Segmentation of Cells with Partial Occlusion and Part Configuration Constraint Using Evolutionary Computation
We propose a method for targeted segmentation that identifies and delineates only those spatially-recurring objects that conform to specific geometrical, topological and appearance priors. By adopting a “tribes”-based, global genetic algorithm, we show how we incorporate such priors into a faithful objective function unconcerned about its convexity. We evaluated our framework on a variety of histology and microscopy images to segment potentially overlapping cells with complex topology. Our experiments confirmed the generality, reproducibility and improved accuracy of our approach compared to competing methods.
Unable to display preview. Download preview PDF.
- 1.Ali, S., Veltri, R., Epstein, J.I., Christudass, C., Madabhushi, A.: Adaptive energy selective active contour with shape priors for nuclear segmentation and gleason grading of prostate cancer. In: Fichtinger, G., Martel, A., Peters, T. (eds.) MICCAI 2011, Part I. LNCS, vol. 6891, pp. 661–669. Springer, Heidelberg (2011)CrossRefGoogle Scholar
- 2.Bernardis, E., et al.: Pop out many small structures from a very large microscopic image. MedIA 15(5), 690–707 (2011)Google Scholar
- 5.Delong, A., et al.: Globally optimal segmentation of multi-region objects. In: ICCV, pp. 285–292 (2009)Google Scholar
- 10.Kuse, M., et al.: Local isotropic phase symmetry measure for detection of beta cells and lymphocytes. J. Pathol. Inf. 2 (2011)Google Scholar
- 11.Mao, K.Z., et al.: Supervised learning-based cell image segmentation for p53 immunohistochemistry. IEEE TBE 53(6), 1153–1163 (2006)Google Scholar
- 14.Wu, X., et al.: Embedding topic discovery in conditional random fields model for segmenting nuclei using multispectral data. IEEE TBE 59(6), 1539–1549 (2012)Google Scholar