Toronto Metropolitan University
Browse
cancers-13-00011-v3.pdf (9.66 MB)

piNET–An Automated Proliferation Index Calculator Framework for Ki67 Breast Cancer Images

Download (9.66 MB)
journal contribution
posted on 2022-11-01, 14:33 authored by Stephny GereadStephny Geread, Abishika Sivanandarajah, Emily Rita Brouwer, Geoffrey A. Wood, Dimitrios Androutsos, Hala Faragalla, April KhademiApril Khademi

In this work, a novel proliferation index (PI) calculator for Ki67 images called piNET is proposed. It is successfully tested on four datasets, from three scanners comprised of patches, tissue microarrays (TMAs) and whole slide images (WSI), representing a diverse multi-centre dataset for evaluating Ki67 quantification. Compared to state-of-the-art methods, piNET consistently performs the best over all datasets with an average PI difference of 5.603%, PI accuracy rate of 86% and correlation coefficient R = 0.927. The success of the system can be attributed to several innovations. Firstly, this tool is built based on deep learning, which can adapt to wide variability of medical images—and it was posed as a detection problem to mimic pathologists’ workflow which improves accuracy and efficiency. Secondly, the system is trained purely on tumor cells, which reduces false positives from non-tumor cells without needing the usual pre-requisite tumor segmentation step for Ki67quantification. Thirdly,theconceptoflearningbackgroundregionsthroughweaksupervisionis introduced, by providing the system with ideal and non-ideal (artifact) patches that further reduces false positives. Lastly, a novel hotspot analysis is proposed to allow automated methods to score patches from WSI that contain “significant” activity.

History

Language

eng

Usage metrics

    Biomedical Engineering

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC