Segmentation method for overlapping cells in cervical smear image

Abstract

The invention discloses a segmentation method for overlapping cells in a cervical smear image. The method comprises the following steps that firstly, an image background is removed, a frontground object, namely a cell aggregate formed by the overlapping cells, is extracted; secondly, cell nucleuses are segmented; thirdly, color partition is carried out on the cell aggregate by using the average value shifting method, and sub-blocks are formed by segmenting by using the watershed algorithm; fourthly, all of combination modes of the sub-blocks are searched, filtering is carried out according to a screening condition, the combinations which are in accordance with the condition are called possible solutions; fifthly, energy functionals of the possible solutions which are obtained in the fourth step are calculated, and a minimum function value is selected as an optimal solution. The sub-blocks are regarded as units to select the optimal possible solution, and the known space is shrunk; an illumination model of a transmitting object overlapping portion is brought up, the theoretical foundation for discrimination of the overlapping sub-blocks is provided; the designed energy functional is integrated with multiple characteristics of the cells, and therefore the selected optimal solution has the reasonability and the effectiveness; a brought up processing frame can be used as a common framework for segmenting the transmitting object overlapping portion.

Description

technical field [0001] The invention relates to the research field of image processing, in particular to a segmentation method for overlapping cells in cervical smear images. Background technique [0002] The incidence of cervical cancer is on the rise in recent years, and the age of patients tends to be younger. Early detection of cervical cancer is of great significance in reducing mortality. Currently, the most widely used techniques for producing cervical smears are Thinprep liquid-based cytologic test (TCT) and liquid-based cytologic test (LCT). At present, most hospitals use manual film reading, which is inefficient and easily affected by the subjective factors of the film reader, thereby reducing the accuracy of cervical smear screening. Using computer-aided diagnosis technology to process smears and replacing manual reading with machine reading not only improves the efficiency but also improves the accuracy rate, which is of great significance to the screening of c...

AI Technical Summary

Problems solved by technology

This segmentation method is not affected by color, even if cells of the same color overlap, effective segmentation results can be obtained, but the disadvantage is that the initial contour is difficult to determine, and the time efficiency is not high

Images