Automatic Detection of Retinal Exudates using a Support Vector Machine

Authors

  • Kittipol WISAENG Department of Computer Science, King Mongkut's Institute of Technology Ladkrabang, Bangkok 10520, Thailand
  • Nualsawat HIRANSAKOLWONG Department of Computer Science, King Mongkut's Institute of Technology Ladkrabang, Bangkok 10520, Thailand
  • Ekkarat POTHIRUK Ophthalmology Unit, Khonkaen Hospital, Khonkaen 40000, Thailand.

Keywords:

Exudates, Diabetic retinopathy, Digital retinal image, Support vector machine

Abstract

Retinal exudates are among the preliminary signs of diabetic retinopathy, a major cause of vision loss in diabetic patients. Correct and efficient screening of exudates is very expensive in professional time and may cause human error. Nowadays, the digital retinal image is frequently used to follow-up and diagnoses eye diseases. Therefore, the retinal image is crucial and essential for experts to detect exudates. Unfortunately, it is a normal situation that retinal images in Thailand are poor quality images. In this paper, we present a series of experiments on feature selection and exudates classification using the support vector machine classifiers. The retinal images are segmented following key preprocessing steps, i.e., color normalization, contrast enhancement, noise removal and color space selection. On data sets of poor quality images, sensitivity, specificity and accuracy is 94.46%, 89.52% and 92.14%, respectively.

Downloads

Published

25.02.2013

How to Cite

1.
WISAENG K, HIRANSAKOLWONG N, POTHIRUK E. Automatic Detection of Retinal Exudates using a Support Vector Machine. Appl Med Inform [Internet]. 2013 Feb. 25 [cited 2024 Jul. 16];32(1):33-42. Available from: https://ami.info.umfcluj.ro/index.php/AMI/article/view/406

Issue

Section

Articles