A benchmark study of automated intra-retinal cyst segmentation algorithms using optical coherence tomography B-scans

G. N. Girish, V. A. Anima, Abhishek R. Kothari, P. V. Sudeep, Sohini Roychowdhury, Jeny Rajan

Research output: Contribution to journalArticle

  • 4 Citations

Abstract

(Background and objectives) Retinal cysts are formed by accumulation of fluid in the retina caused by leakages from inflammation or vitreous fractures. Analysis of the retinal cystic spaces holds significance in detection and treatment of several ocular diseases like age-related macular degeneration, diabetic macular edema etc. Thus, segmentation of intra-retinal cysts and quantification of cystic spaces are vital for retinal pathology and severity detection. In the recent years, automated segmentation of intra-retinal cysts using optical coherence tomography B-scans has gained significant importance in the field of retinal image analysis. The objective of this paper is to compare different intra-retinal cyst segmentation algorithms for comparative analysis and benchmarking purposes. (Methods) In this work, we employ a modular approach for standardizing the different segmentation algorithms. Further, we analyze the variations in automated cyst segmentation performances and method scalability across image acquisition systems by using the publicly available cyst segmentation challenge dataset (OPTIMA cyst segmentation challenge). (Results) Several key automated methods are comparatively analyzed using quantitative and qualitative experiments. Our analysis demonstrates the significance of variations in signal-to-noise ratio (SNR), retinal layer morphology and post-processing steps on the automated cyst segmentation processes. (Conclusion) This benchmarking study provides insights towards the scalability of automated processes across vendor-specific imaging modalities to provide guidance for retinal pathology diagnostics and treatment processes.

LanguageEnglish
Pages105-114
Number of pages10
JournalComputer Methods and Programs in Biomedicine
Volume153
DOIs
Publication statusPublished - 01-01-2018
Externally publishedYes

Fingerprint

Benchmarking
Optical tomography
Optical Coherence Tomography
Pathology
Scalability
Cysts
Image acquisition
Leakage (fluid)
Image analysis
Signal to noise ratio
Imaging techniques
Fluids
Processing
Experiments
Macular Edema
Eye Diseases
Macular Degeneration
Signal-To-Noise Ratio
Retina
Inflammation

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Science Applications
  • Health Informatics

Cite this

Girish, G. N. ; Anima, V. A. ; Kothari, Abhishek R. ; Sudeep, P. V. ; Roychowdhury, Sohini ; Rajan, Jeny. / A benchmark study of automated intra-retinal cyst segmentation algorithms using optical coherence tomography B-scans. In: Computer Methods and Programs in Biomedicine. 2018 ; Vol. 153. pp. 105-114.
@article{f13acb82df754af5abcf87009fed3232,
title = "A benchmark study of automated intra-retinal cyst segmentation algorithms using optical coherence tomography B-scans",
abstract = "(Background and objectives) Retinal cysts are formed by accumulation of fluid in the retina caused by leakages from inflammation or vitreous fractures. Analysis of the retinal cystic spaces holds significance in detection and treatment of several ocular diseases like age-related macular degeneration, diabetic macular edema etc. Thus, segmentation of intra-retinal cysts and quantification of cystic spaces are vital for retinal pathology and severity detection. In the recent years, automated segmentation of intra-retinal cysts using optical coherence tomography B-scans has gained significant importance in the field of retinal image analysis. The objective of this paper is to compare different intra-retinal cyst segmentation algorithms for comparative analysis and benchmarking purposes. (Methods) In this work, we employ a modular approach for standardizing the different segmentation algorithms. Further, we analyze the variations in automated cyst segmentation performances and method scalability across image acquisition systems by using the publicly available cyst segmentation challenge dataset (OPTIMA cyst segmentation challenge). (Results) Several key automated methods are comparatively analyzed using quantitative and qualitative experiments. Our analysis demonstrates the significance of variations in signal-to-noise ratio (SNR), retinal layer morphology and post-processing steps on the automated cyst segmentation processes. (Conclusion) This benchmarking study provides insights towards the scalability of automated processes across vendor-specific imaging modalities to provide guidance for retinal pathology diagnostics and treatment processes.",
author = "Girish, {G. N.} and Anima, {V. A.} and Kothari, {Abhishek R.} and Sudeep, {P. V.} and Sohini Roychowdhury and Jeny Rajan",
year = "2018",
month = "1",
day = "1",
doi = "10.1016/j.cmpb.2017.10.010",
language = "English",
volume = "153",
pages = "105--114",
journal = "Computer Methods and Programs in Biomedicine",
issn = "0169-2607",
publisher = "Elsevier Ireland Ltd",

