CN111583227A - Method, device, equipment and medium for automatically counting fluorescent cells - Google Patents
Method, device, equipment and medium for automatically counting fluorescent cells Download PDFInfo
- Publication number
- CN111583227A CN111583227A CN202010382639.6A CN202010382639A CN111583227A CN 111583227 A CN111583227 A CN 111583227A CN 202010382639 A CN202010382639 A CN 202010382639A CN 111583227 A CN111583227 A CN 111583227A
- Authority
- CN
- China
- Prior art keywords
- image
- cells
- illumination
- fluorescent
- cell
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000005286 illumination Methods 0.000 claims abstract description 86
- 238000001914 filtration Methods 0.000 claims abstract description 30
- 239000012535 impurity Substances 0.000 claims abstract description 19
- 230000002708 enhancing effect Effects 0.000 claims abstract description 9
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 238000009499 grossing Methods 0.000 claims abstract description 8
- 230000006870 function Effects 0.000 claims description 44
- 239000011159 matrix material Substances 0.000 claims description 34
- 230000008569 process Effects 0.000 claims description 26
- 239000003550 marker Substances 0.000 claims description 24
- 238000012545 processing Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 15
- 230000011218 segmentation Effects 0.000 claims description 13
- 238000013507 mapping Methods 0.000 claims description 12
- 230000001965 increasing effect Effects 0.000 claims description 11
- 238000003708 edge detection Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 8
- 230000001464 adherent effect Effects 0.000 claims description 7
- 238000012937 correction Methods 0.000 claims description 7
- 238000005516 engineering process Methods 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 7
- 238000009826 distribution Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 5
- 230000004048 modification Effects 0.000 claims description 5
- 238000012986 modification Methods 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 5
- 230000003044 adaptive effect Effects 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 210000004027 cell Anatomy 0.000 description 136
- 238000010586 diagram Methods 0.000 description 15
- 230000000694 effects Effects 0.000 description 5
- 241001270131 Agaricus moelleri Species 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 230000026683 transduction Effects 0.000 description 4
- 238000010361 transduction Methods 0.000 description 4
- 241000702421 Dependoparvovirus Species 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007797 corrosion Effects 0.000 description 2
- 238000005260 corrosion Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000010339 dilation Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 206010028980 Neoplasm Diseases 0.000 description 1
- 201000011510 cancer Diseases 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 210000002865 immune cell Anatomy 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000001000 micrograph Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011369 optimal treatment Methods 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- 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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10056—Microscopic image
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20172—Image enhancement details
- G06T2207/20192—Edge enhancement; Edge preservation
-
- 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
-
- 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)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Quality & Reliability (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Image Processing (AREA)
- Investigating, Analyzing Materials By Fluorescence Or Luminescence (AREA)
Abstract
The invention provides a method, a device, equipment and a medium for automatically counting fluorescent cells, wherein the method comprises the steps of S1, reading microscopic images of the fluorescent cells; s2, preprocessing the microscopic image of the fluorescent cell, including correcting the uneven illumination of the microscopic image and enhancing the contrast between the cell and the background in the microscopic image; filtering out microscopic image noise by adopting median filtering, and keeping detail information of image edges; removing microscopic image noise and background impurities by adopting open operation, smoothing the outline of cells, breaking the narrow connection of the cells and removing the small protruding part of the cells; step S3, dividing the fluorescent cells adhered on the microscopic image, and taking the adhered cell group as a cell when avoiding cell counting; and step S4, calculating the number of the fluorescent cells. The invention can meet the requirements of most laboratories in terms of efficiency, accuracy and cost.
Description
Technical Field
The invention relates to the technical field of cell counting in biomedicine, in particular to a method, a device, equipment and a medium for automatically counting fluorescent cells.
Background
Cell counting is a routine operation in biomedical experiments and plays an important role in basic research. For example, researchers can study the transduction efficiency of recombinant adeno-associated virus (rAAV) by the number of fluorescent hela cells; doctors can accurately judge the cancer stage of patients according to the number change of some specific immune cells in the pathological tissues and make an optimal treatment scheme. Currently, cell counting techniques are in great demand and widely used in the biomedical field, but the counting efficiency and accuracy are in need of further improvement.
Manual cell counting under the traditional microscope not only consumes time, and is low in efficiency and high in labor intensity, but also is easy to cause large errors due to subjective factors of experimenters. Furthermore, if the counting process is interrupted, it must be restarted, which puts a great strain on the experimenter. Of course, hardware solutions may be chosen to solve the counting problem, such as automatic hematology counters, but these hardware devices are expensive and not equipped by many laboratories.
At present, the widely used flow cytometer changes the spatial position of the cell sample in the counting process, which is not beneficial to the research of some cell dynamics, and still needs a large amount of manual processing work before the cell sample enters the flow cytometer, so that the overall cell counting efficiency is limited. Therefore, there is a need to develop a technical solution for improving the efficiency and accuracy of cell counting.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a method, a device, a system, equipment and a medium for automatically counting fluorescent cells, which overcome the defects of low efficiency and large error of manual cell counting and can replace the expensive automatic hematology counter at lower cost, thereby meeting the requirements of most laboratories on efficiency, accuracy and cost.
