Ridge-branch-based blood vessel detection algorithm for multimodal retinal images

Y. Li, N. Hutchings, R. W. Knighton, Giovanni Gregori, B. J. Lujan, J. G. Flanagan

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

7 Citations (Scopus)

Abstract

Automatic detection of retinal blood vessels is important to medical diagnoses and imaging. With the development of imaging technologies, various modals of retinal images are available. Few of currently published algorithms are applied to multimodal retinal images. Besides, the performance of algorithms with pathologies is expected to be improved. The purpose of this paper is to propose an automatic Ridge-Branch-Based (RBB) detection algorithm of blood vessel centerlines and blood vessels for multimodal retinal images (color fundus photographs, fluorescein angiograms, fundus autofluorescence images, SLO fundus images and OCT fundus images, for example). Ridges, which can be considered as centerlines of vessel-like patterns, are first extracted. The method uses the connective branching information of image ridges: if ridge pixels are connected, they are more likely to be in the same class, vessel ridge pixels or non-vessel ridge pixels. Thanks to the good distinguishing ability of the designed "Segment-Based Ridge Features", the classifier and its parameters can be easily adapted to multimodal retinal images without ground truth training. We present thorough experimental results on SLO images, color fundus photograph database and other multimodal retinal images, as well as comparison between other published algorithms. Results showed that the RBB algorithm achieved a good performance.

Original languageEnglish
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume7259
DOIs
StatePublished - Dec 15 2009
EventMedical Imaging 2009 - Image Processing - Lake Buena Vista, FL, United States
Duration: Feb 8 2009Feb 10 2009

Other

OtherMedical Imaging 2009 - Image Processing
CountryUnited States
CityLake Buena Vista, FL
Period2/8/092/10/09

Fingerprint

retinal images
blood vessels
Blood vessels
Blood Vessels
ridges
Retinal Vessels
Pixels
vessels
Color
pixels
photographs
Medical imaging
Pathology
Diagnostic Imaging
Fluorescein
Angiography
color
Classifiers
ground truth
Databases

Keywords

  • Blood vessel detection
  • Feature selection
  • Multimodal
  • Retinal image
  • Ridge detection

ASJC Scopus subject areas

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

Cite this

Li, Y., Hutchings, N., Knighton, R. W., Gregori, G., Lujan, B. J., & Flanagan, J. G. (2009). Ridge-branch-based blood vessel detection algorithm for multimodal retinal images. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (Vol. 7259). [72594K] https://doi.org/10.1117/12.812414

Ridge-branch-based blood vessel detection algorithm for multimodal retinal images. / Li, Y.; Hutchings, N.; Knighton, R. W.; Gregori, Giovanni; Lujan, B. J.; Flanagan, J. G.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 7259 2009. 72594K.

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

Li, Y, Hutchings, N, Knighton, RW, Gregori, G, Lujan, BJ & Flanagan, JG 2009, Ridge-branch-based blood vessel detection algorithm for multimodal retinal images. in Progress in Biomedical Optics and Imaging - Proceedings of SPIE. vol. 7259, 72594K, Medical Imaging 2009 - Image Processing, Lake Buena Vista, FL, United States, 2/8/09. https://doi.org/10.1117/12.812414
Li Y, Hutchings N, Knighton RW, Gregori G, Lujan BJ, Flanagan JG. Ridge-branch-based blood vessel detection algorithm for multimodal retinal images. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 7259. 2009. 72594K https://doi.org/10.1117/12.812414
Li, Y. ; Hutchings, N. ; Knighton, R. W. ; Gregori, Giovanni ; Lujan, B. J. ; Flanagan, J. G. / Ridge-branch-based blood vessel detection algorithm for multimodal retinal images. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 7259 2009.
@inproceedings{66fa863cdd024b3a9c7b1e241f00587f,
title = "Ridge-branch-based blood vessel detection algorithm for multimodal retinal images",
abstract = "Automatic detection of retinal blood vessels is important to medical diagnoses and imaging. With the development of imaging technologies, various modals of retinal images are available. Few of currently published algorithms are applied to multimodal retinal images. Besides, the performance of algorithms with pathologies is expected to be improved. The purpose of this paper is to propose an automatic Ridge-Branch-Based (RBB) detection algorithm of blood vessel centerlines and blood vessels for multimodal retinal images (color fundus photographs, fluorescein angiograms, fundus autofluorescence images, SLO fundus images and OCT fundus images, for example). Ridges, which can be considered as centerlines of vessel-like patterns, are first extracted. The method uses the connective branching information of image ridges: if ridge pixels are connected, they are more likely to be in the same class, vessel ridge pixels or non-vessel ridge pixels. Thanks to the good distinguishing ability of the designed {"}Segment-Based Ridge Features{"}, the classifier and its parameters can be easily adapted to multimodal retinal images without ground truth training. We present thorough experimental results on SLO images, color fundus photograph database and other multimodal retinal images, as well as comparison between other published algorithms. Results showed that the RBB algorithm achieved a good performance.",
keywords = "Blood vessel detection, Feature selection, Multimodal, Retinal image, Ridge detection",
author = "Y. Li and N. Hutchings and Knighton, {R. W.} and Giovanni Gregori and Lujan, {B. J.} and Flanagan, {J. G.}",
year = "2009",
month = "12",
day = "15",
doi = "10.1117/12.812414",
language = "English",
isbn = "9780819475107",
volume = "7259",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

