Segmentation of Optic Nerve Head Using Two-stage Snakes in Generalized Gradient Vector Field

J. R. Harish Kumar; Sayan Dutta; Avinash Sonthalia; Namratha Pai

doi:10.1109/INDICON56171.2022.10039761

Segmentation of Optic Nerve Head Using Two-stage Snakes in Generalized Gradient Vector Field

J. R. Harish Kumar^*
, Sayan Dutta
, Avinash Sonthalia
, Namratha Pai

^*Corresponding author for this work

Manipal Institute of Technology, Manipal

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

We propose a generalized gradient vector field based two-stage affine snakes method for the segmentation of optic nerve head in retinal fundus images. We obtain the course segmentation using affine transformation of an elliptical shape prior that tends to converge iteratively based on the force computations in generalized gradient vector field of the fundus image. We optimize six affine parameters out of which two for scaling, two for shearing, and two for translation of the shape prior. We obtain the fine segmentation using point snakes algorithm. The two-stage idea resulted in fast convergence of the snake on the optic disc with great segmentation accuracy. The detection of the optic nerve head is done using normalized template matching technique. The proposed method is validated on various publicly available fundus image datasets such as Drions-DB, IDRiD, RIM-ONE, Messidor, and Drishti-GS, resulting in Dice similarity index of 0.91, 0.94, 0.94, 0.91 and 0.95, respectively.

Original language	English
Title of host publication	INDICON 2022 - 2022 IEEE 19th India Council International Conference
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665473507
DOIs	https://doi.org/10.1109/INDICON56171.2022.10039761
Publication status	Published - 2022
Event	19th IEEE India Council International Conference, INDICON 2022 - Kochi, India Duration: 24-11-2022 → 26-11-2022

Publication series

Name	INDICON 2022 - 2022 IEEE 19th India Council International Conference

Conference

Conference	19th IEEE India Council International Conference, INDICON 2022
Country/Territory	India
City	Kochi
Period	24-11-22 → 26-11-22

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

All Science Journal Classification (ASJC) codes

Computer Networks and Communications
Energy Engineering and Power Technology
Renewable Energy, Sustainability and the Environment
Electrical and Electronic Engineering
Safety, Risk, Reliability and Quality
Modelling and Simulation

Access to Document

10.1109/INDICON56171.2022.10039761

Cite this

Harish Kumar, J. R., Dutta, S., Sonthalia, A., & Pai, N. (2022). Segmentation of Optic Nerve Head Using Two-stage Snakes in Generalized Gradient Vector Field. In INDICON 2022 - 2022 IEEE 19th India Council International Conference (INDICON 2022 - 2022 IEEE 19th India Council International Conference). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/INDICON56171.2022.10039761

@inproceedings{a3e7f01388c242dd96873611255c705a,

title = "Segmentation of Optic Nerve Head Using Two-stage Snakes in Generalized Gradient Vector Field",

abstract = "We propose a generalized gradient vector field based two-stage affine snakes method for the segmentation of optic nerve head in retinal fundus images. We obtain the course segmentation using affine transformation of an elliptical shape prior that tends to converge iteratively based on the force computations in generalized gradient vector field of the fundus image. We optimize six affine parameters out of which two for scaling, two for shearing, and two for translation of the shape prior. We obtain the fine segmentation using point snakes algorithm. The two-stage idea resulted in fast convergence of the snake on the optic disc with great segmentation accuracy. The detection of the optic nerve head is done using normalized template matching technique. The proposed method is validated on various publicly available fundus image datasets such as Drions-DB, IDRiD, RIM-ONE, Messidor, and Drishti-GS, resulting in Dice similarity index of 0.91, 0.94, 0.94, 0.91 and 0.95, respectively.",

author = "\{Harish Kumar\}, \{J. R.\} and Sayan Dutta and Avinash Sonthalia and Namratha Pai",

note = "Funding Information: This work is supported by the Science and Engineering Research Board (SERB) - Teachers Associateship for Research Excellence (TARE) Fellowship (No. TAR/2019/000037). Publisher Copyright: {\textcopyright} 2022 IEEE.; 19th IEEE India Council International Conference, INDICON 2022 ; Conference date: 24-11-2022 Through 26-11-2022",

year = "2022",

doi = "10.1109/INDICON56171.2022.10039761",

language = "English",

series = "INDICON 2022 - 2022 IEEE 19th India Council International Conference",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "INDICON 2022 - 2022 IEEE 19th India Council International Conference",

address = "United States",

}

Harish Kumar, JR, Dutta, S, Sonthalia, A & Pai, N 2022, Segmentation of Optic Nerve Head Using Two-stage Snakes in Generalized Gradient Vector Field. in INDICON 2022 - 2022 IEEE 19th India Council International Conference. INDICON 2022 - 2022 IEEE 19th India Council International Conference, Institute of Electrical and Electronics Engineers Inc., 19th IEEE India Council International Conference, INDICON 2022, Kochi, India, 24-11-22. https://doi.org/10.1109/INDICON56171.2022.10039761

