Fully Automated Segmentation of Fluid/Cyst Regions in Optical Coherence Tomography Images with Diabetic Macular Edema Using Neutrosophic Sets and Graph Algorithms

Abdolreza Rashno, Dara Koozekanani, Paul M. Drayna, Behzad Nazari, Saeed Sadri, Hossein Rabbani, Keshab K Parhi

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

This paper presents a fully automated algorithm to segment fluid-associated (fluid-filled) and cyst regions in optical coherence tomography (OCT) retina images of subjects with diabetic macular edema. The OCT image is segmented using a novel neutrosophic transformation and a graph-based shortest path method. In neutrosophic domain, an image g is transformed into three sets: T (true), I (indeterminate) that represents noise, and F (false). This paper makes four key contributions. First, a new method is introduced to compute the indeterminacy set I , and a new \lambda -correction operation is introduced to compute the set T in neutrosophic domain. Second, a graph shortest-path method is applied in neutrosophic domain to segment the inner limiting membrane and the retinal pigment epithelium as regions of interest (ROI) and outer plexiform layer and inner segment myeloid as middle layers using a novel definition of the edge weights. Third, a new cost function for cluster-based fluid/cyst segmentation in ROI is presented which also includes a novel approach in estimating the number of clusters in an automated manner. Fourth, the final fluid regions are achieved by ignoring very small regions and the regions between middle layers. The proposed method is evaluated using two publicly available datasets: Duke, Optima, and a third local dataset from the UMN clinic which is available online. The proposed algorithm outperforms the previously proposed Duke algorithm by 8% with respect to the dice coefficient and by 5% with respect to precision on the Duke dataset, while achieving about the same sensitivity. Also, the proposed algorithm outperforms a prior method for Optima dataset by 6%, 22%, and 23% with respect to the dice coefficient, sensitivity, and precision, respectively. Finally, the proposed algorithm also achieves sensitivity of 67.3%, 88.8%, and 76.7%, for the Duke, Optima, and the university of Minnesota (UMN) datasets, respectively.

Original languageEnglish (US)
Pages (from-to)989-1001
Number of pages13
JournalIEEE Transactions on Biomedical Engineering
Volume65
Issue number5
DOIs
StatePublished - May 2018

Fingerprint

Optical tomography
Fluids
Pigments
Cost functions
Membranes

Keywords

  • Diabetic macular edema
  • fluid/cyst segmentation
  • graph theory
  • neutrosophic set
  • optical coherence tomography

Cite this

Fully Automated Segmentation of Fluid/Cyst Regions in Optical Coherence Tomography Images with Diabetic Macular Edema Using Neutrosophic Sets and Graph Algorithms. / Rashno, Abdolreza; Koozekanani, Dara; Drayna, Paul M.; Nazari, Behzad; Sadri, Saeed; Rabbani, Hossein; Parhi, Keshab K.

In: IEEE Transactions on Biomedical Engineering, Vol. 65, No. 5, 05.2018, p. 989-1001.

Research output: Contribution to journalArticle

@article{fb2d0015b663494fa3fca491dcde4ecc,
title = "Fully Automated Segmentation of Fluid/Cyst Regions in Optical Coherence Tomography Images with Diabetic Macular Edema Using Neutrosophic Sets and Graph Algorithms",
abstract = "This paper presents a fully automated algorithm to segment fluid-associated (fluid-filled) and cyst regions in optical coherence tomography (OCT) retina images of subjects with diabetic macular edema. The OCT image is segmented using a novel neutrosophic transformation and a graph-based shortest path method. In neutrosophic domain, an image g is transformed into three sets: T (true), I (indeterminate) that represents noise, and F (false). This paper makes four key contributions. First, a new method is introduced to compute the indeterminacy set I , and a new \lambda -correction operation is introduced to compute the set T in neutrosophic domain. Second, a graph shortest-path method is applied in neutrosophic domain to segment the inner limiting membrane and the retinal pigment epithelium as regions of interest (ROI) and outer plexiform layer and inner segment myeloid as middle layers using a novel definition of the edge weights. Third, a new cost function for cluster-based fluid/cyst segmentation in ROI is presented which also includes a novel approach in estimating the number of clusters in an automated manner. Fourth, the final fluid regions are achieved by ignoring very small regions and the regions between middle layers. The proposed method is evaluated using two publicly available datasets: Duke, Optima, and a third local dataset from the UMN clinic which is available online. The proposed algorithm outperforms the previously proposed Duke algorithm by 8{\%} with respect to the dice coefficient and by 5{\%} with respect to precision on the Duke dataset, while achieving about the same sensitivity. Also, the proposed algorithm outperforms a prior method for Optima dataset by 6{\%}, 22{\%}, and 23{\%} with respect to the dice coefficient, sensitivity, and precision, respectively. Finally, the proposed algorithm also achieves sensitivity of 67.3{\%}, 88.8{\%}, and 76.7{\%}, for the Duke, Optima, and the university of Minnesota (UMN) datasets, respectively.",
keywords = "Diabetic macular edema, fluid/cyst segmentation, graph theory, neutrosophic set, optical coherence tomography",
author = "Abdolreza Rashno and Dara Koozekanani and Drayna, {Paul M.} and Behzad Nazari and Saeed Sadri and Hossein Rabbani and Parhi, {Keshab K}",
year = "2018",
month = "5",
doi = "10.1109/TBME.2017.2734058",
language = "English (US)",
volume = "65",
pages = "989--1001",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "5",

