Geographic atrophy segmentation in infrared and autofluorescent retina images using supervised learning

K. Devisetti, T. P. Karnowski, L. Giancardo, Y. Li, Edward Chaum

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

Abstract

Geographic Atrophy (GA) of the retinal pigment epithelium (RPE) is an advanced form of atrophic age-related macular degeneration (AMD) and is responsible for about 20% of AMD-related legal blindness in the United States. Two different imaging modalities for retinas, infrared imaging and autofluorescence imaging, serve as interesting complimentary technologies for highlighting GA. In this work we explore the use of neural network classifiers in performing segmentation of GA in registered infrared (IR) and autofluorescence (AF) images. Our segmentation achieved a performance level of 82.5% sensitivity and 92.9% specificity on a per-pixel basis using hold-one-out validation testing. The algorithm, feature extraction, data set and experimental results are discussed and shown.

Original languageEnglish (US)
Title of host publication33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011
Pages3958-3961
Number of pages4
DOIs
StatePublished - Dec 26 2011
Event33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011 - Boston, MA, United States
Duration: Aug 30 2011Sep 3 2011

Publication series

NameProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
ISSN (Print)1557-170X

Other

Other33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011
CountryUnited States
CityBoston, MA
Period8/30/119/3/11

Fingerprint

Geographic Atrophy
Supervised learning
Retina
Macular Degeneration
Learning
Infrared radiation
Imaging techniques
Infrared imaging
Pigments
Feature extraction
Classifiers
Retinal Pigment Epithelium
Pixels
Optical Imaging
Blindness
Neural networks
Testing
Technology
Sensitivity and Specificity

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Cite this

Devisetti, K., Karnowski, T. P., Giancardo, L., Li, Y., & Chaum, E. (2011). Geographic atrophy segmentation in infrared and autofluorescent retina images using supervised learning. In 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011 (pp. 3958-3961). [6090983] (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS). https://doi.org/10.1109/IEMBS.2011.6090983

Geographic atrophy segmentation in infrared and autofluorescent retina images using supervised learning. / Devisetti, K.; Karnowski, T. P.; Giancardo, L.; Li, Y.; Chaum, Edward.

33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011. 2011. p. 3958-3961 6090983 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS).

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

Devisetti, K, Karnowski, TP, Giancardo, L, Li, Y & Chaum, E 2011, Geographic atrophy segmentation in infrared and autofluorescent retina images using supervised learning. in 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011., 6090983, Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, pp. 3958-3961, 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011, Boston, MA, United States, 8/30/11. https://doi.org/10.1109/IEMBS.2011.6090983
Devisetti K, Karnowski TP, Giancardo L, Li Y, Chaum E. Geographic atrophy segmentation in infrared and autofluorescent retina images using supervised learning. In 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011. 2011. p. 3958-3961. 6090983. (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS). https://doi.org/10.1109/IEMBS.2011.6090983
Devisetti, K. ; Karnowski, T. P. ; Giancardo, L. ; Li, Y. ; Chaum, Edward. / Geographic atrophy segmentation in infrared and autofluorescent retina images using supervised learning. 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011. 2011. pp. 3958-3961 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS).
@inproceedings{f7fad8403fc6492c946d83c20ac51608,
title = "Geographic atrophy segmentation in infrared and autofluorescent retina images using supervised learning",
abstract = "Geographic Atrophy (GA) of the retinal pigment epithelium (RPE) is an advanced form of atrophic age-related macular degeneration (AMD) and is responsible for about 20{\%} of AMD-related legal blindness in the United States. Two different imaging modalities for retinas, infrared imaging and autofluorescence imaging, serve as interesting complimentary technologies for highlighting GA. In this work we explore the use of neural network classifiers in performing segmentation of GA in registered infrared (IR) and autofluorescence (AF) images. Our segmentation achieved a performance level of 82.5{\%} sensitivity and 92.9{\%} specificity on a per-pixel basis using hold-one-out validation testing. The algorithm, feature extraction, data set and experimental results are discussed and shown.",
author = "K. Devisetti and Karnowski, {T. P.} and L. Giancardo and Y. Li and Edward Chaum",
year = "2011",
month = "12",
day = "26",
doi = "10.1109/IEMBS.2011.6090983",
language = "English (US)",
isbn = "9781424441211",
series = "Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS",
pages = "3958--3961",
booktitle = "33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011",

}

TY - GEN

T1 - Geographic atrophy segmentation in infrared and autofluorescent retina images using supervised learning

AU - Devisetti, K.

AU - Karnowski, T. P.

AU - Giancardo, L.

AU - Li, Y.

AU - Chaum, Edward

PY - 2011/12/26

Y1 - 2011/12/26

N2 - Geographic Atrophy (GA) of the retinal pigment epithelium (RPE) is an advanced form of atrophic age-related macular degeneration (AMD) and is responsible for about 20% of AMD-related legal blindness in the United States. Two different imaging modalities for retinas, infrared imaging and autofluorescence imaging, serve as interesting complimentary technologies for highlighting GA. In this work we explore the use of neural network classifiers in performing segmentation of GA in registered infrared (IR) and autofluorescence (AF) images. Our segmentation achieved a performance level of 82.5% sensitivity and 92.9% specificity on a per-pixel basis using hold-one-out validation testing. The algorithm, feature extraction, data set and experimental results are discussed and shown.

AB - Geographic Atrophy (GA) of the retinal pigment epithelium (RPE) is an advanced form of atrophic age-related macular degeneration (AMD) and is responsible for about 20% of AMD-related legal blindness in the United States. Two different imaging modalities for retinas, infrared imaging and autofluorescence imaging, serve as interesting complimentary technologies for highlighting GA. In this work we explore the use of neural network classifiers in performing segmentation of GA in registered infrared (IR) and autofluorescence (AF) images. Our segmentation achieved a performance level of 82.5% sensitivity and 92.9% specificity on a per-pixel basis using hold-one-out validation testing. The algorithm, feature extraction, data set and experimental results are discussed and shown.

UR - http://www.scopus.com/inward/record.url?scp=84863561343&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863561343&partnerID=8YFLogxK

U2 - 10.1109/IEMBS.2011.6090983

DO - 10.1109/IEMBS.2011.6090983

M3 - Conference contribution

SN - 9781424441211

T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

SP - 3958

EP - 3961

BT - 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011

ER -