Bilkent University
Department of Computer Engineering
S E M I N A R
Constrained Delaunay Triangulation for Diagnosis and Grading of Colon Cancer
Suleyman Tuncer Erdogan
MSc.Student
Computer Engineering Department
Bilkent University
In our century, the increasing rate of cancer incidents makes it inevitable to employ computerized decision makers, and thus, help pathologists more accurately diagnose patients and grade cancerous tissues. These algorithmic approaches offer more stable and quantitative frameworks, which cause a reduced rate of intra- and inter-observer variability. There has been a large set of studies on the subject of automated cancer diagnosis, especially based on textural and/or structural tissue analysis. Although the previous structural approaches show promising results for different types of tissues, they are still unable to evaluate the potential information that is provided by tissue components rather than cell nuclei. This fundamental information becomes one of the major factors for the tissue types with differentiated components such as luminal regions in a colon tissue. This thesis introduces a novel structural approach, constrained Delaunay triangulation, for the utilization of non-nuclei tissue components. To this end, this approach first defines two sets of nodes on cell nuclei and luminal regions. It then constructs a constrained Delaunay triangulation on the nucleus nodes with the lumen nodes forming its constraints. Finally, it classifies the tissue samples using the features extracted from this newly introduced constrained Delaunay triangulation. Working with 213 colon tissues taken from 58 patients, our experiments demonstrate that the constrained Delaunay triangulation approach leads to higher accuracies of 87.83 percent and 85.71 percent for the training and test sets, respectively. The experiments also show that, with the introduction of novel structure that permits definition of new features, the proposed algorithm provides a more robust graph-based methodology for the examination of cancerous tissues and better performance than its predecessors.
DATE: 23 July, 2009, Thursday@ 10:00
PLACE: EA 409