Histopathological examination is the gold standard for routine clinical diagnosis and grading of cancer. It includes examining a biopsy tissue under a microscope to identify tissue changes associated with cancer. However, this examination mainly relies on the visual interpretation of a pathologist, and thus, it may lead to a considerable amount of subjectivity, especially in cancer grading. To reduce the subjectivity level, it is important to develop analysis tools that operate on quantitative measures and facilitate objective judgment complementary to that of a pathologist.
This project proposes to implement objective decision-making systems based on histopathological images and it aims to improve the accuracy of cancer diagnosis and grading by reducing subjectivity. The design of such systems includes different steps, each of which requires the development of different computational methods and brings out computational challenges to overcome. This project mainly aims to develop 1.) robust algorithms for segmentation of tissue images, 2.) gland segmentation algorithms that locate glands in a tissue image, and 3.) cancer diagnosis and grading systems that rely on the quantification of the distributions of tissue components.
 |
 |
 |
 |