Geometric deformable model driven by CoCRFs

application to optical coherence tomography.

Gabriel Tsechpenakis, Brandon Lujan, Oscar Martinez, Giovanni Gregori, Philip J. Rosenfeld

Research output: Contribution to journalArticle

Abstract

We present a geometric deformable model driven by dynamically updated probability fields. The shape is defined with the signed distance function, and the internal (smoothness) energy consists of a C1 continuity constraint, a shape prior, and a term that forces the zero-level of the shape distance function towards a connected form. The image probability fields are estimated by our collaborative Conditional Random Field (CoCRF), which is updated during the evolution in an active learning manner: it infers class posteriors in pixels or regions with feature ambiguities by assessing the joint appearance of neighboring sites and using the classification confidence. We apply our method to Optical Coherence Tomography fundus images for the segmentation of geographic atrophies in dry age-related macular degeneration of the human eye.

Original languageEnglish (US)
Pages (from-to)883-891
Number of pages9
JournalMedical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
Volume11
Issue numberPt 1
StatePublished - 2008
Externally publishedYes

Fingerprint

Optical Coherence Tomography
Geographic Atrophy
Problem-Based Learning
Macular Degeneration
Joints

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Geometric deformable model driven by CoCRFs : application to optical coherence tomography. / Tsechpenakis, Gabriel; Lujan, Brandon; Martinez, Oscar; Gregori, Giovanni; Rosenfeld, Philip J.

In: Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention, Vol. 11, No. Pt 1, 2008, p. 883-891.

Research output: Contribution to journalArticle

@article{b3153ac6107c4d968c1bae356033266d,
title = "Geometric deformable model driven by CoCRFs: application to optical coherence tomography.",
abstract = "We present a geometric deformable model driven by dynamically updated probability fields. The shape is defined with the signed distance function, and the internal (smoothness) energy consists of a C1 continuity constraint, a shape prior, and a term that forces the zero-level of the shape distance function towards a connected form. The image probability fields are estimated by our collaborative Conditional Random Field (CoCRF), which is updated during the evolution in an active learning manner: it infers class posteriors in pixels or regions with feature ambiguities by assessing the joint appearance of neighboring sites and using the classification confidence. We apply our method to Optical Coherence Tomography fundus images for the segmentation of geographic atrophies in dry age-related macular degeneration of the human eye.",
author = "Gabriel Tsechpenakis and Brandon Lujan and Oscar Martinez and Giovanni Gregori and Rosenfeld, {Philip J.}",
year = "2008",
language = "English (US)",
volume = "11",
pages = "883--891",
journal = "Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention",
number = "Pt 1",

}

TY - JOUR

T1 - Geometric deformable model driven by CoCRFs

T2 - application to optical coherence tomography.

AU - Tsechpenakis, Gabriel

AU - Lujan, Brandon

AU - Martinez, Oscar

AU - Gregori, Giovanni

AU - Rosenfeld, Philip J.

PY - 2008

Y1 - 2008

N2 - We present a geometric deformable model driven by dynamically updated probability fields. The shape is defined with the signed distance function, and the internal (smoothness) energy consists of a C1 continuity constraint, a shape prior, and a term that forces the zero-level of the shape distance function towards a connected form. The image probability fields are estimated by our collaborative Conditional Random Field (CoCRF), which is updated during the evolution in an active learning manner: it infers class posteriors in pixels or regions with feature ambiguities by assessing the joint appearance of neighboring sites and using the classification confidence. We apply our method to Optical Coherence Tomography fundus images for the segmentation of geographic atrophies in dry age-related macular degeneration of the human eye.

AB - We present a geometric deformable model driven by dynamically updated probability fields. The shape is defined with the signed distance function, and the internal (smoothness) energy consists of a C1 continuity constraint, a shape prior, and a term that forces the zero-level of the shape distance function towards a connected form. The image probability fields are estimated by our collaborative Conditional Random Field (CoCRF), which is updated during the evolution in an active learning manner: it infers class posteriors in pixels or regions with feature ambiguities by assessing the joint appearance of neighboring sites and using the classification confidence. We apply our method to Optical Coherence Tomography fundus images for the segmentation of geographic atrophies in dry age-related macular degeneration of the human eye.

UR - http://www.scopus.com/inward/record.url?scp=84883845097&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883845097&partnerID=8YFLogxK

M3 - Article

VL - 11

SP - 883

EP - 891

JO - Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention

JF - Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention

IS - Pt 1

ER -