• Login
    View Item 
    •   UCrea
    • UCrea Investigación
    • Departamento de Tecnología Electrónica e Ing. Sistemas y Automática (TEISA)
    • D50 Congresos
    • View Item
    •   UCrea
    • UCrea Investigación
    • Departamento de Tecnología Electrónica e Ing. Sistemas y Automática (TEISA)
    • D50 Congresos
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Automated segmentation based upon remitted scatter spectra from pathologically distinct tumor regions

    View/Open
    Automated segmentati ... (11.81Mb)
    Identificadores
    URI: http://hdl.handle.net/10902/2516
    DOI: 10.1117/12.808322
    ISSN: 1996-756X
    ISSN: 0277-786X
    Compartir
    RefworksMendeleyBibtexBase
    Estadísticas
    View Usage Statistics
    Google Scholar
    Full record
    Show full item record
    Author
    García Allende, Pilar Beatriz; Krishnaswamy, Venkataramanan; Samkoe, Kimberley S.; Hoopes, P. Jack; Pogue, Brian William; Conde Portilla, Olga MaríaAutoridad Unican; López Higuera, José MiguelAutoridad Unican
    Date
    2009-02-24
    Derechos
    © 2009 Society of Photo-Optical Instrumentation Engineers. One print or electronic copy may be made for personal use only. Systematic electronic or print reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.
    Publicado en
    Proceedings of SPI, 2009, vol. 7187, 718717
    Biomedical Applications of Light Scattering III, San José (CA), 2009
    Publisher
    SPIE Society of Photo-Optical Instrumentation Engineers
    Enlace a la publicación
    http://dx.doi.org/10.1117/12.808322
    Palabras clave
    Automatic classification
    Tumor
    Necrosis
    Confocal reflectance imaging
    Scatter
    Feature extraction
    K-nearest neighbors (kNN)
    Abstract:
    Multi-spectral scatter visualization of tissue ultra-structure in situ can provide a unique tool for guiding surgical resection, but since changes are subtle and the data is multi-parametric, an automated methodology was sought to interpret these data, in order to classify their tissue sub-type. Tissue types observed across AsPC-1 pancreatic tumor samples were pathologically classified under three major groups (epithelium, fibrosis and necrosis) and the variations in scattering parameters, i.e. scattering power, scattering amplitude and average scattered intensity, across these groups were analyzed. The proposed scheme uses statistical pre-processing of the scattering parameter images to create additional data features followed by a k-nearest neighbors (kNN) based algorithm for tissue type classification. The classification accuracy inside some predefined regions of interest was determined and the mean region values of scattering parameters turned out to be stronger data sets for classification, rather than the individual pixel values. This presumably indicates that pixel-to-pixel variations in the remitted spectra need to be minimized for reliable classification approaches. Results show a strong correlation between the automated and expert-based classification within the predefined regions of interest.
    Collections to which it belong
    • D50 Congresos [429]

    UNIVERSIDAD DE CANTABRIA

    Repositorio realizado por la Biblioteca Universitaria utilizando DSpace software
    Contact Us | Send Feedback
    Metadatos sujetos a:licencia de Creative Commons Reconocimiento 3.0 España
     

     

    Browse

    All of UCreaCommunities and CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

    My Account

    LoginRegister

    Statistics

    View Usage Statistics
    About UCrea
    What is UcreaGuide of self-archivingThesis archiveOpen accessCopyright guideInstitutional policy
    Thinks in open
    Piensa en abierto
    Share

    UNIVERSIDAD DE CANTABRIA

    Repositorio realizado por la Biblioteca Universitaria utilizando DSpace software
    Contact Us | Send Feedback
    Metadatos sujetos a:licencia de Creative Commons Reconocimiento 3.0 España