Machine Learning Applications in Retinopathy of Prematurity Diagnosis Using the ROP Retinal Image Dataset
DOI:
https://doi.org/10.52783/jns.v14.1607Keywords:
Retinopathy of Prematurity, Machine Learning, Random Forest, Neonatal Screening, Artificial IntelligenceAbstract
Purpose: Retinopathy of Prematurity (ROP) is a leading cause of childhood blindness, particularly in preterm infants. This study aims to evaluate the performance of machine learning (ML) models for ROP diagnosis using a publicly available retinal image dataset.
Methods: The study utilized the Retinal Image Dataset of Infants and Retinopathy of Prematurity (ROP) from the University Hospital Ostrava, Czech Republic. The dataset comprised 6,004 retinal images and clinical metadata, including gestational age, birth weight, and diagnosis codes. Two ML models, Random Forest and Subspace Discriminant, were implemented. Preprocessing included metadata normalization and stratified sampling into training and testing sets. Model evaluation metrics included accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC).
Results: The Random Forest model achieved an accuracy of 78.62%, sensitivity of 100%, and specificity of 92.21%, indicating strong performance in predicting ROP diagnoses. In contrast, the Subspace Discriminant model underperformed, with an accuracy of 26.90% and no reliable predictions. Feature importance analysis identified gestational age and device type as key predictors.
Conclusion: The Random Forest model demonstrated significant potential for automated ROP diagnosis. Future research should explore multimodal data integration, larger balanced datasets, and advanced deep learning models to enhance predictive accuracy and clinical applicability.
Downloads
Metrics
References
Aiello, L. P., Northrup, J. M., Keyt, B. A., et al. (1995). Hypoxic regulation of vascular endothelial growth factor in retinal cells. Archives of Ophthalmology, 113(12), 1538–1544.
Alon, T., Hemo, I., Itin, A., Pe’er, J., Stone, J., & Keshet, E. (1995). Vascular endothelial growth factor acts as a survival factor for newly formed retinal vessels and has implications for retinopathy of prematurity. Nature Medicine, 1(10), 1024–1028. https://doi.org/10.1038/nm1095-1024
Blencowe, H., Lawn, J. E., Vazquez, T., Fielder, A., & Gilbert, C. (2013). Preterm-associated visual impairment and estimates of retinopathy of prematurity at regional and global levels for 2010. Pediatric Research, 74(1), 35–49. https://doi.org/10.1038/pr.2013.60
Chen, J., & Smith, L. E. H. (2007). Retinopathy of prematurity. Angiogenesis, 10(2), 133–140. https://doi.org/10.1007/s10456-007-9066-0
Darlow, B. A., & Gilbert, C. E. (2013). Retinopathy of prematurity – A world update. Seminars in Perinatology, 37(2), 109–118. https://doi.org/10.1053/j.semperi.2013.02.004
Flynn, J. T. (1983). Acute proliferative retrolental fibroplasia: Multivariate risk analysis. Transactions of the American Ophthalmological Society, 81, 549–591.
Flynn, J. T., & Chan-Ling, T. (2006). Retinopathy of prematurity: Two distinct mechanisms that underlie zone 1 and zone 2 disease. American Journal of Ophthalmology, 142(1), 46–59. https://doi.org/10.1016/j.ajo.2006.02.053
García, H., Villasis-Keever, M. A., Zavala-Vargas, G., Bravo-Ortiz, J. C., Pérez-Méndez, A., & Escamilla-Núñez, A. (2024). Global prevalence and severity of retinopathy of prematurity over the last four decades (1985–2021): A systematic review and meta-analysis. Archives of Medical Research, 55(2), 102967. https://doi.org/10.1016/j.arcmed.2024.102967
Gilbert, C. (2008). Retinopathy of prematurity: A global perspective of the epidemics, population of babies at risk, and implications for control. Early Human Development, 84(2), 77–82. https://doi.org/10.1016/j.earlhumdev.2007.11.009
Gilbert, C., Fielder, A., Gordillo, L., et al. (2008). Characteristics of infants with severe retinopathy of prematurity in countries with low, moderate, and high levels of development: Implications for screening programs. Pediatrics, 115(5), e518–e525. https://doi.org/10.1542/peds.2007-2444
Hasal, M., Nowaková, J., Hernández-Sosa, D., & Timkovič, J. (2022). Image Enhancement in Retinopathy of Prematurity. Lecture Notes in Networks and Systems, 527, 215–228. https://doi.org/10.1007/978-3-031-14627-5_43
Hasal, M., Pecha, M., Nowaková, J., Hernández-Sosa, D., Snášel, V., & Timkovič, J. (2023). Retinal Vessel Segmentation by U-Net with VGG-16 Backbone on Patched Images with Smooth Blending. Lecture Notes on Data Engineering and Communications Technologies, 182, 145–158. https://doi.org/10.1007/978-3-031-40971-4_44
Hellström, A., Perruzzi, C., Ju, M., et al. (2001). Low IGF-I suppresses VEGF-survival signaling in retinal endothelial cells: Direct correlation with clinical retinopathy of prematurity. Proceedings of the National Academy of Sciences, 98(10), 5804–5808. https://doi.org/10.1073/pnas.101113998
Jalali, S., Matalia, J., Hussain, A., & Anand, R. (2006). Modification of screening criteria for retinopathy of prematurity in India and other middle-income countries. American Journal of Ophthalmology, 141(5), 966–968. https://doi.org/10.1016/j.ajo.2005.11.016
Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. MICCAI 2015, 234–241. https://doi.org/10.1007/978-3-319-24574-4_28
Smith, L. E. H., Shen, W., Perruzzi, C., et al. (1999). Regulation of vascular endothelial growth factor-dependent retinal neovascularization by insulin-like growth factor-1 receptor. Nature Medicine, 5(12), 1390–1395. https://doi.org/10.1038/70954
Terry, T. L. (1942). Extreme prematurity and fibroblastic overgrowth of persistent vascular sheath behind each crystalline lens: I. Preliminary report. American Journal of Ophthalmology, 25(2), 203–204.
Timkovič, J., Nowaková, J., Kubíček, J., et al. (2024). Retinal Image Dataset of Infants and Retinopathy of Prematurity. Scientific Data, 11(814). https://doi.org/10.1038/s41597-024-03409-7
Vinekar, A., Dogra, M. R., Sangtam, T., Narang, A., & Gupta, A. (2007). Retinopathy of prematurity in Asian Indian babies weighing greater than 1250 grams at birth: Ten-year data from a tertiary care center in a developing country. Indian Journal of Ophthalmology, 55(5), 331–336. https://doi.org/10.4103/0301-4738.33821
Vinekar, A., Gilbert, C., Dogra, M., et al. (2014). The KIDROP model of combining strategies for providing retinopathy of prematurity screening in underserved areas in India using wide-field imaging, telemedicine, non-physician graders and smartphone reporting. Indian Journal of Ophthalmology, 62(1), 41–49. https://doi.org/10.4103/0301-4738.126179
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
