Automated Detection and Counting of Hard Exudates for Diabetic Retinopathy by using Watershed and Double Top-Bottom Hat Filtering Algorithm

Dafwen Toresa - Faculty of computer science, Lancang Kuning University, Pekanbaru, Riau, Indonesia
Mohamad Shahril - Data Science Research Lab, School of Computing, Universiti Utara Malaysia, Malaysia
Nor Harun - Data Science Research Lab, School of Computing, Universiti Utara Malaysia, Malaysia
Juhaida Bakar - Data Science Research Lab, School of Computing, Universiti Utara Malaysia, Malaysia
Hidra Amnur - Depatment of Information Technology, Politeknik Negeri Padang, Padang, West Sumatera, Indonesia


Citation Format:



DOI: http://dx.doi.org/10.30630/joiv.5.3.664

Abstract


Diabetic Retinopathy (DR) is one of diabetes complications that affects our eyes. Hard Exudate (HE) are known to be the early signs of DR that potentially lead to blindness. Detection of DR automatically is a complicated job since the size of HE is very small. Besides, our community nowadays lack awareness on diabetic where they do not know that diabetes can affect eyes and lead to blindness if regular check-up is not performed. Hence, automated detection of HE known as Eye Retinal Imaging System (EyRis) was created to focus on detecting the HE based on fundus image. The purpose of this system development is for early detection of the symptoms based on retina images captured using fundus camera. Through the captured retina image, we can clearly detect the symptoms that lead to DR. In this study, proposed Watershed segmentation method for detecting HE in fundus images. Top-Hat and Bottom-Hat were use as enhancement technique to improve the quality of the image. This method was tested on 15 retinal images from the Universiti Sains Malaysia Hospital (HUSM) at three different stages: Normal, NPDR, and PDR. Ten of these images have abnormalities, while the rest are normal retinal images. The evaluation of the segmentation images would be compared by Sensitivity, F-score and accuracy based on medical expert's hand drawn ground truth. The results achieve accuracy 0.96 percent with 0.99 percent sensitivity for retinal images.

Keywords


Diabetes; diabetic retinopathy; image segmentation; hard exudates; fundus images.

Full Text:

PDF

References


Felman, “Diabetic retinopathy: Causes, symptoms, and treatments,†2017. [Online]. Available: https://www.medicalnewstoday.com/articles/183417. [Accessed: 27-Jun-2021].

S. Qummar et al., “A Deep Learning Ensemble Approach for Diabetic Retinopathy Detection,†IEEE Access, vol. 7, pp. 150530–150539, 2019, doi: 10.1109/ACCESS.2019.2947484.

R. Maher, S. Kayte, S. Bhable, and J. Kayte, “Automated Detection of Microaneurysm, Hard Exudates, and Cotton Wool Spots in Retinal fundus Images,†IOSR J. Comput. Eng. Ver. I, vol. 17, no. 6, pp. 2278–661, 2015, doi: 10.9790/0661-1761152156.

S. R. Flaxman et al., “Global causes of blindness and distance vision impairment 1990–2020: a systematic review and meta-analysis,†Lancet Glob. Heal., vol. 5, no. 12, pp. e1221–e1234, 2017, doi: 10.1016/S2214-109X(17)30393-5.

World Health Organization, “Diabetes,†p. https://www.who.int/health-topics/diabetes.

B. M. Mafauzy, “Diabetes mellitus in Malaysia,†Medical Journal of Malaysia, vol. 61, no. 4, pp. 397–398, 2006.

“Malaysia has 3.6 million diabetics, says Dzulkefly,†The Star, 2019. [Online]. Available: https://www.thestar.com.my/news/nation/2019/03/27/malaysia-has-36-million-diabeticssays-dzulkefly. [Accessed: 27-Jun-2021].

International Diabetes Federation - Home, “Home,†Online. [Online]. Available: https://idf.org/our-network/regions-members/western-pacific/members/108-malaysia.html. [Accessed: 27-Jun-2021].

L. Guariguata, D. R. Whiting, I. Hambleton, J. Beagley, U. Linnenkamp, and J. E. Shaw, “Global estimates of diabetes prevalence for 2013 and projections for 2035,†Diabetes Res. Clin. Pract., vol. 103, no. 2, pp. 137–149, 2014, doi: 10.1016/j.diabres.2013.11.002.

X. Zeng, H. Chen, Y. Luo, and W. Ye, “Automated diabetic retinopathy detection based on binocular siamese-like convolutional neural network,†IEEE Access, vol. 7, pp. 30744–30753, 2019, doi: 10.1109/ACCESS.2019.2903171.

X. Guo and F. Yu, “A method of automatic cell counting based on microscopic image,†Proc. - 2013 5th Int. Conf. Intell. Human-Machine Syst. Cybern. IHMSC 2013, vol. 1, pp. 293–296, 2013, doi: 10.1109/IHMSC.2013.76.