In a first aspect, the present invention provides a method for automatically counting fluorescent cells, comprising the following steps:
step S1, reading a microscopic image of the fluorescent cell;
step S2, preprocessing the microscopic image of the fluorescent cell, which specifically comprises the following steps:
step S21, correcting uneven illumination of the microscopic image, reducing the brightness value of the image edge over-illumination area, and increasing the brightness value of the image middle over-illumination dark area until the fluorescent cells in the image edge over-illumination area and the image middle over-illumination dark area are highlighted;
step S22, enhancing the contrast ratio of the cells and the background in the microscopic image;
s23, filtering out microscopic image noise by adopting median filtering, and keeping detail information of image edges;
step S24, removing microscopic image noise and background impurities by using open operation, smoothing cell contour, breaking narrow connection of cells and removing small protruding parts of cells;
step S3, segmenting the fluorescent cells adhered on the microscopic image;
and step S4, calculating the number of the fluorescent cells.
In a second aspect, the present invention provides an automatic counting device for fluorescent cells, comprising:
the reading module is used for reading a microscopic image of the fluorescent cell;
the pretreatment module is used for pretreating the microscopic image of the fluorescent cell, and specifically comprises:
the correcting illumination unit is used for correcting uneven illumination of the microscopic image, reducing the brightness value of an image edge over-illumination area, and improving the brightness value of an image middle over-illumination dark area until fluorescent cells in the image edge over-illumination area and the image middle over-illumination dark area are highlighted;
the contrast enhancement unit is used for enhancing the contrast of the cells and the background in the microscopic image;
the noise filtering unit is used for filtering the noise of the microscopic image by adopting median filtering and retaining the detail information of the image edge;
the impurity removing unit is used for removing microscopic image noise and background impurities by adopting open operation, smoothing the outline of cells, breaking the narrow connection of the cells and removing the small protruding part of the cells;
the segmentation module is used for segmenting the fluorescent cells adhered to the microscopic image;
and the counting module is used for counting the number of the fluorescent cells.
In a third aspect, the present invention provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of the first aspect when executing the program.
In a fourth aspect, the invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the method of the first aspect.
One or more technical solutions provided in the embodiments of the present invention have at least the following technical effects or advantages: through an image processing technology, the microscopic image of the fluorescent cell is reasonably processed, particularly in the preprocessing, the brightness value of an image edge over-illumination area is reduced by correcting the uneven illumination of the microscopic image, and the brightness value of an image middle over-illumination dark area is improved, so that the fluorescent cell in the image edge over-illumination area and the image middle over-illumination dark area is highlighted; contrast between the fluorescent cells and the background in the image is enhanced by adopting contrast linear broadening; median filtering is selected to remove noise of the image, and edge detail information of the image is effectively protected; removing microscopic image noise and background impurities by adopting opening operation, smoothing the outline of cells, breaking the narrow connection of the cells and removing the small protruding part of the cells; the method is favorable for subsequently segmenting the fluorescent cells adhered to the microscopic image by using a marker watershed algorithm, can greatly improve the accuracy of counting the fluorescent cells in the microscopic cell image, automatically and quickly calculates the number of the cells in the image by traversing and marking the image matrix connected domain in the aspect of cell counting, shortens the manual counting time, reduces the labor intensity of manual counting, reduces the use cost at the same time, and has great significance for some basic scientific research works of biomedicine.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
The invention will be further described with reference to the following examples with reference to the accompanying drawings.
FIG. 1 is a flow chart of a method according to one embodiment of the present invention;
FIG. 2 is a schematic representation of a fluorescent Hela cell micrograph of the present invention;
FIG. 3 is a schematic diagram of correcting for uneven illumination of an image according to the present invention;
FIG. 4 is a schematic illustration of image contrast enhancement in the present invention;
FIG. 5 is a diagram illustrating median filtering to remove noise in the present invention;
FIG. 6 is a schematic diagram of background impurity and noise removal by the open operation of the present invention;
FIG. 7 is a schematic representation of watershed-segmented adherent cells according to the invention;
FIG. 8 is a diagram showing the results of fluorescent Hela cell counting according to the present invention;
FIG. 9 is a schematic structural diagram of an apparatus according to a second embodiment of the present invention;
fig. 10 is a schematic structural diagram of an electronic device according to a third embodiment of the invention;
fig. 11 is a schematic structural diagram of a medium according to a fourth embodiment of the present invention.
Detailed Description
The embodiment of the application overcomes the defects of low efficiency and large error of manual cell counting by providing a method, a device, equipment and a medium for automatically counting fluorescent cells, and can replace the expensive automatic hematology counter at present at lower cost, thereby meeting the requirements of most laboratories on efficiency, accuracy and cost.
The technical scheme in the embodiment of the application has the following general idea: through an image processing technology, the microscopic image of the fluorescent cell is reasonably processed, particularly in the preprocessing, the brightness value of the area with over-strong illumination at the edge of the image is reduced by correcting the uneven illumination of the microscopic image, and the brightness value of the area with over-dark illumination in the middle of the image is improved, so that the fluorescent cell in the area with over-strong illumination at the edge of the image and the area with over-dark illumination in the middle of the image is highlighted, the noise and background impurities of the microscopic image are removed by adopting open operation, the outline of the cell is smoothed, the narrow connection of the cell is disconnected, and the small protruding part of the cell is removed; therefore, the method is beneficial to subsequently segmenting the fluorescent cells adhered to the microscopic image, can greatly improve the accuracy of counting the fluorescent cells in the microscopic image, shortens the manual counting time, reduces the labor intensity of manual counting, reduces the use cost, and has great significance for some basic scientific research works of biomedicine.
