Retinal thickness measurements from optical coherence tomography using a Markov boundary model

Dara Koozekanani, Kim Boyer, Cynthia Roberts

Research output: Contribution to journalArticle

160 Citations (Scopus)

Abstract

We present a system for detecting retinal boundaries in optical coherence tomography (OCT) B-scans. OCT is a relatively new imaging modality giving cross-sectional images that are qualitatively similar to ultrasound. However, the axial resolution with OCT is much higher, on the order of 10 μm. Objective, quantitative measures of retinal thickness may be made from OCT images. Knowledge of retinal thickness is important in the evaluation and treatment of many ocular diseases. The boundary-detection system presented here uses a one-dimensional edge-detection kernel to yield edge primitives. These edge primitives are rated, selected, and organized to form a coherent boundary structure by use of a Markov model of retinal boundaries as detected by OCT. Qualitatively, the boundaries detected by the automated system generally agreed extremely well with the true retinal structure for the vast majority of OCT images. Only one of the 1450 evaluation images caused the algorithm to fail. A quantitative evaluation of the retinal boundaries was performed as well, using the clinical application of automatic retinal thickness determination. Retinal thickness measurements derived from the algorithm's results were compared with thickness measurements from manually corrected boundaries for 1450 test images. The algorithm's thickness measurements over a 1-mm region near the fovea differed from the corrected thickness measurements by less than 10 μm for 74% of the images and by less than 25 μm (10% of normal retinal thickness) for 98.4% of the images. These errors are near the machine's resolution limit and still well below clinical significance. Current, standard clinical practice involves a qualitative, visual assessment of retinal thickness. A robust, quantitatively accurate system such as ours can be expected to improve patient care.

Original languageEnglish (US)
Pages (from-to)900-916
Number of pages17
JournalIEEE Transactions on Medical Imaging
Volume20
Issue number9
DOIs
StatePublished - Sep 1 2001

Fingerprint

Thickness measurement
Optical tomography
Optical Coherence Tomography
Eye Diseases
Edge detection
Patient Care
Ultrasonics
Imaging techniques

Keywords

  • Boundary detection
  • Edge detection
  • Markov models
  • Ophthalmology
  • Optical coherence tomography
  • Perceptual organization
  • Retina

Cite this

Retinal thickness measurements from optical coherence tomography using a Markov boundary model. / Koozekanani, Dara; Boyer, Kim; Roberts, Cynthia.

In: IEEE Transactions on Medical Imaging, Vol. 20, No. 9, 01.09.2001, p. 900-916.

Research output: Contribution to journalArticle

@article{7e67997dbdf84383b8bb5048a83b4f49,
title = "Retinal thickness measurements from optical coherence tomography using a Markov boundary model",
abstract = "We present a system for detecting retinal boundaries in optical coherence tomography (OCT) B-scans. OCT is a relatively new imaging modality giving cross-sectional images that are qualitatively similar to ultrasound. However, the axial resolution with OCT is much higher, on the order of 10 μm. Objective, quantitative measures of retinal thickness may be made from OCT images. Knowledge of retinal thickness is important in the evaluation and treatment of many ocular diseases. The boundary-detection system presented here uses a one-dimensional edge-detection kernel to yield edge primitives. These edge primitives are rated, selected, and organized to form a coherent boundary structure by use of a Markov model of retinal boundaries as detected by OCT. Qualitatively, the boundaries detected by the automated system generally agreed extremely well with the true retinal structure for the vast majority of OCT images. Only one of the 1450 evaluation images caused the algorithm to fail. A quantitative evaluation of the retinal boundaries was performed as well, using the clinical application of automatic retinal thickness determination. Retinal thickness measurements derived from the algorithm's results were compared with thickness measurements from manually corrected boundaries for 1450 test images. The algorithm's thickness measurements over a 1-mm region near the fovea differed from the corrected thickness measurements by less than 10 μm for 74{\%} of the images and by less than 25 μm (10{\%} of normal retinal thickness) for 98.4{\%} of the images. These errors are near the machine's resolution limit and still well below clinical significance. Current, standard clinical practice involves a qualitative, visual assessment of retinal thickness. A robust, quantitatively accurate system such as ours can be expected to improve patient care.",
keywords = "Boundary detection, Edge detection, Markov models, Ophthalmology, Optical coherence tomography, Perceptual organization, Retina",
author = "Dara Koozekanani and Kim Boyer and Cynthia Roberts",
year = "2001",
month = "9",
day = "1",
doi = "10.1109/42.952728",
language = "English (US)",
volume = "20",
pages = "900--916",
journal = "IEEE Transactions on Medical Imaging",
issn = "0278-0062",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "9",

