Impact of Pre-processing Techniques in Automated Detection of Diabetic Retinopathy
Abstract
Diabetic Retinopathy (DR) is a threat to the visual capabilities of diabetic patients. It needs to be addressed in an early stage to save the eyesight from entering the full blind state. Automated detection of morphological symptoms as early as possible is a combined solution to several socio-medical issues like a burden on ophthalmologists, human-based errors, non-reproducibility due to varied skill sets of different ophthalmologists, etc. To develop an efficient automated diagnosis system for grading DR, it is very important to pre-process the acquired retinal images accordingly. Pre-processing techniques prepare the images to be more suitable for feature extraction. The techniques involve the conditioning of images in such a way that the pathological features become more prominent, the contrast level is enhanced and inherent noise level is reduced. Also, several spatial and texture-based factors play a significant role in deciding the accuracy of the classifier system. Different kind of filters and image processing tools are required to address various image artifacts and acquired noise. This paper is oriented toward the impact and importance of pre-processing techniques for efficient feature extraction and classification system. It also compares the pros and cons of different pre-processing techniques and concludes which kind of data processing is beneficial for specified feature extraction techniques.
References
1. A. Sakaguchi; R. Wu and S. Kamata; (2019) Fundus Image Classification for Diabetic Retinopathy using Disease Severity Grading. 9th International Conference on Biomedical Engineering and Technology, 190- 196.
2. D. Usher; M. Dumskyj; M. Himaga; T. H. Williamson; S. Nussey and J. Boyce; Automated Detection of Diabetic Retinopathy in Digital Retinal Images: A Tool for Diabetic Retinopathy Screening. Diabetic Medicine, 21(1), 84-90 (2004)
3. D. Popescu; L. Ichim and T. Caramihale; (2015) Texture Based Method for Automated Detection, Localization and Evaluation of the Exudates in Retinal Images. 22nd International Conference on Neural Information Processing (ICONIP 2015), Isatanbul, Turkey, 463-472.
4. D. Doshi; A. Shenoy; D. Sidhpura and P. Gharpure; (2016), Diabetic Retinopathy Detection using Deep Convolutional Neural Networks. 2016 International Conference on Computing, Analytics and Security Trends, 261-266.
5. D.Lokuarachchi;K.Gunarathna;L.MuthumalandT.Gamage;(2019)AutomatedDetectionofExudates in Retinal Images. IEEE 15th International Colloquium on Signal Processing & its Applications, 43-47.
6. F. Grassmann; J. Mengelkamp; C. Brandl; S. Harsch; M. E. Zimmermann; B. Linkohr; A. Peters; I. M.
Heid; C. Palm and B. H. F. Weber; A Deep Learning Algorithm for Prediction of Age-related Eye Disease Study Severity Scale for Age-related Macular Degeneration from Color Fundus Photography. Ophthalmology, 125(9), 1410-1420 (2018).
7. H. Pratt; F. Coenen; D. M. Broadbent; S. P. Harding and Y. Zheng; (2016) Convolutional Neural Networks for Diabetic Retinopathy. International Conference On Medical Imaging Understanding and Analysis 2016, Loughborough, UK, Procedia Computer Science, 90, 200-205.
8. I. Bibi; J. Mir and G. Raja; Automated Detection of Diabetic Retinopathy in Fundus Images using Fused Features. Physical and Engineering Sciences in Medicine, 43(4), 1253-1264 (2020).
9. J. Sahlsten; J. Jaskari; J. Kivinen; L. Turunen; E. Jaanio; K. Hietala and K. Kaski; Deep Learning Fundus Image Analysis for Diabetic Retinopathy and Macular Edema Grading. Scientific Reports, Nature, 9, Artilce Id 10750, 1-11 (2019).
10. J. E.W. Koh; U. R. Acharya; Y. Hagiwara; U. Raghavendra, J. H. Tan; S. V. Sree; S. V. Bhandary; A. K. Rao; S. Sivaprasad; K. C. Chua; A. Laude and L. Tong; Diagnosis of Retinal Health in Digital Fundus Images using Continuous Wavelet Transform and Entropies. Computers in Biology and Medicines, 84, 89-97 (2017).
11. K. Xu; D. Feng and H. Mi; Deep Convolutional Neural Network-Based Early Automated Detection of Diabetic Retinopathy using Fundus Image. Molecules 22(12), Artilce Id 2054, 1-7 (2017).
