A novel min-max feature value based neural architecture and learning algorithm for classification of microcalcifications

Brijesh Verma, Rinku Panchal, Kuldeep Kumar

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

4 Citations (Scopus)

Abstract

The paper proposes a novel min-max feature value based neural architecture and learning algorithm for classification of microcalcification patterns in digital mammograms. The neural architecture has a single hidden layer and it has a fixed number of hidden units and outputs. One class is represented by three hidden units and an output. The suspicious areas represented by chain code, are extracted from digital mammograms. The feature values are extracted for benign and malignant microcalcifications. A set of min, average and max values for every input feature is defined and assigned to the weights between input and hidden layer. The weights of the output layer are calculated using least squares methods or assigned in such a way that it maximizes the output value for only one class. Many experiments were conducted on a benchmark database of digital mammograms and comparative results are included in this paper.

Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
Place of PublicationPortland
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages2033-2038
Number of pages6
Volume3
ISBN (Print)0-7803-7898-9
DOIs
Publication statusPublished - 2003
EventInternational Joint Conference on Neural Networks 2003 - Doubletree Hotel - Jantzen Beach, Portland, OR, United States
Duration: 20 Jul 200324 Jul 2003
http://www.conference123.org/ijcnn2003/

Publication series

NameProceedings of the International Joint Conference on Neural Networks, 2003
PublisherIEEE
ISSN (Print)1098-7576

Conference

ConferenceInternational Joint Conference on Neural Networks 2003
Abbreviated titleIEEE
CountryUnited States
CityPortland, OR
Period20/07/0324/07/03
Internet address

Fingerprint

Learning algorithms
Experiments

Cite this

Verma, B., Panchal, R., & Kumar, K. (2003). A novel min-max feature value based neural architecture and learning algorithm for classification of microcalcifications. In Proceedings of the International Joint Conference on Neural Networks (Vol. 3, pp. 2033-2038). (Proceedings of the International Joint Conference on Neural Networks, 2003). Portland: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/IJCNN.2003.1223720
Verma, Brijesh ; Panchal, Rinku ; Kumar, Kuldeep. / A novel min-max feature value based neural architecture and learning algorithm for classification of microcalcifications. Proceedings of the International Joint Conference on Neural Networks. Vol. 3 Portland : IEEE, Institute of Electrical and Electronics Engineers, 2003. pp. 2033-2038 (Proceedings of the International Joint Conference on Neural Networks, 2003).
@inproceedings{6c01f55c06474a4a80273caab5584561,
title = "A novel min-max feature value based neural architecture and learning algorithm for classification of microcalcifications",
abstract = "The paper proposes a novel min-max feature value based neural architecture and learning algorithm for classification of microcalcification patterns in digital mammograms. The neural architecture has a single hidden layer and it has a fixed number of hidden units and outputs. One class is represented by three hidden units and an output. The suspicious areas represented by chain code, are extracted from digital mammograms. The feature values are extracted for benign and malignant microcalcifications. A set of min, average and max values for every input feature is defined and assigned to the weights between input and hidden layer. The weights of the output layer are calculated using least squares methods or assigned in such a way that it maximizes the output value for only one class. Many experiments were conducted on a benchmark database of digital mammograms and comparative results are included in this paper.",
author = "Brijesh Verma and Rinku Panchal and Kuldeep Kumar",
year = "2003",
doi = "10.1109/IJCNN.2003.1223720",
language = "English",
isbn = "0-7803-7898-9",
volume = "3",
series = "Proceedings of the International Joint Conference on Neural Networks, 2003",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
pages = "2033--2038",
booktitle = "Proceedings of the International Joint Conference on Neural Networks",
address = "United States",

}

Verma, B, Panchal, R & Kumar, K 2003, A novel min-max feature value based neural architecture and learning algorithm for classification of microcalcifications. in Proceedings of the International Joint Conference on Neural Networks. vol. 3, Proceedings of the International Joint Conference on Neural Networks, 2003, IEEE, Institute of Electrical and Electronics Engineers, Portland, pp. 2033-2038, International Joint Conference on Neural Networks 2003, Portland, OR, United States, 20/07/03. https://doi.org/10.1109/IJCNN.2003.1223720

A novel min-max feature value based neural architecture and learning algorithm for classification of microcalcifications. / Verma, Brijesh; Panchal, Rinku; Kumar, Kuldeep.

Proceedings of the International Joint Conference on Neural Networks. Vol. 3 Portland : IEEE, Institute of Electrical and Electronics Engineers, 2003. p. 2033-2038 (Proceedings of the International Joint Conference on Neural Networks, 2003).

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

TY - GEN

T1 - A novel min-max feature value based neural architecture and learning algorithm for classification of microcalcifications

AU - Verma, Brijesh

AU - Panchal, Rinku

AU - Kumar, Kuldeep

PY - 2003

Y1 - 2003

N2 - The paper proposes a novel min-max feature value based neural architecture and learning algorithm for classification of microcalcification patterns in digital mammograms. The neural architecture has a single hidden layer and it has a fixed number of hidden units and outputs. One class is represented by three hidden units and an output. The suspicious areas represented by chain code, are extracted from digital mammograms. The feature values are extracted for benign and malignant microcalcifications. A set of min, average and max values for every input feature is defined and assigned to the weights between input and hidden layer. The weights of the output layer are calculated using least squares methods or assigned in such a way that it maximizes the output value for only one class. Many experiments were conducted on a benchmark database of digital mammograms and comparative results are included in this paper.

AB - The paper proposes a novel min-max feature value based neural architecture and learning algorithm for classification of microcalcification patterns in digital mammograms. The neural architecture has a single hidden layer and it has a fixed number of hidden units and outputs. One class is represented by three hidden units and an output. The suspicious areas represented by chain code, are extracted from digital mammograms. The feature values are extracted for benign and malignant microcalcifications. A set of min, average and max values for every input feature is defined and assigned to the weights between input and hidden layer. The weights of the output layer are calculated using least squares methods or assigned in such a way that it maximizes the output value for only one class. Many experiments were conducted on a benchmark database of digital mammograms and comparative results are included in this paper.

UR - http://www.scopus.com/inward/record.url?scp=0141571417&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2003.1223720

DO - 10.1109/IJCNN.2003.1223720

M3 - Conference contribution

SN - 0-7803-7898-9

VL - 3

T3 - Proceedings of the International Joint Conference on Neural Networks, 2003

SP - 2033

EP - 2038

BT - Proceedings of the International Joint Conference on Neural Networks

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Portland

ER -

Verma B, Panchal R, Kumar K. A novel min-max feature value based neural architecture and learning algorithm for classification of microcalcifications. In Proceedings of the International Joint Conference on Neural Networks. Vol. 3. Portland: IEEE, Institute of Electrical and Electronics Engineers. 2003. p. 2033-2038. (Proceedings of the International Joint Conference on Neural Networks, 2003). https://doi.org/10.1109/IJCNN.2003.1223720