Retinopathy of prematurity (ROP) represents a vasoproliferative disease, especially in newborns and infants, which can potentially affect and damage the vision. Despite recent advances in neonatal care and medical guidelines, ROP still remains one of the leading causes of worldwide childhood blindness. The paper presents a unique dataset of 6,004 retinal images of 188 newborns, most of whom are premature infants. The dataset is accompanied by the anonymized patients' information from the ROP screening acquired at the University Hospital Ostrava, Czech Republic. Three digital retinal imaging camera systems are used in the study: Clarity RetCam 3, Natus RetCam Envision, and Phoenix ICON. The study is enriched by the software tool ReLeSeT which is aimed at automatic retinal lesion segmentation and extraction from retinal images. Consequently, this tool enables computing geometric and intensity features of retinal lesions. Also, we publish a set of pre-processing tools for feature boosting of retinal lesions and retinal blood vessels for building classification and segmentation models in ROP analysis.

University Hospital Ostrava Clinic of Ophthalmology Ostrava 708 52 Czech Republic

University of Ostrava Faculty of Medicine Department of Craniofacial Surgery Ostrava 703 00 Czech Republic

VSB Technical University of Ostrava Faculty of Electrical Engineering and Computer Science Department of Computer Science Ostrava 708 00 Czech Republic

VSB Technical University of Ostrava Faculty of Electrical Engineering and Computer Science Department of Cybernetics and Biomedical Engineering Ostrava 708 00 Czech Republic

Zobrazit více v PubMed

Ludwig, C. A., Chen, T. A., Hernandez-Boussard, T., Moshfeghi, A. A. & Moshfeghi, D. M. The epidemiology of retinopathy of prematurity in the united states. Ophthalmic surgery, lasers & imaging retina48, 553 (2017).10.3928/23258160-20170630-06 PubMed DOI

Thomas, K. et al. Retinopathy of prematurity: risk factors and variability in canadian neonatal intensive care units. Journal of neonatal-perinatal medicine8, 207–214 (2015). 10.3233/NPM-15814128 PubMed DOI

Khan, S. M. et al. A global review of publicly available datasets for ophthalmological imaging: barriers to access, usability, and generalisability. The Lancet Digital Health3, e51–e66 (2021). 10.1016/S2589-7500(20)30240-5 PubMed DOI

Fusek, R. Pupil localization using geodesic distance. In Advances in Visual Computing: 13th International Symposium, ISVC 2018, Las Vegas, NV, USA, November 19–21, 2018, Proceedings 13, 433–444 (Springer, 2018).

Ryan, M. C. et al. Development and evaluation of reference standards for image-based telemedicine diagnosis and clinical research studies in ophthalmology. In AMIA annual symposium proceedings, vol. 2014, 1902 (American Medical Informatics Association, 2014). PubMed PMC

Imaging and informatics in retinopathy of prematurity. https://i-rop.github.io/index.html (accessed: 2021-09-16).

Shahrawat, M. Understanding the biomarkers of retinal disease using deep learning. Ph.D. thesis, Massachusetts Institute of Technology (2019).

Ataer-Cansizoglu, E. et al. Computer-based image analysis for plus disease diagnosis in retinopathy of prematurity: performance of the “i-rop” system and image features associated with expert diagnosis. Translational vision science & technology4, 5–5 (2015).10.1167/tvst.4.6.5 PubMed DOI PMC

Worrall, D. E., Wilson, C. M. & Brostow, G. J. Automated retinopathy of prematurity case detection with convolutional neural networks. In Deep learning and data labeling for medical applications, 68–76 (Springer, 2016).

Yildiz, V. M. et al. Plus disease in retinopathy of prematurity: convolutional neural network performance using a combined neural network and feature extraction approach. Translational Vision Science & Technology9, 10–10 (2020).10.1167/tvst.9.2.10 PubMed DOI PMC

Ding, A., Chen, Q., Cao, Y. & Liu, B. Retinopathy of prematurity stage diagnosis using object segmentation and convolutional neural networks. In 2020 International Joint Conference on Neural Networks (IJCNN), 1–6 (IEEE, 2020).

Walz, J. M. et al. The german rop registry: data from 90 infants treated for retinopathy of prematurity. Acta ophthalmologica94, e744–e752 (2016). 10.1111/aos.13069 PubMed DOI

Hong, E. H. et al. Nationwide incidence and treatment pattern of retinopathy of prematurity in south korea using the 2007–2018 national health insurance claims data. Scientific reports11, 1–10 (2021). PubMed PMC

Wang, J. et al. Automated retinopathy of prematurity screening using deep neural networks. EBioMedicine35, 361–368 (2018). 10.1016/j.ebiom.2018.08.033 PubMed DOI PMC

Chiang, M. F. et al. Telemedical retinopathy of prematurity diagnosis: accuracy, reliability, and image quality. Archives of ophthalmology125, 1531–1538 (2007). 10.1001/archopht.125.11.1531 PubMed DOI

Tian, P. et al. A severity score for retinopathy of prematurity. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 1809–1819 (2019).

