Breast Cancer classification using extracted parameters from a terahertz dielectric model of human breast tissue

Bao C Q Truong, H. D. Tuan, Anthony J. Fitzgerald, Vincent P. Wallace, Tuan Nghia Nguyen, H. T. Nguyen

    Research output: Chapter in Book/Conference paperConference paper

    2 Citations (Scopus)

    Abstract

    Our previous study proposed a dielectric model for human breast tissue and provided initial analysis of classification potential of the eight model parameters and their multiparameter combinations with the support vector machine (SVM). A combination of three model parameters could achieve a leave-one-out cross validation accuracy of 93.2%. However, the SVM approach fails to exploit the combinations of more than three model parameters for classification improvement. Thus, the Bayesian neural network (BNN) method is employed to overcome this problem based on its advantages of handling our small data and high complexity of the multiparamter combinations. The BNN successfully classifies the data using the combinations of four model parameters with an accuracy, estimated by leave-one-out cross validation, of 97.3%. Overall performance assessed by leaveone- out and repeated random-subsampling cross validations for all examined combinations is also remarkably improved by BNN. The results indicate the advance of BNN as compared to SVM in utilising the model parameters for detecting tumour from normal breast tissue.

    Original languageEnglish
    Title of host publication2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
    EditorsSergio Cerutti, Paolo Bonato
    PublisherIEEE, Institute of Electrical and Electronics Engineers
    Pages2804-2807
    Number of pages4
    ISBN (Electronic)9781424492718
    DOIs
    Publication statusPublished - 4 Nov 2015
    Event37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015 - Milan, Italy
    Duration: 25 Aug 201529 Aug 2015

    Conference

    Conference37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015
    CountryItaly
    CityMilan
    Period25/08/1529/08/15

    Fingerprint

    Breast
    Tissue
    Breast Neoplasms
    Neural networks
    Support vector machines
    Support Vector Machine
    Tumors

    Cite this

    Truong, B. C. Q., Tuan, H. D., Fitzgerald, A. J., Wallace, V. P., Nguyen, T. N., & Nguyen, H. T. (2015). Breast Cancer classification using extracted parameters from a terahertz dielectric model of human breast tissue. In S. Cerutti, & P. Bonato (Eds.), 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (pp. 2804-2807). [7318974] IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/EMBC.2015.7318974
    Truong, Bao C Q ; Tuan, H. D. ; Fitzgerald, Anthony J. ; Wallace, Vincent P. ; Nguyen, Tuan Nghia ; Nguyen, H. T. / Breast Cancer classification using extracted parameters from a terahertz dielectric model of human breast tissue. 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. editor / Sergio Cerutti ; Paolo Bonato. IEEE, Institute of Electrical and Electronics Engineers, 2015. pp. 2804-2807
    @inproceedings{8a0dd45b60d542a4abe18d16d4c8f3d1,
    title = "Breast Cancer classification using extracted parameters from a terahertz dielectric model of human breast tissue",
    abstract = "Our previous study proposed a dielectric model for human breast tissue and provided initial analysis of classification potential of the eight model parameters and their multiparameter combinations with the support vector machine (SVM). A combination of three model parameters could achieve a leave-one-out cross validation accuracy of 93.2{\%}. However, the SVM approach fails to exploit the combinations of more than three model parameters for classification improvement. Thus, the Bayesian neural network (BNN) method is employed to overcome this problem based on its advantages of handling our small data and high complexity of the multiparamter combinations. The BNN successfully classifies the data using the combinations of four model parameters with an accuracy, estimated by leave-one-out cross validation, of 97.3{\%}. Overall performance assessed by leaveone- out and repeated random-subsampling cross validations for all examined combinations is also remarkably improved by BNN. The results indicate the advance of BNN as compared to SVM in utilising the model parameters for detecting tumour from normal breast tissue.",
    keywords = "classification, dielectric properties, neural network, optimization, support vector machine, terahertz (THz)",
    author = "Truong, {Bao C Q} and Tuan, {H. D.} and Fitzgerald, {Anthony J.} and Wallace, {Vincent P.} and Nguyen, {Tuan Nghia} and Nguyen, {H. T.}",
    year = "2015",
    month = "11",
    day = "4",
    doi = "10.1109/EMBC.2015.7318974",
    language = "English",
    pages = "2804--2807",
    editor = "Sergio Cerutti and Paolo Bonato",
    booktitle = "2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society",
    publisher = "IEEE, Institute of Electrical and Electronics Engineers",
    address = "United States",

