The week's pick
Reseach Article
Automated System for Detection of High Risk Diabetic Macular Edema in Color Retinal Images
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 178 - Number 2 |
| Year of Publication: 2017 |
| Authors: Anaswara Chandran, Nisha K. K., Laxmi Raja |
10.5120/ijca2017915726
|
Anaswara Chandran, Nisha K. K., Laxmi Raja . Automated System for Detection of High Risk Diabetic Macular Edema in Color Retinal Images. International Journal of Computer Applications. 178, 2 ( Nov 2017), 15-21. DOI=10.5120/ijca2017915726
Abstract
The detection of macula and classification of macular edema condition is an open issue for researchers in the field of ophthalmology. Diabetic Macular Edema (DME) is a secondary disease associated with DR (Diabetic Retinopathy), and it acts as a major reason for vision loss in diabetic patients. In this paper an automated system is presented with a Binarized Macula Detection (BMD) algorithm for detection of macula, irrespective of the location of Optic Disk (OD). The work tries to target high risk DME which occurs within 1 Optic Disk Diameter (ODD) area in the macular region. This will help to provide immediate treatment to the patients with high risk of DME. The extraction of texture features from the green channel of Region of Interest (ROI) reduces the time for working with whole image, and the classification system with Support Vector Machine (SVM), K Nearest Neighbor (KNN) and Random Forest classifiers predicts the individual result for input images. The binary classification of Stage 0 (Normal) and Stage 2 (High Risk Diabetic Macular Edema) was performed on dataset from MESSIDOR database, and the SVM classifier with RBF kernel obtained highest accuracy and specificity as 94.58 % and 96.94% respectively. Higher sensitivity was obtained by KNN as 89.66%. The system was also compared with a feature reduction system using Principal Component Analysis (PCA) and the system with, SVM and RBF kernel without feature reduction technique outperformed the results.
References
- 1. M. D. Abramoff, M. Niemeyer, M. S. Suttorp-Schulten, M. A. Viergever, S. R. Russell, and B. van Ginneken, “Evaluation of a system for automatic detection of diabetic retinopathy from color fundus photographs in a large population of patients with diabetes,” J. Diabetes Care, vol. 31, no. 2, pp. 193–198, Nov. 2007.
- K. Sai Deepak, Jayanthi Sivaswamy, “Automatic assessment of Macular Edema from Color Retinal Images”, IEEE Transactions on Medical Imaging, Vol.31, NO. 3, pp. 766-776, March2012.
- Sreejini K. S., V.K. Govindan, “Automatic Grading of severity of Diabetic Macular Edema using Color Fundus Images”, International Conference on Advances in Computing and Communication,pp. 177-180, 2013.
- Aditya Kunwar1,Shrey Magotra,M Partha Sarathi, “Detection of High-Risk Macular Edema using Texture features and Classification using SVM Classifier”, 978-1-4799-8792-4/15/$31.00_c 2015 IEEE.
- Malay Kishore Dutta, M. Parthasarathi, Shaumik Ganguly, Shaunak Ganguly, Kshitij Srivastava, “An efficient image processing based technique for comprehensive detection and grading of nonproliferative diabetic retinopathy from fundus images”, Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization,July,2015.
- Z. Liu, C. Opas, and S. Krishnan. Automatic image analysis of fundus photograph. In EMBS, volume 2, pages 524–525, 1997.
- A. Sagar, S. Balasubramanian, and V. Chandrasekaran. Automatic detection of anatomical structures in digital fundus retinal images. In IAPR - MVA, pages 483–486, 2007.
- N. Tan, D. Wong, J. Liu, W. Ng, Z. Zhang, J. Lim, Z. Tan, Y. Tang, H. Li, S. Lu, and T. Wong, “Automatic detection of the macula in the retinal fundus image by detecting regions with low pixel intensity” In ICBPE, pages 1–5, 2009.
- Umer Aftab, M. Usman Akram, “Automated Identification of Exudates for Detection of Macular Edema”, Cairo International Biomedical Engineering Conference, Cairo, Egypt, pp. 27-30, December2012.
- Namita Sengar, Malay Kishore Dutta, Radim Burget, and Lukas Povoda, “Detection of Diabetic Macular Edema in Retinal Images Using a Region Based Method”, 978-1-4799-8498-5/15/$31.00 ©2015 IEEE.
- Rodrigo Veras, Fátima Medeiros ; Romuere Silva ; Daniela Ushizima, “Assessing the accuracy of macula detection methods in retinal images”, 2013 18th International Conference on Digital Signal Processing (DSP), Fira, 1 – 6, 1-3 July 2013.
- Decenciere et al. Feedback on a publicly distributed database: the Messidor database. Image Analysis & Stereology, v. 33, n. 3, p. 231-234, aug. 2014. ISSN 1854-5165.
- T. Lim, W.M.D.W. Zaki, A. Hussain, S.L. Lim, S. Kusalavan, “Classification of Diabetic Macular Edema in Digital Fundus Images”, 2011 IEEE Colloquium on Humanities, Science and Engineering Research (CHUSER 2011), Dec 5-6 2011, Penang.
- A. Liaw and M. Wiener (2002), “Classification and Regression by random forest”, R News 2(3), 18-22.
Index Terms
Keywords