Example one
This embodiment provides a method for automatically counting fluorescent cells, as shown in fig. 1, comprising the following steps:
step S1, reading a microscopic image of the fluorescent cell;
step S2, preprocessing the microscopic image of the fluorescent cell, which specifically comprises the following steps:
step S3, segmenting the fluorescent cells adhered on the microscopic image;
and step S4, calculating the number of the fluorescent cells.
The preprocessing of step S2 specifically includes:
step S21, correcting uneven illumination of the microscopic image, reducing the brightness value of the image edge over-illumination area, and increasing the brightness value of the image middle over-illumination dark area until the fluorescent cells in the image edge over-illumination area and the image middle over-illumination dark area are highlighted;
step S22, enhancing the contrast ratio of the cells and the background in the microscopic image;
s23, filtering out microscopic image noise by adopting median filtering, and keeping detail information of image edges;
step S24, removing microscopic image noise and background impurities by using open operation, smoothing cell contour, breaking narrow connection of cells and removing small protruding parts of cells;
in the process of acquiring images by a microscope, the cells have different fluorescence expression amounts under the influence factors of different concentrations of culture solutions, different culture times and the like. Generally, the transduction rate of the recombinant adeno-associated virus (rAAV) is gradually increased with the increase of the culture time before the transduction rate reaches the maximum transduction efficiency, that is, the fluorescence expression of the cells is gradually increased with the increase of the culture time; in the experimental process, due to the interaction among cells, the distribution states of cells in different visual fields are completely different, so that the distribution positions of fluorescent cells in the images are different; of course, the spatial resolution caused by the artifacts, scattering and autofluorescence of the fluorescent cells also has a great influence on image acquisition; in addition, some internal hardware of the microscope and other devices inevitably causes certain interference to the image acquisition process, so that the acquired cell image is prone to illumination unevenness. Taking hela cells as an example, the fluorescence hela cell image is shown in fig. 2, and important detail information of a partial region (such as the upper right corner) in the image is easily lost, which seriously affects the image effect and the accuracy of cell counting. Further, the step S21 of correcting the uneven illumination of the image through the gamma function specifically includes the following steps:
step 211, firstly, converting the fluorescent cell image from an RGB color space to an HSV color space by the formula (1);
step 212, extracting the illumination component of the fluorescent cell image by using a multi-scale Gaussian function, wherein the extraction process is shown as formula (2),
wherein: l (x, y) is an illumination component; f (x, y) is the illumination brightness of the input image; g (x, y) is a Gaussian function; n is the degree of the ruler; w is aiExtracting a weight coefficient of the illumination component for the ith Gaussian function;
the gaussian function is defined as follows:
wherein ξ is a normalization constant, b is a scale factor of the Gaussian function, in specific implementation, the scale number N of the Gaussian function is 3, 3 scale factors are respectively set as 15, 80 and 220, and the weight of each scale for extracting the illumination component is wi＝1/3。
Step 213, constructing a gamma function according to the distribution characteristics of the illumination components, and performing adaptive correction processing on the uneven illumination of the image, wherein the expression of the gamma function is as follows:
wherein, Q (x, y) is a gamma function, beta is a brightness enhancement index, and is determined by the illumination component and the brightness mean value n of the illumination component;
step 214, recombining the HSV image corrected by the gamma function into an RGB image through a formula (5);
step 215, outputting the corrected RGB image of the fluorescent cell.
In the embodiment of the present invention, after the gamma function is corrected, the brightness value of the area with too strong illumination at the edge of the image is reduced, the brightness value of the area with too dark illumination in the middle of the image is increased, and the correction result of the cell image with uneven illumination is shown in fig. 3, especially the upper right corner, because the brightness value is reduced, the outline of the cell is highlighted, and the brightness values of the rest parts are increased, so that the outline of the cell is highlighted as well.
The step S22 specifically includes:
mapping the gray scale in the range of (0, f (a)) in the read-in fluorescence Hela cell image into the range of (0, g (b)) by adopting a contrast linear broadening method; mapping the gray scales in the range of the fluorescent cells (f), (a), f (b)) to the range of (g), (a), g (b)); mapping the gray scales in the range of (f), (b) and (255) to the range of (g), (b) and (255) to realize contrast enhancement of the fluorescence Hela cell image; the gray value mapping process is shown in formula (4):
wherein the content of the first and second substances,
α, β and gamma denote the mapping coefficients, respectively, f (i, j) denotes the gray-scale value of the image, g (i, j) denotes the gray-scale value of the image after image enhancement, in the specific embodiment of the present invention, f (a), f (b), g (a) and g (b) are 30, 80, 60 and 180, respectively.
Then, by drawing a gray histogram of the image, setting an image enhancement threshold T, setting the gray value of the image smaller than T as 0, and keeping the gray value of the image larger than or equal to T unchanged, the image enhancement is as shown in formula (7) in the process of enhancing the contrast between the cells and the background in the image:
in an embodiment of the present invention, the result of image contrast enhancement through contrast linear stretching and thresholding is shown in fig. 4.
The step S23 specifically includes:
adopting median filtering, namely selecting the median of gray values of each point in a neighborhood to replace the gray values of surrounding pixels according to the sorting result of the gray values in the neighborhood of a certain pixel point (p), so as to filter image noise, wherein the median replacing process is shown as a formula (8):
wherein p isnIn the embodiment of the invention, an image subjected to median filtering to remove noise is shown in FIG. 5, wherein the image is subjected to median filtering, and the operation is performed by adopting a square window of 3 × 3.
