The human chromosome analysis is widely used to diagnose genetic disease and various congenital anomalies. Many researches on automated chromosome karyotype analysis has been carried out, some of which produced commercial systems. However, there still remains much room for improving the accuracy of chromosome classification. In this paper, We propose an optimal pattern classifier by neural network to improve the accuracy of chromosome classification. The proposed pattern classifier was built up of multi-step multi-layer neural network(MMANN). We reconstructed chromosome image to improve the chromosome classification accuracy and extracted three morphological features parameters such as centromeric index(C.1.), relative length ratio(R.L.), and relative area ratio(R.A.). This Parameters employed as input in neural network by preprocessing twenty human chromosome images. The experiment results show that the chromosome classification error is reduced much more than that of the other classification methods.
Chromosomes, Human ; Classification* ; Humans ; Karyotype*

No abstract available.
Arm* ; Chromosomes, Human, Pair 14*

No abstract available.
Chromosomes, Human, Pair 13 ; Vitiligo*

OBJECTIVETo study the genetic basis of aberrant crypt foci (ACF), which serve as a very early morphological alteration during the development of carcinogenesis by analyzing the loss of heterozygosity (LOH).

METHODSDNA from 35 colorectal carcinomas (CRC) and 34 matched ACF were isolated by microdissection. LOH of microsatellite loci at 18q12, 18q21, 5q12, 5q21, 3p21, 2p16, 17q21, 17q11 and 11p13 was detected by means of ABI-SEQUENCER and GeneScan software was applied for analysis.

RESULTSThe rate of LOH in ACF (41.18%) was less than that in carcinoma (68.57%) (P < 0.05). The profile of LOH rates at loci 18q12, 5q12, 3p21, 17q21, 17q11, 11p13 and 2p16 in ACF was similar to that in carcinoma. The LOH frequencies on 18q12, 18q21, 5q12, 5q21, and 3p21 were higher than that on 17q11 and 11p13. However the rate at 18q21 and 5q21 in ACF was much lower than that in the carcinoma (P < 0.05). The co-existing carcinomas displayed more polypoid growth pattern and located more at the sigmoid colon and rectum. LOH in carcinomas did not correlate with the location, size, type of the carcinoma and Duke's stage.

CONCLUSIONSACF are putative preneoplastic lesions that might represent the earliest morphological lesion with the alteration at molecular genetic level. Our study provides further genetic evidence in the pathogenesis of colorectal carcinomas.

Chromosomes ; Chromosomes, Human, Pair 11 ; Chromosomes, Human, Pair 17 ; Chromosomes, Human, Pair 18 ; Chromosomes, Human, Pair 2 ; Chromosomes, Human, Pair 3 ; Chromosomes, Human, Pair 5 ; Colorectal Neoplasms ; genetics ; pathology ; Humans ; Loss of Heterozygosity ; Precancerous Conditions

Chromosomes, Human, Pair 14 ; Humans ; Ring Chromosomes ; Syndrome

Adult ; Chromosome Aberrations ; Chromosomes, Human, Pair 11 ; Chromosomes, Human, Pair 15 ; Chromosomes, Human, Pair 17 ; Chromosomes, Human, Pair 19 ; Humans ; Leukemia, Promyelocytic, Acute ; genetics ; Male ; Translocation, Genetic

No abstract available.
Brain* ; Chromosomes, Human, Pair 10* ; Molecular Biology*

Chromosomal polymorphism of constitutive heterochromatin regions of chromosome 1, 9, 16, and Y is a stable evolutionary feature that is thought to cause no phenotypic alterations. The presence of definite ethinic and age-related peculiarities of chromosomal polymorphism variants was established. Some authors reported the relationship of the separate variants with the phenotypic characteristics, such as reproductive function, physiological and anthropometric indices, and oncological diseases. Nevertheless, the role of constitutive heterochromatin is still unknown. We experienced and reported short children associated with polymorphisms in chromosme 1qh+ and 16qh+.
Child ; Chromosomes, Human, Pair 1 ; Heterochromatin ; Humans

The task of chromosome analysis is the classification of human chromosomes. The feature parameter of chromosome is very important information for chromosome analysis. The special preprocessing algorithm is required to extracting them. In this paper, we performed quantitative analysis for preprocessing algorithm of observation of chromosomal aberrations. Two algorithms is used MAT and reconstruction. The morphological feature parameters were centromeric index(C.I.), relative length ratio(R.L.), relative area ratio(R.A.) and chromosome length(C.L.), and the density and width profiles. The reconstruction of chromosome images by this reconstruction algorithm was appeared as effective algorithms to observe and extract chromosome parameter.
Chromosome Aberrations ; Chromosomes, Human ; Classification ; Humans

The task of chromosome analysis is the classification of human chromosomes. The feature parameter of chromosome is very important information for chromosome analysis. The special preprocessing algorithm is required to extracting them. In this paper, we performed quantitative analysis for preprocessing algorithm of observation of chromosomal aberrations. Two algorithms is used MAT and reconstruction. The morphological feature parameters were centromeric index(C.I.), relative length ratio(R.L.), relative area ratio(R.A.) and chromosome length(C.L.), and the density and width profiles. The reconstruction of chromosome images by this reconstruction algorithm was appeared as effective algorithms to observe and extract chromosome parameter.
Chromosome Aberrations ; Chromosomes, Human ; Classification ; Humans