Analysis of colonic histopathological images using pixel intensities and Hough transform
It has been reported that in the Philippines, cancer ranks third among the leading causes of morbidity and mortality (Ngelangel and Wang 2002). Cancer of the colon is among the leading types of cancer. Worldwide, colorectal cancer is considered the third most common neoplasm (Shuttleworth 2005). Sim...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | text |
| Published: |
Animo Repository
2010
|
| Subjects: | |
| Online Access: | https://animorepository.dlsu.edu.ph/faculty_research/5813 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | De La Salle University |
| Summary: | It has been reported that in the Philippines, cancer ranks third among the leading causes of morbidity and mortality (Ngelangel and Wang 2002). Cancer of the colon is among the leading types of cancer. Worldwide, colorectal cancer is considered the third most common neoplasm (Shuttleworth 2005). Similar to other types of cancers, early detection of cancer of the colon is key to a successful treatment. Traditionally, pathologists use microscope to examine histopathological images of biopsy samples taken from patients and make judgments based on their professional expertise. Typically, a pathologist would make observations on some key features in the image and subsequently be able to classify whether or not the tissue under examination contains abnormality. Since this procedure is performed by a human expert, it is therefore subject to inconsistencies due to factors that might affect human performance. To overcome this problem, it has been proposed to use mathematics and computers in the analysis of medical images, such as histopathological images of colonic tissues.
Considerable research has been undertaken over the past two decades in an effort to automate cancer diagnosis (Demir and Yener 2005). Based on previous research in this area, it appears that image texture has been a popular choice as basis in choosing discriminating features. Research has shown that textural features derived from grey-level co-occurrence matrices (GLCMs) are very useful. Esgiar et al.(1999) analyzed 44 normal and 58 cancer images captured on a computer via microscope with a CCD camera. Atlamazoglou et al.(2001) used GLCMs to extract. |
|---|