Automatic identification of pathology-distorted retinal layer boundaries using SD-OCT imaging

Md Akter Hussain, Alauddin Bhuiyan, Andrew Turpin, Chi D Luu, Roland Theodore Smith, Robyn H. Guymer, Ramamohanrao Kotagiri

Research output: Contribution to journalArticleResearchpeer-review

12 Citations (Scopus)

Abstract

Objective: We propose an effective automatic method for identification of four retinal layer boundaries from the spectral domain optical coherence tomography images in the presence and absence of pathologies and morphological changes due to disease. Methods: The approach first finds an approximate location of three reference layers and then uses these to bound the search space for the actual layers, which is achieved by modeling the problem as a graph and applying Dijkstra's shortest path algorithm. The edge weight between nodes is determined using pixel distance, slope similarity to a reference, and nonassociativity of the layers, which is designed to overcome the distorting effects that pathology can play in the boundary determination. Results: The accuracy of our method was evaluated on three different datasets. It outperforms the current five state-of-the-art methods. On average, the mean and standard deviation of the root-mean-square error in the form of mean ± standard deviation in pixels for our method is 1.57 ±0.69, which is lower than compared to the existing top five methods of 16.17 ± 22.64, 6.66 ± 9.11, 5.70 ± 10.54, 3.69 ± 2.04, and 2.29 ± 1.54. Conclusion: Our method is highly accurate, robust, reliable, and consistent. This identification can enable to quantify the biomarkers of the retina in largescale study for assessing, monitoring disease progression, as well as early detection of retinal diseases. Significance: Identification of these boundaries can help to determine the loss of neuroretinal cells or layers and the presence of retinal pathology, which can be used as features for the automatic determination of the stages of retinal diseases.

Original languageEnglish
Article number7593230
Pages (from-to)1638-1649
Number of pages12
JournalIEEE Transactions on Biomedical Engineering
Volume64
Issue number7
DOIs
Publication statusPublished - 1 Jul 2017
Externally publishedYes

Keywords

  • Biomedical optical imaging
  • Image segmentation
  • Layer segmentation
  • Retina
  • Shortest path problem
  • Spectral domain optical coherence tomography (SD-OCT)

Cite this

Hussain, Md Akter ; Bhuiyan, Alauddin ; Turpin, Andrew ; Luu, Chi D ; Smith, Roland Theodore ; Guymer, Robyn H. ; Kotagiri, Ramamohanrao. / Automatic identification of pathology-distorted retinal layer boundaries using SD-OCT imaging. In: IEEE Transactions on Biomedical Engineering. 2017 ; Vol. 64, No. 7. pp. 1638-1649.
@article{06c9a530f3b24864a8edfe08e9bc5624,
title = "Automatic identification of pathology-distorted retinal layer boundaries using SD-OCT imaging",
abstract = "Objective: We propose an effective automatic method for identification of four retinal layer boundaries from the spectral domain optical coherence tomography images in the presence and absence of pathologies and morphological changes due to disease. Methods: The approach first finds an approximate location of three reference layers and then uses these to bound the search space for the actual layers, which is achieved by modeling the problem as a graph and applying Dijkstra's shortest path algorithm. The edge weight between nodes is determined using pixel distance, slope similarity to a reference, and nonassociativity of the layers, which is designed to overcome the distorting effects that pathology can play in the boundary determination. Results: The accuracy of our method was evaluated on three different datasets. It outperforms the current five state-of-the-art methods. On average, the mean and standard deviation of the root-mean-square error in the form of mean ± standard deviation in pixels for our method is 1.57 ±0.69, which is lower than compared to the existing top five methods of 16.17 ± 22.64, 6.66 ± 9.11, 5.70 ± 10.54, 3.69 ± 2.04, and 2.29 ± 1.54. Conclusion: Our method is highly accurate, robust, reliable, and consistent. This identification can enable to quantify the biomarkers of the retina in largescale study for assessing, monitoring disease progression, as well as early detection of retinal diseases. Significance: Identification of these boundaries can help to determine the loss of neuroretinal cells or layers and the presence of retinal pathology, which can be used as features for the automatic determination of the stages of retinal diseases.",
keywords = "Biomedical optical imaging, Image segmentation, Layer segmentation, Retina, Shortest path problem, Spectral domain optical coherence tomography (SD-OCT)",
author = "Hussain, {Md Akter} and Alauddin Bhuiyan and Andrew Turpin and Luu, {Chi D} and Smith, {Roland Theodore} and Guymer, {Robyn H.} and Ramamohanrao Kotagiri",
year = "2017",
month = "7",
day = "1",
doi = "10.1109/TBME.2016.2619120",
language = "English",
volume = "64",
pages = "1638--1649",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
number = "7",

}

Automatic identification of pathology-distorted retinal layer boundaries using SD-OCT imaging. / Hussain, Md Akter; Bhuiyan, Alauddin; Turpin, Andrew; Luu, Chi D; Smith, Roland Theodore; Guymer, Robyn H.; Kotagiri, Ramamohanrao.

