Level sets for retinal vasculature segmentation using seeds from ridges and edges from phase maps

Bekir Dizdaro, Esra Ataer-Cansizoglu, Jayashree Kalpathy-Cramer, Katie Keck, Michael Chiang, Deniz Erdogmus

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

15 Citations (Scopus)

Abstract

In this paper, we present a novel modification to level set based automatic retinal vasculature segmentation approaches. The method introduces ridge sample extraction for sampling the vasculature centerline and phase map based edge detection for accurate region boundary detection. Segmenting the vasculature in fundus images has been generally challenging for level set methods employing classical edge-detection methodologies. Furthermore, initialization with seed points determined by sampling vessel centerlines using ridge identification makes the method completely automated. The resulting algorithm is able to segment vasculature in fundus imagery accurately and automatically. Quantitative results supplemented with visual ones support this observation. The methodology could be applied to the broader class of vessel segmentation problems encountered in medical image analytics.

Original languageEnglish (US)
Title of host publicationIEEE International Workshop on Machine Learning for Signal Processing, MLSP
DOIs
StatePublished - 2012
Event2012 22nd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2012 - Santander, Spain
Duration: Sep 23 2012Sep 26 2012

Other

Other2012 22nd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2012
CountrySpain
CitySantander
Period9/23/129/26/12

Fingerprint

Edge detection
Seed
Sampling

Keywords

  • Fundus image
  • level sets
  • phase map for edge detection
  • principal curves as ridges
  • retinal vasculature analysis
  • vessel segmentation

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Signal Processing

Cite this

Dizdaro, B., Ataer-Cansizoglu, E., Kalpathy-Cramer, J., Keck, K., Chiang, M., & Erdogmus, D. (2012). Level sets for retinal vasculature segmentation using seeds from ridges and edges from phase maps. In IEEE International Workshop on Machine Learning for Signal Processing, MLSP [6349730] https://doi.org/10.1109/MLSP.2012.6349730

Level sets for retinal vasculature segmentation using seeds from ridges and edges from phase maps. / Dizdaro, Bekir; Ataer-Cansizoglu, Esra; Kalpathy-Cramer, Jayashree; Keck, Katie; Chiang, Michael; Erdogmus, Deniz.

IEEE International Workshop on Machine Learning for Signal Processing, MLSP. 2012. 6349730.

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

Dizdaro, B, Ataer-Cansizoglu, E, Kalpathy-Cramer, J, Keck, K, Chiang, M & Erdogmus, D 2012, Level sets for retinal vasculature segmentation using seeds from ridges and edges from phase maps. in IEEE International Workshop on Machine Learning for Signal Processing, MLSP., 6349730, 2012 22nd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2012, Santander, Spain, 9/23/12. https://doi.org/10.1109/MLSP.2012.6349730
Dizdaro B, Ataer-Cansizoglu E, Kalpathy-Cramer J, Keck K, Chiang M, Erdogmus D. Level sets for retinal vasculature segmentation using seeds from ridges and edges from phase maps. In IEEE International Workshop on Machine Learning for Signal Processing, MLSP. 2012. 6349730 https://doi.org/10.1109/MLSP.2012.6349730
Dizdaro, Bekir ; Ataer-Cansizoglu, Esra ; Kalpathy-Cramer, Jayashree ; Keck, Katie ; Chiang, Michael ; Erdogmus, Deniz. / Level sets for retinal vasculature segmentation using seeds from ridges and edges from phase maps. IEEE International Workshop on Machine Learning for Signal Processing, MLSP. 2012.
@inproceedings{0ffea2b0e1e043679ba997718b300e4b,
title = "Level sets for retinal vasculature segmentation using seeds from ridges and edges from phase maps",
abstract = "In this paper, we present a novel modification to level set based automatic retinal vasculature segmentation approaches. The method introduces ridge sample extraction for sampling the vasculature centerline and phase map based edge detection for accurate region boundary detection. Segmenting the vasculature in fundus images has been generally challenging for level set methods employing classical edge-detection methodologies. Furthermore, initialization with seed points determined by sampling vessel centerlines using ridge identification makes the method completely automated. The resulting algorithm is able to segment vasculature in fundus imagery accurately and automatically. Quantitative results supplemented with visual ones support this observation. The methodology could be applied to the broader class of vessel segmentation problems encountered in medical image analytics.",
keywords = "Fundus image, level sets, phase map for edge detection, principal curves as ridges, retinal vasculature analysis, vessel segmentation",
author = "Bekir Dizdaro and Esra Ataer-Cansizoglu and Jayashree Kalpathy-Cramer and Katie Keck and Michael Chiang and Deniz Erdogmus",
year = "2012",
doi = "10.1109/MLSP.2012.6349730",
language = "English (US)",
isbn = "9781467310260",
booktitle = "IEEE International Workshop on Machine Learning for Signal Processing, MLSP",

}

TY - GEN

T1 - Level sets for retinal vasculature segmentation using seeds from ridges and edges from phase maps

AU - Dizdaro, Bekir

AU - Ataer-Cansizoglu, Esra

AU - Kalpathy-Cramer, Jayashree

AU - Keck, Katie

AU - Chiang, Michael

AU - Erdogmus, Deniz

PY - 2012

Y1 - 2012

N2 - In this paper, we present a novel modification to level set based automatic retinal vasculature segmentation approaches. The method introduces ridge sample extraction for sampling the vasculature centerline and phase map based edge detection for accurate region boundary detection. Segmenting the vasculature in fundus images has been generally challenging for level set methods employing classical edge-detection methodologies. Furthermore, initialization with seed points determined by sampling vessel centerlines using ridge identification makes the method completely automated. The resulting algorithm is able to segment vasculature in fundus imagery accurately and automatically. Quantitative results supplemented with visual ones support this observation. The methodology could be applied to the broader class of vessel segmentation problems encountered in medical image analytics.

AB - In this paper, we present a novel modification to level set based automatic retinal vasculature segmentation approaches. The method introduces ridge sample extraction for sampling the vasculature centerline and phase map based edge detection for accurate region boundary detection. Segmenting the vasculature in fundus images has been generally challenging for level set methods employing classical edge-detection methodologies. Furthermore, initialization with seed points determined by sampling vessel centerlines using ridge identification makes the method completely automated. The resulting algorithm is able to segment vasculature in fundus imagery accurately and automatically. Quantitative results supplemented with visual ones support this observation. The methodology could be applied to the broader class of vessel segmentation problems encountered in medical image analytics.

KW - Fundus image

KW - level sets

KW - phase map for edge detection

KW - principal curves as ridges

KW - retinal vasculature analysis

KW - vessel segmentation

UR - http://www.scopus.com/inward/record.url?scp=84870723393&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84870723393&partnerID=8YFLogxK

U2 - 10.1109/MLSP.2012.6349730

DO - 10.1109/MLSP.2012.6349730

M3 - Conference contribution

SN - 9781467310260

BT - IEEE International Workshop on Machine Learning for Signal Processing, MLSP

ER -