Page 77 - Computational Retinal Image Analysis

68 CHAPTER 4 Retinal image preprocessing, enhancement, and registration

well-defined task, attempts to provide pertinent benchmarks are starting to appear,
as in Ref. [99] where existing datasets for RIR are compared and a benchmark
methodology is also proposed. Still, there is a clear need for new approaches to
benchmarking that will allow for more direct comparisons of methods and will
account for optical phenomena, such as optical distortions due to the eye lens,
vitreous humor, and chromatic aberrations.

Acknowledgment

The authors thank Polykarpos Karamaounas for technical assistance in the preparation
of the manuscript.

References

[1] M. Matsui, T. Tashiro, K. Matsumoto, S. Yamamoto, A study on automatic and
quantitative diagnosis of fundus photographs (Transl. from Japanese), Nippon Ganka
Gakkai Zasshi 77 (8) (1973) 907–918.
[2] A. Grosso, F. Veglio, M. Porta, F.M. Grignolo, T.Y. Wong, Hypertensive retinopathy
revisited: some answers, more questions, Br. J. Ophthalmol. 89 (12) (2005) 1646–1654,
https://doi.org/10.1136/bjo.2005.072546.
[3] R.P. Danis, M.D. Davis, Proliferative diabetic retinopathy, Diabetic Retinopathy,
Humana Press, Totowa, NJ, 2008, pp. 29–65.
[4] A. Chernomorets, A. Krylov, Blur detection in fundus images, International Conference
on BioMedical Engineering and Informatics, 2012, pp. 243–246.
[5] S. Mohammad, D. Morris, N. Thacker, Segmentation of optic disc in retina images using
texture, International Conference on Computer Vision Theory and Applications, 2014,
pp. 293–300.
[6] A. Fleming, S. Philip, K. Goatman, J. Olson, P. Sharp, Automated microaneurysm
detection using local contrast normalization and local vessel detection, IEEE Trans.
Med. Imaging 25 (9) (2006) 1223–1232.
[7] T. Walter, P. Massin, A. Erginay, R. Ordonez, C. Jeulin, J. Klein, Automatic detection of
microaneurysms in color fundus images, Med. Image Anal. 11 (6) (2007) 555–566.
[8] A. Pujitha, G. Jahnavi, J. Sivaswamy, Detection of neovascularization in retinal images
using semi-supervised learning, IEEE International Symposium on Biomedical Imaging,
2017, pp. 688–691.
[9] A. Deshmukh, T. Patil, S. Patankar, J. Kulkarni, Features based classification of hard
exudates in retinal images, International Conference on Advances in Computing,
Communications and Informatics, 2015, pp. 1652–1655.
[10] N. Salem, A. Nandi, Novel and adaptive contribution of the red channel in pre- processing
of colour fundus images, J. Frankl. Inst. 344 (3) (2007) 243–256.
[11] C. Liu, M. Chang, Y. Chaung, S. Yu, A novel retinal image color texture enhancement
method based on multi-regression analysis, International Symposium on Computer,
Consumer and Control, 2016, pp. 793–796.
[12] J. Zhang, B. Dashtbozorg, E. Bekkers, J. Pluim, R. Duits, B.M. ter Haar Romeny, Robust