A novel cell segmentation method and cell phase identification using Markov model

Abstract

Optical microscopy is becoming an important technique in drug discovery and life science research. The approaches used to analyze optical microscopy images are generally classified into two categories: automatic and manual approaches. However, the existing automatic systems are rather limited in dealing with large volume of time-lapse microscopy images because of the complexity of cell behaviors and morphological variance. On the other hand, manual approaches are very time-consuming. In this paper, we propose an effective automated, quantitative analysis system that can be used to segment, track, and quantize cell cycle behaviors of a large population of cells nuclei effectively and efficiently. We use adaptive thresholding and watershed algorithm for cell nuclei segmentation followed by a fragment merging method that combines two scoring models based on trend and no trend features. Using the context information of time-lapse data, the phases of cell nuclei are identified accurately via a Markov model. Experimental results show that the proposed system is effective for nuclei segmentation and phase identification.

Fig. 1

Flowchart of the proposed system.

Fig. 2

Example segmentation results. (a) Original image. (b) Result of watershed algorithm. (c) Result after the hybrid merging algorithm.

Fig. 3

Four cell phases. (a) Interphase. (b) Prophase. (c) Metaphase. (d) Anaphase.

Fig. 4

Diagram of the four states left–right Markov model. The four states are as follows. (1) Interphase. (2) Prophase. (3) Metaphase. (4) Anaphase. Each state is modeled as a Gaussian mixture model with two mixtures.

Fig. 5

2-D visualization of all the 9600 nuclei in the training dataset. Green spots—interphase; red stars—prophase; blue triangles—metaphase; and black pentacles—anaphase.