CN112504947A - Morphological analysis and counting method for peripheral blood cells - Google Patents
Morphological analysis and counting method for peripheral blood cells Download PDFInfo
- Publication number
- CN112504947A CN112504947A CN202011399853.9A CN202011399853A CN112504947A CN 112504947 A CN112504947 A CN 112504947A CN 202011399853 A CN202011399853 A CN 202011399853A CN 112504947 A CN112504947 A CN 112504947A
- Authority
- CN
- China
- Prior art keywords
- cells
- counting
- cell
- area
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 210000004976 peripheral blood cell Anatomy 0.000 title claims abstract description 17
- 238000004458 analytical method Methods 0.000 title claims abstract description 11
- 230000000877 morphologic effect Effects 0.000 title claims description 7
- 210000004027 cell Anatomy 0.000 claims abstract description 148
- 201000010099 disease Diseases 0.000 claims abstract description 26
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 26
- 238000004364 calculation method Methods 0.000 claims abstract description 16
- 230000011218 segmentation Effects 0.000 claims abstract description 14
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000001514 detection method Methods 0.000 claims abstract description 5
- 238000012098 association analyses Methods 0.000 claims abstract description 4
- 238000000926 separation method Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 238000000556 factor analysis Methods 0.000 claims description 5
- 101001094880 Arabidopsis thaliana Pectinesterase 4 Proteins 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000012986 modification Methods 0.000 claims description 2
- 230000004048 modification Effects 0.000 claims description 2
- 238000010191 image analysis Methods 0.000 abstract description 3
- 230000000717 retained effect Effects 0.000 abstract 1
- 210000000265 leukocyte Anatomy 0.000 description 5
- 210000005259 peripheral blood Anatomy 0.000 description 3
- 239000011886 peripheral blood Substances 0.000 description 3
- 238000004159 blood analysis Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 210000003714 granulocyte Anatomy 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 210000003651 basophil Anatomy 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000000601 blood cell Anatomy 0.000 description 1
- 210000001772 blood platelet Anatomy 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 210000000805 cytoplasm Anatomy 0.000 description 1
- 238000012303 cytoplasmic staining Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 210000003979 eosinophil Anatomy 0.000 description 1
- 210000003743 erythrocyte Anatomy 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000002055 immunohistochemical effect Effects 0.000 description 1
- 210000004698 lymphocyte Anatomy 0.000 description 1
- 210000001616 monocyte Anatomy 0.000 description 1
- 210000000440 neutrophil Anatomy 0.000 description 1
- 238000012758 nuclear staining Methods 0.000 description 1
- 230000007170 pathology Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000010186 staining Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/10—Investigating individual particles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/10—Investigating individual particles
- G01N2015/1006—Investigating individual particles for cytology
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/10—Investigating individual particles
- G01N2015/1022—Measurement of deformation of individual particles by non-optical means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/10—Investigating individual particles
- G01N2015/1024—Counting particles by non-optical means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30024—Cell structures in vitro; Tissue sections in vitro
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30242—Counting objects in image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Biochemistry (AREA)
- Pathology (AREA)
- Immunology (AREA)
- Analytical Chemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Dispersion Chemistry (AREA)
- Geometry (AREA)
- Investigating Or Analysing Biological Materials (AREA)
- Image Analysis (AREA)
Abstract
The invention belongs to the technical field of peripheral blood cell morphology detection, and particularly relates to a peripheral blood cell morphology analysis counting method, which comprises the following steps: s1: scanning a smear and preprocessing; s2: dividing a scanned image into a plurality of areas; s3: different cells are respectively set with different color value areas, and the color value distribution general of RGB three-color space of the counting area image is collected; s4: the a1 color value field in the count area is retained and the remaining pixels are set to black, resulting in a single a1 cell image b1 and stored, S5: respectively operating a C mean value clustering algorithm on the images, and segmenting the images; s6: counting cells of the image after the segmentation is finished; s7: and (3) obtaining data of various cells through calculation, comparing the data with a normal reference value, establishing association with the existing diseases, and performing association analysis. The method is used for solving the problem that the accuracy of the existing image analysis system for identifying and segmenting the overlapped cells is not high enough and often needs manual operation of a doctor for assistance.
