Improving Accuracy in Classification of Chromosomes by Segmentation

An Improved Adaptive Fuzzy C-Means (IAFCM) algorithm was developed and applied to the segmentation and classification of Multicolor Fluorescence in Situ Hybridization (M-FISH) images, which can be used to detect chromosomal abnormalities for cancer and genetic disease diagnosis. IAFCM method gave the considerable classification accuracy among the other existing classifiers tested, it has not employed any preprocessing and post processing steps. In this paper introduces the preprocessing methods such as the background correction, color compensation and filtering can be used before applying IAFCM for increasing the classification accuracy. M-FISH images are jointly segmented and classified with a six-feature, 25class maximum-likelihood classifier. Our method gives the lowest segmentation and classification error, which will contribute to improved diagnosis of genetic diseases and cancers as well as corrects intensity inhomogeneities caused by a microscope imaging system, flairs of targets (chromosomes), and uneven hybridization of DNA.