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). NEW YORK: IEEE Computer Society. https://doi.org/10.1109/ISBI.2008.4541167
    Amaral, Telmo ; McKenna, Stephen ; Robertson, Katherine ; Thompson, Alastair. / Classification of breast-tissue microarray spots using colour and local invariants. 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI. NEW YORK : IEEE Computer Society, 2008. pp. 999-1002
    @inproceedings{ce85e0326252447f90c1d4beb8193e03,
    title = "Classification of breast-tissue microarray spots using colour and local invariants",
    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.",
    keywords = "biological tissues, image texture analysis, VALIDATION",
    author = "Telmo Amaral and Stephen McKenna and Katherine Robertson and Alastair Thompson",
    note = "art no. 4541167",
    year = "2008",
    doi = "10.1109/ISBI.2008.4541167",
    language = "English",
    isbn = "978-1-4244-2002-5",
    pages = "999--1002",
    booktitle = "2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI",
    publisher = "IEEE Computer Society",

    }

    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. IEEE Computer Society, NEW YORK, pp. 999-1002, 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Paris, France, 14/05/08. https://doi.org/10.1109/ISBI.2008.4541167

    Classification of breast-tissue microarray spots using colour and local invariants. / Amaral, Telmo; McKenna, Stephen; Robertson, Katherine; Thompson, Alastair.

    2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI. NEW YORK : IEEE Computer Society, 2008. p. 999-1002.

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

    TY - GEN

    T1 - Classification of breast-tissue microarray spots using colour and local invariants

    AU - Amaral, Telmo

    AU - McKenna, Stephen

    AU - Robertson, Katherine

    AU - Thompson, Alastair

    N1 - art no. 4541167

    PY - 2008

    Y1 - 2008

    N2 - 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.

    AB - 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.

    KW - biological tissues

    KW - image texture analysis

    KW - VALIDATION

    UR - http://www.scopus.com/inward/record.url?scp=51049094185&partnerID=8YFLogxK

    U2 - 10.1109/ISBI.2008.4541167

    DO - 10.1109/ISBI.2008.4541167

    M3 - Conference contribution

    SN - 978-1-4244-2002-5

    SP - 999

    EP - 1002

    BT - 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI

    PB - IEEE Computer Society

    CY - NEW YORK

    ER -

    Amaral T, McKenna S, Robertson K, Thompson A. 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. NEW YORK: IEEE Computer Society. 2008. p. 999-1002 https://doi.org/10.1109/ISBI.2008.4541167