Description
Technical Field
The invention belongs to the technical field of peripheral blood cell morphology detection, and particularly relates to a peripheral blood cell morphology analysis counting method.
Background
In peripheral blood samples, three types of tangible blood cells are contained: erythrocytes, leukocytes and platelets are classified into granulocytes, monocytes and lymphocytes according to the particles contained in the nucleus and the protoplasm, and granulocytes are classified into eosinophils, basophils and neutrophils according to the properties of the particles. The percentage of each kind of white blood cells and the total number of the whole white blood cells is an important item for peripheral blood examination, and after Reye's staining, the kinds of the white blood cells are distinguished according to the forms of nuclear staining, cytoplasmic staining, karyotype and the like of various mature white blood cells under a microscope.
Methods for qualitatively analyzing cell images through a microscope and by using a visual method and diagnosing the health condition of people have an important position in clinical pathology. With the development of computer technology, computer image processing and analyzing technology plays an increasingly important role in clinical diagnosis and treatment, a new image analyzing system is developed, immunohistochemical cell images are automatically processed by a computer for quantitative analysis, and doctors are assisted to make quick and accurate judgment, so that the method has an important application prospect in medical disease diagnosis.
However, the accuracy of the current image analysis system for identifying and segmenting the overlapped cells is not high enough, and manual operation of a doctor is often required for assistance.
Disclosure of Invention
In view of the above, the present invention provides a peripheral blood cell morphological analysis and counting method, which solves the problem that the image analysis system in the prior art is not high enough in accuracy of identifying and segmenting overlapped cells, and often needs manual operation of a doctor for assistance.
The invention solves the technical problems by the following technical means:
a peripheral blood cell morphology analysis counting method comprises the following steps:
s1: scanning the smear, and performing image preprocessing operation on the target; s2: dividing a scanned image into a plurality of regions, and randomly selecting a plurality of counting regions d1, d2 and d3 … … dn with the same size in the plurality of regions; s3: setting color value areas of A1, A2 and A3 … … An cells as a1, a2 and A3 … … An respectively, scanning a d1 counting area, and collecting color value distribution overview of RGB three-color space of An image in the counting area; s4: reserving a region of a1 color values in the counting region, setting the rest pixels of a2 and A3 … … an to be black, obtaining and storing a separate A1 cell image b1, and obtaining and storing b2 and b3 … … bn images in the same way; s5: and (3) running a C-means clustering algorithm on the RGB values of the images b1, b2 and b3 … … bn respectively to segment the images. Performing cell overlapping recognition on the segmented image, and performing cell overlapping segmentation if the segmented image is judged to be an overlapping cell; s6: counting the cells of the image after the segmentation is finished, counting the number of various cells in a d1 counting area, turning to S3, scanning a d2 counting area, counting until the dn counting area is finished, obtaining the total number c1 of A1 cells, the total numbers c2 and c3 … … cn of the rest various cells and the total area of the counting area, and obtaining the distribution ratio of the various cells through calculation; s7: and (3) obtaining data of various cells through calculation, comparing the data with a normal reference value, establishing association with the existing diseases, and performing association analysis.
Preferably, the method comprises the following steps: the method for identifying the cell overlap in the S5 comprises the following steps: b1: determining whether cells overlap by shape factor analysis, PE-4 pi A/L2Wherein A is the area of the judged cell and is obtained by judging the number of pixels in the cell; and L is the cell perimeter, the sum of the distances between adjacent pixels on the edge is used for representing, if the 8-adjacent-point distance d8 is adopted, the distances between 2 adjacent pixels fi, j and fm in the inclined direction are as follows:
the value range of the shape factor is 0< PE ≦ 1, when the image is judged to be close to a circle, the shape factor is close to 1, the threshold value P0 of the shape factor is determined, if PE > P0, the cell is judged not to be overlapped, and if PE < ═ P0, the cell is judged to be overlapped; b2: and calculating and extracting the number N of the core coordinates of the cells in the overlapped area and the core coordinates E of the whole overlapped area, further judging whether the cells are overlapped or not according to the number of the core coordinates N of the cells, and judging that the cells are not overlapped if N is less than 2.
