Journal of Biomedical Engineering Research (대한의용생체공학회:의공학회지)
- Volume 18 Issue 3
- /
- Pages.233-241
- /
- 1997
- /
- 1229-0807(pISSN)
- /
- 2288-9396(eISSN)
The Implementation of Hierarchical Artificial Neural Network Classifier for Chromosome Karyotype Classification
염색체 핵형 분류를 위한 계층적 인공 신경회로망 분류기 구현
- Jeon, Gye-Rok (Dept. of Biomedical Eng. Pusan National Univ. Hospital) ;
- Choe, Uk-Hwan (Dept. of Obstetrics & Gynecology, Pusan National Univ. Hospital) ;
- Nam, Gi-Gon (Dept. of Electronic Eng. Pusan National University) ;
- Eom, Sang-Hui (Dept. of Electronic Eng. Pusan National University) ;
- Lee, Gwon-Sun (Dept. of Electrical Eng., Dong a University) ;
- Jang, Yong-Hun (Dept. of Electrical Eng., Dong a University)
- 전계록 (부산대학교 병원 의공학과) ;
- 최욱환 (부산대학교 병원 산부인과) ;
- 남기곤 (부산대학교 전자공학과) ;
- 엄상희 (부산대학교 전자공학과) ;
- 이권순 (동아대학교 전기공학과) ;
- 장용훈 (동아대학교 전기공학과)
- Published : 1997.09.01
Abstract
The research on chromosomes is very significant in cytogenetics since genes of the chromosomes control revelation of the inheritance plasma. The human chromosome analysis is widely used to study leukemia, malignancy, radiation hazard, and mutagen dosimetry as well as various congenital anomalies such as Down's, Klinefelter's, Edward's, and Patau's syndrome. The framing and analysis of the chromosome karyogram, which requires specific cytogenetic knowledge is most important in this field. Many researches on automated chromosome karyotype analysis methods have been carried out, some of which produced commercial systems. However, there still remains much room to improve the accuracy of chromosome classification and to reduce the processing time in real clinic environments. In this paper, we proposed a hierarchical artificial neural network(HANN) to classify the chromosome karyotype. We extracted three or four chromosome morphological feature parameters such as centromeric index, relative length ratio, relative area ratio, and chromosome length by preprocessing from ten human chromosome images. The feature parameters of five human chromosome images were used to learn HANN and the rest of them were used to classify the chromosome images. The experiment results show that the chromosome classification error is reduced much more than that of the other researchers using less feature parameters.