Phase contrast image segmentation by weak watershed transform assembly

Abstract

We present here a method giving a robust segmentation for in vitro cells observed under standard phase-contrast microscopy. We tackle the problem using the watershed transform. Watershed transform is known for its ability to generate closed contours and its extreme sensitivity to image borders. One main drawback of this method is oversegmentation. In order to circumvent this, marked watershed based on the "modified gradient" method has been developed. However, the choice of the watershed mark locations is critical and their inadequacy may cause wrong results. Similarly to randomization and combination procedures used in the machine learning field, the present paper promotes the use of an assembly of marked watershed transforms, in order to increase the segmentation robustness. This results in the definition of candidate segmentations margins (expressed in terms of object border confidence) from which final segmentation can be chosen by means of thresholding.

Automatic Morphological Measurement of the Quantum Dots Based on Marker-Controlled Watershed Algorithm

“…It is sensitive to weak edges, and is capable of acquiring an interesting solution for image segmentation by producing closed and connected contours [4]. The classical watershed transform can be illustrated by the immersion simulation [13].…”

“…Fortunately, watershed transform can avoid these problems. It is an effective algorithm for image segmentation based on mathematical morphology, and is well known for its ability to generate closed contours [4]. Watershed has been widely applied to various kinds of image segmentation task due to its fast computing speed and high accuracy in locating the weak edges of adjacent regions [5].…”

Integrated approach to the data processing of four-dimensional datasets from phase-contrast x-ray tomography

“…Ref. [11] used a weak watershed transform assembly to increase segmentation robustness. In this method, however, the centroids of the particles need to be marked by a user prior to segmentation.…”

Image Analysis for Calculation of the Toxicity Degree of Cells in Phase Contrast Microscopy Images

“…Although these algorithms provide a good separation of cell regions from the image background, they are not able to classify cells on a differentiated level, e.g. they do not reliably separate attached cells automatically [1].…”