Preferably, the method comprises the following steps: the cell overlap segmentation in the S5 comprises the following steps: c1: judging the concave-convex property of the peak of the overlapped cell image by a vector product method to obtain concave points; c2: according to the relation between the number of concave points N1 and the number of cell core coordinates N2, if N1 is equal to N2, the cells are judged to be in parallel, and if N1 is greater than N2, the cells are judged to be in series; c3: if the cells are connected in series, the pits in a pair are connected to the linear separation overlap region, and if the cells are connected in parallel, the pits and the core coordinates E of the overlap region are connected to the linear separation overlap region.
Preferably, the method comprises the following steps: when the cells are counted in the S6, A is used as the target amount of A1 cell counting, when A is larger than c1, the counting of the next counting area is carried out, and when A < ═ c1, the counting is stopped after counting of the counting area is completed.
Preferably, the method comprises the following steps: the preprocessing operation in S1 includes gray scale transformation, histogram modification, spatial filtering, and frequency filtering.
Preferably, the method comprises the following steps: the S7 comprises the following steps of D1: associating the data of various cells with the existing diseases in the database respectively; d2: comparing the similarity and the dissimilarity of each associated disease, and when the similarity is greater than the dissimilarity, classifying the disease into a suspected disease; d3: multiplying the similarity and the dissimilarity of the matched suspected diseases to finally obtain the similarity and the dissimilarity of the overall detection result on the diseases; d4: and (4) sorting the similarity from high to low, and completing the analysis of the data and the association with the disease.
Preferably, the method comprises the following steps: the method for calculating and extracting the number N of the core coordinates of the cells in the overlapping area and the core coordinates E of the whole overlapping area in the B2 comprises the following steps: the cell boundaries are eroded layer by a mathematical morphological method until being separated into single cells, and then the cores of the individual cells in the overlapped cell region are extracted.
The invention has the beneficial effects that:
1. according to the method, the image is divided into a plurality of regions, the cells in the regions are counted respectively, and when the C-means clustering algorithm is used for calculation, the calculation amount of single calculation is reduced, and the requirement on the calculation speed of a computer is relieved.
2. This application is different through the region of all kinds of cell RGB three-colour spatial colour values, stores calculation alone all kinds of cell images, interference between all kinds of cells when having avoided calculating.
3. Judging whether cells overlap or not by a shape factor analysis method, extracting the core coordinate number N of the cells in the overlapping area and the core coordinate E of the whole overlapping area, and further judging whether the cells overlap or not according to the number of the core coordinate number N of the cells.
4. The method comprises the steps of judging the concave-convex property of the top points of the overlapped cell images through a vector product method to obtain concave points, judging the overlapped type of the overlapped cells through the relation between the number of the concave points N1 and the number of cell core coordinates N2, connecting the concave points in pairs with the core coordinates E of the overlapped regions to form a straight line separating overlapped region if the cells are connected in parallel, and realizing the segmentation of the overlapped cells.
Drawings
FIG. 1 is a flow chart of a method for the morphological analysis and counting of peripheral blood cells according to the present invention;
FIG. 2 is a flow chart of the overlapping cell segmentation of the method for analyzing and counting the morphology of peripheral blood cells according to the present invention.
Detailed Description
The invention will be described in detail below with reference to the following figures and specific examples:
as shown in fig. 1-2, the method for analyzing and counting peripheral blood cell morphology according to the present invention comprises the following steps: s1: scanning smear, and performing image preprocessing operation on the target, wherein the preprocessing operation comprises gray scale transformation, histogram correction, spatial filtering and frequency filtering. S2: dividing a scanned image into a plurality of regions, and randomly selecting a plurality of counting regions d1, d2 and d3 … … dn with the same size in the plurality of regions; s3: setting color value areas of A1, A2 and A3 … … An cells as a1, a2 and A3 … … An respectively, scanning a d1 counting area, and collecting color value distribution overview of RGB three-color space of An image in the counting area; s4: reserving a region of a1 color values in the counting region, setting the rest pixels of a2 and A3 … … an to be black, obtaining and storing a separate A1 cell image b1, and obtaining and storing b2 and b3 … … bn images in the same way; s5: and (3) running a C-means clustering algorithm on the RGB values of the images b1, b2 and b3 … … bn respectively to segment the images. Performing cell overlapping recognition on the segmented image, and performing cell overlapping segmentation if the segmented image is judged to be an overlapping cell; s6: counting the cells of the image after the segmentation is finished, counting the number of various cells in a d1 counting area, turning to S3, scanning a d2 counting area, counting until the dn counting area is finished, obtaining the total number c1 of A1 cells, the total numbers c2 and c3 … … cn of the rest various cells and the total area of the counting area, and obtaining the distribution ratio of the various cells through calculation; s7: and (3) obtaining data of various cells through calculation, comparing the data with a normal reference value, establishing association with the existing diseases, and performing association analysis.
