Background intensity independent texture features for assessing breast cancer risk in screening mammograms

Xi-Zhao Li, Simon Williams, Murk Bottema

    Research output: Contribution to journalArticle

    15 Citations (Scopus)

    Abstract

    Image intensity and texture in screening mammograms are thought to be associated with the risk of breast cancer. Studies on developing automatic breast cancer risk assessment schemes tend to employ texture measures which are correlated to local background intensity. Accordingly, the contribution of texture alone to risk assessment is not known. Here background intensity independent texture measures are used to assess cancer risk. Moreover risk assessment based on background intensity independent texture outperforms intensity dependent texture suggesting that local image background intensity may confound risk assessment. Performance seems to depend on the view of the breast and so suggests that optimizing schemes for different views may improve risk assessment.

    Original languageEnglish
    Pages (from-to)1053-1062
    Number of pages10
    JournalPattern Recognition Letters
    Volume34
    Issue number9
    DOIs
    Publication statusPublished - 2013

    Keywords

    • Breast cancer
    • Density classification
    • Intensity independent
    • Mammogram
    • Risk evaluation
    • Subspace ensemble

    Fingerprint Dive into the research topics of 'Background intensity independent texture features for assessing breast cancer risk in screening mammograms'. Together they form a unique fingerprint.

    Cite this