    }

    Truong, BCQ, Tuan, HD, Fitzgerald, AJ, Wallace, VP, Nguyen, TN & Nguyen, HT 2015, Breast Cancer classification using extracted parameters from a terahertz dielectric model of human breast tissue. in S Cerutti & P Bonato (eds), 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society., 7318974, IEEE, Institute of Electrical and Electronics Engineers, pp. 2804-2807, 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015, Milan, Italy, 25/08/15. https://doi.org/10.1109/EMBC.2015.7318974

    Breast Cancer classification using extracted parameters from a terahertz dielectric model of human breast tissue. / Truong, Bao C Q; Tuan, H. D.; Fitzgerald, Anthony J.; Wallace, Vincent P.; Nguyen, Tuan Nghia; Nguyen, H. T.

    2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. ed. / Sergio Cerutti; Paolo Bonato. IEEE, Institute of Electrical and Electronics Engineers, 2015. p. 2804-2807 7318974.

    Research output: Chapter in Book/Conference paperConference paper

    TY - GEN

    T1 - Breast Cancer classification using extracted parameters from a terahertz dielectric model of human breast tissue

    AU - Truong, Bao C Q

    AU - Tuan, H. D.

    AU - Fitzgerald, Anthony J.

    AU - Wallace, Vincent P.

    AU - Nguyen, Tuan Nghia

    AU - Nguyen, H. T.

    PY - 2015/11/4

    Y1 - 2015/11/4

    N2 - Our previous study proposed a dielectric model for human breast tissue and provided initial analysis of classification potential of the eight model parameters and their multiparameter combinations with the support vector machine (SVM). A combination of three model parameters could achieve a leave-one-out cross validation accuracy of 93.2%. However, the SVM approach fails to exploit the combinations of more than three model parameters for classification improvement. Thus, the Bayesian neural network (BNN) method is employed to overcome this problem based on its advantages of handling our small data and high complexity of the multiparamter combinations. The BNN successfully classifies the data using the combinations of four model parameters with an accuracy, estimated by leave-one-out cross validation, of 97.3%. Overall performance assessed by leaveone- out and repeated random-subsampling cross validations for all examined combinations is also remarkably improved by BNN. The results indicate the advance of BNN as compared to SVM in utilising the model parameters for detecting tumour from normal breast tissue.

    AB - Our previous study proposed a dielectric model for human breast tissue and provided initial analysis of classification potential of the eight model parameters and their multiparameter combinations with the support vector machine (SVM). A combination of three model parameters could achieve a leave-one-out cross validation accuracy of 93.2%. However, the SVM approach fails to exploit the combinations of more than three model parameters for classification improvement. Thus, the Bayesian neural network (BNN) method is employed to overcome this problem based on its advantages of handling our small data and high complexity of the multiparamter combinations. The BNN successfully classifies the data using the combinations of four model parameters with an accuracy, estimated by leave-one-out cross validation, of 97.3%. Overall performance assessed by leaveone- out and repeated random-subsampling cross validations for all examined combinations is also remarkably improved by BNN. The results indicate the advance of BNN as compared to SVM in utilising the model parameters for detecting tumour from normal breast tissue.

    KW - classification

    KW - dielectric properties

    KW - neural network

    KW - optimization

    KW - support vector machine

    KW - terahertz (THz)

    UR - http://www.scopus.com/inward/record.url?scp=84953230134&partnerID=8YFLogxK

    U2 - 10.1109/EMBC.2015.7318974

    DO - 10.1109/EMBC.2015.7318974

    M3 - Conference paper

    SP - 2804

    EP - 2807

    BT - 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society

    A2 - Cerutti, Sergio

    A2 - Bonato, Paolo

    PB - IEEE, Institute of Electrical and Electronics Engineers

    ER -

    Truong BCQ, Tuan HD, Fitzgerald AJ, Wallace VP, Nguyen TN, Nguyen HT. Breast Cancer classification using extracted parameters from a terahertz dielectric model of human breast tissue. In Cerutti S, Bonato P, editors, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE, Institute of Electrical and Electronics Engineers. 2015. p. 2804-2807. 7318974 https://doi.org/10.1109/EMBC.2015.7318974