Browsing by Subject "Histopathological examinations"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Open Access Kanser tanısı için kolon bezlerinin matematiksel analizi(IEEE, 2009-04) Çığır, Celal; Sökmensüer, C.; Gündüz-Demir, ÇiğdemNeoplastic diseases including cancer cause organizational changes in tissues. Histopathological examination, which is routinely used for the diagnosis and grading of these diseases, relies on pathologists to identify such tissue changes under a microscope. However, as this examination mainly relies on the visual interpretation of pathologists, it may lead to a considerable amount of subjectivity. To reduce the subjectivity level, it is proposed to use computational methods that provide objective measures. These methods quantify the tissue changes associated with disease by defining features on tissue images. In this paper, colon glands are mathematically analyzed making use of different feature extraction approaches. In this analysis, morphological, intensity-based, and textural features are investigated and glands are classified using these features. Working on the images of 108 colon tissues of 36 patients, our experiments demonstrate that this classification leads to promising results for differentiating normal glands from the cancerous ones. ©2009 IEEE.Item Open Access Tissue object patterns for segmentation in histopathological images(ACM, 2011) Gündüz-Demir, ÇiğdemIn the current practice of medicine, histopathological examination is the gold standard for routine clinical diagnosis and grading of cancer. However, as this examination involves the visual analysis of biopsies, it is subject to a considerable amount of observer variability. In order to decrease the variability, it has been proposed to develop systems that mathematically model the histopathological tissue images and automate the analysis. Segmentation constitutes the first step for most of these automated systems. Nevertheless, the segmentation in histopathological images remains a challenging task since these images typically show variances due to their complex nature and may include a large amount of noise and artifacts due to the tissue preparation procedures. In our research group, we recently developed different segmentation algorithms that rely on representing a tissue image with a set of tissue objects and using the structural pattern of these objects in segmentation. In this paper, we review these segmentation algorithms, discussing their clinical demonstrations on colon tissues. © 2011 ACM.