Cell overlap recognition in S5The method comprises the following steps: b1: determining whether cells overlap by shape factor analysis, PE-4 pi A/L2Wherein A is the area of the judged cell and is obtained by judging the number of pixels in the cell; and L is the cell perimeter, the sum of the distances between adjacent pixels on the edge is used for representing, if the 8-adjacent-point distance d8 is adopted, the distances between 2 adjacent pixels fi, j and fm in the inclined direction are as follows:
the value range of the shape factor is 0< PE ≦ 1, when the image is judged to be close to a circle, the shape factor is close to 1, the threshold value P0 of the shape factor is determined, if PE > P0, the cell is judged not to be overlapped, and if PE < ═ P0, the cell is judged to be overlapped; b2: and calculating and extracting the number N of the core coordinates of the cells in the overlapped area and the core coordinates E of the whole overlapped area, further judging whether the cells are overlapped or not according to the number of the core coordinates N of the cells, and judging that the cells are not overlapped if N is less than 2.
The method for cell overlap segmentation in S5 comprises: c1: judging the concave-convex property of the peak of the overlapped cell image by a vector product method to obtain concave points; c2: according to the relation between the number of concave points N1 and the number of cell core coordinates N2, if N1 is equal to N2, the cells are judged to be in parallel, and if N1 is greater than N2, the cells are judged to be in series; c3: if the cells are connected in series, the pits in a pair are connected to the linear separation overlap region, and if the cells are connected in parallel, the pits and the core coordinates E of the overlap region are connected to the linear separation overlap region.
In the cell counting in S6, a is set as a target amount of a1 cell counting, and when a > c1, the next counting area is counted, and when a < ═ c1, counting is stopped after counting of the counting area is completed.
S7 includes the steps of D1: associating the data of various cells with the existing diseases in the database respectively; d2: comparing the similarity and the dissimilarity of each associated disease, and when the similarity is greater than the dissimilarity, classifying the disease into a suspected disease; d3: multiplying the similarity and the dissimilarity of the matched suspected diseases to finally obtain the similarity and the dissimilarity of the overall detection result on the diseases; d4: and (4) sorting the similarity from high to low, and completing the analysis of the data and the association with the disease.
The method for calculating and extracting the number N of the core coordinates of the cells in the overlapping area and the core coordinates E of the whole overlapping area in the step B2 comprises the following steps: the cell boundaries are eroded layer by a mathematical morphological method until being separated into single cells, and then the cores of the individual cells in the overlapped cell region are extracted.
The invention takes 200 rows of peripheral blood examination pictures in the hospital as an example, the counting method is used for counting, the counting speed is far higher than the speed of manual examination according to the comparison index which is the data of physician oil-scope examination counting. And the segmentation effect on the overlapped cells and the accuracy are almost negligible compared with the manual test.
According to the method, the image is divided into a plurality of regions, the cells in the regions are counted respectively, and when the C-means clustering algorithm is used for calculation, the calculation amount of single calculation is reduced, and the requirement on the calculation speed of a computer is relieved. This application is different through the region of all kinds of cell RGB three-colour spatial colour values, stores all kinds of cell images alone and calculates, interference between all kinds of cells when having avoided calculating. The method judges whether cells overlap or not by a shape factor analysis method, extracts the cell core coordinate number N of an overlapping area and the core coordinate E of the whole overlapping area, and further judges whether the cells overlap or not according to the number of the cell core coordinate number N. The method comprises the steps of judging the concave-convex of the top point of an overlapped cell image through a vector product method to obtain concave points, judging the overlapped type of the overlapped cells through the relation between the number of the concave points N1 and the number N2 of core coordinates of the cells, connecting the concave points in pairs with the core coordinates E of the overlapped regions to form a straight line separation overlapped region if the cells are connected in parallel, and realizing the segmentation of the overlapped cells.
