인공신경 회로망을 이용한 정자의 형태학적 특성 분석에 관한 연구

A Study on the Morphometric Analysis of Spermatozoa Using Artificial Neural Networks

  • 이원진 (서울대학교 대학원 협동과정 의용생체공학) ;
  • 박광석 (서울대학교 의과대학 의공학 교실) ;
  • 백재승 (서울대학교 의과대학 비뇨기과학 교실) ;
  • 전성수 (서울대학교 의과대학 비뇨기과학 교실)
  • Yi, W.J. (Interdisciplinary Program in Medical and Biological Engineering Major, Seoul Nat'l Univ.) ;
  • Park, K.S. (Dept. of Biomedical Engineering, College of Medicine, Seoul Nat'l Univ.) ;
  • Baek, J.S. (Dept. of Urology, College of Medicine, Seoul Nat'l Univ.) ;
  • Jeon, S.S. (Dept. of Urology, College of Medicine, Seoul Nat'l Univ.)
  • 발행 : 1996.11.15

초록

In male reproducible health and fertility and IVF(in-vitro fertilization), semen analysis has been most important. But the traditional tools for semen analysis are subjective, imprecise, inaccurate, difficult to standardize, and difficult to reproduce mainly due to their manually oriented operations. The purpose of a morphometric analysis of sperm is to microscopically type-classify spermatozoa cytologically according to their morphology of heads. Until now, the strict criteria method has long been used in clinic to discriminate normal spermatozoa from abnormal ones. This method cannot classify the diverse groups of abnormal spermatozoa in detail and shows variations in inter-operators and intra-operator In this paper, we developed a new method of a sperm morphometric analysis using artificial neural networks which are widely used in pattern recognition and image processing.

키워드