Tong, Y., Lu, W., Deng, Q.-q, Chen, C. & Shen, Y. Automated identification of retinopathy of prematurity by image-based deep learning. Eye and Vision7, 1–12 (2020). 10.1186/s40662-020-00206-2 PubMed DOI PMC

Zhang, Y. Dnn classifier of wide-angle retinal images in computer-aided screening for rop, 10.6084/m9.figshare.6367685.v1 (2018).

Zhang, Y. et al. Development of an automated screening system for retinopathy of prematurity using a deep neural network for wide-angle retinal images. Ieee Access7, 10232–10241 (2018).10.1109/ACCESS.2018.2881042 DOI

Huang, Y.-P. et al. Deep learning models for automated diagnosis of retinopathy of prematurity in preterm infants. Electronics9, 1444 (2020).10.3390/electronics9091444 DOI

Bhatkalkar, B., Joshi, A., Prabhu, S. & Bhandary, S. Automated fundus image quality assessment and segmentation of optic disc using convolutional neural networks. International Journal of Electrical & Computer Engineering (2088-8708)10 (2020).

Xu, C. L. et al. Telemedicine retinopathy of prematurity severity score (telerop-ss) versus modified activity score (mrop-acts) retrospective comparison in sundrop cohort. Scientific Reports13, 15219 (2023). 10.1038/s41598-023-42150-w PubMed DOI PMC

Quinn, G. E. et al. Validity of a telemedicine system for the evaluation of acute-phase retinopathy of prematurity. JAMA ophthalmology132, 1178–1184 (2014). 10.1001/jamaophthalmol.2014.1604 PubMed DOI PMC

Tomasi, C. & Manduchi, R. Bilateral filtering for gray and color images. Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271) 839–846, 10.1109/ICCV.1998.710815 (1998).

Wang, L., He, L., Mishra, A. & Li, C. Active contours driven by local gaussian distribution fitting energy. Signal Processing89, 2435–2447, 10.1016/j.sigpro.2009.03.014 (2009).10.1016/j.sigpro.2009.03.014 DOI

Phelps, D. L. Retinopathy of prematurity: history, classification, and pathophysiology. NeoReviews2, e153–e166 (2001).10.1542/neo.2-7-e153 DOI

Visser, L., Singh, R., Young, M. & McKerrow, N. Guideline for the prevention, screening and treatment of retinopathy of prematurity (rop): guideline. South African Medical Journal103, 116–125 (2013).10.7196/SAMJ.6305 PubMed DOI

Wallace, D. K. & Wu, K. Y. Current and future trends in treatment of severe retinopathy of prematurity. Clinics in perinatology40, 297–310 (2013). 10.1016/j.clp.2013.02.005 PubMed DOI

Gole, G. A. et al. The international classification of retinopathy of prematurity revisited. Archives of ophthalmology (Chicago, Ill.: 1960)123, 991–999 (2005). 10.1001/archopht.123.7.991 PubMed DOI

El Din, Z. M. E., El Sada, M. A., Ali, A. A., Al Husseiny, K. & Yousef, A. A. R. Comparison of digital imaging screening and indirect ophthalmoscopy for retinopathy of prematurity. The Indian Journal of Pediatrics82, 80–83 (2015). 10.1007/s12098-014-1525-1 PubMed DOI

Fierson, W. M. et al. Screening examination of premature infants for retinopathy of prematurity. Pediatrics142 (2018). PubMed

Fierson, W. M. et al. Screening examination of premature infants for retinopathy of prematurity. Pediatrics131, 189–195 (2013). 10.1542/peds.2012-2996 PubMed DOI

Good, W. V. Final results of the early treatment for retinopathy of prematurity (etrop) randomized trial. Transactions of the American Ophthalmological Society102, 233 (2004). PubMed PMC

Palmer, E. A. et al. 15-year outcomes following threshold retinopathy of prematurity: final results from the multicenter trial of cryotherapy for retinopathy of prematurity. Archives of ophthalmology123, 311–318 (2005). 10.1001/archopht.123.3.311 PubMed DOI

Timkovic, J. et al. A new modified technique for the treatment of high-risk prethreshold rop under the direct visual control of retcam 3. Biomedical Papers159, 413–416 (2015). 10.5507/bp.2015.027 PubMed DOI

Stahl, A. et al. Ranibizumab versus laser therapy for the treatment of very low birthweight infants with retinopathy of prematurity (rainbow): an open-label randomised controlled trial. The Lancet394, 1551–1559 (2019).10.1016/S0140-6736(19)31344-3 PubMed DOI

Mao, J. et al. New grading criterion for retinal haemorrhages in term newborns based on deep convolutional neural networks. Clinical & Experimental Ophthalmology48, 220–229 (2020). 10.1111/ceo.13670 PubMed DOI

Kubicek, J. et al. Detection and segmentation of retinal lesions in retcam 3 images based on active contours driven by statistical local features. Advances in Electrical and Electronic Engineering17, 194–201, 10.15598/aeee.v17i2.3045 (2019).10.15598/aeee.v17i2.3045 DOI

Justusson, B. Median filtering: Statistical properties. Two-Dimensional Digital Signal Prcessing II: Transforms and Median Filters 161–196 (2006).