Although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted without departing from the spirit and scope of the invention as defined in the appended claims. The techniques, shapes, and configurations not described in detail in the present invention are all known techniques.
Claims (7)
1. A peripheral blood cell morphology analysis counting method is characterized by comprising the following steps:
s1: scanning the smear, and performing image preprocessing operation on the target;
s2: dividing a scanned image into a plurality of regions, and randomly selecting a plurality of counting regions d1, d2 and d3 … … dn with the same size in the plurality of regions;
s3: setting color value areas of A1, A2 and A3 … … An cells as a1, a2 and A3 … … An respectively, scanning a d1 counting area, and collecting color value distribution overview of RGB three-color space of An image in the counting area;
s4: reserving a region of a1 color values in the counting region, setting the rest pixels of a2 and A3 … … an to be black, obtaining and storing a separate A1 cell image b1, and obtaining and storing b2 and b3 … … bn images in the same way;
s5: and (3) running a C-means clustering algorithm on the RGB values of the images b1, b2 and b3 … … bn respectively to segment the images. Performing cell overlapping recognition on the segmented image, and performing cell overlapping segmentation if the segmented image is judged to be an overlapping cell;
s6: counting the cells of the image after the segmentation is finished, counting the number of various cells in a d1 counting area, turning to S3, scanning a d2 counting area, counting until the dn counting area is finished, obtaining the total number c1 of A1 cells, the total numbers c2 and c3 … … cn of the rest various cells and the total area of the counting area, and obtaining the distribution ratio of the various cells through calculation;
s7: and (3) obtaining data of various cells through calculation, comparing the data with a normal reference value, establishing association with the existing diseases, and performing association analysis.
2. The method for morphologically counting peripheral blood cells according to claim 1, wherein: the method for identifying the cell overlap in the S5 comprises the following steps:
b1: determining whether cells overlap by shape factor analysis, PE-4 pi A/L2Wherein A is the area of the judged cell and is obtained by judging the number of pixels in the cell; and L is the cell perimeter, the sum of the distances between adjacent pixels on the edge is used for representing, if the 8-adjacent-point distance d8 is adopted, the distances between 2 adjacent pixels fi, j and fm in the inclined direction are as follows:
the value range of the shape factor is 0< PE ≦ 1, when the image is judged to be close to a circle, the shape factor is close to 1, the threshold value P0 of the shape factor is determined, if PE > P0, the cell is judged not to be overlapped, and if PE < ═ P0, the cell is judged to be overlapped;
b2: and calculating and extracting the number N of the core coordinates of the cells in the overlapped area and the core coordinates E of the whole overlapped area, further judging whether the cells are overlapped or not according to the number of the core coordinates N of the cells, and judging that the cells are not overlapped if N is less than 2.
3. The method for morphologically counting peripheral blood cells according to claim 1, wherein: the cell overlap segmentation in the S5 comprises the following steps:
c1: judging the concave-convex property of the peak of the overlapped cell image by a vector product method to obtain concave points;
c2: according to the relation between the number of concave points N1 and the number of cell core coordinates N2, if N1 is equal to N2, the cells are judged to be in parallel, and if N1 is greater than N2, the cells are judged to be in series;
c3: if the cells are connected in series, the pits in a pair are connected to the linear separation overlap region, and if the cells are connected in parallel, the pits and the core coordinates E of the overlap region are connected to the linear separation overlap region.
4. The method for morphologically counting peripheral blood cells according to claim 1, wherein: when the cells are counted in the S6, A is used as the target amount of A1 cell counting, when A is larger than c1, the counting of the next counting area is carried out, and when A < ═ c1, the counting is stopped after counting of the counting area is completed.
5. The method for morphologically counting peripheral blood cells according to claim 1, wherein: the preprocessing operation in S1 includes gray scale transformation, histogram modification, spatial filtering, and frequency filtering.
6. The method for morphologically counting peripheral blood cells according to claim 1, wherein: the S7 includes the steps of:
d1: associating the data of various cells with the existing diseases in the database respectively;
d2: comparing the similarity and the dissimilarity of each associated disease, and when the similarity is greater than the dissimilarity, classifying the disease into a suspected disease;
d3: multiplying the similarity and the dissimilarity of the matched suspected diseases to finally obtain the similarity and the dissimilarity of the overall detection result on the diseases;
d4: and (4) sorting the similarity from high to low, and completing the analysis of the data and the association with the disease.
