Abstract
Retinal image quality assessment (RIQA) is one of the key components in screening for diabetic retinopathy (DR). As one of the most serious complications of diabetes, DR has become a leading cause of blindness in adults globally. DR screening is essential to achieve early diagnosis so that effective treatment could be provided timely. However, the collected images of medically unsatisfactory quality always lead to failure of diagnosis and waste of ophthalmologists’ precious time. Hence, the first step in a good DR screening program is verifying retinal images of good quality. In this paper, we provide a systematic review on automated assessment of retinal image quality for DR screening. Scheme and parameters for RIQA are firstly presented. Next, we provide detailed understanding of the existing RIQA techniques, algorithms and methodologies, including brief description and analysis of each existing state-of-art approaches and comparison between such methods. Datasets and evaluation metrics are also illustrated. Finally, several challenges and future research directions are summarized and discussed.
Similar content being viewed by others
References
Abdel-Hamid L, El-Rafei A, El-Ramly S, Michelson G, Hornegger J (2016) Retinal image quality assessment based on image clarity and content. J Biomed Opt 21(9):096007
Abdel-Hamid L, El-Rafei A, Michelson G (2017) No-reference quality index for color retinal images. Comput Biol Med 90:68–75
Bartling H, Wanger P, Martin L (2009) Automated quality evaluation of digital fundus photographs. Acta Ophthalmol 87(6):643–647
Chen F, Zeng X, Wang M (2015) Image denoising via local and nonlocal circulant similarity. J Vis Commun Image Rep 30:117–124
Cho N, Shaw J, Karuranga S, Huang Y, da Rocha Fernandes J, Ohlrogge A, Malanda B (2018) IDF diabetes atlas: global estimates of diabetes prevalence for 2017 and projections for 2045. Diabetes Res Clin Pract 138:271–281
Cohen A, Daubechies I, Vial P (1993) Wavelets on the interval and fast wavelet transforms. Appl Comput Harm Anal 1(1):54–81
Cummings E, Facey K, Macpherson K, Morris A, Reay L, Slattery J (2002) Health technology assessement report. Glasgow, Scotland
Das T, Raman R, Ramasamy K (2015) Telemedicine in diabetic retinopathy: current status and future directions. Middle East Afr J Ophthalmol 22(2):174–178
Davis H, Russell S, Barriga E, Abramoff M, Soliz P (2009) Vision based, real-time retinal image quality assessment. IEEE International Symposium on Computer-Based Medical Systems, 1–6
Decenciere E, Zhang X, Cazuguel G, Lay B, Cochener B, Trone C, Gain P, Ordonez R et al (2014) Feedback on a publicly distributed image database: the Messidor database. Image Anal Stereol 33(3):231–234
Dias J, Oliveira CM, da Silva Cruz L (2014) Retinal image quality assessment using generic image quality indicators. Inform Fusion 19:73–90
F. P. R. C. Dept. of Ophthalmology & Visual Sciences of the University of Wisconsin-Madison (1995) ARIC grading protocol. http://eyephoto.ophth.wisc.edu/ResearchAreas.html. Accessed: 30th June 2016
Fleming AD, Philip S, Goatman KA, Olson JA, Sharp PF (2006) Automated assessment of diabetic retinal image quality based on clarity and field definition. Invest Ophthalmol Vis Sci 47(3):1120–1125
Fleming AD, Philip S, Goatman KA, Sharp PF, Olson JA (2012) Automated clarity assessment of retinal images using regionally based structural and statistical measures. Med Eng Phys 34(7):849–859
Fundus disease Group in Ophthalmology Branch of Chinese Medical Association (2017) Guidelines of retinal image acquisition and reading for diabetic retinopathy screening in China. Chin J Ophthalmol 53(12):890–896
Giancardo L, Abramoff MD, Chaum E, Karnowski T, Meriaudeau F, Tobin K (2008) Elliptical local vessel density: a fast and robust quality metric for retinal images. IEEE 30th Annual International Conference of the Engineering in Medicine and Biology Society (EMBS): 3534–3537
Giancardo L, Meriaudeau F, Karnowski TP, Li Y, Garg S, Tobin KW Jr, Chaum E (2012) Exudate-based diabetic macular edema detection in fundus images using publicly available datasets. Med Image Anal 16(1):216–226
Haralick RM, Shanmugan K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybernet 6:610–621
Hoover A, Kouznetsova V, Goldbaum M (2000) Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response. IEEE Trans Med Imaging 19(3):203–210
Hunter A, Lowell JA, Habib M, Ryder B, Basu A, Steel D (2011) An automated retinal image quality grading algorithm. IEEE Annual International Conference of the Engineering in Medicine and Biology Society (EMBS): 5955–5958
Hwang SK, Kim WY (2006) A novel approach to the fast computation of zernike moments. Pattern Recogn 39(11):2065–2076
Katuwal GJ, Kerekes J, Ramchandran R, Sisson C, Rao N (2013) Automatic fundus image field detection and quality assessment. IEEE Western New York Image Processing Workshop (WNYIPW), 9–13.
