Analysis and recognition of touching cell images based on morphological structures.

Automated analysis and recognition of cell-nuclear phases using fluorescence microscopy images play an important role for high-content screening. A major task of automated imaging based high-content screening is to segment and reconstruct each cell from the touching cell images. In this paper we present new useful method for recognizing morphological structural models of touching cells, detecting segmentation points, determining the number of segmented cells in touching cell image, finding the related data of segmented cell arcs and reconstructing segmented cells. The conceptual frameworks are based on the morphological structures where a series of structural points and their morphological relationships are established. Experiment results have shown the efficient application of the new method for analysis and recognition of touching cell images of high-content screening.

A region analysis approach for segmenting neural-cell images.

In this paper we present new algorithms based on region analysis of grey and distance differences of images that successfully circumvent these problems. Two key parameters of this analysis, window width and logical threshold, are automatically extracted for use in logical thresholding, and spurious regions are detected and removed through use of a hierarchical window filter. The efficacy of the developed algorithms is demonstrated here through an analysis of cultured brain neurons from newborn mice.

Segmentation of cultured neurons using logical analysis of grey and distance difference.

The molecular and cellular bases of neuronal cell death that underpin a wide range of neurodegenerative disorders are still not well understood. One approach to investigating neuronal death is through systematic studies of the changing morphology of cultured brain neurons in response to cellular challenges. Image segmentation methods developed to date to analyze such changes have been limited by the low contrast of cells in unstained neuronal cultures and the unimodal histograms generated by these analyses. In this paper we present new algorithms based on logical analysis of grey and distance difference of images that successfully circumvent these problems. Two key parameters of this analysis, window width and logical threshold, are automatically extracted for use in logical level technique, and spurious regions are detected and removed through use of a hierarchical window filter. The efficacy of the developed algorithms is demonstrated here through an analysis of cultured brain neurons from newborn mice.