}

TY - JOUR

T1 - Fully Automated Segmentation of Fluid/Cyst Regions in Optical Coherence Tomography Images with Diabetic Macular Edema Using Neutrosophic Sets and Graph Algorithms

AU - Rashno, Abdolreza

AU - Koozekanani, Dara

AU - Drayna, Paul M.

AU - Nazari, Behzad

AU - Sadri, Saeed

AU - Rabbani, Hossein

AU - Parhi, Keshab K

PY - 2018/5

Y1 - 2018/5

N2 - This paper presents a fully automated algorithm to segment fluid-associated (fluid-filled) and cyst regions in optical coherence tomography (OCT) retina images of subjects with diabetic macular edema. The OCT image is segmented using a novel neutrosophic transformation and a graph-based shortest path method. In neutrosophic domain, an image g is transformed into three sets: T (true), I (indeterminate) that represents noise, and F (false). This paper makes four key contributions. First, a new method is introduced to compute the indeterminacy set I , and a new \lambda -correction operation is introduced to compute the set T in neutrosophic domain. Second, a graph shortest-path method is applied in neutrosophic domain to segment the inner limiting membrane and the retinal pigment epithelium as regions of interest (ROI) and outer plexiform layer and inner segment myeloid as middle layers using a novel definition of the edge weights. Third, a new cost function for cluster-based fluid/cyst segmentation in ROI is presented which also includes a novel approach in estimating the number of clusters in an automated manner. Fourth, the final fluid regions are achieved by ignoring very small regions and the regions between middle layers. The proposed method is evaluated using two publicly available datasets: Duke, Optima, and a third local dataset from the UMN clinic which is available online. The proposed algorithm outperforms the previously proposed Duke algorithm by 8% with respect to the dice coefficient and by 5% with respect to precision on the Duke dataset, while achieving about the same sensitivity. Also, the proposed algorithm outperforms a prior method for Optima dataset by 6%, 22%, and 23% with respect to the dice coefficient, sensitivity, and precision, respectively. Finally, the proposed algorithm also achieves sensitivity of 67.3%, 88.8%, and 76.7%, for the Duke, Optima, and the university of Minnesota (UMN) datasets, respectively.

AB - This paper presents a fully automated algorithm to segment fluid-associated (fluid-filled) and cyst regions in optical coherence tomography (OCT) retina images of subjects with diabetic macular edema. The OCT image is segmented using a novel neutrosophic transformation and a graph-based shortest path method. In neutrosophic domain, an image g is transformed into three sets: T (true), I (indeterminate) that represents noise, and F (false). This paper makes four key contributions. First, a new method is introduced to compute the indeterminacy set I , and a new \lambda -correction operation is introduced to compute the set T in neutrosophic domain. Second, a graph shortest-path method is applied in neutrosophic domain to segment the inner limiting membrane and the retinal pigment epithelium as regions of interest (ROI) and outer plexiform layer and inner segment myeloid as middle layers using a novel definition of the edge weights. Third, a new cost function for cluster-based fluid/cyst segmentation in ROI is presented which also includes a novel approach in estimating the number of clusters in an automated manner. Fourth, the final fluid regions are achieved by ignoring very small regions and the regions between middle layers. The proposed method is evaluated using two publicly available datasets: Duke, Optima, and a third local dataset from the UMN clinic which is available online. The proposed algorithm outperforms the previously proposed Duke algorithm by 8% with respect to the dice coefficient and by 5% with respect to precision on the Duke dataset, while achieving about the same sensitivity. Also, the proposed algorithm outperforms a prior method for Optima dataset by 6%, 22%, and 23% with respect to the dice coefficient, sensitivity, and precision, respectively. Finally, the proposed algorithm also achieves sensitivity of 67.3%, 88.8%, and 76.7%, for the Duke, Optima, and the university of Minnesota (UMN) datasets, respectively.

KW - Diabetic macular edema

KW - fluid/cyst segmentation

KW - graph theory

KW - neutrosophic set

KW - optical coherence tomography

UR - http://www.scopus.com/inward/record.url?scp=85028393046&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028393046&partnerID=8YFLogxK

U2 - 10.1109/TBME.2017.2734058

DO - 10.1109/TBME.2017.2734058

M3 - Article

C2 - 28783619

AN - SCOPUS:85028393046

VL - 65

SP - 989

EP - 1001

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 5

ER -