Gland Segmentation in Histopathology Images Using Random Forest Guided Boundary Construction
This addresses the problem of time-consuming and biased manual segmentation for pathologists, but appears incremental as it builds on existing methods like Random Forest.
The paper tackles automated gland segmentation in histopathology images by detecting boundary epithelial cells and constructing complete gland boundaries, resulting in segmented gland regions for cancer grading.
Grading of cancer is important to know the extent of its spread. Prior to grading, segmentation of glandular structures is important. Manual segmentation is a time consuming process and is subject to observer bias. Hence, an automated process is required to segment the gland structures. These glands show a large variation in shape size and texture. This makes the task challenging as the glands cannot be segmented using mere morphological operations and conventional segmentation mechanisms. In this project we propose a method which detects the boundary epithelial cells of glands and then a novel approach is used to construct the complete gland boundary. The region enclosed within the boundary can then be obtained to get the segmented gland regions.