Contextual detection of ischemic regions in ultra-wide-field-of-view retinal fluorescein angiograms.

E. Trueco; C. R. Buchanan; T. Aslam; B. Dhillon

doi:10.1109/IEMBS.2007.4353908

Contextual detection of ischemic regions in ultra-wide-field-of-view retinal fluorescein angiograms.

E. Trueco, C. R. Buchanan, T. Aslam, B. Dhillon

Research output: Contribution to journal › Article › peer-review

Abstract

We report a novel prototype algorithm using contextual knowledge to locate ischemic regions in ultra-wide-field-of-view retinal fluorescein angiograms. We use high-resolution images acquired by an Optos ultra-wide-field-of-view (more than 200 degrees) scanning laser ophthalmoscope. We leverage the simultaneous occurrence of ischemia with a number of other signs, detected automatically, typical for the state of progress of the condition in a diabetic patient. The specific nature of ischemic and non-ischemic regions is determined with an AdaBoost learning algorithm. Preliminary results demonstrate above 80% pixel classification accuracy against manual annotations.

Original language	English
Article number	4353908
Pages (from-to)	6740-6743
Number of pages	4
Journal	Annual International Conference of the IEEE Engineering in Medicine and Biology. Proceedings
DOIs	https://doi.org/10.1109/IEMBS.2007.4353908
Publication status	Published - 1 Dec 2007

Access to Document

10.1109/IEMBS.2007.4353908

Cite this

@article{9af8e1cfa97e4a65a9d9a91cea56c806,

title = "Contextual detection of ischemic regions in ultra-wide-field-of-view retinal fluorescein angiograms.",

abstract = "We report a novel prototype algorithm using contextual knowledge to locate ischemic regions in ultra-wide-field-of-view retinal fluorescein angiograms. We use high-resolution images acquired by an Optos ultra-wide-field-of-view (more than 200 degrees) scanning laser ophthalmoscope. We leverage the simultaneous occurrence of ischemia with a number of other signs, detected automatically, typical for the state of progress of the condition in a diabetic patient. The specific nature of ischemic and non-ischemic regions is determined with an AdaBoost learning algorithm. Preliminary results demonstrate above 80% pixel classification accuracy against manual annotations.",

author = "E. Trueco and Buchanan, {C. R.} and T. Aslam and B. Dhillon",

year = "2007",

month = dec,

day = "1",

doi = "10.1109/IEMBS.2007.4353908",

language = "English",

pages = "6740--6743",

journal = "Annual International Conference of the IEEE Engineering in Medicine and Biology. Proceedings",

issn = "0589-1019",

publisher = "IEEE",

}

TY - JOUR

T1 - Contextual detection of ischemic regions in ultra-wide-field-of-view retinal fluorescein angiograms.

AU - Trueco, E.

AU - Buchanan, C. R.

AU - Aslam, T.

AU - Dhillon, B.

PY - 2007/12/1

Y1 - 2007/12/1

N2 - We report a novel prototype algorithm using contextual knowledge to locate ischemic regions in ultra-wide-field-of-view retinal fluorescein angiograms. We use high-resolution images acquired by an Optos ultra-wide-field-of-view (more than 200 degrees) scanning laser ophthalmoscope. We leverage the simultaneous occurrence of ischemia with a number of other signs, detected automatically, typical for the state of progress of the condition in a diabetic patient. The specific nature of ischemic and non-ischemic regions is determined with an AdaBoost learning algorithm. Preliminary results demonstrate above 80% pixel classification accuracy against manual annotations.

AB - We report a novel prototype algorithm using contextual knowledge to locate ischemic regions in ultra-wide-field-of-view retinal fluorescein angiograms. We use high-resolution images acquired by an Optos ultra-wide-field-of-view (more than 200 degrees) scanning laser ophthalmoscope. We leverage the simultaneous occurrence of ischemia with a number of other signs, detected automatically, typical for the state of progress of the condition in a diabetic patient. The specific nature of ischemic and non-ischemic regions is determined with an AdaBoost learning algorithm. Preliminary results demonstrate above 80% pixel classification accuracy against manual annotations.

UR - http://www.scopus.com/inward/record.url?scp=84903800053&partnerID=8YFLogxK

U2 - 10.1109/IEMBS.2007.4353908

DO - 10.1109/IEMBS.2007.4353908

M3 - Article

C2 - 18003574

SN - 0589-1019

SP - 6740

EP - 6743

JO - Annual International Conference of the IEEE Engineering in Medicine and Biology. Proceedings

JF - Annual International Conference of the IEEE Engineering in Medicine and Biology. Proceedings

M1 - 4353908

ER -

Contextual detection of ischemic regions in ultra-wide-field-of-view retinal fluorescein angiograms.

Abstract

Access to Document

Other files and links

Fingerprint

Cite this