Kawaguchi A, Sharafeldin N, Sundaram A, Campbell S, Tennant M, Rudnisky C (2018) Tele-Ophthalmology for Age-Related Macular Degeneration and Diabetic Retinopathy Screening: A Systematic Review and Meta-Analysis. Telemedicine and e-Health 24(4):301–308
Lalonde M, Gagnon L, Boucher MC et al (2001) Automatic visual quality assessment in optical fundus images. Proceedings of vision interface, Ottawa 32:259–264
Lee SC, Wang Y (1999) Automatic retinal image quality assessment and enhancement. Proc Int Soc Opt Photo 3661:1581–1590
Li B, Li HK (2013) Automated analysis of diabetic retinopathy images: principles, recent developments, and emerging trends. Curr Diab Rep 13(4):453–459
Li JJ, Zhang L, Peng XY (2014) Some issues of diagnosis based on ocular fundus image reading in teleophthalmology. Ophthalmol Chin 23(4):217–220
Li Y, Ren W, Zhu T, Ren Y, Qin Y, Jie W (2018) RIMS: A Real-time and Intelligent Monitoring System for live-broadcasting platforms. Futur Gener Comput Syst 87:259–266
Lin KY, Wang G (2018) Hallucinated-IQA: No-reference image quality assessment via adversarial learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 732-741
MESSIDOR (2004) Methods for Evaluating Segmentation and Indexing technique Dedicated to Retinal Ophthalmology. http://www.adcis.net/en/download-Third-Party/Messidor.html. Accessed: 25 Nov. 2018
Mora AD, Soares J, Fonseca JM (2014) A template matching technique for artifacts detection in retinal images. International Symposium on Image and Signal Processing and Analysis (ISPA), 717-722
Morse SS (2013) Public health disease surveillance networks. Microbiol Spectrum 2(1):OH-0002-2012
Narvekar ND, Karam LJ (2011) A no-reference image blur metric based on the cumulative probability of blur detection (CPBD). IEEE Trans Image Process 20(9):2678–2683
Nayak J, Acharya R, Bhat PS, Shetty N, Lim TC (2009) Automated diagnosis of glaucoma using digital fundus images. J Med Syst 33(5):337
Nayar SK, Nakagawa Y (1989) Shape from focus. IEEE Trans Pattern Anal Mach Intell 16(8):824–831
Niemeijer M, Staal J, Ginneken B, Loog M, Abramoff M (2004) Drive: digital retinal images for vessel extraction. Methods for Evaluating Segmentation and Indexing Techniques Dedicated to Retinal Ophthalmology. http://www.isi.uu.nl/Research/Databases/DRIVE/. Accessed: 13 Oct. 2017
Niemeijer M, Abramoff MD, Ginneken B (2006) Image structure clustering for image quality verification of color retina images in diabetic retinopathy screening. Med Image Anal 10(6):888–898
Niemeijer M, Van Ginneken B, Cree MJ, Mizutani A, Quellec G, Zhang B, Hornero R et al (2010) Retinopathy online challenge: automatic detection of microaneurysms in digital color fundus photographs. IEEE Trans Med Imaging 29(1):185–195
Niu Y, Lin W, Ke X, Ke L (2017) Fitting-based optimization for image visual salient object detection. IET Comput Vis 11(2):161–172
Niu Y, Lin L, Chen Y, Ke L (2017) Machine learning-based framework for saliency detection in distorted images. Multimed Tools Appl 76(24):26329–26353
Paulus J, Meier J, Bock R, Hornegger J, Michelson G (2010) Automated quality assessment of retinal fundus photos. Int J Comput Assist Radiol Surg 5(6):557–564
Perez J, Espinosa J, Vazquez C, Mas D (2013) Retinal image quality assessment through a visual similarity index. J Mod Opt 60(7):544–550
