2017
Deep learning algorithms for timely diagnosis of retinopathy of prematurity requiring treatment
Nasser Shoeibi1, Nafise Ameri2, Mohammad Reza Hoseinkhani3
1Eye Research Center, Mashhad University of Medical Sciences, Mashhad, Iran.
Insights
Deep learning (DL) algorithms show promise for diagnosing Retinopathy of Prematurity (ROP). MobileNet with CLAHE preprocessing achieved high accuracy and sensitivity for ROP detection in telemedicine screenings.
Area of Science:
- Ophthalmology
- Medical Imaging
- Artificial Intelligence
Background:
- Retinopathy of Prematurity (ROP) is a leading cause of vision impairment in preterm infants.
- Early diagnosis and treatment are crucial to prevent severe visual outcomes.
- Telemedicine systems offer a potential solution for ROP screening in remote or underserved areas.
Purpose of the Study:
- To evaluate the effectiveness of deep learning (DL) algorithms for diagnosing treatment-requiring Retinopathy of Prematurity (ROP).
- To assess the performance of various convolutional neural network (CNN) models using fundus images from a telemedicine consultation system.
Main Methods:
- A retrospective cross-sectional study analyzed 1700 RetCam fundus images from 141 preterm infants.
- Image preprocessing techniques included Contrast Limited Adaptive Histogram Equalisation (CLAHE) and Automated Multiscale Retinex (AMSR).
- Evaluated CNN models: MobileNet, ResNet-18, ResNet-50, and DenseNet-121, using accuracy, sensitivity, specificity, and F1-score.
Main Results:
- MobileNet with CLAHE preprocessing achieved the highest accuracy (91.39%) and sensitivity (94.90%) for ROP detection.
- DenseNet-121 with CLAHE showed high sensitivity (94.26%) and accuracy (90.98%).
- ResNet-50 with AMSR demonstrated strong performance with 90.58% accuracy and 91.44% sensitivity.
Conclusions:
- Deep learning models, particularly MobileNet with CLAHE, are effective for diagnosing treatment-requiring ROP.
- These findings support the feasibility of AI-assisted ROP screening in telemedicine settings.
- Further validation in diverse clinical environments is recommended to confirm real-world applicability.
Background/Objectives:
To evaluate the effectiveness of deep learning (DL) algorithms in diagnosing Retinopathy of Prematurity (ROP) cases that requires treatment using fundus images submitted to the ROP clinic as part of a telemedicine consultation system.
Subjects/Methods:
This retrospective cross-sectional study analysed 1700 RetCam fundus images from 141 preterm infants screened for ROP at Khatam-Al-Anbia Eye Hospital. The images underwent preprocessing using Contrast Limited Adaptive Histogram Equalisation (CLAHE), Automated Multiscale Retinex (AMSR), and a machine learning-based optimisation approach (ML). Various convolutional neural network (CNN) models such as MobileNet, ResNet-18, ResNet-50, and DenseNet-121, were evaluated for their diagnostic performance utilising accuracy, sensitivity, specificity, and F1-score metrics.
Results:
Among the models tested, MobileNet with CLAHE preprocessing achieved the highest accuracy (91.39%) and sensitivity (94.90%), establishing it as the most effective model for ROP detection. DenseNet-121 with CLAHE preprocessing showcased high sensitivity (94.26%) but slightly lower accuracy (90.98%). Additionally, ResNet-50 with AMSR preprocessing also demonstrated high accuracy (90.58%) and sensitivity (91.44%). These findings underscore the feasibility of DL models for real-time ROP screening in telemedicine environments.
Conclusion:
MobileNet with CLAHE preprocessing exhibited the highest diagnostic performance in identifying treatment-requiring ROP, positioning it as a promising tool for AI-assisted screening. Further validation in varied clinical settings is necessary to confirm its real-world applicability.