7. The method according to claim 2, wherein the method comprises: the method for calculating and extracting the number N of the core coordinates of the cells in the overlapping area and the core coordinates E of the whole overlapping area in the B2 comprises the following steps: the cell boundaries are eroded layer by a mathematical morphological method until being separated into single cells, and then the cores of the individual cells in the overlapped cell region are extracted.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011399853.9A CN112504947A (en) | 2020-12-03 | 2020-12-03 | Morphological analysis and counting method for peripheral blood cells |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011399853.9A CN112504947A (en) | 2020-12-03 | 2020-12-03 | Morphological analysis and counting method for peripheral blood cells |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112504947A true CN112504947A (en) | 2021-03-16 |
Family
ID=74968208
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011399853.9A Pending CN112504947A (en) | 2020-12-03 | 2020-12-03 | Morphological analysis and counting method for peripheral blood cells |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112504947A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114004851A (en) * | 2021-11-26 | 2022-02-01 | 广州市艾贝泰生物科技有限公司 | Cell image segmentation method and device and cell counting method |
CN115201092A (en) * | 2022-09-08 | 2022-10-18 | 珠海圣美生物诊断技术有限公司 | Method and device for acquiring cell scanning image |
CN116503859A (en) * | 2023-06-27 | 2023-07-28 | 成都云芯医联科技有限公司 | Data enhancement three-classification leukemia algorithm based on deep learning |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101639941A (en) * | 2009-01-13 | 2010-02-03 | 中国人民解放军军事医学科学院放射与辐射医学研究所 | Method for extracting binuclear lymphocyte accurately and quickly in CB method micronucleated cell image |
US20150111291A1 (en) * | 2012-07-05 | 2015-04-23 | Olympus Corporation | Cell division tracking apparatus and method of the same, and non-transitory computer readable storage medium to store a cell division tracking program |
CN105608694A (en) * | 2015-12-22 | 2016-05-25 | 苏州大学 | Retinal cell microscopic image segmentation and counting method |
CN107833200A (en) * | 2017-09-19 | 2018-03-23 | 浙江农林大学 | It is a kind of to detect the independent method and system with adhesion cardiac muscle cell's core region |
CN107909138A (en) * | 2017-11-14 | 2018-04-13 | 江苏大学 | A kind of class rounded grain thing method of counting based on Android platform |
CN109360198A (en) * | 2018-10-08 | 2019-02-19 | 北京羽医甘蓝信息技术有限公司 | Bone marrwo cell sorting method and sorter based on deep learning |
CN109959388A (en) * | 2019-04-09 | 2019-07-02 | 南京大学 | A kind of intelligent transportation fining paths planning method based on grid extended model |
CN110853017A (en) * | 2019-11-13 | 2020-02-28 | 常州工学院 | Method for counting number of round particles in powder particle image |
CN111832389A (en) * | 2020-05-25 | 2020-10-27 | 中国人民解放军陆军军医大学第二附属医院 | Counting and analyzing method of bone marrow cell morphology automatic detection system |
CN111833296A (en) * | 2020-05-25 | 2020-10-27 | 中国人民解放军陆军军医大学第二附属医院 | Automatic detection and verification system and method for bone marrow cell morphology |
-
2020
- 2020-12-03 CN CN202011399853.9A patent/CN112504947A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101639941A (en) * | 2009-01-13 | 2010-02-03 | 中国人民解放军军事医学科学院放射与辐射医学研究所 | Method for extracting binuclear lymphocyte accurately and quickly in CB method micronucleated cell image |
US20150111291A1 (en) * | 2012-07-05 | 2015-04-23 | Olympus Corporation | Cell division tracking apparatus and method of the same, and non-transitory computer readable storage medium to store a cell division tracking program |
CN105608694A (en) * | 2015-12-22 | 2016-05-25 | 苏州大学 | Retinal cell microscopic image segmentation and counting method |
CN107833200A (en) * | 2017-09-19 | 2018-03-23 | 浙江农林大学 | It is a kind of to detect the independent method and system with adhesion cardiac muscle cell's core region |
