A Novel Framework for Fat, Glandular Tissue, Pectoral Muscle and Nipple Segmentation in Full Field Digital Mammograms

Susan Astley, Hiroshi Fujita (Editor), T Hara (Editor), C Muramatsu (Editor)

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    Abstract

    Automated segmentation of mammograms is an important initial step in a wide range of applications including breast density and texture analysis and computer aided detection of abnormalities. In this paper, we propose a unified machine learning framework that enables simultaneous segmentation of the breast region, fatty tissue, glandular tissue, pectoral muscle and nipple region in full field digital mammograms. We calculate both a multi-label segmentation mask and a probability map associated with each of the segmented classes. The probability map facilitates interpretation of the segmentation mask prior to further analysis. The method is evaluated using left or right MLO views from 100 women in a 5-fold cross validation manner. Our framework is shown to be robust and accurate, achieving sensitivity/specificity from 82.7% to 98.5% at the equal-error-rate point of the ROC curves and area under the ROC curve values from 0.9220 to 0.9998 for the corresponding segmentations.
    Original languageEnglish
    Title of host publicationBreast Imaging: Lecture Notes on Computer Science 8539
    EditorsHiroshi Fujita, T Hara, C Muramatsu
    Place of PublicationSwitzerland
    PublisherSpringer Nature
    Pages201-208
    Number of pages8
    Publication statusPublished - Jun 2014
    EventInternational Workshop on Breast Imaging - Gifu, Japan
    Duration: 1 Jan 1824 → …

    Conference

    ConferenceInternational Workshop on Breast Imaging
    CityGifu, Japan
    Period1/01/24 → …

    Keywords

    • Segmentation
    • Mammogram
    • Pectoral Muscle
    • Nipple
    • Gland
    • Fat
    • Machine Learning

    Fingerprint

    Dive into the research topics of 'A Novel Framework for Fat, Glandular Tissue, Pectoral Muscle and Nipple Segmentation in Full Field Digital Mammograms'. Together they form a unique fingerprint.

    Cite this