A Comparison of Regions of Interest in Parenchymal Analysis for Breast Cancer Risk Assessment

Gerson Africano, Otso Arponen, Antti Sassi, Mirja Karivaara-Mäkelä, Kirsi Holli-Helenius, Irina Rinta-Kiikka, Anna-Leena Lääperi, Said Pertuz

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

    Abstract

    Computerized parenchymal analysis has shown potential to be utilized as an imaging biomarker to estimate the risk of breast cancer. Parenchymal analysis of digital mammograms is based on the extraction of computerized measures to build machine learning-based models for the prediction of breast cancer risk. However, the choice of the region of interest (ROI) for feature extraction within the breast remains an open problem. In this work we perform a comparison between five different methods suggested in the literature for automated ROI selection, including the whole breast (WB), the maximum squared (MS), the retro-areolar region (RA), the lattice-based (LB), and the polar-based (PB) selection methods. For the experiments, we built a retrospective dataset of 896 screening mammograms from 224 women (112 cases and 112 healthy controls). The performance of each ROI selection method was measured in terms of the area under the curve (AUC) values. The AUC values varied between 0.55 and 0.79 depending on the method and experimental settings. The best performance on an independent test set was achieved by the MS method (AUC of 0.59, 95% CI: 0.55-0.64). This method is fully-automated and does not require adjusting hyper-parameters. Based on our results, we prompt the use of the MS method for ROI selection in the computerized parenchymal analysis for breast cancer risk assessment.
    Original languageEnglish
    Title of host publication2020 42nd Annual International Conference of the IEEE Engineering in Medicine Biology Society (EMBC)
    PublisherIEEE
    Pages1136-1139
    Number of pages4
    ISBN (Electronic)978-1-7281-1990-8
    ISBN (Print)978-1-7281-1991-5
    DOIs
    Publication statusPublished - 2020
    Publication typeA4 Article in conference proceedings
    EventAnnual International Conference of the IEEE Engineering in Medicine and Biology Society - Montreal, Canada
    Duration: 20 Jul 202024 Jul 2020
    Conference number: 42nd

    Publication series

    NameAnnual International Conference of the IEEE Engineering in Medicine and Biology Society
    PublisherIEEE
    ISSN (Print)2375-7477
    ISSN (Electronic)2694-0604

    Conference

    ConferenceAnnual International Conference of the IEEE Engineering in Medicine and Biology Society
    Country/TerritoryCanada
    CityMontreal
    Period20/07/2024/07/20

    Keywords

    • cancer
    • feature extraction
    • gynaecology
    • learning (artificial intelligence)
    • mammography
    • medical image processing
    • AUC
    • area under the curve values
    • RA
    • maximum squared
    • machine learning-based models
    • computerized measures
    • digital mammograms
    • breast cancer risk assessment
    • computerized parenchymal analysis
    • MS method
    • ROI selection method
    • screening mammograms
    • polar-based selection methods
    • lattice-based
    • retro-areolar region
    • automated ROI selection
    • Feature extraction
    • Breast cancer
    • Tuning
    • Risk management
    • Mammography
    • Computational modeling
    • Area Under Curve
    • Breast Neoplasms
    • Female
    • Humans
    • Retrospective Studies
    • Risk Assessment

    Publication forum classification

    • Publication forum level 1

    Fingerprint

    Dive into the research topics of 'A Comparison of Regions of Interest in Parenchymal Analysis for Breast Cancer Risk Assessment'. Together they form a unique fingerprint.

    Cite this