Abstract
Fundus images are usually used for the diagnosis of ocular pathologies such as diabetic retinopathy. Image quality need however to be sufficient in order to enable grading of the severity of the condition. In this paper, we propose a new method to evaluate the quality of retinal images by computing a score for each image. Images are classified as gradable or ungradable based on this score. First, we use two different U-Net models to segment the macula and the vessels in the original image. We then extract a patch around the macula in the image containing the vessels. Finally, we compute a quality score based on the presence of small vessels in this patch. The score is interpretable as the method is heavily inspired by the way clinicians assess image quality, according to the Scottish Diabetic Retinopathy Grading Scheme. The performances are evaluated on a validation database labeled by a clinician. This method presented a sensitivity of 95% and a specificity of 100% on this database.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Drive Database. https://drive.grand-challenge.org/
Messidor Database. http://www.adcis.net/fr/logiciels-tiers/messidor-fr/
Scottish Diabetic Retinopathy Grading Scheme (2007). https://www.ndrs.scot.nhs.uk/
Abdel-Hamid, L., El-Rafei, A., El-Ramly, S., Michelson, G., Hornegger, J.: Retinal image quality assessment based on image clarity and content. J. Biomed. Opt. 21(9), 1–17 (2016). https://doi.org/10.1117/1.JBO.21.9.096007
Dias, J.M.P., Oliveira, C.M., da Silva Cruz, L.A.: Retinal image quality assessment using generic image quality indicators. Inf. Fusion 19, 73–90 (2014). https://doi.org/10.1016/j.inffus.2012.08.001. http://www.sciencedirect.com/science/article/pii/S1566253512000656. Special Issue on Information Fusion in Medical Image Computing and Systems
Fasih, M.: Retinal image quality assessment using supervised classification. Masters thesis, École Polytechnique de Montréal (2014)
Fu, H., et al.: Evaluation of retinal image quality assessment networks in different color-spaces. arXiv e-prints arXiv:1907.05345 (July 2019)
Hunter, A., Lowell, J.A., Habib, M., Ryder, B., Basu, A., Steel, D.: An automated retinal image quality grading algorithm. In: 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 5955–5958 (August 2011). https://doi.org/10.1109/IEMBS.2011.6091472
Raj, A., Tiwari, A.K., Martini, M.G.: Fundus image quality assessment: survey, challenges, and future scope. IET Image Process. 13(8), 1211–1224 (2019). https://doi.org/10.1049/iet-ipr.2018.6212
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. arXiv e-prints arXiv:1505.04597 (May 2015)
Zago, G.T., Andreão, R.V., Dorizzi, B., Salles, E.O.T.: Retinal image quality assessment using deep learning. Comput. Biol. Med. 103, 64–70 (2018). https://doi.org/10.1016/j.compbiomed.2018.10.004. http://www.sciencedirect.com/science/article/pii/S001048251830297X
Acknowledgements
The authors wish to acknowledge the financial support from the CIHR SPOR Network in Diabetes and its Related Complications (DAC) and the department of ophthalmology at the university of Montreal, Quebec, Canada.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Peskine, Y., Boucher, MC., Cheriet, F. (2020). An Interpretable Data-Driven Score for the Assessment of Fundus Images Quality. In: Campilho, A., Karray, F., Wang, Z. (eds) Image Analysis and Recognition. ICIAR 2020. Lecture Notes in Computer Science(), vol 12132. Springer, Cham. https://doi.org/10.1007/978-3-030-50516-5_28
Download citation
DOI: https://doi.org/10.1007/978-3-030-50516-5_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-50515-8
Online ISBN: 978-3-030-50516-5
eBook Packages: Computer ScienceComputer Science (R0)