Automatic Segmentation of Optic Disc Using Affine Snakes in Gradient Vector Field

Sidhartha Dey, Kapil Tahiliani, J. R. Harish Kumar, A. K. Pediredla, Chandra Sekhar Seelamantula

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

Abstract

The optic disc is one of the prominent features of a retinal fundus image, and its segmentation is a critical component in automated retinal screening systems for ophthalmic anomalies, such as diabetic retinopathy and glaucoma. In this paper, we propose a novel method for optic disc segmentation using affine snakes, where the snake evolves using an affine transformation and requires a priori knowledge of the desired object shape. We determine the affine transformation parameters by first computing a force field on the image and then deforming the snake till the net force on the snake is zero. The affine snakes technique excels in its speed of convergence. This is attributed to the fact that only six parameters require optimization, the six parameters being the horizontal and vertical scaling, shearing and translation components of an affine transformation. Localization of the optic disc is done using normalized cross-correlation and segmentation is done using the affine snakes technique. This technique is tested on publicly available fundus image datasets, such as IDRiD, Drishti-GS, RIM-ONE, DRIONS-DB, and Messidor, with Dice In-dices of 0.943, 0.958, 0.933, 0.913, and 0.912, respectively.

Original languageEnglish
Title of host publication2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1204-1208
Number of pages5
ISBN (Electronic)9781479981311
DOIs
Publication statusPublished - 01-05-2019
Externally publishedYes
Event44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Brighton, United Kingdom
Duration: 12-05-201917-05-2019

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2019-May
ISSN (Print)1520-6149

Conference

Conference44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019
CountryUnited Kingdom
CityBrighton
Period12-05-1917-05-19

Fingerprint

Optics
Reaction injection molding
Shearing
Screening

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Dey, S., Tahiliani, K., Harish Kumar, J. R., Pediredla, A. K., & Seelamantula, C. S. (2019). Automatic Segmentation of Optic Disc Using Affine Snakes in Gradient Vector Field. In 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings (pp. 1204-1208). [8682408] (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2019-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2019.8682408
Dey, Sidhartha ; Tahiliani, Kapil ; Harish Kumar, J. R. ; Pediredla, A. K. ; Seelamantula, Chandra Sekhar. / Automatic Segmentation of Optic Disc Using Affine Snakes in Gradient Vector Field. 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 1204-1208 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).
@inproceedings{e395e08be1cf4fa19667e868027cc7e3,
title = "Automatic Segmentation of Optic Disc Using Affine Snakes in Gradient Vector Field",
abstract = "The optic disc is one of the prominent features of a retinal fundus image, and its segmentation is a critical component in automated retinal screening systems for ophthalmic anomalies, such as diabetic retinopathy and glaucoma. In this paper, we propose a novel method for optic disc segmentation using affine snakes, where the snake evolves using an affine transformation and requires a priori knowledge of the desired object shape. We determine the affine transformation parameters by first computing a force field on the image and then deforming the snake till the net force on the snake is zero. The affine snakes technique excels in its speed of convergence. This is attributed to the fact that only six parameters require optimization, the six parameters being the horizontal and vertical scaling, shearing and translation components of an affine transformation. Localization of the optic disc is done using normalized cross-correlation and segmentation is done using the affine snakes technique. This technique is tested on publicly available fundus image datasets, such as IDRiD, Drishti-GS, RIM-ONE, DRIONS-DB, and Messidor, with Dice In-dices of 0.943, 0.958, 0.933, 0.913, and 0.912, respectively.",
author = "Sidhartha Dey and Kapil Tahiliani and {Harish Kumar}, {J. R.} and Pediredla, {A. K.} and Seelamantula, {Chandra Sekhar}",
year = "2019",
month = "5",
day = "1",
doi = "10.1109/ICASSP.2019.8682408",
language = "English",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1204--1208",
booktitle = "2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings",
address = "United States",

}

Dey, S, Tahiliani, K, Harish Kumar, JR, Pediredla, AK & Seelamantula, CS 2019, Automatic Segmentation of Optic Disc Using Affine Snakes in Gradient Vector Field. in 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings., 8682408, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2019-May, Institute of Electrical and Electronics Engineers Inc., pp. 1204-1208, 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019, Brighton, United Kingdom, 12-05-19. https://doi.org/10.1109/ICASSP.2019.8682408

Automatic Segmentation of Optic Disc Using Affine Snakes in Gradient Vector Field. / Dey, Sidhartha; Tahiliani, Kapil; Harish Kumar, J. R.; Pediredla, A. K.; Seelamantula, Chandra Sekhar.

2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 1204-1208 8682408 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2019-May).

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

TY - GEN

T1 - Automatic Segmentation of Optic Disc Using Affine Snakes in Gradient Vector Field

AU - Dey, Sidhartha

AU - Tahiliani, Kapil

AU - Harish Kumar, J. R.

AU - Pediredla, A. K.

AU - Seelamantula, Chandra Sekhar

PY - 2019/5/1

Y1 - 2019/5/1

N2 - The optic disc is one of the prominent features of a retinal fundus image, and its segmentation is a critical component in automated retinal screening systems for ophthalmic anomalies, such as diabetic retinopathy and glaucoma. In this paper, we propose a novel method for optic disc segmentation using affine snakes, where the snake evolves using an affine transformation and requires a priori knowledge of the desired object shape. We determine the affine transformation parameters by first computing a force field on the image and then deforming the snake till the net force on the snake is zero. The affine snakes technique excels in its speed of convergence. This is attributed to the fact that only six parameters require optimization, the six parameters being the horizontal and vertical scaling, shearing and translation components of an affine transformation. Localization of the optic disc is done using normalized cross-correlation and segmentation is done using the affine snakes technique. This technique is tested on publicly available fundus image datasets, such as IDRiD, Drishti-GS, RIM-ONE, DRIONS-DB, and Messidor, with Dice In-dices of 0.943, 0.958, 0.933, 0.913, and 0.912, respectively.

AB - The optic disc is one of the prominent features of a retinal fundus image, and its segmentation is a critical component in automated retinal screening systems for ophthalmic anomalies, such as diabetic retinopathy and glaucoma. In this paper, we propose a novel method for optic disc segmentation using affine snakes, where the snake evolves using an affine transformation and requires a priori knowledge of the desired object shape. We determine the affine transformation parameters by first computing a force field on the image and then deforming the snake till the net force on the snake is zero. The affine snakes technique excels in its speed of convergence. This is attributed to the fact that only six parameters require optimization, the six parameters being the horizontal and vertical scaling, shearing and translation components of an affine transformation. Localization of the optic disc is done using normalized cross-correlation and segmentation is done using the affine snakes technique. This technique is tested on publicly available fundus image datasets, such as IDRiD, Drishti-GS, RIM-ONE, DRIONS-DB, and Messidor, with Dice In-dices of 0.943, 0.958, 0.933, 0.913, and 0.912, respectively.

UR - http://www.scopus.com/inward/record.url?scp=85068979384&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068979384&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2019.8682408

DO - 10.1109/ICASSP.2019.8682408

M3 - Conference contribution

AN - SCOPUS:85068979384

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 1204

EP - 1208

BT - 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Dey S, Tahiliani K, Harish Kumar JR, Pediredla AK, Seelamantula CS. Automatic Segmentation of Optic Disc Using Affine Snakes in Gradient Vector Field. In 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. p. 1204-1208. 8682408. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2019.8682408