Improving the automatic karyotyping accuracy of the unrefined chromosome features using fuzzy logic

One of the most under consideration progresses in medical image processing is chromosome analysis and classification performed on dividing cells in their metaphase stage what is called a kryotype. Many studies for computer-based chromosome analysis using artificial neural network (ANN) have shown that it would be a good idea for classification of chromosomes. But in most of those works some limitations appears. There are many sources of uncertainty in this problem domain, making complete karyotyping a difficult task. Thus one of the most important aspects is the lack of approximate reasoning. In this work it is tried to give this ability to those classifiers in a very simple way using adaptive structure of fuzzy systems. The experiments show that the performance of this system in case of unrefined data like old version of Copenhagen data set is better than previous works.