}

A benchmark study of automated intra-retinal cyst segmentation algorithms using optical coherence tomography B-scans. / Girish, G. N.; Anima, V. A.; Kothari, Abhishek R.; Sudeep, P. V.; Roychowdhury, Sohini; Rajan, Jeny.

In: Computer Methods and Programs in Biomedicine, Vol. 153, 01.01.2018, p. 105-114.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A benchmark study of automated intra-retinal cyst segmentation algorithms using optical coherence tomography B-scans

AU - Girish, G. N.

AU - Anima, V. A.

AU - Kothari, Abhishek R.

AU - Sudeep, P. V.

AU - Roychowdhury, Sohini

AU - Rajan, Jeny

PY - 2018/1/1

Y1 - 2018/1/1

N2 - (Background and objectives) Retinal cysts are formed by accumulation of fluid in the retina caused by leakages from inflammation or vitreous fractures. Analysis of the retinal cystic spaces holds significance in detection and treatment of several ocular diseases like age-related macular degeneration, diabetic macular edema etc. Thus, segmentation of intra-retinal cysts and quantification of cystic spaces are vital for retinal pathology and severity detection. In the recent years, automated segmentation of intra-retinal cysts using optical coherence tomography B-scans has gained significant importance in the field of retinal image analysis. The objective of this paper is to compare different intra-retinal cyst segmentation algorithms for comparative analysis and benchmarking purposes. (Methods) In this work, we employ a modular approach for standardizing the different segmentation algorithms. Further, we analyze the variations in automated cyst segmentation performances and method scalability across image acquisition systems by using the publicly available cyst segmentation challenge dataset (OPTIMA cyst segmentation challenge). (Results) Several key automated methods are comparatively analyzed using quantitative and qualitative experiments. Our analysis demonstrates the significance of variations in signal-to-noise ratio (SNR), retinal layer morphology and post-processing steps on the automated cyst segmentation processes. (Conclusion) This benchmarking study provides insights towards the scalability of automated processes across vendor-specific imaging modalities to provide guidance for retinal pathology diagnostics and treatment processes.

AB - (Background and objectives) Retinal cysts are formed by accumulation of fluid in the retina caused by leakages from inflammation or vitreous fractures. Analysis of the retinal cystic spaces holds significance in detection and treatment of several ocular diseases like age-related macular degeneration, diabetic macular edema etc. Thus, segmentation of intra-retinal cysts and quantification of cystic spaces are vital for retinal pathology and severity detection. In the recent years, automated segmentation of intra-retinal cysts using optical coherence tomography B-scans has gained significant importance in the field of retinal image analysis. The objective of this paper is to compare different intra-retinal cyst segmentation algorithms for comparative analysis and benchmarking purposes. (Methods) In this work, we employ a modular approach for standardizing the different segmentation algorithms. Further, we analyze the variations in automated cyst segmentation performances and method scalability across image acquisition systems by using the publicly available cyst segmentation challenge dataset (OPTIMA cyst segmentation challenge). (Results) Several key automated methods are comparatively analyzed using quantitative and qualitative experiments. Our analysis demonstrates the significance of variations in signal-to-noise ratio (SNR), retinal layer morphology and post-processing steps on the automated cyst segmentation processes. (Conclusion) This benchmarking study provides insights towards the scalability of automated processes across vendor-specific imaging modalities to provide guidance for retinal pathology diagnostics and treatment processes.

UR - http://www.scopus.com/inward/record.url?scp=85031760704&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85031760704&partnerID=8YFLogxK

U2 - 10.1016/j.cmpb.2017.10.010

DO - 10.1016/j.cmpb.2017.10.010

M3 - Article

VL - 153

SP - 105

EP - 114

JO - Computer Methods and Programs in Biomedicine

T2 - Computer Methods and Programs in Biomedicine

JF - Computer Methods and Programs in Biomedicine

SN - 0169-2607

ER -