Timkovič, J. et al. Retinal image dataset of infants and rop. Figshare10.6084/m9.figshare.c.6626162.v1 (2023).10.6084/m9.figshare.c.6626162.v1 DOI

Timkovič, J. et al. Retinal image dataset of infants and rop. Kagglehttps://www.kaggle.com/datasets/jananowakova/retinal-image-dataset-of-infants-and-rop (2023).

Timkovič, J. et al. Retinal image dataset of infants and rop. GitHubhttps://github.com/JanaNowakova/Retinal-Image-Dataset-of-Infants-and-ROP.git (2023).

Stokowski, L. A. Age terminology during the perinatal period. Advances in Neonatal Care5, 62 (2005).

Chiang, M. F. et al. International classification of retinopathy of prematurity. Ophthalmology128, e51–e68 (2021). 10.1016/j.ophtha.2021.05.031 PubMed DOI PMC

Hasal, M. et al. Retinal vessel segmentation by u-net with vgg-16 backbone on patched images with smooth blending. In International Conference on Intelligent Networking and Collaborative Systems, 465–474 (Springer, 2023).

Kubicek, J. et al. Extraction of optical disc geometrical parameters with using of active snake model with gradient directional information. In Intelligent Information and Database Systems: 9th Asian Conference, ACIIDS 2017, Kanazawa, Japan, April 3–5, 2017, Proceedings, Part II 9, 445–454 (Springer, 2017).

Kubicek, J. et al. Retinal blood vessels modeling based on fuzzy sobel edge detection and morphological segmentation. In Biodevices, 121–126 (2019).

Rochtchina, E., Wang, J. J., Taylor, B., Wong, T. Y. & Mitchell, P. Ethnic variability in retinal vessel caliber: A potential source of measurement error from ocular pigmentation?—the sydney childhood eye study. Investigative ophthalmology & visual science49, 1362, 10.1167/iovs.07-0150 (2008). 10.1167/iovs.07-0150 PubMed DOI

Hasal, M., Nowaková, J., Hernández-Sosa, D. & Timkovič, J. Image enhancement in retinopathy of prematurity. In International Conference on Intelligent Networking and Collaborative Systems, 422–431 (Springer, 2022).

Pizer, S. M. et al. Adaptive histogram equalization and its variations. Computer Vision, Graphics, and Image Processing39, 355–368, 10.1016/S0734-189X(87)80186-X (1987).

Lakshmanan, V., Görner, M. & Gillard, R. Practical Machine Learning for Computer Vision (O’Reilly Media, Inc., 2021).

Hasal, M., Nowaková, J., Hernández-Sosa, D. & Timkovič, J. Image enhancement retinopathy of prematurity. GitHubhttps://github.com/JanaNowakova/Image_enhancement_retinopathy_of_prematurity (2022).

Hasal, M. et al.Retinal vessel segmentation by u-net with vgg-16 Backbone on patched images with smooth blending. GitHubhttps://github.com/MartinHasal/RetinaVesselSeg_tf (2023).

Varyšová, A., Kubíček, J. & Augustynek, M. Releset (retinal lesions segmentation tool). GitHub, https://github.com/alivar123/ReLeSeT-Retinal-Lesions-Segmentation.git (2022).

American academy of opthalmology - retinopathy of prematurity - asia pacific. https://www.aao.org/topic-detail/retinopathy-of-prematurity-asia-pacific (accessed: 2022-09-15).

American academy of opthalmology - retinopathy of prematurity - europe. https://www.aao.org/topic-detail/retinopathy-of-prematurity-europe (accessed: 2022-09-15).

American academy of opthalmology - retinopathy of prematurity - latin america. https://www.aao.org/topic-detail/retinopathy-of-prematurity-latin-america (accessed: 2022-09-15).

American academy of opthalmology - retinopathy of prematurity - middle east/north africa. https://www.aao.org/topic-detail/retinopathy-of-prematurity-middle-eastnorth-afric (accessed: 2022-09-15).

American academy of opthalmology - retinopathy of prematurity - sub-saharan africa. https://www.aao.org/topic-detail/retinopathy-of-prematurity-subsaharan-africa (accessed: 2022-09-15).

Murickan, T. et al. External validation of autonomous retinopathy of prematurity screening in the sundrop program. Investigative Ophthalmology & Visual Science64, 268–268 (2023).

Wang, S. K. et al. Sundrop: six years of screening for retinopathy of prematurity with telemedicine. Canadian Journal of Ophthalmology50, 101–106 (2015). 10.1016/j.jcjo.2014.11.005 PubMed DOI

Wade, K. C. et al. Factors in premature infants associated with low risk of developing retinopathy of prematurity. JAMA ophthalmology137, 160–166 (2019). 10.1001/jamaophthalmol.2018.5520 PubMed DOI PMC

At a glance: Retinopathy of prematurity. https://www.nei.nih.gov/learn-about-eye-health/eye-conditions-and-diseases/retinopathy-prematurity (accessed: 2022-08-17).

Agarwal, K. & Jalali, S. Classification of retinopathy of prematurity: from then till now. Community Eye Health31, S4 (2018). PubMed PMC