dc.contributor.advisor | Demir, Çiğdem Gündüz | |
dc.contributor.author | Çığır, Celal | |
dc.date.accessioned | 2016-01-08T18:24:07Z | |
dc.date.available | 2016-01-08T18:24:07Z | |
dc.date.issued | 2011 | |
dc.identifier.uri | http://hdl.handle.net/11693/15752 | |
dc.description | Ankara : The Department of Computer Engineering and the Graduate School of Engineering and Science of Bilkent University, 2011. | en_US |
dc.description | Thesis (Master's) -- Bilkent University, 2011. | en_US |
dc.description | Includes bibliographical references leaves 69-79. | en_US |
dc.description.abstract | Over the last decade, computer aided diagnosis (CAD) systems have gained great
importance to help pathologists improve the interpretation of histopathological
tissue images for cancer detection. These systems offer valuable opportunities to
reduce and eliminate the inter- and intra-observer variations in diagnosis, which
is very common in the current practice of histopathological examination. Many
studies have been dedicated to develop such systems for cancer diagnosis and
grading, especially based on textural and structural tissue image analysis. Although
the recent textural and structural approaches yield promising results for
different types of tissues, they are still unable to make use of the potential biological
information carried by different tissue components. However, these tissue
components help better represent a tissue, and hence, they help better quantify
the tissue changes caused by cancer.
This thesis introduces a new textural approach, called Salient Point Patterns
(SPP), for the utilization of tissue components in order to represent colon biopsy
images. This textural approach first defines a set of salient points that correspond
to nuclear, stromal, and luminal components of a colon tissue. Then, it
extracts some features around these salient points to quantify the images. Finally,
it classifies the tissue samples by using the extracted features. Working
with 3236 colon biopsy samples that are taken from 258 different patients, our
experiments demonstrate that Salient Point Patterns approach improves the classification
accuracy, compared to its counterparts, which do not make use of tissue
components in defining their texture descriptors. These experiments also show
that different set of features can be used within the SPP approach for better representation of a tissue image. | en_US |
dc.description.statementofresponsibility | Çığır, Celal | en_US |
dc.format.extent | xvi, 79 leaves, illustrations | en_US |
dc.language.iso | English | en_US |
dc.rights | info:eu-repo/semantics/openAccess | en_US |
dc.subject | Salient point patterns | en_US |
dc.subject | Texture | en_US |
dc.subject | Histopathological image analysis | en_US |
dc.subject | Automated cancer diagnosis and grading | en_US |
dc.subject | Colon cancer | en_US |
dc.subject.lcc | WB141 .C54 2011 | en_US |
dc.subject.lcsh | Diagnostic imaging--Digital techniques. | en_US |
dc.subject.lcsh | Imaging systems in medicine. | en_US |
dc.subject.lcsh | Image processing--Digital techniques. | en_US |
dc.subject.lcsh | Computer simulation. | en_US |
dc.subject.lcsh | Digital computer vision. | en_US |
dc.subject.lcsh | Medical image analysis. | en_US |
dc.subject.lcsh | Cancer--Diagnosis--Data processing. | en_US |
dc.title | Histopathological image classification using salient point patterns | en_US |
dc.type | Thesis | en_US |
dc.department | Department of Computer Engineering | en_US |
dc.publisher | Bilkent University | en_US |
dc.description.degree | M.S. | en_US |
dc.identifier.itemid | B130082 | |