Seed-Point Based Geometric Partitioning of Nuclei Clumps
This addresses the need for more accurate automatic analysis of cell nuclei in biomedical imaging, though it appears incremental as it builds on existing partitioning approaches.
The paper tackles the problem of partitioning overlapping cell nuclei in fluorescence or histopathological images by introducing a seed-point based geometric partitioning method with two types of cuts, which was tested on 2420 clumps and outperformed current popular software.
When applying automatic analysis of fluorescence or histopathological images of cells, it is necessary to partition, or de-clump, partially overlapping cell nuclei. In this work, I describe a method of partitioning partially overlapping cell nuclei using a seed-point based geometric partitioning. The geometric partitioning creates two different types of cuts, cuts between two boundary vertices and cuts between one boundary vertex and a new vertex introduced to the boundary interior. The cuts are then ranked according to a scoring metric, and the highest scoring cuts are used. This method was tested on a set of 2420 clumps of nuclei and was found to produced better results than current popular analysis software.