The step S24 specifically includes:
and removing image noise and background impurities by adopting an opening operation. The opening operation is a processing process of firstly corroding and then expanding the image through a structural element, and can delete an object region which cannot contain the structural element, so as to smooth the cell contour, break the narrow connection of the cell and remove the small protruding part of the cell. When the opening operation processing is performed on the cell image, in view of the fact that the shape of the hela cell is mostly circular or elliptical, the invention defines the structural element as a circular disc with the radius of 3 to process the image. The open operation is represented by the following formula:
wherein F is the image to be processed, A is a structural element, ⊙ represents corrosion operation,
indicating the dilation operation. In the embodiment of the present invention, an image with noise and background impurities removed by the on operation processing is shown in fig. 6.
The step S3 specifically includes:
s31, when the marker watershed algorithm is controlled to segment the adherent cells, edge detection is carried out through a Sobel operator to obtain a gradient image;
image edge detection is defined as follows:
wherein I is the original microscopic cell image, GxAnd GyThe derivative values of a certain point in the image in the x direction and the y direction are respectively, and G is the gradient corresponding to the certain point.
Step S32, the Euclidean distance conversion is carried out on the image, and the external marker, the boundary pixel (x) in the Euclidean distance is extractedn,yn) And region pixel (x)0,y0) The minimum neighborhood distance between them is calculated as follows:
step S33, then determining a local minimum region of the image, setting a threshold h to expand the local minimum region of the image, and implementing extraction of the internal marker, where the threshold h is defined as follows:
wherein: m is0Representing a gradient image mean; m is1Means representing local minima of the gradient image; m is2Means representing local maxima of the gradient image; m is2-m1Representing the average depth of the catchment basin;
step S34, after obtaining the internal marker and the external marker, modifying the image gradient by using a forced minimum technology, eliminating irrelevant local minimum areas, and modifying the result of distance change to ensure that the local minimum areas only appear at expected positions;
s35, finally, performing watershed transformation on the image after gradient modification to find a watershed ridge line, and overlapping the watershed ridge line on the original image to realize the segmentation of the adhesion cells;
in this embodiment, the results of segmenting adherent cells based on marker watershed are shown in FIG. 7.
The step S4 specifically includes:
traversing a matrix corresponding to the image after the watershed segmentation, marking different connected domains in the matrix, recording the number of the connected domains by using a variable Num, wherein the finally obtained total connected domain value Num is the number of the fluorescent cells, and the automatic counting process of the fluorescent cells is as follows:
step 41, initializing a connected domain mark variable mark to be 1, and initializing a connected domain numerical variable Num to be 0;
step 42, traversing the elements of a in the matrix in sequence, and when encountering the matrix element aijWhen the number is 1, judging whether the element is marked by a connected domain mark variable mark, if the element is marked, scanning aijOther elements in the eight neighborhood; if not marked, assigning a mark value to the element A at the corresponding position in the mark matrix AijMarking and marking the element aijThe coordinate values of the corresponding pixel points are stored in a queue ary;
step 43, followed by element aijContinuously traversing the elements in the eight neighborhoods as the center, judging whether the element is marked when detecting that a certain element in the eight neighborhoods is 1, if not, marking in the mark matrix A by using a connected domain mark variable mark in the same way, and storing the coordinate value of the pixel point corresponding to the element in a queue ary;
step 44, matrix element aijAnd after eight neighborhoods are scanned and marked, the next element a is carried outi，j+1And eight neighborhood scanning and marking thereof;
step 45, when one connected domain is marked, the total connected domain Num and the mark variable mark are increased by 1, the queue is emptied, and a new connected domain is marked;
and step 46, circularly traversing the matrix of the whole binary image in such a way until all connected domains are marked, wherein the finally returned total connected domain value Num is the number of the image cells. The effect of counting the fluorescent cells is shown in fig. 8, the number of circles drawn in the figure is the counted number of the fluorescent cells, and compared with the actual number, the accuracy rate is more than 90%.
Based on the same inventive concept, the application also provides a device corresponding to the method in the first embodiment, which is detailed in the second embodiment.
Example two
As shown in fig. 9, in the present embodiment, there is provided an automatic counting apparatus for fluorescent cells, comprising:
the reading module is used for reading a microscopic image of the fluorescent cell;
the pretreatment module is used for pretreating the microscopic image of the fluorescent cell, and specifically comprises:
the segmentation module is used for segmenting the fluorescent cells adhered to the microscopic image;
and the counting module is used for counting the number of the fluorescent cells.
Wherein the preprocessing module further comprises:
the correcting illumination unit is used for correcting uneven illumination of the microscopic image, reducing the brightness value of an image edge over-illumination area, and improving the brightness value of an image middle over-illumination dark area until fluorescent cells in the image edge over-illumination area and the image middle over-illumination dark area are highlighted;
the contrast enhancement unit is used for enhancing the contrast of the cells and the background in the microscopic image;
the noise filtering unit is used for filtering the noise of the microscopic image by adopting median filtering and retaining the detail information of the image edge;
the impurity removing unit is used for removing microscopic image noise and background impurities by adopting open operation, smoothing the outline of cells, breaking the narrow connection of the cells and removing the small protruding part of the cells;
further, the correction illumination unit specifically executes the following processes:
step 211, firstly, converting the fluorescent cell image from an RGB color space to an HSV color space by the formula (1);
step 212, extracting the illumination component of the fluorescent cell image by using a multi-scale Gaussian function, wherein the extraction process is shown as formula (2),
wherein: l (x, y) is an illumination component; f (x, y) is the illumination brightness of the input image; g (x, y) is a Gaussian function; n is the degree of the ruler; w is aiExtracting a weight coefficient of the illumination component for the ith Gaussian function;
the gaussian function is defined as follows:
where ξ is a normalization constant and b is a scale factor of a Gaussian function;
step 213, constructing a gamma function according to the distribution characteristics of the illumination components, and performing adaptive correction processing on the uneven illumination of the image, wherein the expression of the gamma function is as follows:
wherein, Q (x, y) is a gamma function, beta is a brightness enhancement index, and is determined by the illumination component and the brightness mean value n of the illumination component;
step 214, recombining the HSV image corrected by the gamma function into an RGB image through a formula (5);
step 215, outputting the corrected RGB image of the fluorescent cell.