12. K. Y. Win and S. Choomchuay; (2016) Automated Detection of Exudates using Histogram Analysis for Digital Retinal Images. 2016 International Symposium on Intelligent Signal Processing and Communication Systems, 1-6.
13. L. Seoud; T. Hurtut; J. Chelbi; F. Cheriet and J. M. P. Langlois; Red Lesion Detection using Dynamic Shape Features for Diabetic Retinopathy Screening. IEEE Transactions on Medical Imaging, 35(4), 1116- 1126 (2015).
14. L. Giancardo; F. Meriaudeau; T. P. Karnowski; Y. Li; S. Garg; K. W. Tobin Jr. and E. Chaum; Exudate- Based Diabetic Macular Edema Detection in Fundus Images using Publicly Available Datasets. Medical Image Analysis , 16(1), 216-226 (2012).
15. M. U. Akram; A. Tariq; S. A. Khan and M. Y. Javed; Automated Detection of Exudates and Macula for Grading of Diabetic Macular Edema. Computer Methods and Programs in Biomedicine, 114(2), 141-152 (2014).
16.M. U. Akram; S. Khalid; A.Tariq; S. A. Khan and F. Azam; Detection and Classification of Retinal Lesions for Grading of Diabetic Retinopathy. Computers in Biology and Medicines, 45, 161-171 (2014).
17. M. Mateen; J. Wen; N. Nasrullah; S. Sun and S. Hayat; Exudate Detection for Diabetic Retinopathy using
Pre-trained Convolutional Neural Network. Complexity, 2020, Artilce Id 5801870, 1-11 (2020).
18. M. Zubair; S. A. Khan and U. U. Yasin; Classification of Diabetic Macular Edema and Its Stages using
Color Fundus Image. Journal of Electronic Science and Technology, 12(2), 1-4 (2014).
19.P. C. Siddalingaswamy and K. GopalakrishnaPrabhu; (2008) Automated Detection of Optic Disc and
Exudates in Retinal Images, 13th International Conference on Biomedical Engineering, Springer, 227-279.
20. P. Khojasteh; B. Aliahmad and D. K. Kumar; Fundus Images Analysis using Deep Features for Detection
of Exudates, Hemorrhages and Microaneurysms. BMC Ophthalmology, 18, Artilce Id 288, 1-13 (2018).
21. R. Suma; D. Devara and S. C. P. Kumar; (2018) Detection of Exudates through Local Binary Pattern in Diabetic Retinopathy. International Conference on Cognitive Computing and Information Processing, 29-39.
22.R. Bhattacharjee and M. Chakraborty; (2012) Exudates, Retinal and Statistical Features Detection from Diabetic Retinopathy and Normal Fundus Images: An Automated Comparative Approach. 2012 National Conference on Computing and Communication Systems, 1-6.
23. S. T. Lim; W. M. D. W. Zaki; A. Hussain; S. L. Lim and S. Kusalavan; (2011) Automatic Classification of Diabetic Macular Edema in Digital Fundus Images. 2011 IEEE Colloquium on Humanities, Science and Engineering Research, 265-269.
24. S. Sridhar and S. Sanagavarapu; (2020) Detection and Prognosis Evaluation of Diabetic Retinopathy using Ensemble Deep Convolutional Neural Networks. 2020 International Electronics Symposium(IES), Surabaya, Indonesia, 78-85.
25.P. Shah; D. K. Mishra; M. P. Shanmugam; B. Doshi; H. Jayaraj and R. Ramanjulu; Validation of Deep Convolutional Neural Network-based Algorithm for Detection of Diabetic Retinopathy-Artificial Intelligence Versus Clinician for Screening. Indian J Ophthalmol, 68(2), 398-405 (2020).
26. T. Malik and V. Nandal; (2022) Automated Detection of Diabetic Retinopathy: A Comprehensive Study. 2022 Fifth International Conference on Computational Intelligence and Communication Technologies, (CCICT), Sonepat, India, 31-36.
27. U. R. Acharya; M. R. K. Mookiah; J. E.W. Koh; J. H. Tan; S. V. Bhandary; A. K. Rao; H. Fujita; Y. Hagiwara; C. K. Chua and A. Laude; Automated Screening System for Retinal Health using Bi- dimensional Empirical Mode Decomposition and Integrated Index. Computers in Biology and Medicine, 75, 54-62 (2016).
28.V. Deepa; C. S. Kumar and S. S. Andrews; Automated Detection of Microaneurysms using Stockwell Transform and Statistical Features. IET Image Process, 13(8), 1341-1348 (2019).
Trion Studio
