Digital fundus image quality assessment

Diabetic retinopathy (DR) is a disease caused by complications of diabetes. It starts asymptomatically and can end in blindness. To detect it, doctors use special fundus cameras that allow them to register images of the retina in the visible range of the spectrum. On these images one can see features, which determine the presence of DR and its grade. Researchers around the world are developing systems for the automated analysis of fundus images. At present, the level of accuracy of classification of diseases caused by DR by systems based on machine learning is comparable to the level of qualified medical doctors.

The article shows variants for representation of the retina in digital images by different cameras. We define the task to develop a universal approach for the image quality assessment of a retinal image obtained by an arbitrary fundus camera. It is solved in the first block of any automated retinal image analysis system. The quality assessment procedure is carried out in several stages. At the first stage, it is necessary to perform binarization of the original image and build a retinal mask. Such a mask is individual for each image, even among the images recorded by one camera. For this, a new universal retinal image binarization algorithm is proposed. By analyzing result of the binarization, it is possible to identify and remove imagesoutliers, which show not the retina, but other objects. Further, the problem of no-reference image quality assessment is solved and images are classified into two classes: satisfactory and unsatisfactory for analysis. Contrast, sharpness and possibility of segmentation of the vascular system on the retinal image are evaluated step by step. It is shown that the problem of no-reference image quality assessment of an arbitrary fundus image can be solved.

Experiments were performed on a variety of images from the available retinal image databases.

1. Diabetes – Statistics & Facts [Электронный ресурс]. – Режим доступа: https://www.statista.com/topics/1723/diabetes/#dossierKeyfigures. – Дата доступа: 03.11.2021.

2. Tilahun M., et al. Prevalence of diabetic retinopathy and its associated factors among diabetic patients at Debre Markos referral hospital, Northwest Ethiopia, 2019: hospital-based cross-sectional study, Diabetes, Metabolic Syndrome and Obesity: Targets and Therapy. – 2020. – Vol.13. – pp.2179.

3. Krause J., et al. Grader variability and the importance of reference standards for evaluating machine learning models for diabetic retinopathy, Ophthalmology, 2018, Vol.125, No.8, pp.1264–1272.

4. Manohar P., Mallikarjun S. Holi Comparative study of methods for fundus mask generation, International Journal of Advanced Science and Technology, 2020, Vol. 29, No. 3, pp. 9642–9653.

5. Gagnon L., et al. Procedure to detect anatomical structures in optical fundus images, SPIE Conf. on Medical Imaging, 2001, Vol. 4322, pp. 1218–1225.

6. Youssif A.A. H.A. R., Ghalwash A. Z., Ghoneim A.A. S.A. R. Optic disc detection from normalized digital fundus images by means of a vessels direction matched filter, IEEE Transactions on Medical Imaging, 2007, Vol. 27, No. 1, pp. 11–18. doi: 10.1109/TMI.2007.900326.

7. Niemeijer M., et al. Fast detection of the optic disc and fovea in color fundus photographs, Medical Image Analysis, 2009, Vol.13, No.6, pp. 859–870. doi:10.1016/j.media.2009.08.003.

8. DRIMDB – Database for quality testing of retinal images [Электронный ресурс]. – Режим доступа: https:// academictorrents.com/details/99811ba62918f8e73791d21be29dcc 372d660. – Дата доступа: 09.09.2021.

9. Khan S. M., et al. A global review of publicly available datasets for ophthalmological imaging: barriers to access, usability, and generalisability, The Lancet Digital Health, 2021, Vol. 3, No.1, pp. e51-e66. doi: 10.1016/S2589– 7500(20)30240–5.

10. Ter Haar F. Automatic localization of the optic disc in digital colour images of the human retina, Utrecht University. 2005, MS thesis, 83p.

11. Hashim F.A., Salem N. M., Seddik A. F. Preprocessing of color retinal fundus images, 2nd Int. Japan-Egypt Conference on Electronics, Communications and Computers, 2013 Dec 17, pp. 190–193. doi: 10.1109/JEC-ECC.2013.6766410.

12. Otsu N. A threshold selection method from gray-level histograms, IEEE Transactions on Systems, Man, and Cybernetics, 1979, Vol.9, No.1, pp.: 62–66.

13. Aibinu A. M., Salami M. J.E., Shafie A.A. Retina fundus image mask generation using pseudo parametric modeling technique, IIUM Engineering Journal, 2010, Vol.11, No.2, pp.163–177.

14. Database EyePACS [Электронный ресурс]. – Режим доступа: http://www.eyepacs.com/. – Дата доступа: 03.11.2021.

15. Pertuz S., Puig D., Garcia M.A. Analysis of focus measure operators for shape-from-focus, Pattern Recognition, 2013, Vol. 46, No.5, pp.1415–1432. DOI: 10.1016/j.patcog.2012.11.011.

16. Golub, Y. I. Study of local assessments of contrast for digital images / Y. I. Golub, F. V. Starovoitov // System Analysis and Applied Information Science, 2019, No.2 (22), pp. 4–11.

17. Golub Y. I., Starovoitov F. V. Comparative analysis of no-reference measures for digital image sharpness assessment, Doklady BGUIR, 2019, No.7 (125), pp. 113–120.

18. Zhai G., Min X. Perceptual image quality assessment: a survey, Science China Information Sciences, 2020, Vol. 63, No.11, pp. 83–135.

19. Gvozden G., Grgic S., Grgic M. Blind image sharpness assessment based on local contrast map statistics, Journal of Visual Communication and Image Representation, 2018, Vol.50, pp.145–158. doi: 10.1016/j.jvcir.2017.11.017.

20. Narvekar N. D., Karam L. J. A no-reference perceptual image sharpness metric based on a cumulative probability of blur detection. 2009 International Workshop on Quality of Multimedia Experience, 2009, pp.87–91. doi: 10.1109/QOMEX.2009.5246972.