Published January 1, 2009 | Version v1
Journal article Open

Object-oriented texture analysis for the unsupervised segmentation of biopsy images for cancer detection

  • 1. Bilkent Univ, Dept Comp Engn, TR-06800 Ankara, Turkey
  • 2. Hacettepe Univ, Sch Med, Dept Pathol, TR-06100 Ankara, Turkey

Description

Staining methods routinely used in pathology lead to similar color distributions in the biologically different regions of histopathological images. This causes problems in image segmentation for the quantitative analysis and detection of cancer. To overcome this problem, unlike previous methods that use pixel distributions, we propose a new homogeneity measure based on the distribution of the objects that we define to represent tissue components. Using this measure, we demonstrate a new object-oriented segmentation algorithm. Working with colon biopsy images, we show that this algorithm segments the cancerous and normal regions with 94.89 percent accuracy on the average and significantly improves the segmentation accuracy compared to its pixel-based counterpart. (C) 2008 Elsevier Ltd. All rights reserved.

Files

bib-fc130f02-d4b4-4d06-93cd-06f58e2fe449.txt

Files (211 Bytes)

Name Size Download all
md5:1d32aa07685dc43d91c79978ea8cbaad
211 Bytes Preview Download