Empirical mode decomposition of digital mammograms for the statistical based characterization of architectural distortion

I. Zyout, Roberto Togneri

    Research output: Chapter in Book/Conference paperConference paper

    4 Citations (Scopus)

    Abstract

    © 2015 IEEE. Among the different and common mammographic signs of the early-stage breast cancer, the architectural distortion is the most difficult to be identified. In this paper, we propose a new multiscale statistical texture analysis to characterize the presence of architectural distortion by distinguishing between textural patterns of architectural distortion and normal breast parenchyma. The proposed approach, firstly, applies the bidimensional empirical mode decomposition algorithm to decompose each mammographic region of interest into a set of adaptive and data-driven two-dimensional intrinsic mode functions (IMF) layers that capture details or high-frequency oscillations of the input image. Then, a model-based approach is applied to IMF histograms to acquire the first order statistics. The normalized entropy measure is also computed from each IMF and used as a complementary textural feature for the recognition of architectural distortion patterns. For evaluating the proposed AD characterization approach, we used a mammographic dataset of 187 true positive regions (i.e. depicting architectural distortion) and 887 true negative (normal parenchyma) regions, extracted from the DDSM database. Using the proposed multiscale textural features and the nonlinear support vector machine classifier, the best classification performance, in terms of the area under the receiver operating characteristic curve (or Az value), achieved was 0.88.
    Original languageEnglish
    Title of host publicationThe Annual International Conference of the IEEE Engineering in Medicine and Biology Society
    PublisherIEEE, Institute of Electrical and Electronics Engineers
    Pages109-112
    Volume2015-November
    ISBN (Print)9781424492718
    DOIs
    Publication statusPublished - 2015
    EventEmpirical mode decomposition of digital mammograms for the statistical based characterization of architectural distortion - Milan, Italy
    Duration: 1 Jan 2015 → …

    Conference

    ConferenceEmpirical mode decomposition of digital mammograms for the statistical based characterization of architectural distortion
    Period1/01/15 → …

    Fingerprint

    Entropy
    ROC Curve
    Breast
    Databases
    Breast Neoplasms
    Datasets
    Support Vector Machine

    Cite this

    Zyout, I., & Togneri, R. (2015). Empirical mode decomposition of digital mammograms for the statistical based characterization of architectural distortion. In The Annual International Conference of the IEEE Engineering in Medicine and Biology Society (Vol. 2015-November, pp. 109-112). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/EMBC.2015.7318312
    Zyout, I. ; Togneri, Roberto. / Empirical mode decomposition of digital mammograms for the statistical based characterization of architectural distortion. The Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol. 2015-November IEEE, Institute of Electrical and Electronics Engineers, 2015. pp. 109-112
    @inproceedings{01aec4650b284d16a3e130da4c3067d1,
    title = "Empirical mode decomposition of digital mammograms for the statistical based characterization of architectural distortion",
    abstract = "{\circledC} 2015 IEEE. Among the different and common mammographic signs of the early-stage breast cancer, the architectural distortion is the most difficult to be identified. In this paper, we propose a new multiscale statistical texture analysis to characterize the presence of architectural distortion by distinguishing between textural patterns of architectural distortion and normal breast parenchyma. The proposed approach, firstly, applies the bidimensional empirical mode decomposition algorithm to decompose each mammographic region of interest into a set of adaptive and data-driven two-dimensional intrinsic mode functions (IMF) layers that capture details or high-frequency oscillations of the input image. Then, a model-based approach is applied to IMF histograms to acquire the first order statistics. The normalized entropy measure is also computed from each IMF and used as a complementary textural feature for the recognition of architectural distortion patterns. For evaluating the proposed AD characterization approach, we used a mammographic dataset of 187 true positive regions (i.e. depicting architectural distortion) and 887 true negative (normal parenchyma) regions, extracted from the DDSM database. Using the proposed multiscale textural features and the nonlinear support vector machine classifier, the best classification performance, in terms of the area under the receiver operating characteristic curve (or Az value), achieved was 0.88.",
    author = "I. Zyout and Roberto Togneri",
    year = "2015",
    doi = "10.1109/EMBC.2015.7318312",
    language = "English",
    isbn = "9781424492718",
    volume = "2015-November",
    pages = "109--112",
    booktitle = "The Annual International Conference of the IEEE Engineering in Medicine and Biology Society",
    publisher = "IEEE, Institute of Electrical and Electronics Engineers",
    address = "United States",