The contrast enhancement unit is specifically:
mapping the gray scale in the range of (0, f (a)) in the read-in fluorescence Hela cell image into the range of (0, g (b)) by adopting a contrast linear broadening method; mapping the gray scales in the range of the fluorescent cells (f), (a), f (b)) to the range of (g), (a), g (b)); mapping the gray scales in the range of (f), (b) and (255) to the range of (g), (b) and (255) to realize contrast enhancement of the fluorescence Hela cell image; the gray value mapping process is shown in formula (4):
wherein the content of the first and second substances,
α, β and gamma denote the mapping coefficients, respectively, f (i, j) denotes the gray-scale value of the image, g (i, j) denotes the gray-scale value of the image after image enhancement, in the specific embodiment of the present invention, f (a), f (b), g (a) and g (b) are 30, 80, 60 and 180, respectively.
Then, by drawing a gray histogram of the image, setting an image enhancement threshold T, setting the gray value of the image smaller than T as 0, and keeping the gray value of the image larger than or equal to T unchanged, the image enhancement is as shown in formula (7) in the process of enhancing the contrast between the cells and the background in the image:
in an embodiment of the present invention, the result of image contrast enhancement through contrast linear stretching and thresholding is shown in fig. 4.
The noise filtering unit specifically comprises:
adopting median filtering, namely selecting the median of gray values of each point in a neighborhood to replace the gray values of surrounding pixels according to the sorting result of the gray values in the neighborhood of a certain pixel point (p), so as to filter image noise, wherein the median replacing process is shown as a formula (8):
wherein p isnIn the embodiment of the invention, an image subjected to median filtering to remove noise is shown in FIG. 5, wherein the image is subjected to median filtering, and the operation is performed by adopting a square window of 3 × 3.
The impurity removing unit is specifically as follows: and removing image noise and background impurities by adopting an opening operation. The opening operation is a processing process of firstly corroding and then expanding the image through a structural element, and can delete an object region which cannot contain the structural element, so as to smooth the cell contour, break the narrow connection of the cell and remove the small protruding part of the cell. When the opening operation processing is performed on the cell image, in view of the fact that the shape of the hela cell is mostly circular or elliptical, the invention defines the structural element as a circular disc with the radius of 3 to process the image. The open operation is represented by the following formula:
wherein F is the image to be processed, A is a structural element, ⊙ represents corrosion operation,
indicating the dilation operation. In the embodiment of the present invention, the image after the noise and background impurities are removed by the opening operation processing is shown in fig. 6 in the specification.
The segmentation module specifically executes the following processes:
s31, when the marker watershed algorithm is controlled to segment the adherent cells, edge detection is carried out through a Sobel operator to obtain a gradient image;
image edge detection is defined as follows:
wherein I is the original microscopic cell image, GxAnd GyThe derivative values of a certain point in the image in the x direction and the y direction are respectively, and G is the gradient corresponding to the certain point.
Step S32, the Euclidean distance conversion is carried out on the image, and the external marker, the boundary pixel (x) in the Euclidean distance is extractedn,yn) And region pixel (x)0,y0) The minimum neighborhood distance between them is calculated as follows:
step S33, then determining a local minimum region of the image, setting a threshold h to expand the local minimum region of the image, and implementing extraction of the internal marker, where the threshold h is defined as follows:
wherein: m is0Representing a gradient image mean; m is1Means representing local minima of the gradient image; m is2Means representing local maxima of the gradient image; m is2-m1Representing the average depth of the catchment basin;
step S34, after obtaining the internal marker and the external marker, modifying the image gradient by using a forced minimum technology, eliminating irrelevant local minimum areas, and modifying the result of distance change to ensure that the local minimum areas only appear at expected positions;
s35, finally, performing watershed transformation on the image after gradient modification to find a watershed ridge line, and overlapping the watershed ridge line on the original image to realize the segmentation of the adhesion cells;
in this embodiment, the results of segmenting adherent cells based on marker watersheds are shown in FIG. 7.
The counting module specifically executes the following processes:
traversing a matrix corresponding to the image after the watershed segmentation, marking different connected domains in the matrix, recording the number of the connected domains by using a variable Num, wherein the finally obtained total connected domain value Num is the number of the fluorescent cells, and the automatic counting process of the fluorescent cells is as follows:
step 41, initializing a connected domain mark variable mark to be 1, and initializing a connected domain numerical variable Num to be 0;
step 42, traversing the elements of a in the matrix in sequence, and when encountering the matrix element aijWhen the number is 1, judging whether the element is marked by a connected domain mark variable mark, if the element is marked, scanning aijOther elements in the eight neighborhood; if not marked, assigning a mark value to the element A at the corresponding position in the mark matrix AijMarking and marking the element aijThe coordinate values of the corresponding pixel points are stored in a queue ary;
step 43, followed by element aijContinuously traversing the elements in the eight neighborhoods as the center, judging whether the element is marked when detecting that a certain element in the eight neighborhoods is 1, if not, marking in the mark matrix A by using a connected domain mark variable mark in the same way, and storing the coordinate value of the pixel point corresponding to the element in a queue ary;
step 44, matrix element aijAnd after eight neighborhoods are scanned and marked, the next element a is carried outi，j+1And eight neighborhood scanning and marking thereof;
step 45, when one connected domain is marked, the total connected domain Num and the mark variable mark are increased by 1, the queue is emptied, and a new connected domain is marked;
and step 46, circularly traversing the matrix of the whole binary image in such a way until all connected domains are marked, wherein the finally returned total connected domain value Num is the number of the image cells.
