The Assessment of Time-Domain Features for Detecting Symptoms of Diabetic Retinopathy

Abstract

 Diabetes affects the capillary vessels in retina and causes vision loss. This disorder of retina due to diabetes is named as Diabetic Retinopathy (DR). Diagnosing the stages of DR is performed on a publicly available database (DiaraetDB1) via detecting the symptoms of this disease. Time-domain features are extracted and selected to classify a fundus image. Fisher’s Linear Discriminant Analysis (FLDA), Linear Bayes Normal Classifier (LDC), Decision Tree (DT) and k-Nearest Neighbor (k-NN) are used as the classification methods in the experimental benchmarking. The recognition accuracies are obtained using all features (68 features) and selected features separately. k-NN is observed as the best classification method for without feature selection case and it gives averagely 92.22% accuracy. For feature selection case, LDC gives the best average accuracy as 92.45% with maximum 7 carefully chosen features.

Keywords

• Sequential feature selection,diabetic retinopathy,microaneurysms,hemorrhages,exudates

References

1. [1] Jagadish Nayak et al. (2007). Automated Identification of Diabetic Retinopathy Stages Using Digital Fundus Images. Journal of Medical System. Vol. 32. Pages. 107-115.
2. [2] Ronald Klein, Barbara E.K. Klein, Susan C. Jensen and Scot E. Moss (2001). The relation of socioeconomic factors to the incidence of early age-related maculopathy: The Beaver Dam Eye Study. American Journal of Ophthalmology. Vol. 132. Pages. 128–131.
3. [3] Ankita Agrawal, Charul Bhatnagar and Anand Singh Jalal (2013). A Survey on Automated Microaneurysm Detection in Diabetic Retinopathy Retinal Images. Information Systems and Computer Networks (ISCON). Pages. 24-29.
4. [4] Micheal D. Abramoff, Mona K. Garvin and Milan Sonka (2010). Retinal Imaging and Image Analysis. IEEE Reviews in Biomedical Engineering. Vol. 3. Pages. 169-208.
5. [5] Akara Sopharak, Bunyarit Uyyanonvara, Sarah Barman and Thomas H. Williamson (2008). Automatic Detection of Diabetic Retinopathy Exudates from Non-Dilated Retinal Images Using Mathematical Morphology Methods. Computerized Medical Imaging and Graphics. Vol. 32. Pages. 720–727.
6. [6] Diptoneel Kayal and Sreeparna Banerjee (2014). A New Dynamic Tresholding Based Technique for Detection of Hard Exudates in Digital Retinal Fundus Image. International Conference on Signal Processing and Integrated Networks (SPIN). Pages.141-144.
7. [7] T.Kauppi et al. DIARETDB1 diabetic retinopathy database and evaluationprotocol. Available: http://www.it.lut.fi/project/ imageret/diaretdb1/.
8. [8] M. Usman Akram, Shehzad Khalid and Shoab A. Khan (2013). Identification and classification of microaneurysms for early detection of diabetic retinopathy. Pattern Recognition. Vol. 46. Pages. 107-116.

9. [9] Kanika Verma, Prakash Deep and A.G. Ramakrishnan (2011). Detection and Classification of Diabetic Retinopathy using Retinal Images. India Conference (INDICON). Pages. 1-6.
10. [10] Marwan D. Saleh and C. Eswaran (2012). An Automated Decision-Support System for Non-Proliferative Diabetic Retinopathy Disease Based on MAs and Has detection. Computer Methods and Programs in Biomedicine. Vol. 108. Pages. 186-196.
11. [11] Wong Li Yun et. al. (2008). Identification of Different Stages of Diabetic Retinopathy Using Retinal Optical Images. Information Sciences. Vol. 178. Pages. 106-121.
12. [12] Maria Garcia, Roberto Hornero, Clara I. Sánchez, María I. López and Ana Díez (2007). Feature Extraction and Selection for the Automatic Detection of Hard Exudates in Retinal Images. Proceedings of the 29th Annual International Conference of the IEEE EMB. Pages. 4969-4972.
13. [13] Mahendran Gandhi and Dr. R. Dhanasekaran (2013). Diagnosis of Diabetic Retinopathy Using Morphological Process and SVM Classifier. International conference on Communication and Signal Processing, India. Pages. 873-877.
14. [14] R. A. Fisher Sc.D., F.R.S. (1936). The Use of Multiple Measurements in Taxonomic Problems. Annuals of Eugenics. Vol. 7. Pages. 179-188.
15. [15] Richard O. Duda, Peter E. Hart, and David G. Stork (2001). Pattern Classification 2nd edition. John Wiley and Sons, New York.
16. [16] J.R. Quinlan (1987). Simplifying Decision Trees. International Journal of Man-Machine Studies. Vol. 27. Pages. 221-234.
17. [17] T. Cover and P. Hart (1967). Nearest Neighbor Pattern Classification. IEEE Transactions on Information Theory. Vol. 13. Pages. 21-27.
18. [18] Nikhil R. Pal, Brojeshwar Bhowmick, Sanjaya K. Patel, Srimanta Pal and J. Das (2008). A Multi-Stage Neural Network Aided System for Detection of Microcalcifications in Digitized Mammograms. Neurocomputing. Vol. 71. Pages. 2625-2634.
19. [19] R.P.W. Duin et. al. PRTools4 A Matlab Toolbox for Pattern Recognition.Available: http://prtools.org.