Automated Classification of Local Patches in Colon Histopathology

Kalkan H., Nap M., Duin R. P. W. , Loog M.

21st International Conference on Pattern Recognition (ICPR), Tsukuba, Japan, 11 - 15 November 2012, pp.61-64 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • City: Tsukuba
  • Country: Japan
  • Page Numbers: pp.61-64


An automated histology analysis is proposed for classification of local image patches of colon histopathology images into four principle classes: normal, cancer, adenomatous and inflamed classes. Shape features based on stroma, lumen and imperfectly segmented nuclei are combined with texture features for classification. The classification is analyzed under the three scenarios: normal vs. abnormal, cancer vs. non-cancer and four-class classification on a labeled dataset consisting of 2000 patches per class which were collected from 55 different slices. The proposed method achieves 79.28% mean accuracy between normal and abnormal; 87.67% accuracy between cancer and non-cancer and 75.15% between the four classes with equal class priories.