In this embodiment, the effect of fluorescent cell counting is shown in FIG. 8 of the specification.
Since the apparatus described in the second embodiment of the present invention is an apparatus used for implementing the method of the first embodiment of the present invention, based on the method described in the first embodiment of the present invention, a person skilled in the art can understand the specific structure and the deformation of the apparatus, and thus the details are not described herein. All the devices adopted in the method of the first embodiment of the present invention belong to the protection scope of the present invention.
Based on the same inventive concept, the application provides an electronic device embodiment corresponding to the first embodiment, which is detailed in the third embodiment.
EXAMPLE III
The present embodiment provides an electronic device, as shown in fig. 10, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, any one of the first embodiment modes may be implemented.
Since the electronic device described in this embodiment is a device used for implementing the method in the first embodiment of the present application, based on the method described in the first embodiment of the present application, a specific implementation of the electronic device in this embodiment and various variations thereof can be understood by those skilled in the art, and therefore, how to implement the method in the first embodiment of the present application by the electronic device is not described in detail herein. The equipment used by those skilled in the art to implement the methods in the embodiments of the present application is within the scope of the present application.
Based on the same inventive concept, the application provides a storage medium corresponding to the fourth embodiment, which is described in detail in the fourth embodiment.
Example four
The present embodiment provides a computer-readable storage medium, as shown in fig. 11, on which a computer program is stored, and when the computer program is executed by a processor, any one of the first embodiment can be implemented.
The technical scheme provided in the embodiment of the application at least has the following technical effects or advantages: the method, the device, the system, the equipment and the medium provided by the embodiment of the application are combined with a digital image processing technology, and the automatic counting function of the fluorescent cell microscopic image is realized simply, conveniently and efficiently at low cost. Firstly, carrying out a series of preprocessing operations on the image, such as correcting uneven illumination of the microscopic image through gamma; contrast between the fluorescent cells and the background in the image is enhanced by adopting contrast linear broadening; median filtering is selected to remove noise of the image, and edge detail information of the image is effectively protected; and removing noise and background impurities in the image by utilizing open operation processing. Meanwhile, the cells which are adhered and overlapped with each other are segmented by a marker watershed algorithm, so that the counting accuracy is effectively improved. In the aspect of cell counting, the cell number in the image is automatically and quickly calculated through traversing and marking the connected domain of the image matrix.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Although specific embodiments of the invention have been described above, it will be understood by those skilled in the art that the specific embodiments described are illustrative only and are not limiting upon the scope of the invention, and that equivalent modifications and variations can be made by those skilled in the art without departing from the spirit of the invention, which is to be limited only by the appended claims.
Claims (10)
1. A method for automatically counting fluorescent cells, which is characterized in that: the method comprises the following steps:
step S1, reading a microscopic image of the fluorescent cell;
step S2, preprocessing the microscopic image of the fluorescent cell, which specifically comprises the following steps:
step S21, correcting uneven illumination of the microscopic image, reducing the brightness value of the image edge over-illumination area, and increasing the brightness value of the image middle over-illumination dark area until the fluorescent cells in the image edge over-illumination area and the image middle over-illumination dark area are highlighted;
step S22, enhancing the contrast ratio of the cells and the background in the microscopic image;
s23, filtering out microscopic image noise by adopting median filtering, and keeping detail information of image edges;
step S24, further removing microscopic image noise and background impurities by adopting open operation, smoothing the outline of cells, breaking the narrow connection of cells and removing the small protruding part of cells; step S3, segmenting the adhered fluorescent cells in the microscopic image; and step S4, calculating the number of the fluorescent cells.
2. The method for automatically counting fluorescent cells according to claim 1, wherein: the step S21 specifically includes the following steps:
step 211, firstly, converting the fluorescent cell image from an RGB color space to an HSV color space by the formula (1);
0≤V≤1，0≤S≤1，0≤H≤360 (1)；
step 212, extracting the illumination component of the fluorescence cell image by using a multi-scale Gaussian function, wherein the extraction process is shown as formula (2),
wherein: l (x, y) is an illumination component; f (x, y) is the illumination brightness of the input image; g (x, y) is a Gaussian function; n is the degree of the ruler; w is aiExtracting a weight coefficient of the illumination component for the ith Gaussian function;
the gaussian function is defined as follows:
where ξ is a normalization constant and b is a scale factor of a Gaussian function;
step 213, constructing a gamma function according to the distribution characteristics of the illumination components, and performing adaptive correction processing on the uneven illumination of the image, wherein the expression of the gamma function is as follows:
wherein, Q (x, y) is a gamma function, beta is a brightness enhancement index, and is determined by the illumination component and the brightness mean value n of the illumination component;
step 214, recombining the HSV image corrected by the gamma function into an RGB image through a formula (5);
step 215, outputting the corrected RGB image of the fluorescent cell.
