Investigation of multiorientation and multiresolution features for microcalcifications classification in mammograms

Aqilah Baseri Huddin, Brian W H Ng, Derek Abbott

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

3 Citations (Scopus)

Abstract

Breast cancer is one of the most common cancers among women. One of the early signs of the disease is the appearance of microcalcifications clusters, which often show up as bright spots in mammograms. It is important to be able to distinguish between the shapes of these clusters to increase the reliability and accuracy of the diagnosis. In this paper, a new method to extract features to classify the microcalcification clusters using steerable pyramid decomposition is presented. The method is motivated by the fact that microcalcification clusters can be of arbitrary sizes and orientations. Thus, it is important to extract the features in all possible orientations to capture most of the distinguishing information for classification. The proposed method shows a clear improvement in the classification performance when compared to the wavelet transform; the most commonly used multiscale analysis technique at present.

Original languageEnglish
Title of host publicationProceedings of the 2011 7th International Conference on Intelligent Sensors, Sensor Networks and Information Processing, ISSNIP 2011
Pages52-57
Number of pages6
DOIs
Publication statusPublished - 2011
Externally publishedYes
Event2011 7th International Conference on Intelligent Sensors, Sensor Networks and Information Processing, ISSNIP 2011 - Adelaide, SA
Duration: 6 Dec 20119 Dec 2011

Other

Other2011 7th International Conference on Intelligent Sensors, Sensor Networks and Information Processing, ISSNIP 2011
CityAdelaide, SA
Period6/12/119/12/11

Fingerprint

Wavelet transforms
Decomposition

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications

Cite this

Huddin, A. B., Ng, B. W. H., & Abbott, D. (2011). Investigation of multiorientation and multiresolution features for microcalcifications classification in mammograms. In Proceedings of the 2011 7th International Conference on Intelligent Sensors, Sensor Networks and Information Processing, ISSNIP 2011 (pp. 52-57). [6146615] https://doi.org/10.1109/ISSNIP.2011.6146615

Investigation of multiorientation and multiresolution features for microcalcifications classification in mammograms. / Huddin, Aqilah Baseri; Ng, Brian W H; Abbott, Derek.

Proceedings of the 2011 7th International Conference on Intelligent Sensors, Sensor Networks and Information Processing, ISSNIP 2011. 2011. p. 52-57 6146615.

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

Huddin, AB, Ng, BWH & Abbott, D 2011, Investigation of multiorientation and multiresolution features for microcalcifications classification in mammograms. in Proceedings of the 2011 7th International Conference on Intelligent Sensors, Sensor Networks and Information Processing, ISSNIP 2011., 6146615, pp. 52-57, 2011 7th International Conference on Intelligent Sensors, Sensor Networks and Information Processing, ISSNIP 2011, Adelaide, SA, 6/12/11. https://doi.org/10.1109/ISSNIP.2011.6146615
Huddin AB, Ng BWH, Abbott D. Investigation of multiorientation and multiresolution features for microcalcifications classification in mammograms. In Proceedings of the 2011 7th International Conference on Intelligent Sensors, Sensor Networks and Information Processing, ISSNIP 2011. 2011. p. 52-57. 6146615 https://doi.org/10.1109/ISSNIP.2011.6146615
Huddin, Aqilah Baseri ; Ng, Brian W H ; Abbott, Derek. / Investigation of multiorientation and multiresolution features for microcalcifications classification in mammograms. Proceedings of the 2011 7th International Conference on Intelligent Sensors, Sensor Networks and Information Processing, ISSNIP 2011. 2011. pp. 52-57
@inproceedings{dd28285e70224c75be4fd401fd456f7e,
title = "Investigation of multiorientation and multiresolution features for microcalcifications classification in mammograms",
abstract = "Breast cancer is one of the most common cancers among women. One of the early signs of the disease is the appearance of microcalcifications clusters, which often show up as bright spots in mammograms. It is important to be able to distinguish between the shapes of these clusters to increase the reliability and accuracy of the diagnosis. In this paper, a new method to extract features to classify the microcalcification clusters using steerable pyramid decomposition is presented. The method is motivated by the fact that microcalcification clusters can be of arbitrary sizes and orientations. Thus, it is important to extract the features in all possible orientations to capture most of the distinguishing information for classification. The proposed method shows a clear improvement in the classification performance when compared to the wavelet transform; the most commonly used multiscale analysis technique at present.",
author = "Huddin, {Aqilah Baseri} and Ng, {Brian W H} and Derek Abbott",
year = "2011",
doi = "10.1109/ISSNIP.2011.6146615",
language = "English",
isbn = "9781457706738",
pages = "52--57",
booktitle = "Proceedings of the 2011 7th International Conference on Intelligent Sensors, Sensor Networks and Information Processing, ISSNIP 2011",

}

TY - GEN

T1 - Investigation of multiorientation and multiresolution features for microcalcifications classification in mammograms

AU - Huddin, Aqilah Baseri

AU - Ng, Brian W H

AU - Abbott, Derek

PY - 2011

Y1 - 2011

N2 - Breast cancer is one of the most common cancers among women. One of the early signs of the disease is the appearance of microcalcifications clusters, which often show up as bright spots in mammograms. It is important to be able to distinguish between the shapes of these clusters to increase the reliability and accuracy of the diagnosis. In this paper, a new method to extract features to classify the microcalcification clusters using steerable pyramid decomposition is presented. The method is motivated by the fact that microcalcification clusters can be of arbitrary sizes and orientations. Thus, it is important to extract the features in all possible orientations to capture most of the distinguishing information for classification. The proposed method shows a clear improvement in the classification performance when compared to the wavelet transform; the most commonly used multiscale analysis technique at present.

AB - Breast cancer is one of the most common cancers among women. One of the early signs of the disease is the appearance of microcalcifications clusters, which often show up as bright spots in mammograms. It is important to be able to distinguish between the shapes of these clusters to increase the reliability and accuracy of the diagnosis. In this paper, a new method to extract features to classify the microcalcification clusters using steerable pyramid decomposition is presented. The method is motivated by the fact that microcalcification clusters can be of arbitrary sizes and orientations. Thus, it is important to extract the features in all possible orientations to capture most of the distinguishing information for classification. The proposed method shows a clear improvement in the classification performance when compared to the wavelet transform; the most commonly used multiscale analysis technique at present.

UR - http://www.scopus.com/inward/record.url?scp=84857950030&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84857950030&partnerID=8YFLogxK

U2 - 10.1109/ISSNIP.2011.6146615

DO - 10.1109/ISSNIP.2011.6146615

M3 - Conference contribution

AN - SCOPUS:84857950030

SN - 9781457706738

SP - 52

EP - 57

BT - Proceedings of the 2011 7th International Conference on Intelligent Sensors, Sensor Networks and Information Processing, ISSNIP 2011

ER -