A Highly Accurate Level Set Approach for Segmenting Green Microalgae Images

We present a method for segmenting 2D microscopy images of freshwater green microalgae. Our approach is based on a specialized level set method, leading to efficient and highly accurate algae segmentation. The level set formulation of our problem allows us to generate an algae's boundary curve as the result of an evolving level curve, based on computed background and algae regions in a given image. By characterizing the distributions of image intensity values in local regions, we are able to automatically classify image regions into background and algae regions. We present results obtained with our method. These results are very promising as they document that we can achieve highly accurate algae segmentations when comparing ours against manually segmented images (segmented by an expert biologist) and with results derived by other approaches covered in the literature.

[1]  Christophe Zimmer,et al.  Segmenting and tracking fluorescent cells in dynamic 3-D microscopy with coupled active surfaces , 2005, IEEE Transactions on Image Processing.

[2]  Yang Yu,et al.  Sparse Deformable Models with Application to Cardiac Motion Analysis , 2013, IPMI.

[3]  Charles A. Taylor,et al.  In Vitro Validation of Finite Element Analysis of Blood Flow in Deformable Models , 2011, Annals of Biomedical Engineering.

[4]  Chunming Li,et al.  Distance Regularized Level Set Evolution and Its Application to Image Segmentation , 2010, IEEE Transactions on Image Processing.

[5]  Marcel Bauer,et al.  Numerical Methods for Partial Differential Equations , 1994 .

[6]  Alan L. Yuille,et al.  Region Competition: Unifying Snakes, Region Growing, and Bayes/MDL for Multiband Image Segmentation , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Xiang Zhu,et al.  Automatic Parameter Selection for Denoising Algorithms Using a No-Reference Measure of Image Content , 2010, IEEE Transactions on Image Processing.

[8]  Reiner Lenz,et al.  Modified Gradient Search for Level Set Based Image Segmentation , 2013, IEEE Transactions on Image Processing.

[9]  Xuelong Li,et al.  An Efficient MRF Embedded Level Set Method for Image Segmentation , 2015, IEEE Transactions on Image Processing.

[10]  D. Mumford,et al.  Optimal approximations by piecewise smooth functions and associated variational problems , 1989 .

[11]  Karl Rohr,et al.  Efficient globally optimal segmentation of cells in fluorescence microscopy images using level sets and convex energy functionals , 2012, Medical Image Anal..

[12]  Guillermo Sapiro,et al.  Geodesic Active Contours , 1995, International Journal of Computer Vision.

[13]  J. Sethian,et al.  Fronts propagating with curvature-dependent speed: algorithms based on Hamilton-Jacobi formulations , 1988 .

[14]  Rachid Deriche,et al.  Geodesic Active Regions and Level Set Methods for Supervised Texture Segmentation , 2002, International Journal of Computer Vision.

[15]  Lei Zhang,et al.  Active contours with selective local or global segmentation: A new formulation and level set method , 2010, Image Vis. Comput..

[16]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[17]  Zhongxuan Luo,et al.  Comparative study of C-V active contour model and subdivision for micro algae image segmentation , 2011, 2011 International Conference on Electric Information and Control Engineering.

[18]  Baba C. Vemuri,et al.  Shape Modeling with Front Propagation: A Level Set Approach , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  Lars Linsen,et al.  VANLO - Interactive visual exploration of aligned biological networks , 2009, BMC Bioinformatics.

[20]  A. Verikas,et al.  Boosting performance of the edge-based active contour model applied to phytoplankton images , 2012, 2012 IEEE 13th International Symposium on Computational Intelligence and Informatics (CINTI).

[21]  R. Deriche,et al.  A variational framework for active and adaptative segmentation of vector valued images , 2002, Workshop on Motion and Video Computing, 2002. Proceedings..

[22]  S. Osher,et al.  Algorithms Based on Hamilton-Jacobi Formulations , 1988 .

[23]  K. V. Embleton,et al.  Automated counting of phytoplankton by pattern recognition: a comparison with a manual counting method , 2003 .

[24]  S. Osher,et al.  Level set methods: an overview and some recent results , 2001 .

[25]  A. Yezzi,et al.  On the relationship between parametric and geometric active contours , 2000, Conference Record of the Thirty-Fourth Asilomar Conference on Signals, Systems and Computers (Cat. No.00CH37154).

[26]  Kurt Maute,et al.  Level-set methods for structural topology optimization: a review , 2013 .

[27]  Kang Lin,et al.  A system for identification of marine phytoplankton , 2010, 2010 2nd International Conference on Signal Processing Systems.

[28]  John Cairns,et al.  Algae as indicators of environmental change , 1994, Journal of Applied Phycology.

[29]  Tai Sing Lee,et al.  Region competition: unifying snakes, region growing, energy/Bayes/MDL for multi-band image segmentation , 1995, Proceedings of IEEE International Conference on Computer Vision.

[30]  Tony F. Chan,et al.  Active contours without edges , 2001, IEEE Trans. Image Process..

[31]  Pakaket Wattuya,et al.  Automated Microalgae Image Classification , 2014, ICCS.

[32]  Xavier Bresson,et al.  Fast Global Minimization of the Active Contour/Snake Model , 2007, Journal of Mathematical Imaging and Vision.

[33]  Jos B T M Roerdink,et al.  Automatic segmentation of diatom images for classification , 2004, Microscopy research and technique.

[34]  L. Vese,et al.  A level set algorithm for minimizing the Mumford-Shah functional in image processing , 2001, Proceedings IEEE Workshop on Variational and Level Set Methods in Computer Vision.