Recognition of Colon Cells Using Ensemble of Classifiers

The paper presents the application of an ensemble of neural classifiers for the recognition of colon cells on the basis of the microscope colon image. The solved task include: the segmentation of individual cells from the image using the morphological operations, the preprocessing stages leading to the extraction of features, selection of the most important features, and the classification stage applying the neural classifiers arranged in the form of ensemble. The paper presents and discusses the results concerning the recognition of four most important colon cell types: eosinophylic granulocyte, neutrophilic granulocyte, lymphocyte and plasmocyte. The proposed system is able to recognize the cells with the accuracy comparable to the human expert (around 4% of discrepancy).