Transactions of the Korean Society of Mechanical Engineers B (대한기계학회논문집B)

The Korean Society of Mechanical Engineers (대한기계학회)
권호 표지
DOI QR코드

DOI QR Code

Cluster Cell Separation Algorithm for Automated Cell Tracking

자동 세포 추적을 위한 클러스터 세포 분리 알고리즘

  • 조미경 (동명대학교 미디어공학과) ;
  • 심재술 (영남대학교 기계공학부)
  • Received : 2012.05.02
  • Accepted : 2012.12.26
  • Published : 2013.03.01
Download PDF
⟨ Previous Next ⟩

Abstract

An automated cell tracking system is used to automatically analyze and track the changes in cell behavior in time-lapse cell images acquired using a microscope with a cell culture. Clustering is the partial overlapping of neighboring cells in the process of cell change. Separating clusters into individual cells is very important for cell tracking. In this study, we proposed an algorithm for separating clusters by using ellipse fitting based on a direct least square method. We extracted the contours of clusters, divided them into line segments, and then produced their fitted ellipses using a direct least square method for each line segment. All of the fitted ellipses could be used to separate their corresponding clusters. In experiments, our algorithm separated clusters with average precisions of 91% for two overlapping cells, 84% for three overlapping cells, and about 73% for four overlapping cells.

광학 현미경을 통해 일정한 시간 간격으로 얻은 세포 이미지로부터 세포 변화를 자동적으로 추적 및 분석하는 것이 세포 트래킹이라고 한다. 세포 변화 과정에서 이웃에 있는 세포들이 겹쳐져 있는 상태를 클러스터라고 하며 세포트래킹에서 클러스터를 다시 세포로 분리하는 작업은 매우 중요하다. 본 논문에서는 타원 근사법을 기반으로 클러스터를 분리하기 위한 알고리즘을 제안한다. 클러스터의 외곽선을 추출한 후 외곽선의 오목정점을 이용하여 클러스터를 라인 세그먼트들로 분리한 다음 휴리스틱을 이용하여 라인 세그먼트들을 결합해 가며 근사 타원을 생성한다. 실험 결과 두 개의 세포가 겹쳐진 클러스터의 경우 평균적으로 91%, 세 개의 세포가 겹쳐진 경우 평균적으로 84% 그리고 겹쳐진 세포의 개수가 네 개 이상인 경우 약 73%의 정확도로 클러스터를 분리해 주었다.

Keywords

References

  1. Bise, R., Li, K., Eom, S. and Kanade, T., 2009, "Reliable Tracking Partially Overlapping Neural Stemm Cells in DIC Microscopy Image Sequences," MICCAI Workshop on Optical Tissue Image Analysis in Microscopy, Histopathology and Endoscopy Imperial College London, pp. 67-77.
  2. Wang, W., 1998, "Binary Image Segmentation of Aggregates Based on Polygonal Approximation and Classification of Concavities," Pattern Recognition, Vol. 31, pp. 1503-1524. https://doi.org/10.1016/S0031-3203(97)00145-3
  3. Jin, Y.X.C., Jayasooriah, S.H.O. and Sinniah, R., 1994, "Clump Splitting Through Concavity Analysis," Pattern Recognition Letters, Vol.15, pp. 1013-1018. https://doi.org/10.1016/0167-8655(94)90033-7
  4. Kumar, S., Ong, S.H., Ranganath, S., Ong, T.C. and Chew, F.T., 2006, "A Rule-Based Approach for Robust Clump Splitting," Pattern Recognition, Vol. 39, pp. 1088-1098. https://doi.org/10.1016/j.patcog.2005.11.014
  5. Mao, K.Z., Zhao, P. and Tan, P., 2006, "Supervised Learning-Based Cell Image Segmentation for P53 Immunohistochemistry," IEEE Transactions on Biomedical Engineering, Vol. 53, No. 6, pp. 1153-1163. https://doi.org/10.1109/TBME.2006.873538
  6. Ruberto, C.D., Dempster, A., Khan, S. and Jarra, B., 2002, "Analysis of Infected Blood Cell Images Using Morphological Operators," Image and Vision Computing, Vol. 20, pp. 133-146. https://doi.org/10.1016/S0262-8856(01)00092-0
  7. Talbot, H. and Appleton, B.C., 2002, "Elliptical Distance Transforms and the Object Splitting Problem," Proceedings of International Symposium on Mathematical Morphology, Sydney, Australia, pp. 229-240.
  8. Yu, D., Pham, T.D., Zhou, X. and Wong, S.T.C., 2007, "Segmentation, Recognition and Tracing Analysis for High-Content Cell-Cycle Screening," Proceedings of International Symposium on Computational Models for Life Sciences, Queensland, Australia, pp. 66-75.
  9. Bai, X., Sun, C. and Zhou, F., 2009, "Splitting Touching Cells Based on Concave Points and Ellipse Fitting," Pattern Recognition, 42, pp. 2434-2446. https://doi.org/10.1016/j.patcog.2009.04.003
  10. Kothari, S., Chaudry, Q. and Wang, M. D., 2009, "Automated Cell Counting and Cluster Segmentation Using Concavity Detection and Ellipse Fitting Techniques," IEEE International Symposium on Biomedical Imaging: From Nano to Macro.
  11. Cho, M., Shim, J., Kim, J. and Moon, S., 2011, "Classifying and Counting Cells and Clusters Using Concave Points," Korea Computer Congress 2011 Vol. C, pp. 184-187.
  12. Cho, M. and Shim, J., 2012, "An Ellipse Fitting based Algorithm for Separating Overlapping Cells," Proceeding of The Korea Institute of Information and Communication Engineering 2012 Spring, pp. 912-915.
  13. Cho, M., Kim, J. and Shim, J., 2011, "Optical Microscope Image Processing for Automated Cells Counting," Journal of The Korea Institute of Information and Communication Engineering, Vol. 15, No. 12, pp. 2494-2495.
  14. Cho, M. and Shim, J., 2012, "Ellipse based Cell Separation Algorithm for Tens of Thousands of Overlapping Cells," The 2nd International conference on Convergence Technology 2012, pp. 205-208.
  15. Fitzgibbon, A., Pilu, M. and Fisher, R. B., 1999, "Direct Least Square Fitting of Ellipses," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 21, No. 5, pp. 476-480. https://doi.org/10.1109/34.765658