}

TY - GEN

T1 - Ridge-branch-based blood vessel detection algorithm for multimodal retinal images

AU - Li, Y.

AU - Hutchings, N.

AU - Knighton, R. W.

AU - Gregori, Giovanni

AU - Lujan, B. J.

AU - Flanagan, J. G.

PY - 2009/12/15

Y1 - 2009/12/15

N2 - Automatic detection of retinal blood vessels is important to medical diagnoses and imaging. With the development of imaging technologies, various modals of retinal images are available. Few of currently published algorithms are applied to multimodal retinal images. Besides, the performance of algorithms with pathologies is expected to be improved. The purpose of this paper is to propose an automatic Ridge-Branch-Based (RBB) detection algorithm of blood vessel centerlines and blood vessels for multimodal retinal images (color fundus photographs, fluorescein angiograms, fundus autofluorescence images, SLO fundus images and OCT fundus images, for example). Ridges, which can be considered as centerlines of vessel-like patterns, are first extracted. The method uses the connective branching information of image ridges: if ridge pixels are connected, they are more likely to be in the same class, vessel ridge pixels or non-vessel ridge pixels. Thanks to the good distinguishing ability of the designed "Segment-Based Ridge Features", the classifier and its parameters can be easily adapted to multimodal retinal images without ground truth training. We present thorough experimental results on SLO images, color fundus photograph database and other multimodal retinal images, as well as comparison between other published algorithms. Results showed that the RBB algorithm achieved a good performance.

AB - Automatic detection of retinal blood vessels is important to medical diagnoses and imaging. With the development of imaging technologies, various modals of retinal images are available. Few of currently published algorithms are applied to multimodal retinal images. Besides, the performance of algorithms with pathologies is expected to be improved. The purpose of this paper is to propose an automatic Ridge-Branch-Based (RBB) detection algorithm of blood vessel centerlines and blood vessels for multimodal retinal images (color fundus photographs, fluorescein angiograms, fundus autofluorescence images, SLO fundus images and OCT fundus images, for example). Ridges, which can be considered as centerlines of vessel-like patterns, are first extracted. The method uses the connective branching information of image ridges: if ridge pixels are connected, they are more likely to be in the same class, vessel ridge pixels or non-vessel ridge pixels. Thanks to the good distinguishing ability of the designed "Segment-Based Ridge Features", the classifier and its parameters can be easily adapted to multimodal retinal images without ground truth training. We present thorough experimental results on SLO images, color fundus photograph database and other multimodal retinal images, as well as comparison between other published algorithms. Results showed that the RBB algorithm achieved a good performance.

KW - Blood vessel detection

KW - Feature selection

KW - Multimodal

KW - Retinal image

KW - Ridge detection

UR - http://www.scopus.com/inward/record.url?scp=71649108197&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=71649108197&partnerID=8YFLogxK

U2 - 10.1117/12.812414

DO - 10.1117/12.812414

M3 - Conference contribution

AN - SCOPUS:71649108197

SN - 9780819475107

VL - 7259

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

ER -