Feature-extraction method based on the ideal observer

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

Abstract

A feature extraction method was designed for medical imaging systems for tumor-detection based on the strategy of the ideal observer. The strategy of linear discriminant functions was applied by means of a mathematical model using probability density functions, matrix algebra and artificial neural networks. The model took into account Gaussian processes and white noise in the image analysis.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
EditorsM. Sonka, K.M. Hanson
Pages440-447
Number of pages8
Volume4322
Edition1
DOIs
StatePublished - 2001
EventMedical Imaging 2001 Image Processing - San Diego, CA, United States
Duration: Feb 19 2001Feb 22 2001

Other

OtherMedical Imaging 2001 Image Processing
CountryUnited States
CitySan Diego, CA
Period2/19/012/22/01

Fingerprint

Medical imaging
White noise
pattern recognition
Imaging systems
Image analysis
Probability density function
Feature extraction
Tumors
Mathematical models
Neural networks
white noise
probability density functions
image analysis
mathematical models
algebra
tumors

Keywords

  • Feature extraction
  • Ideal observer
  • Neural network

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Zhang, H., Clarkson, E. W., & Barrett, H. H. (2001). Feature-extraction method based on the ideal observer. In M. Sonka, & K. M. Hanson (Eds.), Proceedings of SPIE - The International Society for Optical Engineering (1 ed., Vol. 4322, pp. 440-447) https://doi.org/10.1117/12.431116

Feature-extraction method based on the ideal observer. / Zhang, H.; Clarkson, Eric W; Barrett, Harrison H.

Proceedings of SPIE - The International Society for Optical Engineering. ed. / M. Sonka; K.M. Hanson. Vol. 4322 1. ed. 2001. p. 440-447.

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

Zhang, H, Clarkson, EW & Barrett, HH 2001, Feature-extraction method based on the ideal observer. in M Sonka & KM Hanson (eds), Proceedings of SPIE - The International Society for Optical Engineering. 1 edn, vol. 4322, pp. 440-447, Medical Imaging 2001 Image Processing, San Diego, CA, United States, 2/19/01. https://doi.org/10.1117/12.431116
Zhang H, Clarkson EW, Barrett HH. Feature-extraction method based on the ideal observer. In Sonka M, Hanson KM, editors, Proceedings of SPIE - The International Society for Optical Engineering. 1 ed. Vol. 4322. 2001. p. 440-447 https://doi.org/10.1117/12.431116
Zhang, H. ; Clarkson, Eric W ; Barrett, Harrison H. / Feature-extraction method based on the ideal observer. Proceedings of SPIE - The International Society for Optical Engineering. editor / M. Sonka ; K.M. Hanson. Vol. 4322 1. ed. 2001. pp. 440-447
@inproceedings{e93bf025e3824aeba55331644890db2a,
title = "Feature-extraction method based on the ideal observer",
abstract = "A feature extraction method was designed for medical imaging systems for tumor-detection based on the strategy of the ideal observer. The strategy of linear discriminant functions was applied by means of a mathematical model using probability density functions, matrix algebra and artificial neural networks. The model took into account Gaussian processes and white noise in the image analysis.",
keywords = "Feature extraction, Ideal observer, Neural network",
author = "H. Zhang and Clarkson, {Eric W} and Barrett, {Harrison H}",
year = "2001",
doi = "10.1117/12.431116",
language = "English (US)",
volume = "4322",
pages = "440--447",
editor = "M. Sonka and K.M. Hanson",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",
edition = "1",

}

TY - GEN

T1 - Feature-extraction method based on the ideal observer

AU - Zhang, H.

AU - Clarkson, Eric W

AU - Barrett, Harrison H

PY - 2001

Y1 - 2001

N2 - A feature extraction method was designed for medical imaging systems for tumor-detection based on the strategy of the ideal observer. The strategy of linear discriminant functions was applied by means of a mathematical model using probability density functions, matrix algebra and artificial neural networks. The model took into account Gaussian processes and white noise in the image analysis.

AB - A feature extraction method was designed for medical imaging systems for tumor-detection based on the strategy of the ideal observer. The strategy of linear discriminant functions was applied by means of a mathematical model using probability density functions, matrix algebra and artificial neural networks. The model took into account Gaussian processes and white noise in the image analysis.

KW - Feature extraction

KW - Ideal observer

KW - Neural network

UR - http://www.scopus.com/inward/record.url?scp=0034841675&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034841675&partnerID=8YFLogxK

U2 - 10.1117/12.431116

DO - 10.1117/12.431116

M3 - Conference contribution

AN - SCOPUS:0034841675

VL - 4322

SP - 440

EP - 447

BT - Proceedings of SPIE - The International Society for Optical Engineering

A2 - Sonka, M.

A2 - Hanson, K.M.

ER -