Nonparametric segmentation and classification of small size irregularly shaped stem cell nuclei using adjustable windowing

We present nonparametric methods for segmenting and classifying stem cell nuclei so as to enable the automatic monitoring of stem cell growth and development. The approach is based on combining level set methods, multiresolution wavelet analysis, and non-parametric estimation of the density functions of the wavelet coefficients from the decomposition. Additionally, to deal with small size textures where the largest inscribed rectangular window may not contain a sufficient number of pixels for multiresolution analysis, we propose an adjustable windowing method that enables the multiresolution analysis of elongated and irregularly shaped nuclei. We illustrate cases where the adjustable windowing approach combined with non-parametric density models yields better classification for cases where parametric density modeling of wavelet coefficients may not applicable.