Segmentation of Optic Nerve Head Using Two-stage Snakes in Generalized Gradient Vector Field. / Harish Kumar, J. R.; Dutta, Sayan; Sonthalia, Avinash et al.
INDICON 2022 - 2022 IEEE 19th India Council International Conference. Institute of Electrical and Electronics Engineers Inc., 2022. (INDICON 2022 - 2022 IEEE 19th India Council International Conference).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Segmentation of Optic Nerve Head Using Two-stage Snakes in Generalized Gradient Vector Field

AU - Harish Kumar, J. R.

AU - Dutta, Sayan

AU - Sonthalia, Avinash

AU - Pai, Namratha

N1 - Funding Information: This work is supported by the Science and Engineering Research Board (SERB) - Teachers Associateship for Research Excellence (TARE) Fellowship (No. TAR/2019/000037). Publisher Copyright: © 2022 IEEE.

PY - 2022

Y1 - 2022

N2 - We propose a generalized gradient vector field based two-stage affine snakes method for the segmentation of optic nerve head in retinal fundus images. We obtain the course segmentation using affine transformation of an elliptical shape prior that tends to converge iteratively based on the force computations in generalized gradient vector field of the fundus image. We optimize six affine parameters out of which two for scaling, two for shearing, and two for translation of the shape prior. We obtain the fine segmentation using point snakes algorithm. The two-stage idea resulted in fast convergence of the snake on the optic disc with great segmentation accuracy. The detection of the optic nerve head is done using normalized template matching technique. The proposed method is validated on various publicly available fundus image datasets such as Drions-DB, IDRiD, RIM-ONE, Messidor, and Drishti-GS, resulting in Dice similarity index of 0.91, 0.94, 0.94, 0.91 and 0.95, respectively.

AB - We propose a generalized gradient vector field based two-stage affine snakes method for the segmentation of optic nerve head in retinal fundus images. We obtain the course segmentation using affine transformation of an elliptical shape prior that tends to converge iteratively based on the force computations in generalized gradient vector field of the fundus image. We optimize six affine parameters out of which two for scaling, two for shearing, and two for translation of the shape prior. We obtain the fine segmentation using point snakes algorithm. The two-stage idea resulted in fast convergence of the snake on the optic disc with great segmentation accuracy. The detection of the optic nerve head is done using normalized template matching technique. The proposed method is validated on various publicly available fundus image datasets such as Drions-DB, IDRiD, RIM-ONE, Messidor, and Drishti-GS, resulting in Dice similarity index of 0.91, 0.94, 0.94, 0.91 and 0.95, respectively.

UR - https://www.scopus.com/pages/publications/85149199025

UR - https://www.scopus.com/pages/publications/85149199025#tab=citedBy

U2 - 10.1109/INDICON56171.2022.10039761

DO - 10.1109/INDICON56171.2022.10039761

M3 - Conference contribution

AN - SCOPUS:85149199025

T3 - INDICON 2022 - 2022 IEEE 19th India Council International Conference

BT - INDICON 2022 - 2022 IEEE 19th India Council International Conference

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 19th IEEE India Council International Conference, INDICON 2022

Y2 - 24 November 2022 through 26 November 2022

ER -

Harish Kumar JR, Dutta S, Sonthalia A, Pai N. Segmentation of Optic Nerve Head Using Two-stage Snakes in Generalized Gradient Vector Field. In INDICON 2022 - 2022 IEEE 19th India Council International Conference. Institute of Electrical and Electronics Engineers Inc. 2022. (INDICON 2022 - 2022 IEEE 19th India Council International Conference). doi: 10.1109/INDICON56171.2022.10039761

Segmentation of Optic Nerve Head Using Two-stage Snakes in Generalized Gradient Vector Field

Abstract

Publication series

Conference

UN SDGs

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this