An adaptive grid for graph-based segmentation in retinal OCT

Andrew Lang, Aaron Carass, Peter Calabresi, Howard S. Ying, Jerry Ladd Prince

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Graph-based methods for retinal layer segmentation have proven to be popular due to their efficiency and accuracy. These methods build a graph with nodes at each voxel location and use edges connecting nodes to encode the hard constraints of each layer's thickness and smoothness. In this work, we explore deforming the regular voxel grid to allow adjacent vertices in the graph to more closely follow the natural curvature of the retina. This deformed grid is constructed by fixing node locations based on a regression model of each layer's thickness relative to the overall retina thickness, thus we generate a subject specific grid. Graph vertices are not at voxel locations, which allows for control over the resolution that the graph represents. By incorporating soft constraints between adjacent nodes, segmentation on this grid will favor smoothly varying surfaces consistent with the shape of the retina. Our final segmentation method then follows our previous work. Boundary probabilities are estimated using a random forest classifier followed by an optimal graph search algorithm on the new adaptive grid to produce a final segmentation. Our method is shown to produce a more consistent segmentation with an overall accuracy of 3.38 μm across all boundaries.

Original languageEnglish (US)
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
PublisherSPIE
Volume9034
ISBN (Print)9780819498274
DOIs
StatePublished - 2014
EventMedical Imaging 2014: Image Processing - San Diego, CA, United States
Duration: Feb 16 2014Feb 18 2014

Other

OtherMedical Imaging 2014: Image Processing
CountryUnited States
CitySan Diego, CA
Period2/16/142/18/14

Fingerprint

grids
retina
Retina
apexes
Classifiers
classifiers
fixing
regression analysis
curvature

Keywords

  • Adaptive grid
  • Classification
  • Layer segmentation
  • OCT
  • Retina

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Lang, A., Carass, A., Calabresi, P., Ying, H. S., & Prince, J. L. (2014). An adaptive grid for graph-based segmentation in retinal OCT. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (Vol. 9034). [903402] SPIE. https://doi.org/10.1117/12.2043040

An adaptive grid for graph-based segmentation in retinal OCT. / Lang, Andrew; Carass, Aaron; Calabresi, Peter; Ying, Howard S.; Prince, Jerry Ladd.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 9034 SPIE, 2014. 903402.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lang, A, Carass, A, Calabresi, P, Ying, HS & Prince, JL 2014, An adaptive grid for graph-based segmentation in retinal OCT. in Progress in Biomedical Optics and Imaging - Proceedings of SPIE. vol. 9034, 903402, SPIE, Medical Imaging 2014: Image Processing, San Diego, CA, United States, 2/16/14. https://doi.org/10.1117/12.2043040
Lang A, Carass A, Calabresi P, Ying HS, Prince JL. An adaptive grid for graph-based segmentation in retinal OCT. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 9034. SPIE. 2014. 903402 https://doi.org/10.1117/12.2043040
Lang, Andrew ; Carass, Aaron ; Calabresi, Peter ; Ying, Howard S. ; Prince, Jerry Ladd. / An adaptive grid for graph-based segmentation in retinal OCT. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 9034 SPIE, 2014.
@inproceedings{98327dfcbfc64dd8b6c40c15f159f17a,
title = "An adaptive grid for graph-based segmentation in retinal OCT",
abstract = "Graph-based methods for retinal layer segmentation have proven to be popular due to their efficiency and accuracy. These methods build a graph with nodes at each voxel location and use edges connecting nodes to encode the hard constraints of each layer's thickness and smoothness. In this work, we explore deforming the regular voxel grid to allow adjacent vertices in the graph to more closely follow the natural curvature of the retina. This deformed grid is constructed by fixing node locations based on a regression model of each layer's thickness relative to the overall retina thickness, thus we generate a subject specific grid. Graph vertices are not at voxel locations, which allows for control over the resolution that the graph represents. By incorporating soft constraints between adjacent nodes, segmentation on this grid will favor smoothly varying surfaces consistent with the shape of the retina. Our final segmentation method then follows our previous work. Boundary probabilities are estimated using a random forest classifier followed by an optimal graph search algorithm on the new adaptive grid to produce a final segmentation. Our method is shown to produce a more consistent segmentation with an overall accuracy of 3.38 μm across all boundaries.",
keywords = "Adaptive grid, Classification, Layer segmentation, OCT, Retina",
author = "Andrew Lang and Aaron Carass and Peter Calabresi and Ying, {Howard S.} and Prince, {Jerry Ladd}",
year = "2014",
doi = "10.1117/12.2043040",
language = "English (US)",
isbn = "9780819498274",
volume = "9034",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
publisher = "SPIE",

}

TY - GEN

T1 - An adaptive grid for graph-based segmentation in retinal OCT

AU - Lang, Andrew

AU - Carass, Aaron

AU - Calabresi, Peter

AU - Ying, Howard S.

AU - Prince, Jerry Ladd

PY - 2014

Y1 - 2014

N2 - Graph-based methods for retinal layer segmentation have proven to be popular due to their efficiency and accuracy. These methods build a graph with nodes at each voxel location and use edges connecting nodes to encode the hard constraints of each layer's thickness and smoothness. In this work, we explore deforming the regular voxel grid to allow adjacent vertices in the graph to more closely follow the natural curvature of the retina. This deformed grid is constructed by fixing node locations based on a regression model of each layer's thickness relative to the overall retina thickness, thus we generate a subject specific grid. Graph vertices are not at voxel locations, which allows for control over the resolution that the graph represents. By incorporating soft constraints between adjacent nodes, segmentation on this grid will favor smoothly varying surfaces consistent with the shape of the retina. Our final segmentation method then follows our previous work. Boundary probabilities are estimated using a random forest classifier followed by an optimal graph search algorithm on the new adaptive grid to produce a final segmentation. Our method is shown to produce a more consistent segmentation with an overall accuracy of 3.38 μm across all boundaries.

AB - Graph-based methods for retinal layer segmentation have proven to be popular due to their efficiency and accuracy. These methods build a graph with nodes at each voxel location and use edges connecting nodes to encode the hard constraints of each layer's thickness and smoothness. In this work, we explore deforming the regular voxel grid to allow adjacent vertices in the graph to more closely follow the natural curvature of the retina. This deformed grid is constructed by fixing node locations based on a regression model of each layer's thickness relative to the overall retina thickness, thus we generate a subject specific grid. Graph vertices are not at voxel locations, which allows for control over the resolution that the graph represents. By incorporating soft constraints between adjacent nodes, segmentation on this grid will favor smoothly varying surfaces consistent with the shape of the retina. Our final segmentation method then follows our previous work. Boundary probabilities are estimated using a random forest classifier followed by an optimal graph search algorithm on the new adaptive grid to produce a final segmentation. Our method is shown to produce a more consistent segmentation with an overall accuracy of 3.38 μm across all boundaries.

KW - Adaptive grid

KW - Classification

KW - Layer segmentation

KW - OCT

KW - Retina

UR - http://www.scopus.com/inward/record.url?scp=84895779503&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84895779503&partnerID=8YFLogxK

U2 - 10.1117/12.2043040

DO - 10.1117/12.2043040

M3 - Conference contribution

C2 - 27773959

AN - SCOPUS:84895779503

SN - 9780819498274

VL - 9034

BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

PB - SPIE

ER -