Diagnosis of Corneal Arcus Using Statistical Feature Extraction and Support Vector Machine
Corneal arcus is a white ring or arc deposited in the corneal region of the human eye. This corneal abnormality is significantly associated with the lipid disorders and atherosclerosis. In this paper, we proposed a computer-aided diagnosis system to detect the corneal arcus. The proposed method detects the corneal arcus using the statistical features extracted from the iris region of the eye image. The iris region is segmented from the other regions of the eye image using circular Hough transform (CHT). In order to achieve the better classification results, a morphological operation-based specular reflection removal and colour transformation-based enhancement methods are also developed in this paper. The proposed method was implemented and evaluated using the abnormal eye images from our own database and normal eye images collected from UBIRIS.v1 database. Our database contains the eye images with different grades of corneal arcus abnormality. The performance of our method was evaluated using the confusion matrix-based metrics. In the training phase, our method achieved a classification accuracy of 1. In the testing phase, our method achieved a classification accuracy of 0.96 with a positive predictive value 0.9791 and negative predictive value 0.9423.
KeywordsCorneal arcus Eye image Iris segmentation Statistical features Classification
We would like to thank Dr. N. Ezhilvathani, HOD, Department of Ophthalmology, Indira Gandhi Medical College and Research Institute (IGMC&RI), Puducherry for her suggestions and support on the corneal arcus eye image collection for this work.
- 2.Urbano FL. Ocular signs of hyperlipidemia. Rev Clin Signs. Hospital Phys. 2001;51–53.Google Scholar
- 3.Gaynor PM, Zhang W-Y, Salehizadeh B, Pettiford B, Kruth HS. Cholesterol accumulation in human cornea: evidence that extracellular cholesteryl ester-rich lipid particles deposit independently of foam cells. J Lipid Res. 1996;1849–1861.Google Scholar
- 4.Moosavi M, Sareshtedar A, Zarei-Ghanavati S, Zarei-Ghanavati M, Ramezanfar N. Risk factors for senile corneal arcus in patients with acute myocardial infarction. J Ophthal Vis Res. 2010;228–31.Google Scholar
- 5.Zech LA Jr, Hoeg JM. Correlating corneal arcus with atherosclerosis in familial hypercholesterolemia. Lipids Health Dis. 2008. doi: 10.1186/1476-511X-7-7.
- 6.Morello R, De Caupa C, Fabbiano L, Vacca G. Image based detection of Kayser-Fleischer ring in patient with wilson disease. In: IEEE International symposium on medical measurements and applications proceedings (MeMeA); 2013. p. 101–106.Google Scholar
- 7.Lesmana IPD, Purnama IKE, Purnomo MH. Abnormal condition detection of pancreatic beta-cells as the cause of diabetes mellitus based on iris image. In: 2nd International conference on instrumentation, communications, information technology, and biomedical engineering (ICICI-BME); 2011. p. 150–155. doi: 10.1109/ICICI-BME.2011.6108614.
- 8.Acharya R et al. Computer based classification of eye diseases. In: IEEE proceedings of EMBS international conference; 2006. p. 6121–6124.Google Scholar
- 9.Ramlee RA, Ranjit S. Using iris recognition algorithm, detecting cholesterol presence. In: International conference on information management and engineering. IEEE Computer Society; 2009. p. 714–717. doi: 10.1109/ICIME.2009.61.
- 10.Ramlee RA et al. Automated detecting arcus senilis, symptom for cholesterol presence using iris recognition algorithm. J Telecommun Electron Comput Eng. 2011;29–39.Google Scholar
- 11.Masek L. Recognition of human iris patterns for biometric identification. Dissertation. The University of Western Australia; 2003.Google Scholar
- 12.Proenca H, Alexandre LA. UBIRIS: a noisy iris image databse. In: Proceedings of 13th international conference on Image analysis and processing; 2005. p. 970–977.Google Scholar
- 13.Frieß T-T, Cristianini N, Campbell C. The Kernel-Adatron algorithm: a fast and simple learning procedure for support vector machines. In: Proceedings of the fifteenth international conference on machine learning. Morgan Kaufmann Publishers Inc.; 1998. p. 188–196.Google Scholar