Automated detection of drusen in the macula

D. E. Freund, Neil M Bressler, Philippe Burlina

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

Abstract

Age related macular degeneration (AMD) is a condition of the retina that occurs with individuals over 50. AMD is characterized by the formation of drusen in the macula. This condition leads to a deterioration of foveal vision and eventually functional blindness. Automatically screening atrisk individuals may allow the detection of intermediate stage AMD where it is still treatable using anti-VEGH therapy. One of the difficulties in detecting and locating drusen is that their aspect (shape, texture, color, extent) varies significantly, and because of this it is often difficult to build a classifier. To address this difficulty we use a two pronged approach based on (a) multiscale analysis and (b) kernel based anomaly detection. We show experimental results on examples of fundus images taken from healthy and affected patients.

Original languageEnglish (US)
Title of host publicationProceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009
Pages61-64
Number of pages4
DOIs
StatePublished - 2009
Event2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009 - Boston, MA, United States
Duration: Jun 28 2009Jul 1 2009

Other

Other2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009
CountryUnited States
CityBoston, MA
Period6/28/097/1/09

Fingerprint

Macular Degeneration
Deterioration
Screening
Classifiers
Textures
Color
Blindness
Retina
Therapeutics

Keywords

  • Detection of retinal abnormalities
  • Macular pathologies
  • Support vector methods

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Freund, D. E., Bressler, N. M., & Burlina, P. (2009). Automated detection of drusen in the macula. In Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009 (pp. 61-64). [5192983] https://doi.org/10.1109/ISBI.2009.5192983

Automated detection of drusen in the macula. / Freund, D. E.; Bressler, Neil M; Burlina, Philippe.

Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009. 2009. p. 61-64 5192983.

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

Freund, DE, Bressler, NM & Burlina, P 2009, Automated detection of drusen in the macula. in Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009., 5192983, pp. 61-64, 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009, Boston, MA, United States, 6/28/09. https://doi.org/10.1109/ISBI.2009.5192983
Freund DE, Bressler NM, Burlina P. Automated detection of drusen in the macula. In Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009. 2009. p. 61-64. 5192983 https://doi.org/10.1109/ISBI.2009.5192983
Freund, D. E. ; Bressler, Neil M ; Burlina, Philippe. / Automated detection of drusen in the macula. Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009. 2009. pp. 61-64
@inproceedings{5c1025e32ca44964a067b6c0002ba315,
title = "Automated detection of drusen in the macula",
abstract = "Age related macular degeneration (AMD) is a condition of the retina that occurs with individuals over 50. AMD is characterized by the formation of drusen in the macula. This condition leads to a deterioration of foveal vision and eventually functional blindness. Automatically screening atrisk individuals may allow the detection of intermediate stage AMD where it is still treatable using anti-VEGH therapy. One of the difficulties in detecting and locating drusen is that their aspect (shape, texture, color, extent) varies significantly, and because of this it is often difficult to build a classifier. To address this difficulty we use a two pronged approach based on (a) multiscale analysis and (b) kernel based anomaly detection. We show experimental results on examples of fundus images taken from healthy and affected patients.",
keywords = "Detection of retinal abnormalities, Macular pathologies, Support vector methods",
author = "Freund, {D. E.} and Bressler, {Neil M} and Philippe Burlina",
year = "2009",
doi = "10.1109/ISBI.2009.5192983",
language = "English (US)",
isbn = "9781424439324",
pages = "61--64",
booktitle = "Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009",

}

TY - GEN

T1 - Automated detection of drusen in the macula

AU - Freund, D. E.

AU - Bressler, Neil M

AU - Burlina, Philippe

PY - 2009

Y1 - 2009

N2 - Age related macular degeneration (AMD) is a condition of the retina that occurs with individuals over 50. AMD is characterized by the formation of drusen in the macula. This condition leads to a deterioration of foveal vision and eventually functional blindness. Automatically screening atrisk individuals may allow the detection of intermediate stage AMD where it is still treatable using anti-VEGH therapy. One of the difficulties in detecting and locating drusen is that their aspect (shape, texture, color, extent) varies significantly, and because of this it is often difficult to build a classifier. To address this difficulty we use a two pronged approach based on (a) multiscale analysis and (b) kernel based anomaly detection. We show experimental results on examples of fundus images taken from healthy and affected patients.

AB - Age related macular degeneration (AMD) is a condition of the retina that occurs with individuals over 50. AMD is characterized by the formation of drusen in the macula. This condition leads to a deterioration of foveal vision and eventually functional blindness. Automatically screening atrisk individuals may allow the detection of intermediate stage AMD where it is still treatable using anti-VEGH therapy. One of the difficulties in detecting and locating drusen is that their aspect (shape, texture, color, extent) varies significantly, and because of this it is often difficult to build a classifier. To address this difficulty we use a two pronged approach based on (a) multiscale analysis and (b) kernel based anomaly detection. We show experimental results on examples of fundus images taken from healthy and affected patients.

KW - Detection of retinal abnormalities

KW - Macular pathologies

KW - Support vector methods

UR - http://www.scopus.com/inward/record.url?scp=70449371801&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70449371801&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2009.5192983

DO - 10.1109/ISBI.2009.5192983

M3 - Conference contribution

AN - SCOPUS:70449371801

SN - 9781424439324

SP - 61

EP - 64

BT - Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009

ER -