Journal of Biomedical Engineering Research (대한의용생체공학회:의공학회지)

The Korean Society of Medical and Biological Engineering (대한의용생체공학회)
권호 표지

A Study on Segmentation of Uterine Cervical Pap-Smears Images Using Neural Networks

신경 회로망을 이용한 자궁 경부 세포진 영상의 영역 분할에 관한 연구

  • 김선아 (한림대학교 컴퓨터공학과) ;
  • 김백섭 (한림대학교 컴퓨터공학과)
  • Published : 2001.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

This paper proposes a region segmenting method for the Pap-smear image. The proposed method uses a pixel classifier based on neural network, which consists of four stages : preprocessing, feature extraction, region segmentation and postprocessing. In the preprocessing stage, brightness value is normalized by histogram stretching. In the feature extraction stage, total 36 features are extracted from $3{\times}3$ or $5{\times}5$ window. In the region segmentation stage, each pixel which is associated with 36 features, is classified into 3 groups : nucleus, cytoplasm and background. The backpropagation network is used for classification. In the postprocessing stage, the pixel, which have been rejected by the above classifier, are re-classified by the relaxation algorithm. It has been shown experimentally that the proposed method finds the nucleus region accurately and it can find the cytoplasm region too.

Keywords

References

  1. 대한 세포병리학회지 v.5 no.1 영상처리를 이용한 자궁경부 세포진의 자동탐색 방법에 관한 연구 은성경;박찬모;박화순;윤소영;조민선;조수연;김성숙
  2. Computer Graphics and Image Processing v.3 An Automated apparatus for Cancer Prescreening : CYBEST Sadakazu Watanabe;The CYBEST Group
  3. Automated Cervial Cancer Screening Heinz K. Grohs;O. A. Nasseem Husain
  4. United States Patent, Patent Number 5,828,776 Apparatus for identification and integration of multiple cell patterns Shin-Jong J.Lee;Chih-Chau I;Kuan, Wendy R.Bannister;Paul S.Wilhelm;Michael G. Meyer
  5. United States Patent, Patent Number 5,978,498 cellgroupings Paul S. Wilhelm;Shih-Jong J. Lee
  6. United States Patent, Patent Number 5,257,182 Morphological classification system and method Randall L.Luck;Richard Scott
  7. United States Patent, Patent Number 4,965,725 Neural network based automated cytological specimen classification system and method Mark R.Rutenberg
  8. Morphological segmentation of histology cell images A. Nedzved;S. Ablameyko;I. Pitas
  9. 한국정보과학회 가을학술발표논문집 v.26 no.2 칼라 유방암조직영상에서 질감 특징과 신경회로망을 이용한 양성 세포핵과 음성세포핵의 자동 분할 최현주;허민권;최흥국;김상균;최항묵;박세명
  10. Abdominal Organ REcognition using 3D Mathematical Morphology Toyohisa Kaneko;Lixu Gu;Hideyuki Fujimoto
  11. Unsupervised Segmentation of Color Images Based on k-means Clustering in the Chromaticity Plane Unsupervised Segmentation of Color Images Based on k-means Clustering in the Chromaticity Plane L. Lucchese;S. K. Mitra
  12. A Simplified Approach to Image Processing Randy Crane
  13. IEEE Trans Man Cybernet 3 Textural features for image classfication Haralick RM
  14. Algorithms for Image Processing and Computer Vision J. R. Parker
  15. Proceedings of ICPR '96 v.II Algorithm for Feature Selection: An Evaluation Douglas Zongker;Anil Jain
  16. Southeastcon '92, Proceedings.,IEEE v.1 Automatic image segmentation using edge detection by tissue classfication in local neighborhoods Singleton, H.R
  17. Optical Engineering v.34 no.12 Feature evaluation and selection based on an entropy measure with data clustering Zheru Chi;Hong Yan
  18. Proc. 7th IEEE Symp. Adaptive Processes The information content measure as a performance criterion for feature selection H. F. Ryan
  19. Pattern Recognition and Neural Networks B. D. Ripley
  20. Pattern Recognition v.28 no.1 Image Thresholdings by Minimizing The Measures of Fuzziness Liang-Kai Huang;Mao-Jiun J.Wang
  21. Pattern Recognition v.19 no.1 Minimum error thresholding J. Kittler;J. Illingworth