Muscularis mucosae layer detection in colon biopsy images

Abstract

Manual screening of colon cancer biopsy tissue under microscope is difficult and time consuming. With the help of a computerized system, the diagnosis time can be shortened. In this paper, we proposed a method of detecting the layer of muscularis mucosae in the colon biopsy tissue image. By using RGB color information, we analyzed 65 images and preserved a specific range of color and evaluated the density of the preserved colour. A separation line is drawn to distinguish the layers. The result shows that by using the proposed method, layer of muscularis mucosae are detected with about 84% accuracy. The output of this detection is highly important as supporting evidence in the colon cancer cells image detection.