Constructing and applying higher order textons: Estimating breast cancer risk

Xi-Zhao Li, Simon Williams, Murk Bottema

    Research output: Contribution to journalArticlepeer-review

    7 Citations (Scopus)

    Abstract

    Texture analysis based on textons is extended by introducing a method for computing textons of arbitrary order. First-, second- and third-order textons are applied to classify screening mammograms as to indicate a low or high risk of breast cancer. First-order textons are found to provide better estimates of breast cancer risk than other orders on their own but the combination of first- and second-order textons outperforms first-order textons alone and other combinations of two orders. Combining all three orders of textons does not improve classification. This example indicates that including higher-order textons has the potential to improve classification performance.

    Original languageEnglish
    Pages (from-to)1375-1382
    Number of pages8
    JournalPattern Recognition Letters
    Volume47
    Issue number3
    DOIs
    Publication statusPublished - Mar 2014

    Keywords

    • Breast cancer
    • Higher order textons
    • Risk assessment
    • Textons
    • Texture analysis

    Fingerprint Dive into the research topics of 'Constructing and applying higher order textons: Estimating breast cancer risk'. Together they form a unique fingerprint.

    Cite this