Performance evaluation of automated segmentation software on optical coherence tomography volume data

Jing Tian, Boglarka Varga, Erika Tatrai, Palya Fanni, Gabor Mark Somfai, William E Smiddy, Delia Cabrera DeBuc

Research output: Contribution to journalArticle

24 Citations (Scopus)

Abstract

Over the past two decades a significant number of OCT segmentation approaches have been proposed in the literature. Each methodology has been conceived for and/or evaluated using specific datasets that do not reflect the complexities of the majority of widely available retinal features observed in clinical settings. In addition, there does not exist an appropriate OCT dataset with ground truth that reflects the realities of everyday retinal features observed in clinical settings. While the need for unbiased performance evaluation of automated segmentation algorithms is obvious, the validation process of segmentation algorithms have been usually performed by comparing with manual labelings from each study and there has been a lack of common ground truth.

Original languageEnglish (US)
JournalJournal of Biophotonics
DOIs
StateAccepted/In press - 2016

Fingerprint

ground truth
Optical tomography
Optical Coherence Tomography
Software
tomography
computer programs
evaluation
Labeling
marking
methodology
Datasets

Keywords

  • Automated segmentation software
  • Ground truth
  • Optical coherence tomography
  • Performance evaluation
  • Spectralis SD-OCT

ASJC Scopus subject areas

  • Materials Science(all)
  • Engineering(all)
  • Physics and Astronomy(all)
  • Chemistry(all)
  • Biochemistry, Genetics and Molecular Biology(all)

Cite this

Performance evaluation of automated segmentation software on optical coherence tomography volume data. / Tian, Jing; Varga, Boglarka; Tatrai, Erika; Fanni, Palya; Somfai, Gabor Mark; Smiddy, William E; Cabrera DeBuc, Delia.

In: Journal of Biophotonics, 2016.

Research output: Contribution to journalArticle

@article{3d71ef56e28d442e8d645b246d80e5dc,
title = "Performance evaluation of automated segmentation software on optical coherence tomography volume data",
abstract = "Over the past two decades a significant number of OCT segmentation approaches have been proposed in the literature. Each methodology has been conceived for and/or evaluated using specific datasets that do not reflect the complexities of the majority of widely available retinal features observed in clinical settings. In addition, there does not exist an appropriate OCT dataset with ground truth that reflects the realities of everyday retinal features observed in clinical settings. While the need for unbiased performance evaluation of automated segmentation algorithms is obvious, the validation process of segmentation algorithms have been usually performed by comparing with manual labelings from each study and there has been a lack of common ground truth.",
keywords = "Automated segmentation software, Ground truth, Optical coherence tomography, Performance evaluation, Spectralis SD-OCT",
author = "Jing Tian and Boglarka Varga and Erika Tatrai and Palya Fanni and Somfai, {Gabor Mark} and Smiddy, {William E} and {Cabrera DeBuc}, Delia",
year = "2016",
doi = "10.1002/jbio.201500239",
language = "English (US)",
journal = "Journal of Biophotonics",
issn = "1864-063X",
publisher = "Wiley-VCH Verlag",

}

TY - JOUR

T1 - Performance evaluation of automated segmentation software on optical coherence tomography volume data

AU - Tian, Jing

AU - Varga, Boglarka

AU - Tatrai, Erika

AU - Fanni, Palya

AU - Somfai, Gabor Mark

AU - Smiddy, William E

AU - Cabrera DeBuc, Delia

PY - 2016

Y1 - 2016

N2 - Over the past two decades a significant number of OCT segmentation approaches have been proposed in the literature. Each methodology has been conceived for and/or evaluated using specific datasets that do not reflect the complexities of the majority of widely available retinal features observed in clinical settings. In addition, there does not exist an appropriate OCT dataset with ground truth that reflects the realities of everyday retinal features observed in clinical settings. While the need for unbiased performance evaluation of automated segmentation algorithms is obvious, the validation process of segmentation algorithms have been usually performed by comparing with manual labelings from each study and there has been a lack of common ground truth.

AB - Over the past two decades a significant number of OCT segmentation approaches have been proposed in the literature. Each methodology has been conceived for and/or evaluated using specific datasets that do not reflect the complexities of the majority of widely available retinal features observed in clinical settings. In addition, there does not exist an appropriate OCT dataset with ground truth that reflects the realities of everyday retinal features observed in clinical settings. While the need for unbiased performance evaluation of automated segmentation algorithms is obvious, the validation process of segmentation algorithms have been usually performed by comparing with manual labelings from each study and there has been a lack of common ground truth.

KW - Automated segmentation software

KW - Ground truth

KW - Optical coherence tomography

KW - Performance evaluation

KW - Spectralis SD-OCT

UR - http://www.scopus.com/inward/record.url?scp=84960434380&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84960434380&partnerID=8YFLogxK

U2 - 10.1002/jbio.201500239

DO - 10.1002/jbio.201500239

M3 - Article

C2 - 27159849

AN - SCOPUS:84960434380

JO - Journal of Biophotonics

JF - Journal of Biophotonics

SN - 1864-063X

ER -