3. The method for automatically counting fluorescent cells according to claim 1, wherein: the step S22 specifically includes: mapping the gray value of an input cell image into different gray ranges by adopting a contrast linear broadening method, then drawing a gray histogram of the image with broadened contrast, setting the gray mode in the histogram as a threshold, setting the gray value of the image smaller than the threshold as 0, and keeping the gray value of the image larger than or equal to an enhancement threshold unchanged so as to further enhance the contrast of the cells and the background in the image;
the step S23 specifically includes:
adopting median filtering, namely adopting a 3 multiplied by 3 square window to carry out operation, and selecting the median of gray values of each point in a neighborhood to replace the gray values of surrounding pixels according to the sorting result of the gray values in the neighborhood of a certain pixel point (p), thereby removing image noise, retaining image detail information and protecting cell morphology; the median replacement formula is:
wherein p isnIs the gray value in the pixel neighborhood of a certain point.
4. The method for automatically counting fluorescent cells according to claim 1, wherein: the step S3 specifically includes:
s31, when the marker watershed algorithm is controlled to segment the adherent cells, edge detection is carried out through a Sobel operator to obtain a gradient image;
image edge detection is defined as follows:
wherein I is the original microscopic cell image, GxAnd GyRespectively obtaining the derivative values of a certain point in the image in the x direction and the y direction, wherein G is the gradient corresponding to the certain point;
step S32, the Euclidean distance conversion is carried out on the image, and the external marker, the boundary pixel (x) in the Euclidean distance is extractedn,yn) And region pixel (x)0,y0) The minimum neighborhood distance between them is calculated as follows:
step S33, then determining a local minimum region of the image, setting a threshold h to expand the local minimum region of the image, and implementing extraction of the internal marker, where the threshold h is defined as follows:
wherein: m is0Representing a gradient image mean; m is1Means representing local minima of the gradient image; m is2Means representing local maxima of the gradient image; m is2-m1Representing the average depth of the catchment basin;
step S34, after obtaining the internal marker and the external marker, modifying the image gradient by using a forced minimum technology, eliminating irrelevant local minimum areas, and modifying the result of distance change to ensure that the local minimum areas only appear at expected positions;
s35, finally, performing watershed transformation on the image after gradient modification to find a watershed ridge line, and overlapping the watershed ridge line on the original image to realize the segmentation of the adhesion cells;
the step S4 specifically includes:
traversing a matrix corresponding to the image after the watershed segmentation, marking different connected domains in the matrix, recording the number of the connected domains by using a variable Num, wherein the finally obtained total connected domain value Num is the number of the fluorescent cells, and the automatic counting process of the fluorescent cells is as follows:
step 41, initializing a connected domain mark variable mark to be 1, and initializing a connected domain numerical variable Num to be 0;
step 42, traversing the elements of a in the matrix in sequence, and when encountering the matrix element aijWhen the number is 1, judging whether the element is marked by a connected domain mark variable mark, if the element is marked, scanning aijOther elements in the eight neighborhood; if not marked, assigning a mark value to the element A at the corresponding position in the mark matrix AijMarking and marking the element aijThe coordinate values of the corresponding pixel points are stored in a queue ary;
step 43, followed by element aijContinuously traversing the elements in the eight neighborhoods as the center, judging whether the element is marked when detecting that a certain element in the eight neighborhoods is 1, if not, marking in the mark matrix A by using a connected domain mark variable mark in the same way, and storing the coordinate value of the pixel point corresponding to the element in a queue ary;
step 44, matrix element aijAnd after eight neighborhoods are scanned and marked, the next element a is carried outi，j+1And eight neighborhood scanning and marking thereof;
step 45, when one connected domain is marked, the total connected domain Num and the mark variable mark are increased by 1, the queue is emptied, and a new connected domain is marked;
and step 46, circularly traversing the matrix of the whole binary image in such a way until all connected domains are marked, wherein the finally returned total connected domain value Num is the number of the image cells.
5. An automatic counting device for fluorescent cells is characterized in that: the method comprises the following steps:
the reading module is used for reading a microscopic image of the fluorescent cell;
the pretreatment module is used for pretreating the microscopic image of the fluorescent cell, and specifically comprises:
the correcting illumination unit is used for correcting uneven illumination of the microscopic image, reducing the brightness value of an image edge over-illumination area, and improving the brightness value of an image middle over-illumination dark area until fluorescent cells in the image edge over-illumination area and the image middle over-illumination dark area are highlighted;
the contrast enhancement unit is used for enhancing the contrast of the cells and the background in the microscopic image;
the noise filtering unit is used for filtering the noise of the microscopic image by adopting median filtering and retaining the detail information of the image edge;
the impurity removing unit is used for removing microscopic image noise and background impurities by adopting open operation, smoothing the outline of cells, breaking the narrow connection of the cells and removing the small protruding part of the cells;
the segmentation module is used for segmenting the fluorescent cells adhered to the microscopic image;
and the counting module is used for counting the number of the fluorescent cells.
