Diagnostic classification of digital mammograms by wavelet-based spectral tools: A comparative study

Erin K. Hamilton, Seonghye Jeon, Pepa Ramírez Cobo, Kichun Lee, Brani Vidakovic

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

3 Citations (Scopus)

Abstract

The aim of this paper is to present results from a comparative investigation into the diagnostic performance of several wavelet-based estimators of scaling, some from published literature and some newly proposed. These estimators are evaluated based on their ability to classify digitized mammogram images from a clinical database, for which the true disease status is known by biopsy. We found that Abry-Veitch and modified weighted Theil-type estimators provided the best classification rates, while the standard wavelet-based OLS estimator performed worst. The results are robust with respect to choice of wavelets (Haar wavelet being an exception) and are of potential clinical value. The diagnostic is based on the properties of image backgrounds (which is an unused diagnostic modality in Mammograms) and the best correct classification rates achieve 90\%, varying slightly with the choice of basis, levels used, and size of training set.

Original languageEnglish
Title of host publicationProceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011
Pages384-389
Number of pages6
DOIs
StatePublished - 2011 Dec 1
Event2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011 - Atlanta, GA, United States
Duration: 2011 Nov 122011 Nov 15

Other

Other2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011
CountryUnited States
CityAtlanta, GA
Period11/11/1211/11/15

Fingerprint

Biopsy
Databases

Keywords

  • Breast cancer diagnostic
  • fBm
  • Mammogram analysis
  • Scaling
  • Wavelets

Cite this

Hamilton, E. K., Jeon, S., Cobo, P. R., Lee, K., & Vidakovic, B. (2011). Diagnostic classification of digital mammograms by wavelet-based spectral tools: A comparative study. In Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011 (pp. 384-389). [6120470] https://doi.org/10.1109/BIBM.2011.44
Hamilton, Erin K. ; Jeon, Seonghye ; Cobo, Pepa Ramírez ; Lee, Kichun ; Vidakovic, Brani. / Diagnostic classification of digital mammograms by wavelet-based spectral tools : A comparative study. Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011. 2011. pp. 384-389
@inproceedings{99b6966691ba49eeb681d3350e324c7f,
title = "Diagnostic classification of digital mammograms by wavelet-based spectral tools: A comparative study",
abstract = "The aim of this paper is to present results from a comparative investigation into the diagnostic performance of several wavelet-based estimators of scaling, some from published literature and some newly proposed. These estimators are evaluated based on their ability to classify digitized mammogram images from a clinical database, for which the true disease status is known by biopsy. We found that Abry-Veitch and modified weighted Theil-type estimators provided the best classification rates, while the standard wavelet-based OLS estimator performed worst. The results are robust with respect to choice of wavelets (Haar wavelet being an exception) and are of potential clinical value. The diagnostic is based on the properties of image backgrounds (which is an unused diagnostic modality in Mammograms) and the best correct classification rates achieve 90\{\%}, varying slightly with the choice of basis, levels used, and size of training set.",
keywords = "Breast cancer diagnostic, fBm, Mammogram analysis, Scaling, Wavelets",
author = "Hamilton, {Erin K.} and Seonghye Jeon and Cobo, {Pepa Ram{\'i}rez} and Kichun Lee and Brani Vidakovic",
year = "2011",
month = "12",
day = "1",
doi = "10.1109/BIBM.2011.44",
language = "English",
isbn = "9780769545745",
pages = "384--389",
booktitle = "Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011",

}

Hamilton, EK, Jeon, S, Cobo, PR, Lee, K & Vidakovic, B 2011, Diagnostic classification of digital mammograms by wavelet-based spectral tools: A comparative study. in Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011., 6120470, pp. 384-389, 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011, Atlanta, GA, United States, 11/11/12. https://doi.org/10.1109/BIBM.2011.44

Diagnostic classification of digital mammograms by wavelet-based spectral tools : A comparative study. / Hamilton, Erin K.; Jeon, Seonghye; Cobo, Pepa Ramírez; Lee, Kichun; Vidakovic, Brani.

Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011. 2011. p. 384-389 6120470.

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

TY - GEN

T1 - Diagnostic classification of digital mammograms by wavelet-based spectral tools

T2 - A comparative study

AU - Hamilton, Erin K.

AU - Jeon, Seonghye

AU - Cobo, Pepa Ramírez

AU - Lee, Kichun

AU - Vidakovic, Brani

PY - 2011/12/1

Y1 - 2011/12/1

N2 - The aim of this paper is to present results from a comparative investigation into the diagnostic performance of several wavelet-based estimators of scaling, some from published literature and some newly proposed. These estimators are evaluated based on their ability to classify digitized mammogram images from a clinical database, for which the true disease status is known by biopsy. We found that Abry-Veitch and modified weighted Theil-type estimators provided the best classification rates, while the standard wavelet-based OLS estimator performed worst. The results are robust with respect to choice of wavelets (Haar wavelet being an exception) and are of potential clinical value. The diagnostic is based on the properties of image backgrounds (which is an unused diagnostic modality in Mammograms) and the best correct classification rates achieve 90\%, varying slightly with the choice of basis, levels used, and size of training set.

AB - The aim of this paper is to present results from a comparative investigation into the diagnostic performance of several wavelet-based estimators of scaling, some from published literature and some newly proposed. These estimators are evaluated based on their ability to classify digitized mammogram images from a clinical database, for which the true disease status is known by biopsy. We found that Abry-Veitch and modified weighted Theil-type estimators provided the best classification rates, while the standard wavelet-based OLS estimator performed worst. The results are robust with respect to choice of wavelets (Haar wavelet being an exception) and are of potential clinical value. The diagnostic is based on the properties of image backgrounds (which is an unused diagnostic modality in Mammograms) and the best correct classification rates achieve 90\%, varying slightly with the choice of basis, levels used, and size of training set.

KW - Breast cancer diagnostic

KW - fBm

KW - Mammogram analysis

KW - Scaling

KW - Wavelets

UR - http://www.scopus.com/inward/record.url?scp=84862967288&partnerID=8YFLogxK

U2 - 10.1109/BIBM.2011.44

DO - 10.1109/BIBM.2011.44

M3 - Conference contribution

AN - SCOPUS:84862967288

SN - 9780769545745

SP - 384

EP - 389

BT - Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011

ER -

Hamilton EK, Jeon S, Cobo PR, Lee K, Vidakovic B. Diagnostic classification of digital mammograms by wavelet-based spectral tools: A comparative study. In Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011. 2011. p. 384-389. 6120470 https://doi.org/10.1109/BIBM.2011.44