}

TY - JOUR

T1 - Retinal thickness measurements from optical coherence tomography using a Markov boundary model

AU - Koozekanani, Dara

AU - Boyer, Kim

AU - Roberts, Cynthia

PY - 2001/9/1

Y1 - 2001/9/1

N2 - We present a system for detecting retinal boundaries in optical coherence tomography (OCT) B-scans. OCT is a relatively new imaging modality giving cross-sectional images that are qualitatively similar to ultrasound. However, the axial resolution with OCT is much higher, on the order of 10 μm. Objective, quantitative measures of retinal thickness may be made from OCT images. Knowledge of retinal thickness is important in the evaluation and treatment of many ocular diseases. The boundary-detection system presented here uses a one-dimensional edge-detection kernel to yield edge primitives. These edge primitives are rated, selected, and organized to form a coherent boundary structure by use of a Markov model of retinal boundaries as detected by OCT. Qualitatively, the boundaries detected by the automated system generally agreed extremely well with the true retinal structure for the vast majority of OCT images. Only one of the 1450 evaluation images caused the algorithm to fail. A quantitative evaluation of the retinal boundaries was performed as well, using the clinical application of automatic retinal thickness determination. Retinal thickness measurements derived from the algorithm's results were compared with thickness measurements from manually corrected boundaries for 1450 test images. The algorithm's thickness measurements over a 1-mm region near the fovea differed from the corrected thickness measurements by less than 10 μm for 74% of the images and by less than 25 μm (10% of normal retinal thickness) for 98.4% of the images. These errors are near the machine's resolution limit and still well below clinical significance. Current, standard clinical practice involves a qualitative, visual assessment of retinal thickness. A robust, quantitatively accurate system such as ours can be expected to improve patient care.

AB - We present a system for detecting retinal boundaries in optical coherence tomography (OCT) B-scans. OCT is a relatively new imaging modality giving cross-sectional images that are qualitatively similar to ultrasound. However, the axial resolution with OCT is much higher, on the order of 10 μm. Objective, quantitative measures of retinal thickness may be made from OCT images. Knowledge of retinal thickness is important in the evaluation and treatment of many ocular diseases. The boundary-detection system presented here uses a one-dimensional edge-detection kernel to yield edge primitives. These edge primitives are rated, selected, and organized to form a coherent boundary structure by use of a Markov model of retinal boundaries as detected by OCT. Qualitatively, the boundaries detected by the automated system generally agreed extremely well with the true retinal structure for the vast majority of OCT images. Only one of the 1450 evaluation images caused the algorithm to fail. A quantitative evaluation of the retinal boundaries was performed as well, using the clinical application of automatic retinal thickness determination. Retinal thickness measurements derived from the algorithm's results were compared with thickness measurements from manually corrected boundaries for 1450 test images. The algorithm's thickness measurements over a 1-mm region near the fovea differed from the corrected thickness measurements by less than 10 μm for 74% of the images and by less than 25 μm (10% of normal retinal thickness) for 98.4% of the images. These errors are near the machine's resolution limit and still well below clinical significance. Current, standard clinical practice involves a qualitative, visual assessment of retinal thickness. A robust, quantitatively accurate system such as ours can be expected to improve patient care.

KW - Boundary detection

KW - Edge detection

KW - Markov models

KW - Ophthalmology

KW - Optical coherence tomography

KW - Perceptual organization

KW - Retina

UR - http://www.scopus.com/inward/record.url?scp=0035437720&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035437720&partnerID=8YFLogxK

U2 - 10.1109/42.952728

DO - 10.1109/42.952728

M3 - Article

C2 - 11585207

AN - SCOPUS:0035437720

VL - 20

SP - 900

EP - 916

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

SN - 0278-0062

IS - 9

ER -