Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations
IEEE Transactions on Pattern Analysis and Machine Intelligence
Segmentation of heterogeneous blob objects through voting and level set formulation
Pattern Recognition Letters
Iterative Voting for Inference of Structural Saliency and Characterization of Subcellular Events
IEEE Transactions on Image Processing
Morphometric subtyping for a panel of breast cancer cell lines
ISBI'09 Proceedings of the Sixth IEEE international conference on Symposium on Biomedical Imaging: From Nano to Macro
Multiphase level set for automated delineation of membrane-bound macromolecules
ISBI'10 Proceedings of the 2010 IEEE international conference on Biomedical imaging: from nano to Macro
Clump splitting via bottleneck detection and shape classification
Pattern Recognition
| Hi-index | 0.00 |
Cell-based fluorescence imaging assays have the potential to generate massive amount of data, which requires detailed quantitative analysis. Often, as a result of fixation, labeled nuclei overlap and create a clump of cells. However, it is important to quantify phenotypic read out on a cell-by-cell basis. In this paper, we propose a novel method for decomposing clumps of nuclei using high-level geometric constraints that are derived from low-level features of maximum curvature computed along the contour of each clump. Points of maximum curvature are used as vertices for Delaunay triangulation (DT), which provides a set of edge hypotheses for decomposing a clump of nuclei. Each hypothesis is subsequently tested against a constraint satisfaction network for a near optimum decomposition. The proposed method is compared with other traditional techniques such as the watershed method with/without markers. The experimental results show that our approach can overcome the deficiencies of the traditional methods and is very effective in separating severely touching nuclei.