Choriocapillaris evaluation in choroideremia using optical coherence tomography angiography

Simon S. Gao, Rachel C. Patel, Nieraj Jain, Miao Zhang, Richard Weleber, David Huang, Mark Pennesi, Jia Yali

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

The choriocapillaris plays an important role in supporting the metabolic demands of the retina. Studies of the choriocapillaris in disease states with optical coherence tomography angiography (OCTA) have proven insightful. However, image artifacts complicate the identification and quantification of the choriocapillaris in degenerative diseases such as choroideremia. Here, we demonstrate a supervised machine learning approach to detect intact choriocapillaris based on training with results from an expert grader. We trained a random forest classifier to evaluate en face structural OCT and OCTA information along with spatial image features. Evaluation of the trained classifier using previously unseen data showed good agreement with manual grading.

Original languageEnglish (US)
Article number#276323
Pages (from-to)48-56
Number of pages9
JournalBiomedical Optics Express
Volume8
Issue number1
DOIs
StatePublished - Jan 1 2017

Fingerprint

Choroideremia
angiography
Optical Coherence Tomography
classifiers
Angiography
tomography
machine learning
retina
evaluation
Artifacts
Retina
artifacts
education

Keywords

  • Image processing
  • Medical and biological imaging
  • Ophthalmology
  • Optical coherence tomography

ASJC Scopus subject areas

  • Biotechnology
  • Atomic and Molecular Physics, and Optics

Cite this

Choriocapillaris evaluation in choroideremia using optical coherence tomography angiography. / Gao, Simon S.; Patel, Rachel C.; Jain, Nieraj; Zhang, Miao; Weleber, Richard; Huang, David; Pennesi, Mark; Yali, Jia.

In: Biomedical Optics Express, Vol. 8, No. 1, #276323, 01.01.2017, p. 48-56.

Research output: Contribution to journalArticle

@article{08bf94a8755f49a69e498839283037b5,
title = "Choriocapillaris evaluation in choroideremia using optical coherence tomography angiography",
abstract = "The choriocapillaris plays an important role in supporting the metabolic demands of the retina. Studies of the choriocapillaris in disease states with optical coherence tomography angiography (OCTA) have proven insightful. However, image artifacts complicate the identification and quantification of the choriocapillaris in degenerative diseases such as choroideremia. Here, we demonstrate a supervised machine learning approach to detect intact choriocapillaris based on training with results from an expert grader. We trained a random forest classifier to evaluate en face structural OCT and OCTA information along with spatial image features. Evaluation of the trained classifier using previously unseen data showed good agreement with manual grading.",
keywords = "Image processing, Medical and biological imaging, Ophthalmology, Optical coherence tomography",
author = "Gao, {Simon S.} and Patel, {Rachel C.} and Nieraj Jain and Miao Zhang and Richard Weleber and David Huang and Mark Pennesi and Jia Yali",
year = "2017",
month = "1",
day = "1",
doi = "10.1364/BOE.8.000048",
language = "English (US)",
volume = "8",
pages = "48--56",
journal = "Biomedical Optics Express",
issn = "2156-7085",
publisher = "The Optical Society",
number = "1",

}

TY - JOUR

T1 - Choriocapillaris evaluation in choroideremia using optical coherence tomography angiography

AU - Gao, Simon S.

AU - Patel, Rachel C.

AU - Jain, Nieraj

AU - Zhang, Miao

AU - Weleber, Richard

AU - Huang, David

AU - Pennesi, Mark

AU - Yali, Jia

PY - 2017/1/1

Y1 - 2017/1/1

N2 - The choriocapillaris plays an important role in supporting the metabolic demands of the retina. Studies of the choriocapillaris in disease states with optical coherence tomography angiography (OCTA) have proven insightful. However, image artifacts complicate the identification and quantification of the choriocapillaris in degenerative diseases such as choroideremia. Here, we demonstrate a supervised machine learning approach to detect intact choriocapillaris based on training with results from an expert grader. We trained a random forest classifier to evaluate en face structural OCT and OCTA information along with spatial image features. Evaluation of the trained classifier using previously unseen data showed good agreement with manual grading.

AB - The choriocapillaris plays an important role in supporting the metabolic demands of the retina. Studies of the choriocapillaris in disease states with optical coherence tomography angiography (OCTA) have proven insightful. However, image artifacts complicate the identification and quantification of the choriocapillaris in degenerative diseases such as choroideremia. Here, we demonstrate a supervised machine learning approach to detect intact choriocapillaris based on training with results from an expert grader. We trained a random forest classifier to evaluate en face structural OCT and OCTA information along with spatial image features. Evaluation of the trained classifier using previously unseen data showed good agreement with manual grading.

KW - Image processing

KW - Medical and biological imaging

KW - Ophthalmology

KW - Optical coherence tomography

UR - http://www.scopus.com/inward/record.url?scp=85008949749&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85008949749&partnerID=8YFLogxK

U2 - 10.1364/BOE.8.000048

DO - 10.1364/BOE.8.000048

M3 - Article

AN - SCOPUS:85008949749

VL - 8

SP - 48

EP - 56

JO - Biomedical Optics Express

JF - Biomedical Optics Express

SN - 2156-7085

IS - 1

M1 - #276323

ER -