Automated nuclei clump splitting by combining local concavity orientation and graph partitioning

Automated clump decomposition is essential for single cell based analysis of fluorescent microscopy images. This paper presents a new method for automatically splitting clumps of cell nuclei in fluorescence microscopy images. Nuclei are first segmented using histogram concavity analysis. Clumps of nuclei are detected by fitting an ellipse to the segmented objects and examining objects where the fitted ellipse does not overlap accurately with the segmented object. These clumps are then further processed to find concave points on the object boundaries. The orientation of the detected concavities is subsequently calculated based on the local shape of the object border. Finally, a graph segmentation based approach is used to pair concavities that represent best candidates for splitting touching nuclei based on properties derived from the local concavity properties. This approach was validated by manual inspection and has shown promising results in the high throughput analysis of HeLa cell images.

[1]  Sim Heng Ong,et al.  Clump splitting through concavity analysis , 1994, Pattern Recognit. Lett..

[2]  A. Schapira,et al.  Mitochondrial Contribution to Parkinson's Disease Pathogenesis , 2011, Parkinson's disease.

[3]  Oliver Schmitt,et al.  On the Decomposition of Cell Clusters , 2008, Journal of Mathematical Imaging and Vision.

[4]  Changming Sun,et al.  Splitting touching cells based on concave points and ellipse fitting , 2009, Pattern Recognit..

[5]  Nicholas W Wood,et al.  Cell metabolism affects selective vulnerability in PINK1-associated Parkinson's disease , 2011, Journal of Cell Science.

[6]  Reinhold Nafe,et al.  The morphology of perinecrotic tumor cell nuclei in glioblastomas shows a significant relationship with survival time. , 2006, Oncology reports.

[7]  Azriel Rosenfeld,et al.  Histogram concavity analysis as an aid in threshold selection , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[8]  Donggang Yu,et al.  Analysis and Recognition of Touching Cell Images Based on Morphological Structures , 2007, KES.

[9]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[10]  S. Carpenter,et al.  Early Warnings of Regime Shifts: A Whole-Ecosystem Experiment , 2011, Science.

[11]  S. Carpenter,et al.  Anticipating Critical Transitions , 2012, Science.

[12]  Dmitry Chetverikov,et al.  A Simple and Efficient Algorithm for Detection of High Curvature Points in Planar Curves , 2003, CAIP.

[13]  Sim Heng Ong,et al.  A rule-based approach for robust clump splitting , 2006, Pattern Recognit..

[14]  Rudi Balling,et al.  The hallmarks of Parkinson's disease , 2013, The FEBS journal.

[15]  Olli Yli-Harja,et al.  A novel method for splitting clumps of convex objects incorporating image intensity and using rectangular window-based concavity point-pair search , 2013, Pattern Recognit..

[16]  Paola Piccini,et al.  Priorities in Parkinson's disease research , 2011, Nature Reviews Drug Discovery.

[17]  May D. Wang,et al.  Automated cell counting and cluster segmentation using concavity detection and ellipse fitting techniques , 2009, 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[18]  M Fenech,et al.  Necrosis, apoptosis, cytostasis and DNA damage in human lymphocytes measured simultaneously within the cytokinesis-block micronucleus assay: description of the method and results for hydrogen peroxide. , 1999, Mutagenesis.