F. S. Pranata, J. Na’am, and R. Hidayat, “Color feature segmentation image for identification of cotton wool spots on diabetic retinopathy fundus,†Int. J. Adv. Sci. Eng. Inf. Technol., vol. 10, no. 3, pp. 974–979, 2020, doi: 10.18517/ijaseit.10.3.11877.

V. Satyananda, K. V. Narayanaswamy, and Karibasappa, “Hard exudate extraction from fundus images using watershed transform,†Indones. J. Electr. Eng. Informatics, vol. 7, no. 3, pp. 449–462, 2019, doi: 10.11591/ijeei.v7i3.775.

K. Gayathri, D. Narmadha, K. Thilagavathi, K. Pavithra, and M. Pradeepa, “Detection of Dark Lesions from Coloured Retinal Image Using Curvelet Transform and Morphological Operation,†vol. 2, pp. 15–21, 2014.

S. Long, X. Huang, Z. Chen, S. Pardhan, D. Zheng, and F. Scalzo, “Automatic detection of hard exudates in color retinal images using dynamic threshold and SVM classification: Algorithm development and evaluation,†Biomed Res. Int., vol. 2019, 2019, doi: 10.1155/2019/3926930.

S. A. Ali Shah, A. Laude, I. Faye, and T. B. Tang, “Automated microaneurysm detection in diabetic retinopathy using curvelet transform,†J. Biomed. Opt., vol. 21, no. 10, p. 101404, 2016, doi: 10.1117/1.jbo.21.10.101404.

J. P. Bae, K. G. Kim, H. C. Kang, C. B. Jeong, K. H. Park, and J. M. Hwang, “A study on hemorrhage detection using hybrid method in fundus images,†J. Digit. Imaging, vol. 24, no. 3, pp. 394–404, 2011, doi: 10.1007/s10278-010-9274-9.

P. Wang, X. Hu, Y. Li, Q. Liu, and X. Zhu, “Automatic cell nuclei segmentation and classification of breast cancer histopathology images,†Signal Processing, vol. 122, pp. 1–13, 2016, doi: 10.1016/j.sigpro.2015.11.011.

A. Sopharak, B. Uyyanonvara, and S. Barman, “Automatic exudate detection from non-dilated diabetic retinopathy retinal images using Fuzzy C-means clustering,†Sensors, vol. 9, no. 3, pp. 2148–2161, 2009, doi: 10.3390/s90302148.

R. Harini and N. Sheela, “Feature extraction and classification of retinal images for automated detection of Diabetic Retinopathy,†Proc. - 2016 2nd Int. Conf. Cogn. Comput. Inf. Process. CCIP 2016, pp. 7–10, 2016, doi: 10.1109/CCIP.2016.7802862.

R. S. Biyani and B. M. Patre, “A clustering approach for exudates detection in screening of diabetic retinopathy,†2016 Int. Conf. Signal Inf. Process. IConSIP 2016, 2017, doi: 10.1109/ICONSIP.2016.7857495.

K. Wisaeng and W. Sa-ngiamvibool, “Automatic detection and recognition of optic disk with maker-controlled watershed segmentation and mathematical morphology in color retinal images,†Soft Comput., vol. 22, no. 19, pp. 6329–6339, 2018, doi: 10.1007/s00500-017-2681-9.

H. A. Khan and G. M. Maruf, “Counting clustered cells using distance mapping,†2013 Int. Conf. Informatics, Electron. Vision, ICIEV 2013, 2013, doi: 10.1109/ICIEV.2013.6572677.

W. Tangsuksant, C. Pintavirooj, S. Taertulakarn, and S. Daochai, “Development algorithm to count blood cells in urine sediment using ANN and Hough Transform,†BMEiCON 2013 - 6th Biomed. Eng. Int. Conf., no. June, 2013, doi: 10.1109/BMEiCon.2013.6687725.

A. M. Sirisha and P. Venkateswararao, “Image processing techniques on radiological images of human lungs effected by COVID-19,†Int. J. Informatics Vis., vol. 4, no. 2, pp. 69–72, 2020, doi: 10.30630/joiv.4.2.359.

R. Hidayat, F. N. Jaafar, I. M. Yassin, A. Zabidi, F. H. K. Zaman, and Z. I. Rizman, “Face detection using Min-Max features enhanced with Locally Linear Embedding,†TEM J., vol. 7, no. 3, pp. 678–685, 2018, doi: 10.18421/TEM73-27.

Y. Yunus, J. Harlan, J. Santony, R. Hidayat, and J. Na’am, “Enhancement on enlarge image for identification lumbar radiculopathy at magnetic resonance imaging,†TEM J., vol. 9, no. 2, pp. 649–655, 2020, doi: 10.18421/TEM92-30.