New automatic karyotyping technique for chromosome classification

ABSTRACT Chromosome karyotyping is an important procedure in clinical and cancer cytogenetics research. In this study, based onefficient chromosome image processing and approximate knowledge-based geometry classification, a new automatickaryotyping technique is introduced which comprises some efficient intelligent sequential phases, namely chromosomeimage collector, chromosome image processor, chromosome analysis result database. In this paper, detailed techniquesincluding image preprocessing, chromosome incision and chromosome classification have been presented. By testing ona large number of clinical data, excellent result has been reached and the performance of automation has been greatly improved. Keywords: Chromosome image, karyotyping, image capture and piecing together, image segmentation & cutting, feature extraction, pattern recognition, approximate geometry classification 1. INTRODUCTION It's well known that it's DNA who carries nearly all the genetic information of human being, and as carriers of it,chromosomes are also very crucial to human. When a cell division happens, the whole pair of chromosomes will becopied into a new cell, which means the genetic information ofthe old cell is copied into the new one. By this way, thecharacteristics ofhuman could be represented by all the cells ofhim and part ofthem will be copied to and inherited byhis children. Chromosomes really play a key role in the vital activities. If some error takes place in the copy process ofchromosomes, if the chromosomes are caught in some error, many diseases will be aroused, because the geneticinformation of human maybe has been missing or changed. So by detecting the status of chromosomes, we can get more