Journal of Biomedical Engineering Research (대한의용생체공학회:의공학회지)

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

Discrimination of Cancer Cells by Dominant Feature Parameters Method in Thyroid Gland Cells

우세특징파라미터를 이용한 갑상선 암세포의 식별

  • 나철훈 (전남대학교 공과대학 전자공학과) ;
  • 정동명 (원공대학교 공과대학 전자공학과)
  • Published : 1994.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

A new method of digital image analysis technique for discrimination of cancer cell was presented in this paper. The object image was the Thyroid Gland cells image that was diagnosed as normal and abnormal (two types of abnormal : follicular neoplastic cell, and papillary neoplastic cell), respectively. By using the proposed region segmentation algorithm, the cells were segmented into nucleus. The 16 feature parameters were used to calculate the features of each nucleus. As a consequence of using dominant feature parameters method proposed in this paper, discrimination rate of 91.11 % was obtained for Thyroid Gland cells.

본 연구는 인간의 갑상선 세포를 대상으로 암세포의 식별을 위하여 새로운 디지털 영상기술을 적용하여 해석한 것으로 이를 위하여 세포영상해석에 필요한 개선된 처리방법들을 제안하였다. 실험대상으로 정상세포와 암세포로 확진된 갑상선세포의 현미경 영상을 사용하였다. 세포영상으로부터 세포핵을 구분하기 위하여 기존의 방법을 개선한 방향각을 갖는 Contour Following법을 시도하여 세포핵의 영상을 매우 효과적으로 얻을 수 있음을 입증하였고, 세포핵의 특징추출을 위하여 16개의 특징파라미터들을 사용하였고 식별율을 높이기 위하여 우세특징파라미터를 선택하여 식별을 향상을 꾀하였다. 실험 결과 평균 91.11%의 식별률을 얻음으로서 효과적으로 갑상선의 암세포를 식별할 수 있음을 증명하였다.

Keywords

References

  1. Pattern Recognition and Image Preprocessing Sing-Tze Bow
  2. IEEE Trans. on Systems, Man, and Cybernetics v.SMC-17 Feature Selection for Texture Recognition Based on Image Systhesis A.Khotanzad;R.Kashyap
  3. Analytical and Quantitative Cytology v.1 no.3 Studies on Papanicolaou Staining W.Galvraith(et al.)
  4. Tutorials of Cytology v.9 no.25 In Compendium on Cytopreparatory Techniques G.W.Gill;K.A.Miller
  5. Pathol. Annu. v.16 Computer Analysis of microscopic image : application in cytopathology G.L.Wied;M.Bibbo;P.G.Bartels
  6. Surgical Pathogy of the Thyroid Virginia A. LiVolsi
  7. Computer Graphics and Image Processing v.7 no.2 A Survey of Threshold Selection Techniques J.S.Weska
  8. JACM v.9 no.2 Operations Useful for Similarity-Invariant Pattern Recognition W.Doyle
  9. Proc. of IEEE 1993 NSS and MIC v.2 Effective Discrimination of Cancer cells in Medical Images Cheol-Hun Na;Hyeon-Jae Kim
  10. Digital Image Processing(2nd ed.) W.K.Pratt
  11. Proc. UMR-Mervin J. Kelly Communications Conference Visual Texture Analysis A.Rosenfeld;E.B.Troy