Segmentation and Tracking of Lymphocytes Based on Modified Active Contour Models in Phase Contrast Microscopy Images

Abstract

The paper proposes an improved active contour model for segmenting and tracking accurate boundaries of the single lymphocyte in phase-contrast microscopic images. Active contour models have been widely used in object segmentation and tracking. However, current external-force-inspired methods are weak at handling low-contrast edges and suffer from initialization sensitivity. In order to segment low-contrast boundaries, we combine the region information of the object, extracted by morphology gray-scale reconstruction, and the edge information, extracted by the Laplacian of Gaussian filter, to obtain an improved feature map to compute the external force field for the evolution of active contours. To alleviate initial location sensitivity, we set the initial contour close to the real boundaries by performing morphological image processing. The proposed method was tested on live lymphocyte images acquired through the phase-contrast microscope from the blood samples of mice, and comparative experimental results showed the advantages of the proposed method in terms of the accuracy and the speed. Tracking experiments showed that the proposed method can accurately segment and track lymphocyte boundaries in microscopic images over time even in the presence of low-contrast edges, which will provide a good prerequisite for the quantitative analysis of lymphocyte morphology and motility.

Figure 1

The original image and two differrent external force fields. (a) Cell image captured by the phase-contrast microscope, and the lymphoctye is in the center of the view. The ROI contains the target-lymphoctye, marked as in the rectangular. (b) The traditional external force field based on (5). (c) The proposed external force field based on (7).

Figure 2

The procedure of obtaining the initial contour. (a) The ROI. (b) MGR of the ROI. (c) The coarse binary image of (b). (d) The initial contour extracted from the binary image.

Figure 3

Segmentation of sample lymphocytes. The first line: the ROI (Img 1, Img 2, Img 3, and Img 4). The second, third, fourth, and fifth lines present the results for GAC, GVF, CV, and the proposed VFC_MGRL method. The last line is the ground truth.

Figure 4

Detailed evaluation results. Horizontal axis shows the numbered images used for evaluation. Separate bars indicate the results of different methods: blue (the first bar) is GVF; red (the second bar) is GAC; green (the third bar) is CV; purple (the fourth bar) is the proposed VFC_MGRL method.

Figure 5

(a) The workflow of segmentation and tracking of the target-cell in an image sequence. (b) Segmentation and tracking of cell by using VFC_MGRL snakes at frame 130, 250, 370, 490, 610, and 730, respectively. The frame interval is 0.04 seconds.