Publication detail

Computer Vision Method for Grading of Health of a Fundus Image on Basis of Presence of Red Lesions

KOLAŘÍK, M. BURGET, R. UHER, V. DUTTA, M.

Original Title

Computer Vision Method for Grading of Health of a Fundus Image on Basis of Presence of Red Lesions

English Title

Computer Vision Method for Grading of Health of a Fundus Image on Basis of Presence of Red Lesions

Type

conference paper

Language

en

Original Abstract

Diabetic Retinopathy is one of those eye diseases which may cause permanent loss of vision if not treated at an early stage. The current paper proposes an algorithmic rule for detection of red lesions and grading the severity of a fundus image depending on its location in the image. Some significant and deciding objects like optic disc and macula are segmented using adaptive intensity-based threshold, geometrical features, kmeans clustering and morphological operations. Imaging techniques like color normalization, median filtering and morphological operations are used for segmentation of blood vessels and red lesions. Finally, a region-based framework has been used for grading the severity of the disease affecting the patient. The proposed method has achieved an accuracy of 89%. The proposed method has given encouraging results and can be used in development of some devices in this field.

English abstract

Diabetic Retinopathy is one of those eye diseases which may cause permanent loss of vision if not treated at an early stage. The current paper proposes an algorithmic rule for detection of red lesions and grading the severity of a fundus image depending on its location in the image. Some significant and deciding objects like optic disc and macula are segmented using adaptive intensity-based threshold, geometrical features, kmeans clustering and morphological operations. Imaging techniques like color normalization, median filtering and morphological operations are used for segmentation of blood vessels and red lesions. Finally, a region-based framework has been used for grading the severity of the disease affecting the patient. The proposed method has achieved an accuracy of 89%. The proposed method has given encouraging results and can be used in development of some devices in this field.

Keywords

Diabetic Retinopathy; Glaucoma; Fundus Images; Image Processing; Red Lesions; Blood Vessels; Optic Disc, Regionbased Grading

Released

04.07.2018

Publisher

IEEE

Location

Athens, Greece

ISBN

978-1-5386-4695-3

Book

Proceedings of the 2018 41st International Conference on Telecommunications and Signal Processing (TSP)

Pages from

222

Pages to

227

Pages count

6

BibTex


@inproceedings{BUT148983,
  author="Martin {Kolařík} and Radim {Burget} and Malay Kishore {Dutta} and Sayantan {Bhattacharya} and Jai {Sehgal} and Ashish {Issac}",
  title="Computer Vision Method for Grading of Health of a Fundus Image on Basis of Presence of Red Lesions",
  annote="Diabetic Retinopathy is one of those eye diseases which may cause permanent loss of vision if not treated at an early stage. The current paper proposes an algorithmic rule for detection of red lesions and grading the severity of a fundus image depending on its location in the image. Some significant and deciding objects like optic disc and macula are segmented using adaptive intensity-based threshold, geometrical features, kmeans clustering and morphological operations. Imaging techniques like color normalization, median filtering and morphological operations are used for segmentation of blood vessels and red lesions. Finally, a region-based framework has been used for grading the severity of the disease affecting the patient. The proposed method has achieved an accuracy of 89%. The proposed method has given encouraging results and can be used in development of some devices in this field.",
  address="IEEE",
  booktitle="Proceedings of the 2018 41st International Conference on Telecommunications and Signal Processing (TSP)",
  chapter="148983",
  howpublished="online",
  institution="IEEE",
  year="2018",
  month="july",
  pages="222--227",
  publisher="IEEE",
  type="conference paper"
}