    }

    Zyout, I & Togneri, R 2015, Empirical mode decomposition of digital mammograms for the statistical based characterization of architectural distortion. in The Annual International Conference of the IEEE Engineering in Medicine and Biology Society. vol. 2015-November, IEEE, Institute of Electrical and Electronics Engineers, pp. 109-112, Empirical mode decomposition of digital mammograms for the statistical based characterization of architectural distortion, 1/01/15. https://doi.org/10.1109/EMBC.2015.7318312

    Empirical mode decomposition of digital mammograms for the statistical based characterization of architectural distortion. / Zyout, I.; Togneri, Roberto.

    The Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol. 2015-November IEEE, Institute of Electrical and Electronics Engineers, 2015. p. 109-112.

    Research output: Chapter in Book/Conference paperConference paper

    TY - GEN

    T1 - Empirical mode decomposition of digital mammograms for the statistical based characterization of architectural distortion

    AU - Zyout, I.

    AU - Togneri, Roberto

    PY - 2015

    Y1 - 2015

    N2 - © 2015 IEEE. Among the different and common mammographic signs of the early-stage breast cancer, the architectural distortion is the most difficult to be identified. In this paper, we propose a new multiscale statistical texture analysis to characterize the presence of architectural distortion by distinguishing between textural patterns of architectural distortion and normal breast parenchyma. The proposed approach, firstly, applies the bidimensional empirical mode decomposition algorithm to decompose each mammographic region of interest into a set of adaptive and data-driven two-dimensional intrinsic mode functions (IMF) layers that capture details or high-frequency oscillations of the input image. Then, a model-based approach is applied to IMF histograms to acquire the first order statistics. The normalized entropy measure is also computed from each IMF and used as a complementary textural feature for the recognition of architectural distortion patterns. For evaluating the proposed AD characterization approach, we used a mammographic dataset of 187 true positive regions (i.e. depicting architectural distortion) and 887 true negative (normal parenchyma) regions, extracted from the DDSM database. Using the proposed multiscale textural features and the nonlinear support vector machine classifier, the best classification performance, in terms of the area under the receiver operating characteristic curve (or Az value), achieved was 0.88.

    AB - © 2015 IEEE. Among the different and common mammographic signs of the early-stage breast cancer, the architectural distortion is the most difficult to be identified. In this paper, we propose a new multiscale statistical texture analysis to characterize the presence of architectural distortion by distinguishing between textural patterns of architectural distortion and normal breast parenchyma. The proposed approach, firstly, applies the bidimensional empirical mode decomposition algorithm to decompose each mammographic region of interest into a set of adaptive and data-driven two-dimensional intrinsic mode functions (IMF) layers that capture details or high-frequency oscillations of the input image. Then, a model-based approach is applied to IMF histograms to acquire the first order statistics. The normalized entropy measure is also computed from each IMF and used as a complementary textural feature for the recognition of architectural distortion patterns. For evaluating the proposed AD characterization approach, we used a mammographic dataset of 187 true positive regions (i.e. depicting architectural distortion) and 887 true negative (normal parenchyma) regions, extracted from the DDSM database. Using the proposed multiscale textural features and the nonlinear support vector machine classifier, the best classification performance, in terms of the area under the receiver operating characteristic curve (or Az value), achieved was 0.88.

    U2 - 10.1109/EMBC.2015.7318312

    DO - 10.1109/EMBC.2015.7318312

    M3 - Conference paper

    SN - 9781424492718

    VL - 2015-November

    SP - 109

    EP - 112

    BT - The Annual International Conference of the IEEE Engineering in Medicine and Biology Society

    PB - IEEE, Institute of Electrical and Electronics Engineers

    ER -

    Zyout I, Togneri R. Empirical mode decomposition of digital mammograms for the statistical based characterization of architectural distortion. In The Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol. 2015-November. IEEE, Institute of Electrical and Electronics Engineers. 2015. p. 109-112 https://doi.org/10.1109/EMBC.2015.7318312