CHROMOSOME IDENTIFICAION USING ARTIFICIAL NEURAL NETWORK

Abstract

Cytogenetics plays a central role in the detection of chromosomal abnormalities and in the diagnosis of genetic
diseases. The study of human metaphase chromosomes is an important aspect in clinical diagnosis of genetic disorders. A
karyogram is representation of human chromosomes where they are arranged in decreasing order of size and Karyotyping is
a set of procedures that produces a karyogram during the metaphase step of the cellular division, called mitosis Many image
processing techniques have been developed for chromosomal karyotyping to assist in laboratory diagnosis, they fail to
provide reliable results in segmenting and extracting the centerline of chromosomes due to their shape variability when
placed on microscope slides. Effective identification of the chromosome outline with its center line provides a basis for
further operations such as automated chromosome classification and centromere identification. Karyotypin g and
chromosome analysis are very useful in biological applications, e.g. disease identification. The very first step of karyotypi ng
is the identification of chromosome.Manual karyotyping is tedious, complex and time consuming, as it requires meticulous
attention to details and well trained personnel. Automated system gives countless advantages like speed, simplicity and
storage.This method is considered simple and, yet, robust for this purpose. In this project, we aim to build an automated
karyotyping system for chromosome analysis.
In this paper we have discusssed the fundamental problems of classification of human chromosomes and have explained the
solution to the problem.We have given the introduction about the human chromosomes and the basic theory of the algorithm
used.AAN has been implemented to classify the chromosomes.