Krzysztof Krawiec


Home

Research:

edit SideBar

We present an automated, end-to-end approach for Stage 1 breast cancer detection. The first phase of our proposed workflow takes individual digital mammograms as input and outputs several smaller subimages from which the background has been removed. Next, we extract a set of features which capture textural information from the segmented images. In the final phase, the most salient of these features are fed into a Multi-Objective Genetic Programming system which then evolves classifiers capable of identifying those segments which may have suspicious areas that require further investigation.A key aspect of this work is the examination of several new experimental configurations which focus on textural asymmetry between breasts. The best evolved classifier using such a configuration can deliver results of 100 percent accuracy on true positives and a false positive per image rating of just 0.33, which is better than the current state of the art.

@INPROCEEDINGS { Fitzgerald2015Gecco,
    AUTHOR = { Fitzgerald, Jeannie and Ryan, Conor and Medernach, David and Krawiec, Krzysztof },
    TITLE = { An Integrated Approach to Stage 1 Breast Cancer Detection },
    BOOKTITLE = { Proceedings of the 2015 Annual Conference on Genetic and Evolutionary Computation },
    SERIES = { GECCO '15 },
    YEAR = { 2015 },
    ISBN = { 978-1-4503-3472-3 },
    LOCATION = { Madrid, Spain },
    PAGES = { 1199--1206 },
    NUMPAGES = { 8 },
    URL = { http://doi.acm.org/10.1145/2739480.2754761 },
    DOI = { 10.1145/2739480.2754761 },
    ACMID = { 2754761 },
    PUBLISHER = { ACM },
    ADDRESS = { New York, NY, USA },
    KEYWORDS = { classification, mammography, multi-objective genetic programming },
    ABSTRACT = { We present an automated, end-to-end approach for Stage 1 breast cancer detection. The first phase of our proposed workflow takes individual digital mammograms as input and outputs several smaller subimages from which the background has been removed. Next, we extract a set of features which capture textural information from the segmented images. In the final phase, the most salient of these features are fed into a Multi-Objective Genetic Programming system which then evolves classifiers capable of identifying those segments which may have suspicious areas that require further investigation.A key aspect of this work is the examination of several new experimental configurations which focus on textural asymmetry between breasts. The best evolved classifier using such a configuration can deliver results of 100 percent accuracy on true positives and a false positive per image rating of just 0.33, which is better than the current state of the art. },
}


Powered by PmWiki