Automated detection of preserved photoreceptor on optical coherence tomography in choroideremia based on machine learning

Zhuo Wang, Acner Camino, Ahmed M. Hagag, Jie Wang, Richard G. Weleber, Paul Yang, Mark E. Pennesi, David Huang, Dengwang Li, Yali Jia

Research output: Contribution to journalArticle

  • 3 Citations

Abstract

Optical coherence tomography (OCT) can demonstrate early deterioration of the photoreceptor integrity caused by inherited retinal degeneration diseases (IRDs). A machine learning method based on random forests was developed to automatically detect continuous areas of preserved ellipsoid zone structure (an easily recognizable part of the photoreceptors on OCT) in 16 eyes of patients with choroideremia (a type of IRD). Pseudopodial extensions protruding from the preserved ellipsoid zone areas are detected separately by a local active contour routine. The algorithm is implemented on en face images with minimum segmentation requirements, only needing delineation of the Bruch's membrane, thus evading the inaccuracies and technical challenges associated with automatic segmentation of the ellipsoid zone in eyes with severe retinal degeneration.

LanguageEnglish (US)
JournalJournal of Biophotonics
DOIs
StateAccepted/In press - Jan 1 2018

Fingerprint

Choroideremia
photoreceptors
Retinal Degeneration
machine learning
degeneration
Optical tomography
Optical Coherence Tomography
ellipsoids
Learning systems
Retinal Diseases
tomography
Bruch Membrane
Deterioration
delineation
Membranes
deterioration
integrity
membranes
requirements
Machine Learning

Keywords

  • Choroideremia
  • Ellipsoid zone
  • Image reconstruction
  • Machine learning
  • Medical and biomedical imaging
  • Ophthalmology
  • Optical coherence tomography
  • Photoreceptor

ASJC Scopus subject areas

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

Cite this

@article{36e89dc3ec844756aa933bb6a0eb6966,
title = "Automated detection of preserved photoreceptor on optical coherence tomography in choroideremia based on machine learning",
abstract = "Optical coherence tomography (OCT) can demonstrate early deterioration of the photoreceptor integrity caused by inherited retinal degeneration diseases (IRDs). A machine learning method based on random forests was developed to automatically detect continuous areas of preserved ellipsoid zone structure (an easily recognizable part of the photoreceptors on OCT) in 16 eyes of patients with choroideremia (a type of IRD). Pseudopodial extensions protruding from the preserved ellipsoid zone areas are detected separately by a local active contour routine. The algorithm is implemented on en face images with minimum segmentation requirements, only needing delineation of the Bruch's membrane, thus evading the inaccuracies and technical challenges associated with automatic segmentation of the ellipsoid zone in eyes with severe retinal degeneration.",
keywords = "Choroideremia, Ellipsoid zone, Image reconstruction, Machine learning, Medical and biomedical imaging, Ophthalmology, Optical coherence tomography, Photoreceptor",
author = "Zhuo Wang and Acner Camino and Hagag, {Ahmed M.} and Jie Wang and Weleber, {Richard G.} and Paul Yang and Pennesi, {Mark E.} and David Huang and Dengwang Li and Yali Jia",
year = "2018",
month = "1",
day = "1",
doi = "10.1002/jbio.201700313",
language = "English (US)",
journal = "Journal of Biophotonics",
issn = "1864-063X",
publisher = "Wiley-VCH Verlag",

}

TY - JOUR

T1 - Automated detection of preserved photoreceptor on optical coherence tomography in choroideremia based on machine learning

AU - Wang, Zhuo

AU - Camino, Acner

AU - Hagag, Ahmed M.

AU - Wang, Jie

AU - Weleber, Richard G.

AU - Yang, Paul

AU - Pennesi, Mark E.

AU - Huang, David

AU - Li, Dengwang

AU - Jia, Yali

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Optical coherence tomography (OCT) can demonstrate early deterioration of the photoreceptor integrity caused by inherited retinal degeneration diseases (IRDs). A machine learning method based on random forests was developed to automatically detect continuous areas of preserved ellipsoid zone structure (an easily recognizable part of the photoreceptors on OCT) in 16 eyes of patients with choroideremia (a type of IRD). Pseudopodial extensions protruding from the preserved ellipsoid zone areas are detected separately by a local active contour routine. The algorithm is implemented on en face images with minimum segmentation requirements, only needing delineation of the Bruch's membrane, thus evading the inaccuracies and technical challenges associated with automatic segmentation of the ellipsoid zone in eyes with severe retinal degeneration.

AB - Optical coherence tomography (OCT) can demonstrate early deterioration of the photoreceptor integrity caused by inherited retinal degeneration diseases (IRDs). A machine learning method based on random forests was developed to automatically detect continuous areas of preserved ellipsoid zone structure (an easily recognizable part of the photoreceptors on OCT) in 16 eyes of patients with choroideremia (a type of IRD). Pseudopodial extensions protruding from the preserved ellipsoid zone areas are detected separately by a local active contour routine. The algorithm is implemented on en face images with minimum segmentation requirements, only needing delineation of the Bruch's membrane, thus evading the inaccuracies and technical challenges associated with automatic segmentation of the ellipsoid zone in eyes with severe retinal degeneration.

KW - Choroideremia

KW - Ellipsoid zone

KW - Image reconstruction

KW - Machine learning

KW - Medical and biomedical imaging

KW - Ophthalmology

KW - Optical coherence tomography

KW - Photoreceptor

UR - http://www.scopus.com/inward/record.url?scp=85041733140&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041733140&partnerID=8YFLogxK

U2 - 10.1002/jbio.201700313

DO - 10.1002/jbio.201700313

M3 - Article

JO - Journal of Biophotonics

T2 - Journal of Biophotonics

JF - Journal of Biophotonics

SN - 1864-063X

ER -