CN107909138A (en) * | 2017-11-14 | 2018-04-13 | 江苏大学 | A kind of class rounded grain thing method of counting based on Android platform |
CN109360198A (en) * | 2018-10-08 | 2019-02-19 | 北京羽医甘蓝信息技术有限公司 | Bone marrwo cell sorting method and sorter based on deep learning |
CN109959388A (en) * | 2019-04-09 | 2019-07-02 | 南京大学 | A kind of intelligent transportation fining paths planning method based on grid extended model |
CN110853017A (en) * | 2019-11-13 | 2020-02-28 | 常州工学院 | Method for counting number of round particles in powder particle image |
CN111832389A (en) * | 2020-05-25 | 2020-10-27 | 中国人民解放军陆军军医大学第二附属医院 | Counting and analyzing method of bone marrow cell morphology automatic detection system |
CN111833296A (en) * | 2020-05-25 | 2020-10-27 | 中国人民解放军陆军军医大学第二附属医院 | Automatic detection and verification system and method for bone marrow cell morphology |
Non-Patent Citations (2)
Title |
---|
傅蓉: "细胞重叠与融合性图像的分离与分割技术研究", 《中国优秀博硕士学位论文全文数据库(博士) 医药卫生科技辑》 * |
马小薇: "基于压缩感知的OMP图像重构算法改进", 《电子科技》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114004851A (en) * | 2021-11-26 | 2022-02-01 | 广州市艾贝泰生物科技有限公司 | Cell image segmentation method and device and cell counting method |
CN115201092A (en) * | 2022-09-08 | 2022-10-18 | 珠海圣美生物诊断技术有限公司 | Method and device for acquiring cell scanning image |
CN116503859A (en) * | 2023-06-27 | 2023-07-28 | 成都云芯医联科技有限公司 | Data enhancement three-classification leukemia algorithm based on deep learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112070772B (en) | Blood leukocyte image segmentation method based on UNet++ and ResNet | |
CN112504947A (en) | Morphological analysis and counting method for peripheral blood cells | |
CN102682305B (en) | Automatic screening system and automatic screening method using thin-prep cytology test | |
Mohapatra et al. | Automated leukemia detection using hausdorff dimension in blood microscopic images | |
Jitpakdee et al. | A survey on hemorrhage detection in diabetic retinopathy retinal images | |
CN110120056B (en) | Blood leukocyte segmentation method based on adaptive histogram threshold and contour detection | |
Mohapatra et al. | Automated leukemia detection in blood microscopic images using statistical texture analysis | |
CN103020639A (en) | Method for automatically identifying and counting white blood cells | |
Alreza et al. | Design a new algorithm to count white blood cells for classification leukemic blood image using machine vision system | |
CN111476754B (en) | Bone marrow cell image artificial intelligence auxiliary grading diagnosis system and method | |
CN110148126B (en) | Blood leukocyte segmentation method based on color component combination and contour fitting | |
CN114283407A (en) | Self-adaptive automatic leukocyte segmentation and subclass detection method and system | |
CN109886346A (en) | A kind of cardiac muscle MRI image categorizing system | |
Angulo et al. | Ontology-based lymphocyte population description using mathematical morphology on colour blood images | |
KR20010017092A (en) | Method for counting and analyzing morphology of blood cell automatically | |
Barpanda | Use of image processing techniques to automatically diagnose sickle-cell anemia present in red blood cells smear | |
KR20200136004A (en) | Method for detecting cells with at least one malformation in a cell sample | |
Anderson et al. | The use of an automated image cytometer for screening and quantitative assessment of cervical lesions in the British Columbia Cervical Smear Screening Programme | |
Priyankara et al. | An extensible computer vision application for blood cell recognition and analysis | |
CN111311628A (en) | Full-automatic high-performance leukocyte segmentation method | |
Arunachalam | Applications of Machine learning and Image processing techniques in the detection of leukemia | |
Nithya et al. | Detection of Anaemia using Image Processing Techniques from microscopy blood smear images | |
CN113052806B (en) | Canceration degree grading system | |
CN112951427B (en) | System for classifying abnormal cells | |
Chitra et al. | Detection of aml in blood microscopic images using local binary pattern and supervised classifier |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210316 |