• Login
    View Item 
    •   Home
    • Graduate Theses, Dissertations and Projects
    • Queen's Graduate Theses and Dissertations
    • View Item
    •   Home
    • Graduate Theses, Dissertations and Projects
    • Queen's Graduate Theses and Dissertations
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Stochastic Modeling of Temporal Ultrasound Data for Prostate Cancer Diagnostics

    Thumbnail
    View/Open
    Thesis Document (10.86Mb)
    Author
    Nahlawi, Layan
    Metadata
    Show full item record
    Abstract
    Despite recent advances in clinical oncology, prostate cancer remains a major health concern in men, where current detection techniques still lead to both over- and underdiagnosis. More accurate prediction and detection of prostate cancer can improve disease management and treatment outcome.

    Temporal Enhanced Ultrasound (TeUS) is a promising imaging approach that can help identify tissue-specifi c patterns in time-series of ultrasound data and, in turn, differentiate between benign and malignant tissues. We introduce a probabilistic temporal framework, based on hidden Markov models, for modeling ultrasound time series data obtained from prostate cancer patients. The proposed models capture the temporal signatures of tissue-speci fic responses to prolonged sonication. Our results show improved prediction of malignancy compared to previously reported results,

    where we identify cancerous regions with over 85.6% accuracy.

    However, adopting this approach in diagnostic procedures requires understanding of the physical properties of TeUS and its interactions with tissues. We therefore utilize our probabilistic modeling approach to examine two properties of TeUS signals - temporal order and length - and present a new framework to assess their impact on tissue information. Our results strongly indicate that temporal order has signi ficant impact on TeUS performance, and it thus plays a important role in conveying tissue-specifi c information. Additionally, we demonstrate the feasibility of reducing the duration of data collection to shorten the sequences while maintaining sufficient information for tissue typing.

    To investigate the tissue characteristics interrogated by TeUS, we compare the predictions of our models with malignancy markings on multi-parametric magnetic resonance images. Our fi ndings show that the proposed models have the highest

    agreement in detecting cancer with Dynamic Contrast-Enhanced (DCE) sequences as compared to Apparent Diffusion Coefficient (ADC) maps and T2-Weighted (T2W) images. Hence, this agreement suggests that the effect of agiogenesis, visualized on DCE images, may also be detected using TeUS, and, in turn, paving the way for further investigation about tissue characteristics captured by TeUS.
    URI for this record
    http://hdl.handle.net/1974/22812
    Collections
    • School of Computing Graduate Theses
    • Queen's Graduate Theses and Dissertations
    Request an alternative format
    If you require this document in an alternate, accessible format, please contact the Queen's Adaptive Technology Centre

    DSpace software copyright © 2002-2015  DuraSpace
    Contact Us
    Theme by 
    Atmire NV
     

     

    Browse

    All of QSpaceCommunities & CollectionsPublished DatesAuthorsTitlesSubjectsTypesThis CollectionPublished DatesAuthorsTitlesSubjectsTypes

    My Account

    LoginRegister

    Statistics

    View Usage StatisticsView Google Analytics Statistics

    DSpace software copyright © 2002-2015  DuraSpace
    Contact Us
    Theme by 
    Atmire NV