Real-time automatic segmentation of optical coherence tomography volume data of the macular region

Jing Tian, Boglárka Varga, Gábor Márk Somfai, Wen-Hsiang Lee, William E Smiddy, Delia Cabrera DeBuc

Research output: Contribution to journalArticle

43 Citations (Scopus)

Abstract

Optical coherence tomography (OCT) is a high speed, high resolution and non-invasive imaging modality that enables the capturing of the 3D structure of the retina. The fast and automatic analysis of 3D volume OCT data is crucial taking into account the increased amount of patient-specific 3D imaging data. In this work, we have developed an automatic algorithm, OCTRIMA 3D (OCT Retinal IMage Analysis 3D), that could segment OCT volume data in the macular region fast and accurately. The proposed method is implemented using the shortestpath based graph search, which detects the retinal boundaries by searching the shortest-path between two end nodes using Dijkstra's algorithm. Additional techniques, such as inter-frame flattening, inter-frame search region refinement, masking and biasing were introduced to exploit the spatial dependency between adjacent frames for the reduction of the processing time. Our segmentation algorithm was evaluated by comparing with themanual labelings and three state of the art graph-based segmentationmethods. The processing time for the whole OCT volume of 496×644×51 voxels (captured by Spectralis SD-OCT) was 26.15 seconds which is at least a 2-8-fold increase in speed compared to other, similar reference algorithms used in the comparisons. The average unsigned error was about 1 pixel (∼4 microns), which was also lower compared to the reference algorithms.We believe that OCTRIMA 3D is a leap forward towards achieving reliable, real-time analysis of 3D OCT retinal data.

Original languageEnglish (US)
Article numbere0133908
JournalPLoS One
Volume10
Issue number8
DOIs
StatePublished - Aug 10 2015

Fingerprint

Optical tomography
tomography
Optical Coherence Tomography
image analysis
Imaging techniques
Spatial Analysis
Processing
retina
Labeling
Image analysis
Retina
Pixels
methodology

ASJC Scopus subject areas

  • Agricultural and Biological Sciences(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Medicine(all)

Cite this

Real-time automatic segmentation of optical coherence tomography volume data of the macular region. / Tian, Jing; Varga, Boglárka; Somfai, Gábor Márk; Lee, Wen-Hsiang; Smiddy, William E; Cabrera DeBuc, Delia.

In: PLoS One, Vol. 10, No. 8, e0133908, 10.08.2015.

Research output: Contribution to journalArticle

Tian, Jing ; Varga, Boglárka ; Somfai, Gábor Márk ; Lee, Wen-Hsiang ; Smiddy, William E ; Cabrera DeBuc, Delia. / Real-time automatic segmentation of optical coherence tomography volume data of the macular region. In: PLoS One. 2015 ; Vol. 10, No. 8.
@article{6346b0acc3f04569bd34324518a2aada,
title = "Real-time automatic segmentation of optical coherence tomography volume data of the macular region",
abstract = "Optical coherence tomography (OCT) is a high speed, high resolution and non-invasive imaging modality that enables the capturing of the 3D structure of the retina. The fast and automatic analysis of 3D volume OCT data is crucial taking into account the increased amount of patient-specific 3D imaging data. In this work, we have developed an automatic algorithm, OCTRIMA 3D (OCT Retinal IMage Analysis 3D), that could segment OCT volume data in the macular region fast and accurately. The proposed method is implemented using the shortestpath based graph search, which detects the retinal boundaries by searching the shortest-path between two end nodes using Dijkstra's algorithm. Additional techniques, such as inter-frame flattening, inter-frame search region refinement, masking and biasing were introduced to exploit the spatial dependency between adjacent frames for the reduction of the processing time. Our segmentation algorithm was evaluated by comparing with themanual labelings and three state of the art graph-based segmentationmethods. The processing time for the whole OCT volume of 496×644×51 voxels (captured by Spectralis SD-OCT) was 26.15 seconds which is at least a 2-8-fold increase in speed compared to other, similar reference algorithms used in the comparisons. The average unsigned error was about 1 pixel (∼4 microns), which was also lower compared to the reference algorithms.We believe that OCTRIMA 3D is a leap forward towards achieving reliable, real-time analysis of 3D OCT retinal data.",
author = "Jing Tian and Bogl{\'a}rka Varga and Somfai, {G{\'a}bor M{\'a}rk} and Wen-Hsiang Lee and Smiddy, {William E} and {Cabrera DeBuc}, Delia",
year = "2015",
month = "8",
day = "10",
doi = "10.1371/journal.pone.0133908",
language = "English (US)",
volume = "10",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "8",

