A shape cognitron neural network for breast cancer detection

San Kan Lee, Pau-Choo Chung, Chein I. Chang, Chien Shun Lo, Tain Lee, Giu Cheng Hsu, Chin Wen Yang

Research output: Contribution to conferencePaper

5 Citations (Scopus)

Abstract

A Neocognition-like neural network built with universal feature planes, called Shape Cognitron (S-Cognitron) is introduced to classify clustered microcalcifications (MCC's). The S-Cognitron is composed of two modules. The first module consists of (a) a shape orientation layer, to convert first-order shape orientations into numeric values, and (b) a complex layer to extract second-order shape features. Followed is a 3-D figure layer to extract the shape curvatures. It is then followed by a second module made up of a feature formation layer and a probabilistic neural network (PNN)-based classification layer, to construct "potential" high-order shape features and perform the classification. The experimental results show the promising of the system.

Original languageEnglish
Pages822-827
Number of pages6
Publication statusPublished - 2002 Jan 1
Event2002 International Joint Conference on Neural Networks (IJCNN '02) - Honolulu, HI, United States
Duration: 2002 May 122002 May 17

Other

Other2002 International Joint Conference on Neural Networks (IJCNN '02)
CountryUnited States
CityHonolulu, HI
Period02-05-1202-05-17

Fingerprint

Neural networks

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Cite this

Lee, S. K., Chung, P-C., Chang, C. I., Lo, C. S., Lee, T., Hsu, G. C., & Yang, C. W. (2002). A shape cognitron neural network for breast cancer detection. 822-827. Paper presented at 2002 International Joint Conference on Neural Networks (IJCNN '02), Honolulu, HI, United States.
Lee, San Kan ; Chung, Pau-Choo ; Chang, Chein I. ; Lo, Chien Shun ; Lee, Tain ; Hsu, Giu Cheng ; Yang, Chin Wen. / A shape cognitron neural network for breast cancer detection. Paper presented at 2002 International Joint Conference on Neural Networks (IJCNN '02), Honolulu, HI, United States.6 p.
@conference{1d65fd39cc75448590bb493dccf18612,
title = "A shape cognitron neural network for breast cancer detection",
abstract = "A Neocognition-like neural network built with universal feature planes, called Shape Cognitron (S-Cognitron) is introduced to classify clustered microcalcifications (MCC's). The S-Cognitron is composed of two modules. The first module consists of (a) a shape orientation layer, to convert first-order shape orientations into numeric values, and (b) a complex layer to extract second-order shape features. Followed is a 3-D figure layer to extract the shape curvatures. It is then followed by a second module made up of a feature formation layer and a probabilistic neural network (PNN)-based classification layer, to construct {"}potential{"} high-order shape features and perform the classification. The experimental results show the promising of the system.",
author = "Lee, {San Kan} and Pau-Choo Chung and Chang, {Chein I.} and Lo, {Chien Shun} and Tain Lee and Hsu, {Giu Cheng} and Yang, {Chin Wen}",
year = "2002",
month = "1",
day = "1",
language = "English",
pages = "822--827",
note = "2002 International Joint Conference on Neural Networks (IJCNN '02) ; Conference date: 12-05-2002 Through 17-05-2002",

}

Lee, SK, Chung, P-C, Chang, CI, Lo, CS, Lee, T, Hsu, GC & Yang, CW 2002, 'A shape cognitron neural network for breast cancer detection' Paper presented at 2002 International Joint Conference on Neural Networks (IJCNN '02), Honolulu, HI, United States, 02-05-12 - 02-05-17, pp. 822-827.

A shape cognitron neural network for breast cancer detection. / Lee, San Kan; Chung, Pau-Choo; Chang, Chein I.; Lo, Chien Shun; Lee, Tain; Hsu, Giu Cheng; Yang, Chin Wen.

2002. 822-827 Paper presented at 2002 International Joint Conference on Neural Networks (IJCNN '02), Honolulu, HI, United States.

Research output: Contribution to conferencePaper

TY - CONF

T1 - A shape cognitron neural network for breast cancer detection

AU - Lee, San Kan

AU - Chung, Pau-Choo

AU - Chang, Chein I.

AU - Lo, Chien Shun

AU - Lee, Tain

AU - Hsu, Giu Cheng

AU - Yang, Chin Wen

PY - 2002/1/1

Y1 - 2002/1/1

N2 - A Neocognition-like neural network built with universal feature planes, called Shape Cognitron (S-Cognitron) is introduced to classify clustered microcalcifications (MCC's). The S-Cognitron is composed of two modules. The first module consists of (a) a shape orientation layer, to convert first-order shape orientations into numeric values, and (b) a complex layer to extract second-order shape features. Followed is a 3-D figure layer to extract the shape curvatures. It is then followed by a second module made up of a feature formation layer and a probabilistic neural network (PNN)-based classification layer, to construct "potential" high-order shape features and perform the classification. The experimental results show the promising of the system.

AB - A Neocognition-like neural network built with universal feature planes, called Shape Cognitron (S-Cognitron) is introduced to classify clustered microcalcifications (MCC's). The S-Cognitron is composed of two modules. The first module consists of (a) a shape orientation layer, to convert first-order shape orientations into numeric values, and (b) a complex layer to extract second-order shape features. Followed is a 3-D figure layer to extract the shape curvatures. It is then followed by a second module made up of a feature formation layer and a probabilistic neural network (PNN)-based classification layer, to construct "potential" high-order shape features and perform the classification. The experimental results show the promising of the system.

UR - http://www.scopus.com/inward/record.url?scp=0036078871&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036078871&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0036078871

SP - 822

EP - 827

ER -

Lee SK, Chung P-C, Chang CI, Lo CS, Lee T, Hsu GC et al. A shape cognitron neural network for breast cancer detection. 2002. Paper presented at 2002 International Joint Conference on Neural Networks (IJCNN '02), Honolulu, HI, United States.