Locating the optic nerve in retinal images

Comparing model-based and Bayesian decision methods

Thomas P. Karnowski, V. Priya Govindasamy, Kenneth W. Tobin, Edward Chaum

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

17 Citations (Scopus)

Abstract

In this work we compare two methods for automatic optic nerve (ON) localization in retinal imagery. The first method uses a Bayesian decision theory discriminator based on four spatial features of the retina imagery. The second method uses a principal component-based reconstruction to model the ON. We report on an improvement to the model-based technique by incorporating linear discriminant analysis and Bayesian decision theory methods. We explore a method to combine both techniques to produce a composite technique with high accuracy and rapid throughput. Results are shown for a data set of 395 images with 2-fold validation testing.

Original languageEnglish (US)
Title of host publication28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06
Pages4436-4439
Number of pages4
DOIs
StatePublished - Dec 1 2006
Event28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06 - New York, NY, United States
Duration: Aug 30 2006Sep 3 2006

Other

Other28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06
CountryUnited States
CityNew York, NY
Period8/30/069/3/06

Fingerprint

Bayes Theorem
Decision theory
Optic Nerve
Optics
Discriminators
Decision Theory
Discriminant analysis
Imagery (Psychotherapy)
Throughput
Composite materials
Testing
Discriminant Analysis
Retina

All Science Journal Classification (ASJC) codes

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

Cite this

Karnowski, T. P., Govindasamy, V. P., Tobin, K. W., & Chaum, E. (2006). Locating the optic nerve in retinal images: Comparing model-based and Bayesian decision methods. In 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06 (pp. 4436-4439). [4029156] https://doi.org/10.1109/IEMBS.2006.259406

Locating the optic nerve in retinal images : Comparing model-based and Bayesian decision methods. / Karnowski, Thomas P.; Govindasamy, V. Priya; Tobin, Kenneth W.; Chaum, Edward.

28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06. 2006. p. 4436-4439 4029156.

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

Karnowski, TP, Govindasamy, VP, Tobin, KW & Chaum, E 2006, Locating the optic nerve in retinal images: Comparing model-based and Bayesian decision methods. in 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06., 4029156, pp. 4436-4439, 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06, New York, NY, United States, 8/30/06. https://doi.org/10.1109/IEMBS.2006.259406
Karnowski TP, Govindasamy VP, Tobin KW, Chaum E. Locating the optic nerve in retinal images: Comparing model-based and Bayesian decision methods. In 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06. 2006. p. 4436-4439. 4029156 https://doi.org/10.1109/IEMBS.2006.259406
Karnowski, Thomas P. ; Govindasamy, V. Priya ; Tobin, Kenneth W. ; Chaum, Edward. / Locating the optic nerve in retinal images : Comparing model-based and Bayesian decision methods. 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06. 2006. pp. 4436-4439
@inproceedings{afc12ea4bf774baa8e62241e2a0934ba,
title = "Locating the optic nerve in retinal images: Comparing model-based and Bayesian decision methods",
abstract = "In this work we compare two methods for automatic optic nerve (ON) localization in retinal imagery. The first method uses a Bayesian decision theory discriminator based on four spatial features of the retina imagery. The second method uses a principal component-based reconstruction to model the ON. We report on an improvement to the model-based technique by incorporating linear discriminant analysis and Bayesian decision theory methods. We explore a method to combine both techniques to produce a composite technique with high accuracy and rapid throughput. Results are shown for a data set of 395 images with 2-fold validation testing.",
author = "Karnowski, {Thomas P.} and Govindasamy, {V. Priya} and Tobin, {Kenneth W.} and Edward Chaum",
year = "2006",
month = "12",
day = "1",
doi = "10.1109/IEMBS.2006.259406",
language = "English (US)",
isbn = "1424400325",
pages = "4436--4439",
booktitle = "28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06",

}

TY - GEN

T1 - Locating the optic nerve in retinal images

T2 - Comparing model-based and Bayesian decision methods

AU - Karnowski, Thomas P.

AU - Govindasamy, V. Priya

AU - Tobin, Kenneth W.

AU - Chaum, Edward

PY - 2006/12/1

Y1 - 2006/12/1

N2 - In this work we compare two methods for automatic optic nerve (ON) localization in retinal imagery. The first method uses a Bayesian decision theory discriminator based on four spatial features of the retina imagery. The second method uses a principal component-based reconstruction to model the ON. We report on an improvement to the model-based technique by incorporating linear discriminant analysis and Bayesian decision theory methods. We explore a method to combine both techniques to produce a composite technique with high accuracy and rapid throughput. Results are shown for a data set of 395 images with 2-fold validation testing.

AB - In this work we compare two methods for automatic optic nerve (ON) localization in retinal imagery. The first method uses a Bayesian decision theory discriminator based on four spatial features of the retina imagery. The second method uses a principal component-based reconstruction to model the ON. We report on an improvement to the model-based technique by incorporating linear discriminant analysis and Bayesian decision theory methods. We explore a method to combine both techniques to produce a composite technique with high accuracy and rapid throughput. Results are shown for a data set of 395 images with 2-fold validation testing.

UR - http://www.scopus.com/inward/record.url?scp=34047148415&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34047148415&partnerID=8YFLogxK

U2 - 10.1109/IEMBS.2006.259406

DO - 10.1109/IEMBS.2006.259406

M3 - Conference contribution

SN - 1424400325

SN - 9781424400324

SP - 4436

EP - 4439

BT - 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06

ER -