Pires R, Jelinek HF, Wainer J, Rocha A (2012) Retinal image quality analysis for automatic diabetic retinopathy detection. IEEE 25th Conf Graph Patterns Images (SIBGRAPI): 229–236
Pratt H, Coenen F, Broadbent DM, Harding SP, Zheng Y (2016) Convolutional neural networks for diabetic retinopathy. Proc Comput Sci 90:200–205
Sevik U, Kose C, Berber T, Erdol H (2014) Identification of suitable fundus images using automated quality assessment methods. J Biomed Opt 19(4):046006
Shao F, Yang Y, Jiang Q, Jiang G, Ho YS (2018) Automated quality assessment of fundus images via analysis of illumination, naturalness and structure. IEEE Access 6:806–817
Sim DA, Keane PA, Tufail A, Egan CA, Aiello LP, Silva PS (2015) Automated retinal image analysis for diabetic retinopathy in telemedicine. Curr Diab Rep 15(3):1–9
Sopharak A, Uyyanonvara B, Barman S (2011) Automatic microaneurysm detection from non-dilated diabetic retinopathy retinal images using mathematical morphology methods. IAENG Int J Comput Sci 38(3):295–301
Soto-Pedre E, Navea A, Millan S, Hernaez-Ortega MC, Morales J, Desco MC, P’erez P (2015) Evaluation of automated image analysis software for the detection of diabetic retinopathy to reduce the ophthalmologists’ workload. Acta Ophthalmol 93(1):e52–e56
Usher D, Himaga M, Dumskyj M, Boyce J (2003) Automated assessment of digital fundus image quality using detected vessel area. Proceedings of Medical Image Understanding and Analysis: 81–84
Wang S, Guo W (2017) Sparse multi-graph embedding for multimodal feature representation. IEEE Trans Multimedia 19(7):1454–1466
Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612
Welikala R, Fraz M, Foster P, Whincup P, Rudnicka AR, Owen GG, Strachan D et al (2016) Automated retinal image quality assessment on the uk biobank dataset for epidemiological studies. Comput Biol Med 71:67–76
Xia Y, Leung H, Kamel MS (2016) A discrete-time learning algorithm for image restoration using a novel l2-norm noise constrained estimation. Neurocomputing 198:155–170
Yao Z, Zhang Z, Xu LQ, Fan Q, Xu L (2016) Generic features for fundus image quality evaluation. IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom), 1–6
Yin F, Wong DWK, Yow AP, Lee BH, Quan Y, Zhang Z, Gopalakrishnan K, Li R, Liu J (2014) Automatic retinal interest evaluation system (ARIES). IEEE 36th Annual International Conference of the Engineering in Medicine and Biology Society (EMBC), 162–165.
Yu H, Agurto C, Barriga S, Nemeth SC, Soliz P, Zamora G (2012) Automated image quality evaluation of retinal fundus photographs in diabetic retinopathy screening. IEEE southwest symposium on Image Analysis and Interpretation (SSIAI), 125-128
Yu F, Sun J, Li A, Cheng J, Wan C, Liu J (2017) Image quality classification for dr screening using deep learning. IEEE 39th Annual International Conference of the Engineering in Medicine and Biology Society (EMBC), 664–667
Acknowledgments
This work is supported by the National Natural Science Foundation of China (No. 41801324), by the Natural Science Foundation of Fujian Province, China (No.2016 J0129), by the Educational Commission of Fujian Province of China (No.JAT160070).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Lin, J., Yu, L., Weng, Q. et al. Retinal image quality assessment for diabetic retinopathy screening: A survey. Multimed Tools Appl 79, 16173–16199 (2020). https://doi.org/10.1007/s11042-019-07751-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-019-07751-6