Improving vessel segmentation in ultra-wide field-of-view retinal fluorescein angiograms

A. Perez-Rovira; K. Zutis; J. P. Hubschman; E. Trucco

doi:10.1109/IEMBS.2011.6090721

Improving vessel segmentation in ultra-wide field-of-view retinal fluorescein angiograms

A. Perez-Rovira, K. Zutis, J. P. Hubschman, E. Trucco

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

21 Citations (Scopus)

Abstract

Vessel segmentation on ultra-wide field-of-view fluorescein angiogram sequences of the retina is a challenging problem. Vessel appearance undergoes severe changes, as different portions of the vascular structure become perfused in different frames. This paper presents a method for segmenting vessels in such sequences using steerable filters and automatic thresholding. We introduce a penalization stage on regions with high vessel response in the filtered image, improving the detection of peripheral vessels and reducing false positives around the optic disc and in regions of choroidal vessels and lesions. Quantitative results are provided, in which the penalization stage improves the segmentation precision segmentation by 11.84%, the recall by 12.98% and the accuracy by 0.40%. To facilitate further evaluation, usage, and algorithm comparison, the algorithm, the data set used, the ground truth, and the results are made available on the internet.

Original language	English
Title of host publication	Proceedings of the 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC
Place of Publication	New York
Publisher	IEEE Computer Society
Pages	2614-2617
Number of pages	4
ISBN (Electronic)	9781424441228
ISBN (Print)	9781424441211
DOIs	https://doi.org/10.1109/IEMBS.2011.6090721
Publication status	Published - 2011
Event	33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society - Boston, United States Duration: 30 Aug 2011 → 3 Sept 2011

Conference

Conference	33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Abbreviated title	EMBC 2011
Country/Territory	United States
City	Boston
Period	30/08/11 → 3/09/11

Keywords

BLOOD-VESSELS

Access to Document

10.1109/IEMBS.2011.6090721

http://www.scopus.com/record/display.url?eid=2-s2.0-84055183536&origin=resultslist&sort=plf-f&src=s&st1=Improving+vessel+segmentation+in+ultra-wide+field-of-view+retinal+fluorescein+angiograms&sid=0721474E7BC0782D42D99C8F88821FEC.mw4ft95QGjz1tIFG9A1uw%3a370&sot=b&sdt=b&sl=103&s=TITLE-ABS-KEY%28Improving+vessel+segmentation+in+ultra-wide+field-of-view+retinal+fluorescein+angiograms%29&relpos=0&relpos=0&searchTerm=TITLE-ABS-KEY%28Improving+vessel+segmentation+in+ultra-wide+field-of-view+retinal+fluorescein+angiograms%29

21 Citations
1 Paper

Improving vessel segmentation in ultra-wide field-of-view retinal fluorescein angiograms
Perez-Rovira, A., Zutis, K., Hubschman, J. P. & Trucco, E., 2011.
Research output: Contribution to conference › Paper

1 Participation in conference

33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Trucco, E. (Participant)
30 Aug 2011 → 3 Sept 2011
Activity: Participating in or organising an event types › Participation in conference

Cite this

@inproceedings{8c3dfda4b9ca4533a8c510f308123b33,

title = "Improving vessel segmentation in ultra-wide field-of-view retinal fluorescein angiograms",

abstract = "Vessel segmentation on ultra-wide field-of-view fluorescein angiogram sequences of the retina is a challenging problem. Vessel appearance undergoes severe changes, as different portions of the vascular structure become perfused in different frames. This paper presents a method for segmenting vessels in such sequences using steerable filters and automatic thresholding. We introduce a penalization stage on regions with high vessel response in the filtered image, improving the detection of peripheral vessels and reducing false positives around the optic disc and in regions of choroidal vessels and lesions. Quantitative results are provided, in which the penalization stage improves the segmentation precision segmentation by 11.84%, the recall by 12.98% and the accuracy by 0.40%. To facilitate further evaluation, usage, and algorithm comparison, the algorithm, the data set used, the ground truth, and the results are made available on the internet.",

keywords = "BLOOD-VESSELS",

author = "A. Perez-Rovira and K. Zutis and Hubschman, {J. P.} and E. Trucco",

note = "Article number 6090721; 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society , EMBC 2011 ; Conference date: 30-08-2011 Through 03-09-2011",

year = "2011",

doi = "10.1109/IEMBS.2011.6090721",

language = "English",

isbn = "9781424441211 ",

pages = "2614--2617",

booktitle = "Proceedings of the 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC",

publisher = "IEEE Computer Society",

}

Perez-Rovira, A, Zutis, K, Hubschman, JP & Trucco, E 2011, Improving vessel segmentation in ultra-wide field-of-view retinal fluorescein angiograms. in Proceedings of the 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC. IEEE Computer Society, New York, pp. 2614-2617, 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society , Boston, United States, 30/08/11. https://doi.org/10.1109/IEMBS.2011.6090721

Improving vessel segmentation in ultra-wide field-of-view retinal fluorescein angiograms. / Perez-Rovira, A.; Zutis, K.; Hubschman, J. P. et al.
Proceedings of the 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC. New York: IEEE Computer Society, 2011. p. 2614-2617.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Improving vessel segmentation in ultra-wide field-of-view retinal fluorescein angiograms

AU - Perez-Rovira, A.

AU - Zutis, K.

AU - Hubschman, J. P.

AU - Trucco, E.

N1 - Article number 6090721

PY - 2011

Y1 - 2011

N2 - Vessel segmentation on ultra-wide field-of-view fluorescein angiogram sequences of the retina is a challenging problem. Vessel appearance undergoes severe changes, as different portions of the vascular structure become perfused in different frames. This paper presents a method for segmenting vessels in such sequences using steerable filters and automatic thresholding. We introduce a penalization stage on regions with high vessel response in the filtered image, improving the detection of peripheral vessels and reducing false positives around the optic disc and in regions of choroidal vessels and lesions. Quantitative results are provided, in which the penalization stage improves the segmentation precision segmentation by 11.84%, the recall by 12.98% and the accuracy by 0.40%. To facilitate further evaluation, usage, and algorithm comparison, the algorithm, the data set used, the ground truth, and the results are made available on the internet.

AB - Vessel segmentation on ultra-wide field-of-view fluorescein angiogram sequences of the retina is a challenging problem. Vessel appearance undergoes severe changes, as different portions of the vascular structure become perfused in different frames. This paper presents a method for segmenting vessels in such sequences using steerable filters and automatic thresholding. We introduce a penalization stage on regions with high vessel response in the filtered image, improving the detection of peripheral vessels and reducing false positives around the optic disc and in regions of choroidal vessels and lesions. Quantitative results are provided, in which the penalization stage improves the segmentation precision segmentation by 11.84%, the recall by 12.98% and the accuracy by 0.40%. To facilitate further evaluation, usage, and algorithm comparison, the algorithm, the data set used, the ground truth, and the results are made available on the internet.

KW - BLOOD-VESSELS

U2 - 10.1109/IEMBS.2011.6090721

DO - 10.1109/IEMBS.2011.6090721

M3 - Conference contribution

C2 - 22254877

SN - 9781424441211

SP - 2614

EP - 2617

BT - Proceedings of the 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC

PB - IEEE Computer Society

CY - New York

T2 - 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society

Y2 - 30 August 2011 through 3 September 2011

ER -

Improving vessel segmentation in ultra-wide field-of-view retinal fluorescein angiograms

Abstract

Conference

Keywords

Access to Document

Fingerprint

Research output

Improving vessel segmentation in ultra-wide field-of-view retinal fluorescein angiograms

Activities

33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society

Cite this