A Marker Controlled Watershed Algorithm with Priori Shape Information for Segmentation of Clustered Nuclei

Main Article Content

M. Mohideen Fatima Alias Niraimathi
Dr.V. Seenivasagam

Abstract

Microscopy cell image analysis is a fundamental tool for biological research. This analysis is used in studies of different aspects of
cell cultures. Visual inspection of individual cells is very time consuming, insufficient to detect or describe delicate changes in cellular
morphology. The main challenges in segmenting nuclei in histometry are due to the fact that the specimen is a 2-D section of a 3-D tissue
sample. The 2-D sectioning can result in partially imaged nuclei, sectioning of nuclei at odd angles, and damage due to the sectioning process.
Furthermore, sections have finite thickness resulting in aggregating or overlapping nuclei in planar images. Hence a set of image objects that
differ considerably from the ideal of round blob-like shapes occur. Their sizes and shapes in images can be irregular. The classic methodology
for cell detection is image segmentation, which is a fundamental and difficult problem in computer vision. Image segmentation is a fundamental
and difficult problem in computer vision. The difficulty in automatic segmentation of images of cells is often uneven due to auto fluorescence
from the tissue and fluorescence from out-of-focus objects. This unevenness makes the separation of foreground and background a non-trivial
task. The intensity variations within the nuclei further complicate the segmentation as the nuclei may be split into more than one object, leading
to over-segmentation. Due to the cell nuclei are often clustered, make it difficult to separate the individual nuclei. Hence an automatic
segmentation of cell nuclei is an essential step in image histometry and cytometry. This paper presents a robust method to segment clustered
overlapping or aggregating nuclei cells using priori information of shape markers and marking function in a watershed-like algorithm. The shape
markers are extracted using adaptive H-minima transform and prior information about the usual shape of normal/pathological nuclei cells. A new
marking function based on outer distance transform, to avoid jagged boundaries of segmented objects is created. Thus the right sets of markers
and a marking function are used to accurately separate clustered nuclei.

 

 

Keywords: Active contours, aggregating/overlapping nuclei, adaptive H-minima, markers, marking function, watershed segmentation.

Downloads

Download data is not yet available.

Article Details

Section
Articles