Rank M-type radial basis functions network for medical image processing applications

Research output: Contribution to conferencePaperResearch

Abstract

In this paper we present the capability of the Rank M-Type Radial Basis Function (RMRBF) Neural Network in medical image processing applications. The proposed neural network uses the proposed RM-estimators in the scheme of radial basis function to train the neural network. The RMRBF-based training is less biased by the presence of outliers in the training set and was proved an accurate estimation of the implied probabilities. Other RBF based algorithms were compared with our approach in pdf estimation on the microcalcification detection in mammographic image analysis. From simulation results we observe that the RMRBF gives better estimation of the implied pdfs and has show better classification capabilities. © 2007 SPIE-IS&T.
Original languageAmerican English
DOIs
StatePublished - 31 Aug 2007
Externally publishedYes
EventProceedings of SPIE - The International Society for Optical Engineering -
Duration: 31 Aug 2007 → …

Conference

ConferenceProceedings of SPIE - The International Society for Optical Engineering
Period31/08/07 → …

Fingerprint

Medical image processing
Radial basis function networks
outlier
image processing
image analysis
train
Neural networks
simulation
Image analysis
detection

Cite this

@conference{f541bb4a8fcc4ae09c9f856e4d9ed065,
title = "Rank M-type radial basis functions network for medical image processing applications",
abstract = "In this paper we present the capability of the Rank M-Type Radial Basis Function (RMRBF) Neural Network in medical image processing applications. The proposed neural network uses the proposed RM-estimators in the scheme of radial basis function to train the neural network. The RMRBF-based training is less biased by the presence of outliers in the training set and was proved an accurate estimation of the implied probabilities. Other RBF based algorithms were compared with our approach in pdf estimation on the microcalcification detection in mammographic image analysis. From simulation results we observe that the RMRBF gives better estimation of the implied pdfs and has show better classification capabilities. {\circledC} 2007 SPIE-IS&T.",
author = "Moreno-Escobar, {Jos{\'e} A.} and Gallegos-Funes, {Francisco J.} and Ponomaryov, {Volodymyr I.}",
year = "2007",
month = "8",
day = "31",
doi = "10.1117/12.699250",
language = "American English",
note = "Proceedings of SPIE - The International Society for Optical Engineering ; Conference date: 31-08-2007",

}

Rank M-type radial basis functions network for medical image processing applications. / Moreno-Escobar, José A.; Gallegos-Funes, Francisco J.; Ponomaryov, Volodymyr I.

2007. Paper presented at Proceedings of SPIE - The International Society for Optical Engineering, .

Research output: Contribution to conferencePaperResearch

TY - CONF

T1 - Rank M-type radial basis functions network for medical image processing applications

AU - Moreno-Escobar, José A.

AU - Gallegos-Funes, Francisco J.

AU - Ponomaryov, Volodymyr I.

PY - 2007/8/31

Y1 - 2007/8/31

N2 - In this paper we present the capability of the Rank M-Type Radial Basis Function (RMRBF) Neural Network in medical image processing applications. The proposed neural network uses the proposed RM-estimators in the scheme of radial basis function to train the neural network. The RMRBF-based training is less biased by the presence of outliers in the training set and was proved an accurate estimation of the implied probabilities. Other RBF based algorithms were compared with our approach in pdf estimation on the microcalcification detection in mammographic image analysis. From simulation results we observe that the RMRBF gives better estimation of the implied pdfs and has show better classification capabilities. © 2007 SPIE-IS&T.

AB - In this paper we present the capability of the Rank M-Type Radial Basis Function (RMRBF) Neural Network in medical image processing applications. The proposed neural network uses the proposed RM-estimators in the scheme of radial basis function to train the neural network. The RMRBF-based training is less biased by the presence of outliers in the training set and was proved an accurate estimation of the implied probabilities. Other RBF based algorithms were compared with our approach in pdf estimation on the microcalcification detection in mammographic image analysis. From simulation results we observe that the RMRBF gives better estimation of the implied pdfs and has show better classification capabilities. © 2007 SPIE-IS&T.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=34548215148&origin=inward

UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=34548215148&origin=inward

U2 - 10.1117/12.699250

DO - 10.1117/12.699250

M3 - Paper

ER -