Automatic delineation of macular regions based on a locally defined contrast function

J. R.Harish Kumar, Rittwik Adhikari, Yogish Kamath, Rajani Jampala, Chandra Sekhar Seelamantula

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We consider the problem of fovea segmentation and develop a technique for delineation of macular regions based on the active-disc formalism that we recently introduced. The outlining problem is posed as one of the optimization of a locally defined contrast function using gradient-ascent maximization with respect to the affine transformation parameters that characterize the active disc. For automatic localization of the fovea and initialization of the active disc, we use the directional-derivative-based matched filter. We report validation results on three publicly available fundus image databases, amounting to a total of 1370 fundus images for automatic fovea localization and 370 fundus images for fovea segmentation and macular regions delineation. The proposed method results in a fovea localization accuracy of 100%, 92%, and 99.4%, and an average Dice similarity index of 77.78%, 67.46%, and 76.56% on DRIVE, DIARETDB0, and MESSIDOR fundus image databases, respectively. We have also developed an ImageJ plugin and an iOS App based on the proposed method.

Original languageEnglish
Title of host publication2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings
PublisherIEEE Computer Society
Pages1362-1366
Number of pages5
Volume2017-September
ISBN (Electronic)9781509021758
DOIs
Publication statusPublished - 20-02-2018
Event24th IEEE International Conference on Image Processing, ICIP 2017 - Beijing, China
Duration: 17-09-201720-09-2017

Conference

Conference24th IEEE International Conference on Image Processing, ICIP 2017
CountryChina
CityBeijing
Period17-09-1720-09-17

Fingerprint

Matched filters
Application programs
Derivatives
iOS (operating system)

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Kumar, J. R. H., Adhikari, R., Kamath, Y., Jampala, R., & Seelamantula, C. S. (2018). Automatic delineation of macular regions based on a locally defined contrast function. In 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings (Vol. 2017-September, pp. 1362-1366). IEEE Computer Society. https://doi.org/10.1109/ICIP.2017.8296504
Kumar, J. R.Harish ; Adhikari, Rittwik ; Kamath, Yogish ; Jampala, Rajani ; Seelamantula, Chandra Sekhar. / Automatic delineation of macular regions based on a locally defined contrast function. 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. Vol. 2017-September IEEE Computer Society, 2018. pp. 1362-1366
@inproceedings{8e4c1d4d18c647f89a36e0535c80142e,
title = "Automatic delineation of macular regions based on a locally defined contrast function",
abstract = "We consider the problem of fovea segmentation and develop a technique for delineation of macular regions based on the active-disc formalism that we recently introduced. The outlining problem is posed as one of the optimization of a locally defined contrast function using gradient-ascent maximization with respect to the affine transformation parameters that characterize the active disc. For automatic localization of the fovea and initialization of the active disc, we use the directional-derivative-based matched filter. We report validation results on three publicly available fundus image databases, amounting to a total of 1370 fundus images for automatic fovea localization and 370 fundus images for fovea segmentation and macular regions delineation. The proposed method results in a fovea localization accuracy of 100{\%}, 92{\%}, and 99.4{\%}, and an average Dice similarity index of 77.78{\%}, 67.46{\%}, and 76.56{\%} on DRIVE, DIARETDB0, and MESSIDOR fundus image databases, respectively. We have also developed an ImageJ plugin and an iOS App based on the proposed method.",
author = "Kumar, {J. R.Harish} and Rittwik Adhikari and Yogish Kamath and Rajani Jampala and Seelamantula, {Chandra Sekhar}",
year = "2018",
month = "2",
day = "20",
doi = "10.1109/ICIP.2017.8296504",
language = "English",
volume = "2017-September",
pages = "1362--1366",
booktitle = "2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings",
publisher = "IEEE Computer Society",
address = "United States",

}

Kumar, JRH, Adhikari, R, Kamath, Y, Jampala, R & Seelamantula, CS 2018, Automatic delineation of macular regions based on a locally defined contrast function. in 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. vol. 2017-September, IEEE Computer Society, pp. 1362-1366, 24th IEEE International Conference on Image Processing, ICIP 2017, Beijing, China, 17-09-17. https://doi.org/10.1109/ICIP.2017.8296504

Automatic delineation of macular regions based on a locally defined contrast function. / Kumar, J. R.Harish; Adhikari, Rittwik; Kamath, Yogish; Jampala, Rajani; Seelamantula, Chandra Sekhar.

2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. Vol. 2017-September IEEE Computer Society, 2018. p. 1362-1366.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Automatic delineation of macular regions based on a locally defined contrast function

AU - Kumar, J. R.Harish

AU - Adhikari, Rittwik

AU - Kamath, Yogish

AU - Jampala, Rajani

AU - Seelamantula, Chandra Sekhar

PY - 2018/2/20

Y1 - 2018/2/20

N2 - We consider the problem of fovea segmentation and develop a technique for delineation of macular regions based on the active-disc formalism that we recently introduced. The outlining problem is posed as one of the optimization of a locally defined contrast function using gradient-ascent maximization with respect to the affine transformation parameters that characterize the active disc. For automatic localization of the fovea and initialization of the active disc, we use the directional-derivative-based matched filter. We report validation results on three publicly available fundus image databases, amounting to a total of 1370 fundus images for automatic fovea localization and 370 fundus images for fovea segmentation and macular regions delineation. The proposed method results in a fovea localization accuracy of 100%, 92%, and 99.4%, and an average Dice similarity index of 77.78%, 67.46%, and 76.56% on DRIVE, DIARETDB0, and MESSIDOR fundus image databases, respectively. We have also developed an ImageJ plugin and an iOS App based on the proposed method.

AB - We consider the problem of fovea segmentation and develop a technique for delineation of macular regions based on the active-disc formalism that we recently introduced. The outlining problem is posed as one of the optimization of a locally defined contrast function using gradient-ascent maximization with respect to the affine transformation parameters that characterize the active disc. For automatic localization of the fovea and initialization of the active disc, we use the directional-derivative-based matched filter. We report validation results on three publicly available fundus image databases, amounting to a total of 1370 fundus images for automatic fovea localization and 370 fundus images for fovea segmentation and macular regions delineation. The proposed method results in a fovea localization accuracy of 100%, 92%, and 99.4%, and an average Dice similarity index of 77.78%, 67.46%, and 76.56% on DRIVE, DIARETDB0, and MESSIDOR fundus image databases, respectively. We have also developed an ImageJ plugin and an iOS App based on the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=85045296208&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045296208&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2017.8296504

DO - 10.1109/ICIP.2017.8296504

M3 - Conference contribution

VL - 2017-September

SP - 1362

EP - 1366

BT - 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings

PB - IEEE Computer Society

ER -

Kumar JRH, Adhikari R, Kamath Y, Jampala R, Seelamantula CS. Automatic delineation of macular regions based on a locally defined contrast function. In 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. Vol. 2017-September. IEEE Computer Society. 2018. p. 1362-1366 https://doi.org/10.1109/ICIP.2017.8296504