White blood cell image processing method and system based on connected area subtraction

Abstract

The invention belongs to the technical field of basic laboratory science, and discloses a white blood cell image processing method and system based on the subtraction of connected area. Each individual connected area forms an identified block for marking white pixels in a binary image. After the connected region is marked, the area of each connected region is obtained, and the connected region whose area is less than a certain value is deleted by using the MATLAB function bwareaopen. In the original image of granular and non-granular leukocytes, a classic and useful image segmentation method-Dam algorithm is utilized, i. e. Watershed, divides and counts non-granular leukocytes, removes the non-granular leukocytes from the original image using the function imsubtract to obtain an image containing only granular leukocytes, and divides the total granular leukocyte area by the average area to obtain the granular leukocyte count. The invention can clearly distinguish granular leukocyte fromnon-granular leukocyte, has clear image and accurate counting.

Description

technical field [0001] The invention belongs to the technical field of basic laboratory science, and in particular relates to a white blood cell image processing method and system based on connected area subtraction. Background technique [0002] At present, the existing technologies commonly used in the industry are as follows: [0003] White blood cells are colorless nucleated cells, neutrophils, eosinophils, basophils, lymphocytes and monocytes are commonly found in normal peripheral blood. White blood cells are a very important type of blood cells in human blood. White blood cells take on many important tasks in the human body. They have the functions of phagocytizing foreign bodies and producing antibodies, the ability to heal body damage, the ability to resist pathogen invasion, and immune resistance to diseases. In fact, white blood cells can also be subdivided into five types. Using instruments or manual methods to count these five types of cells separately is call...

AI Technical Summary

Problems solved by technology

[0006] (1) Directly use the watershed algorithm for segmentation and counting, the counting accuracy is not high, especially the cells with very serious adhesion cannot be segmented, and it is easy to cause over-segmentation

[0007] (2) The existing technology can only calculate the total number of cells, but cannot classify and count white blood cells, and cannot clearly distinguish granular white blood cells from agranular white blood cells;

[0008] (3) Without the complete program code, the user cannot directly extract the test and obtain the final segmentation and counting effect

[0011] 1: The counting accuracy is not high, especially the cells with severe adhesion cannot be segmented, and it is easy to cause over-segmentation

[0012] 2: Only the total number of cells can be calculated, and white blood cells cannot be classified and counted. Such counts can only be used for study and research, not for clinical practice

[0013] 3: Without the complete program code, the user cannot directly extract the test and obtain the final segmentation and counting effect

Images