}

TY - JOUR

T1 - Real-time automatic segmentation of optical coherence tomography volume data of the macular region

AU - Tian, Jing

AU - Varga, Boglárka

AU - Somfai, Gábor Márk

AU - Lee, Wen-Hsiang

AU - Smiddy, William E

AU - Cabrera DeBuc, Delia

PY - 2015/8/10

Y1 - 2015/8/10

N2 - Optical coherence tomography (OCT) is a high speed, high resolution and non-invasive imaging modality that enables the capturing of the 3D structure of the retina. The fast and automatic analysis of 3D volume OCT data is crucial taking into account the increased amount of patient-specific 3D imaging data. In this work, we have developed an automatic algorithm, OCTRIMA 3D (OCT Retinal IMage Analysis 3D), that could segment OCT volume data in the macular region fast and accurately. The proposed method is implemented using the shortestpath based graph search, which detects the retinal boundaries by searching the shortest-path between two end nodes using Dijkstra's algorithm. Additional techniques, such as inter-frame flattening, inter-frame search region refinement, masking and biasing were introduced to exploit the spatial dependency between adjacent frames for the reduction of the processing time. Our segmentation algorithm was evaluated by comparing with themanual labelings and three state of the art graph-based segmentationmethods. The processing time for the whole OCT volume of 496×644×51 voxels (captured by Spectralis SD-OCT) was 26.15 seconds which is at least a 2-8-fold increase in speed compared to other, similar reference algorithms used in the comparisons. The average unsigned error was about 1 pixel (∼4 microns), which was also lower compared to the reference algorithms.We believe that OCTRIMA 3D is a leap forward towards achieving reliable, real-time analysis of 3D OCT retinal data.

AB - Optical coherence tomography (OCT) is a high speed, high resolution and non-invasive imaging modality that enables the capturing of the 3D structure of the retina. The fast and automatic analysis of 3D volume OCT data is crucial taking into account the increased amount of patient-specific 3D imaging data. In this work, we have developed an automatic algorithm, OCTRIMA 3D (OCT Retinal IMage Analysis 3D), that could segment OCT volume data in the macular region fast and accurately. The proposed method is implemented using the shortestpath based graph search, which detects the retinal boundaries by searching the shortest-path between two end nodes using Dijkstra's algorithm. Additional techniques, such as inter-frame flattening, inter-frame search region refinement, masking and biasing were introduced to exploit the spatial dependency between adjacent frames for the reduction of the processing time. Our segmentation algorithm was evaluated by comparing with themanual labelings and three state of the art graph-based segmentationmethods. The processing time for the whole OCT volume of 496×644×51 voxels (captured by Spectralis SD-OCT) was 26.15 seconds which is at least a 2-8-fold increase in speed compared to other, similar reference algorithms used in the comparisons. The average unsigned error was about 1 pixel (∼4 microns), which was also lower compared to the reference algorithms.We believe that OCTRIMA 3D is a leap forward towards achieving reliable, real-time analysis of 3D OCT retinal data.

UR - http://www.scopus.com/inward/record.url?scp=84942436789&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84942436789&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0133908

DO - 10.1371/journal.pone.0133908

M3 - Article

C2 - 26258430

AN - SCOPUS:84942436789

VL - 10

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 8

M1 - e0133908

ER -