Spatially adaptive relaxation for active contour cell segmentation

This paper presents a segmentation framework in a high content screening (HCS) context based on variational snakes. We introduce a modified internal energy function for the snake evolution taking into account the different artifacts appearing in confocal microscopic images during a screening session. This framework is particularly well suited and efficient for nuclei segmentation, providing an accurate base for higher level image analysis.

[1]  Michael Unser,et al.  Snakuscules , 2008, IEEE Transactions on Image Processing.

[2]  Thierry Blu,et al.  Efficient energies and algorithms for parametric snakes , 2004, IEEE Transactions on Image Processing.

[3]  Thierry Dorval,et al.  Inhomogeneous deconvolution in a biological images context , 2008, 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[4]  Thierry Dorval,et al.  Bias Image Correction Via Stationarity Maximization , 2007, MICCAI.

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

[6]  Edwin R. Hancock,et al.  Consistent topographic surface labelling , 1999, Pattern Recognit..

[7]  Jean-Christophe Olivo-Marin,et al.  Coupled parametric active contours , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.