Classification of breast-tissue microarray spots using colour and local invariants

Telmo Amaral, Stephen McKenna, Katherine Robertson, Alastair Thompson

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    10 Citations (Scopus)

    Abstract

    Breast tissue microarrays facilitate the survey of very large numbers of tumours but their scoring by pathologists is time consuming, typically highly quantised and not without error. Automated segmentation of cells and intra-cellular compartments in such data can be problematic for reasons that include cell overlapping, complex tissue structure, debris, and variable appearance. This paper proposes a computationally efficient approach that uses colour and differential invariants to assign class posterior probabilities to pixels and then performs probabilistic classification of TMA spots using features analogous to the Quickscore system currently used by pathologists. It does not rely on accurate segmentation of individual cells. Classification performance at both pixel and spot levels was assessed using 110 spots from the Adjuvant Breast Cancer (ABC) Chemotherapy Trial. The use of differential invariants in addition to colour yielded a small improvement in accuracy. Some reasons for classification results in disagreement with pathologist-provided labels are discussed and include noise in the class labels.

    Original languageEnglish
    Title of host publication2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI
    Place of PublicationNEW YORK
    PublisherIEEE Computer Society
    Pages999-1002
    Number of pages4
    ISBN (Print)978-1-4244-2002-5
    DOIs
    Publication statusPublished - 2008
    Event2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Paris, France
    Duration: 14 May 200817 May 2008
    http://www.biomedicalimaging.org/archive/2008/

    Conference

    Conference2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro
    Abbreviated titleISBI '08
    CountryFrance
    CityParis
    Period14/05/0817/05/08
    Internet address

    Keywords

    • biological tissues
    • image texture analysis
    • VALIDATION

    Cite this

    Amaral, T., McKenna, S., Robertson, K., & Thompson, A. (2008). Classification of breast-tissue microarray spots using colour and local invariants. In 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI (pp. 999-1002). IEEE Computer Society. https://doi.org/10.1109/ISBI.2008.4541167