Automated detection of optic disc contours in fundus images using decision tree classifier

Sumaiya Pathan, Preetham Kumar, Radhika Pai, Sulatha V. Bhandary

Research output: Contribution to journalArticle

Abstract

Automated segmentation of optic disc in fundus images plays a vital role in computer aided diagnosis (CAD) of eye pathologies. In this paper, a novel method is proposed which detects and excludes the blood vessel for accurate optic disc segmentation. This is achieved in two steps. First, an effective blood vessel detection and exclusion algorithm is developed using directional filter. In the second step, a decision tree classifier is used to obtain an adaptive threshold in order to detect the contour of optic disc. The proposed method aids in computationally robust segmentation of optic disc even in fundus images having illuminations, reflections and exudates. The proposed method is tested on two different datasets which includes 300 fundus images collected from Kasturba Medical College (KMC) Manipal and also the publically available RIM-ONE database. The average values of Jaccard index, dice coefficient, sensitivity, specificity and accuracy obtained for KMC images is 91.28 %, 94.17 %, 92.71 %, 99.89 % and 99.61 % respectively. For RIM-ONE database the obtained average values of Jaccard index, dice coefficient, sensitivity, specificity and accuracy are 85.30 %, 90.69 %, 93.90 %, 99.39 % and 99.15 % respectively. The obtained segmentation results proves the efficiency of the algorithm to be incorporated in CAD of eye diseases.

Original languageEnglish
Pages (from-to)52-64
Number of pages13
JournalBiocybernetics and Biomedical Engineering
Volume40
Issue number1
DOIs
Publication statusPublished - 01-01-2020

Fingerprint

Decision trees
Optics
Classifiers
Reaction injection molding
Computer aided diagnosis
Blood vessels
Pathology
Lighting

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering

Cite this

@article{ffda3a1731b84d8ab85c58e350f15def,
title = "Automated detection of optic disc contours in fundus images using decision tree classifier",
abstract = "Automated segmentation of optic disc in fundus images plays a vital role in computer aided diagnosis (CAD) of eye pathologies. In this paper, a novel method is proposed which detects and excludes the blood vessel for accurate optic disc segmentation. This is achieved in two steps. First, an effective blood vessel detection and exclusion algorithm is developed using directional filter. In the second step, a decision tree classifier is used to obtain an adaptive threshold in order to detect the contour of optic disc. The proposed method aids in computationally robust segmentation of optic disc even in fundus images having illuminations, reflections and exudates. The proposed method is tested on two different datasets which includes 300 fundus images collected from Kasturba Medical College (KMC) Manipal and also the publically available RIM-ONE database. The average values of Jaccard index, dice coefficient, sensitivity, specificity and accuracy obtained for KMC images is 91.28 {\%}, 94.17 {\%}, 92.71 {\%}, 99.89 {\%} and 99.61 {\%} respectively. For RIM-ONE database the obtained average values of Jaccard index, dice coefficient, sensitivity, specificity and accuracy are 85.30 {\%}, 90.69 {\%}, 93.90 {\%}, 99.39 {\%} and 99.15 {\%} respectively. The obtained segmentation results proves the efficiency of the algorithm to be incorporated in CAD of eye diseases.",
author = "Sumaiya Pathan and Preetham Kumar and Radhika Pai and Bhandary, {Sulatha V.}",
year = "2020",
month = "1",
day = "1",
doi = "10.1016/j.bbe.2019.11.003",
language = "English",
volume = "40",
pages = "52--64",
journal = "Biocybernetics and Biomedical Engineering",
issn = "0208-5216",
publisher = "PWN-Polish Scientific Publishers",
number = "1",

}

Automated detection of optic disc contours in fundus images using decision tree classifier. / Pathan, Sumaiya; Kumar, Preetham; Pai, Radhika; Bhandary, Sulatha V.

In: Biocybernetics and Biomedical Engineering, Vol. 40, No. 1, 01.01.2020, p. 52-64.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automated detection of optic disc contours in fundus images using decision tree classifier

AU - Pathan, Sumaiya

AU - Kumar, Preetham

AU - Pai, Radhika

AU - Bhandary, Sulatha V.

PY - 2020/1/1

Y1 - 2020/1/1

N2 - Automated segmentation of optic disc in fundus images plays a vital role in computer aided diagnosis (CAD) of eye pathologies. In this paper, a novel method is proposed which detects and excludes the blood vessel for accurate optic disc segmentation. This is achieved in two steps. First, an effective blood vessel detection and exclusion algorithm is developed using directional filter. In the second step, a decision tree classifier is used to obtain an adaptive threshold in order to detect the contour of optic disc. The proposed method aids in computationally robust segmentation of optic disc even in fundus images having illuminations, reflections and exudates. The proposed method is tested on two different datasets which includes 300 fundus images collected from Kasturba Medical College (KMC) Manipal and also the publically available RIM-ONE database. The average values of Jaccard index, dice coefficient, sensitivity, specificity and accuracy obtained for KMC images is 91.28 %, 94.17 %, 92.71 %, 99.89 % and 99.61 % respectively. For RIM-ONE database the obtained average values of Jaccard index, dice coefficient, sensitivity, specificity and accuracy are 85.30 %, 90.69 %, 93.90 %, 99.39 % and 99.15 % respectively. The obtained segmentation results proves the efficiency of the algorithm to be incorporated in CAD of eye diseases.

AB - Automated segmentation of optic disc in fundus images plays a vital role in computer aided diagnosis (CAD) of eye pathologies. In this paper, a novel method is proposed which detects and excludes the blood vessel for accurate optic disc segmentation. This is achieved in two steps. First, an effective blood vessel detection and exclusion algorithm is developed using directional filter. In the second step, a decision tree classifier is used to obtain an adaptive threshold in order to detect the contour of optic disc. The proposed method aids in computationally robust segmentation of optic disc even in fundus images having illuminations, reflections and exudates. The proposed method is tested on two different datasets which includes 300 fundus images collected from Kasturba Medical College (KMC) Manipal and also the publically available RIM-ONE database. The average values of Jaccard index, dice coefficient, sensitivity, specificity and accuracy obtained for KMC images is 91.28 %, 94.17 %, 92.71 %, 99.89 % and 99.61 % respectively. For RIM-ONE database the obtained average values of Jaccard index, dice coefficient, sensitivity, specificity and accuracy are 85.30 %, 90.69 %, 93.90 %, 99.39 % and 99.15 % respectively. The obtained segmentation results proves the efficiency of the algorithm to be incorporated in CAD of eye diseases.

UR - http://www.scopus.com/inward/record.url?scp=85076091224&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85076091224&partnerID=8YFLogxK

U2 - 10.1016/j.bbe.2019.11.003

DO - 10.1016/j.bbe.2019.11.003

M3 - Article

AN - SCOPUS:85076091224

VL - 40

SP - 52

EP - 64

JO - Biocybernetics and Biomedical Engineering

JF - Biocybernetics and Biomedical Engineering

SN - 0208-5216

IS - 1

ER -