Methods Inf Med 2012; 51(03): 260-267
DOI: 10.3414/ME11-02-0015
Focus Theme – Original Articles
Schattauer GmbH

A Fast, Automatic Segmentation Algorithm for Locating and Delineating Touching Cell Boundaries in Imaged Histopathology

X. Qi
1  Department of Pathology and Laboratory Medicine, UMDNJ-Robert Wood Johnson Medical School, Piscataway, NJ, USA
2  Center for Biomedical Imaging & Informatics, The Cancer Institute of New Jersey, UMDNJ-Robert Wood Johnson Medical School, Piscataway, NJ, USA
,
F. Xing
3  Division of Biomedical Informatics, Department of Biostatistics, University of Kentucky, Lexington, KY, USA
,
D. J. Foran
1  Department of Pathology and Laboratory Medicine, UMDNJ-Robert Wood Johnson Medical School, Piscataway, NJ, USA
2  Center for Biomedical Imaging & Informatics, The Cancer Institute of New Jersey, UMDNJ-Robert Wood Johnson Medical School, Piscataway, NJ, USA
,
L. Yang
2  Center for Biomedical Imaging & Informatics, The Cancer Institute of New Jersey, UMDNJ-Robert Wood Johnson Medical School, Piscataway, NJ, USA
3  Division of Biomedical Informatics, Department of Biostatistics, University of Kentucky, Lexington, KY, USA
› Author Affiliations
Further Information

Publication History

received:24 February 2011

accepted:13 February 2012

Publication Date:
20 January 2018 (online)

Summary

Background: Automated analysis of imaged histopathology specimens could potentially provide support for improved reliability in detection and classification in a range of investigative and clinical cancer applications. Automated segmentation of cells in the digitized tissue microarray (TMA) is often the prerequisite for quantitative analysis. However overlapping cells usually bring significant challenges for traditional segmentation algorithms.

Objectives: In this paper, we propose a novel, automatic algorithm to separate overlapping cells in stained histology specimens acquired using bright-field RGB imaging.

Methods: It starts by systematically identifying salient regions of interest throughout the image based upon their underlying visual content. The segmentation algorithm subsequently performs a quick, voting based seed detection. Finally, the contour of each cell is obtained using a repulsive level set deformable model using the seeds generated in the previous step. We compared the experimental results with the most current literature, and the pixel wise accuracy between human experts’ annotation and those generated using the automatic segmentation algorithm.

Results: The method is tested with 100 image patches which contain more than 1000 overlapping cells. The overall precision and recall of the developed algorithm is 90% and 78%, respectively. We also implement the algorithm on GPU. The parallel implementation is 22 times faster than its C/C++ sequential implementation.

Conclusion: The proposed segmentation algorithm can accurately detect and effectively separate each of the overlapping cells. GPU is proven to be an efficient parallel platform for overlapping cell segmentation.