Share Email Print

Proceedings Paper

A novel unsupervised segmentation method for overlapping cervical cell images
Author(s): Lili Zhao; Jianping Yin; Yongkai Ye; Kuan Li; Minghui Qiu
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Overlapping cell segmentation is a prerequisite for the analysis of cervical smear images. Because of the complexity of overlapping situations and the poor contrast of overlapping edges, this problem is one of the most challenges in this field. In this paper, a novel unsupervised segmentation method without needing the training data for overlapping cervical smear images is proposed. First, this method uses a kind of graph cuts to separate all cell clumps from the background. A cell clump may contain the different number of cervical cells. Second, each clump is segmented into non-overlapping regions as rough cells using Voronoi diagram. Third, in order to refine the segmentation of overlapping regions, a minimum enclosing ellipse is used to fit in each rough cell and the overlapped parts of each cell are replaced with the relational regions in this ellipse. Finally, the above overlapped parts and the connected parts of the Voronoi rough cell are merged to form a complete cell. Experiments are conducted on 2 publicly released ISBI datasets and results show that the proposed segmentation method achieves the state-of-art performance.

Paper Details

Date Published: 21 July 2017
PDF: 7 pages
Proc. SPIE 10420, Ninth International Conference on Digital Image Processing (ICDIP 2017), 1042028 (21 July 2017);
Show Author Affiliations
Lili Zhao, National Univ. of Defense Technology (China)
Jianping Yin, National Univ. of Defense Technology (China)
Yongkai Ye, National Univ. of Defense Technology (China)
Kuan Li, National Univ. of Defense Technology (China)
Minghui Qiu, Chinese PLA General Hospital (China)

Published in SPIE Proceedings Vol. 10420:
Ninth International Conference on Digital Image Processing (ICDIP 2017)
Charles M. Falco; Xudong Jiang, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?