Weakly Supervised Domain Adaptation with Point Supervision in Histopathological Image Segmentation

Shun Obikane, Yoshimitsu Aoki

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

    Abstract

    When a model learned in a domain is applied to a different domain, even if in the same task, there is no guarantee of accuracy. This is a very important issue when deep learning and machine learning are applied in the field. In medical applications, there is a wide variety of domain bias, making it very difficult to create a model appropriate for all domains. Furthermore, semantic segmentation needs fine annotation and its high labor cost makes its application difficult. Histopathological image segmentation enables drug discovery and medical image analysis, but it is expensive due to its annotation cost and the need for the skills of histopathological experts. In this paper, we focus on a weakly supervised method using point annotation unique to histopathological image segmentation, and tackled on weakly supervised domain adaptation to suppress domain gaps. Providing point level annotation instead of fine annotation decreases the high cost of labor normally required.

    Original languageEnglish
    Title of host publicationPattern Recognition - ACPR 2019 Workshops, Proceedings
    EditorsMichael Cree, Fay Huang, Junsong Yuan, Wei Qi Yan
    PublisherSpringer
    Pages127-140
    Number of pages14
    ISBN (Print)9789811536502
    DOIs
    Publication statusPublished - 2020 Jan 1
    Event5th Asian Conference on Pattern Recognition,ACPR 2019 - Auckland, New Zealand
    Duration: 2019 Nov 262019 Nov 29

    Publication series

    NameCommunications in Computer and Information Science
    Volume1180 CCIS
    ISSN (Print)1865-0929
    ISSN (Electronic)1865-0937

    Conference

    Conference5th Asian Conference on Pattern Recognition,ACPR 2019
    CountryNew Zealand
    CityAuckland
    Period19/11/2619/11/29

    Keywords

    • Histopathology image segmentation
    • Medical image analysis
    • Semantic segmentation
    • Weakly supervised domain adaptation

    ASJC Scopus subject areas

    • Computer Science(all)
    • Mathematics(all)

    Fingerprint Dive into the research topics of 'Weakly Supervised Domain Adaptation with Point Supervision in Histopathological Image Segmentation'. Together they form a unique fingerprint.

    Cite this