In: IEEE Transactions on Biomedical Engineering, Vol. 64, No. 7, 7593230, 01.07.2017, p. 1638-1649.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Automatic identification of pathology-distorted retinal layer boundaries using SD-OCT imaging

AU - Hussain, Md Akter

AU - Bhuiyan, Alauddin

AU - Turpin, Andrew

AU - Luu, Chi D

AU - Smith, Roland Theodore

AU - Guymer, Robyn H.

AU - Kotagiri, Ramamohanrao

PY - 2017/7/1

Y1 - 2017/7/1

N2 - Objective: We propose an effective automatic method for identification of four retinal layer boundaries from the spectral domain optical coherence tomography images in the presence and absence of pathologies and morphological changes due to disease. Methods: The approach first finds an approximate location of three reference layers and then uses these to bound the search space for the actual layers, which is achieved by modeling the problem as a graph and applying Dijkstra's shortest path algorithm. The edge weight between nodes is determined using pixel distance, slope similarity to a reference, and nonassociativity of the layers, which is designed to overcome the distorting effects that pathology can play in the boundary determination. Results: The accuracy of our method was evaluated on three different datasets. It outperforms the current five state-of-the-art methods. On average, the mean and standard deviation of the root-mean-square error in the form of mean ± standard deviation in pixels for our method is 1.57 ±0.69, which is lower than compared to the existing top five methods of 16.17 ± 22.64, 6.66 ± 9.11, 5.70 ± 10.54, 3.69 ± 2.04, and 2.29 ± 1.54. Conclusion: Our method is highly accurate, robust, reliable, and consistent. This identification can enable to quantify the biomarkers of the retina in largescale study for assessing, monitoring disease progression, as well as early detection of retinal diseases. Significance: Identification of these boundaries can help to determine the loss of neuroretinal cells or layers and the presence of retinal pathology, which can be used as features for the automatic determination of the stages of retinal diseases.

AB - Objective: We propose an effective automatic method for identification of four retinal layer boundaries from the spectral domain optical coherence tomography images in the presence and absence of pathologies and morphological changes due to disease. Methods: The approach first finds an approximate location of three reference layers and then uses these to bound the search space for the actual layers, which is achieved by modeling the problem as a graph and applying Dijkstra's shortest path algorithm. The edge weight between nodes is determined using pixel distance, slope similarity to a reference, and nonassociativity of the layers, which is designed to overcome the distorting effects that pathology can play in the boundary determination. Results: The accuracy of our method was evaluated on three different datasets. It outperforms the current five state-of-the-art methods. On average, the mean and standard deviation of the root-mean-square error in the form of mean ± standard deviation in pixels for our method is 1.57 ±0.69, which is lower than compared to the existing top five methods of 16.17 ± 22.64, 6.66 ± 9.11, 5.70 ± 10.54, 3.69 ± 2.04, and 2.29 ± 1.54. Conclusion: Our method is highly accurate, robust, reliable, and consistent. This identification can enable to quantify the biomarkers of the retina in largescale study for assessing, monitoring disease progression, as well as early detection of retinal diseases. Significance: Identification of these boundaries can help to determine the loss of neuroretinal cells or layers and the presence of retinal pathology, which can be used as features for the automatic determination of the stages of retinal diseases.

KW - Biomedical optical imaging

KW - Image segmentation

KW - Layer segmentation

KW - Retina

KW - Shortest path problem

KW - Spectral domain optical coherence tomography (SD-OCT)

UR - http://www.scopus.com/inward/record.url?scp=85026757559&partnerID=8YFLogxK

U2 - 10.1109/TBME.2016.2619120

DO - 10.1109/TBME.2016.2619120

M3 - Article

VL - 64

SP - 1638

EP - 1649

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 7

M1 - 7593230

ER -