6. The automatic counting device of fluorescent cells according to claim 5, wherein: the correction illumination unit specifically executes the following process:
step 211, firstly, converting the fluorescent cell image from an RGB color space to an HSV color space by the formula (1);
0≤V≤1，0≤S≤1，0≤H≤360 (1)；
step 212, extracting the illumination component of the fluorescent cell image by using a multi-scale Gaussian function, wherein the extraction process is shown as formula (2),
wherein: l (x, y) is an illumination component; f (x, y) is the illumination brightness of the input image; g (x, y) is a Gaussian function; n is the degree of the ruler; w is aiExtracting a weight coefficient of the illumination component for the ith Gaussian function;
the gaussian function is defined as follows:
where ξ is a normalization constant and b is a scale factor of a Gaussian function;
step 213, constructing a gamma function according to the distribution characteristics of the illumination components, and performing adaptive correction processing on the uneven illumination of the image, wherein the expression of the gamma function is as follows:
wherein, Q (x, y) is a gamma function, beta is a brightness enhancement index, and is determined by the illumination component and the brightness mean value n of the illumination component;
step 214, recombining the HSV image corrected by the gamma function into an RGB image through a formula (5);
step 215, outputting the corrected RGB image of the fluorescent cell.
7. The automatic counting device of fluorescent cells according to claim 5, wherein:
the contrast enhancement unit is specifically:
mapping the gray value of an input cell image into different gray ranges by adopting a contrast linear broadening method, then drawing a gray histogram of the image with broadened contrast, setting the gray mode in the histogram as a threshold, setting the gray value of the image smaller than the threshold as 0, and keeping the gray value of the image larger than or equal to an enhancement threshold unchanged so as to further enhance the contrast of the cells and the background in the image;
the noise filtering unit specifically comprises:
adopting median filtering, namely adopting a 3 multiplied by 3 square window to carry out operation, and selecting the median of gray values of each point in a neighborhood to replace the gray values of surrounding pixels according to the sorting result of the gray values in the neighborhood of a certain pixel point (p), thereby removing image noise, retaining image detail information and protecting cell morphology; the median replacement formula is:
wherein p isnIs the gray value in the pixel neighborhood of a certain point.
8. The automatic counting device of fluorescent cells according to claim 5, wherein: the segmentation module specifically executes the following processes:
s31, when the marker watershed algorithm is controlled to segment the adherent cells, edge detection is carried out through a Sobel operator to obtain a gradient image;
image edge detection is defined as follows:
wherein I is the original microscopic cell image, GxAnd GyThe derivative values of a certain point in the image in the x direction and the y direction are respectively, and G is the gradient corresponding to the certain point.
Step S32, the Euclidean distance transformation is carried out on the image, and the image is extractedPart marker, boundary pixel (x) in Euclidean distancen,yn) And region pixel (x)0,y0) The minimum neighborhood distance between them is calculated as follows:
step S33, then determining a local minimum region of the image, setting a threshold h to expand the local minimum region of the image, and implementing extraction of the internal marker, where the threshold h is defined as follows:
wherein: m is0Representing a gradient image mean; m is1Means representing local minima of the gradient image; m is2Means representing local maxima of the gradient image; m is2-m1Representing the average depth of the catchment basin;
step S34, after obtaining the internal marker and the external marker, modifying the image gradient by using a forced minimum technology, eliminating irrelevant local minimum areas, and modifying the result of distance change to ensure that the local minimum areas only appear at expected positions;
s35, finally, performing watershed transformation on the image after gradient modification to find a watershed ridge line, and overlapping the watershed ridge line on the original image to realize the segmentation of the adhesion cells;
the counting module specifically executes the following processes:
traversing a matrix corresponding to the image after the watershed segmentation, marking different connected domains in the matrix, recording the number of the connected domains by using a variable Num, wherein the finally obtained total connected domain value Num is the number of the fluorescent cells, and the automatic counting process of the fluorescent cells is as follows:
step 41, initializing a connected domain mark variable mark to be 1, and initializing a connected domain numerical variable Num to be 0;
step 42, traversing the elements of a in the matrix in sequence, and when encountering the matrix element aijWhen the number is 1, judging whether the element is connected or notMarking by field mark variable mark, if element is marked, scanning aijOther elements in the eight neighborhood; if not marked, assigning a mark value to the element A at the corresponding position in the mark matrix AijMarking and marking the element aijThe coordinate values of the corresponding pixel points are stored in a queue ary;
step 43, followed by element aijContinuously traversing the elements in the eight neighborhoods as the center, judging whether the element is marked when detecting that a certain element in the eight neighborhoods is 1, if not, marking in the mark matrix A by using a connected domain mark variable mark in the same way, and storing the coordinate value of the pixel point corresponding to the element in a queue ary;
step 44, matrix element aijAnd after eight neighborhoods are scanned and marked, the next element a is carried outi，j+1And eight neighborhood scanning and marking thereof;
step 45, when one connected domain is marked, the total connected domain Num and the mark variable mark are increased by 1, the queue is emptied, and a new connected domain is marked;
and step 46, circularly traversing the matrix of the whole binary image in such a way until all connected domains are marked, wherein the finally returned total connected domain value Num is the number of the image cells.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1 to 4 when executing the program.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010382639.6A CN111583227B (en) | 2020-05-08 | 2020-05-08 | Method, device, equipment and medium for automatically counting fluorescent cells |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010382639.6A CN111583227B (en) | 2020-05-08 | 2020-05-08 | Method, device, equipment and medium for automatically counting fluorescent cells |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111583227A true CN111583227A (en) | 2020-08-25 |
| CN111583227B CN111583227B (en) | 2023-03-24 |
Family
ID=72122831
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010382639.6A Active CN111583227B (en) | 2020-05-08 | 2020-05-08 | Method, device, equipment and medium for automatically counting fluorescent cells |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111583227B (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112037217A (en) * | 2020-09-09 | 2020-12-04 | 南京诺源医疗器械有限公司 | Intraoperative blood flow imaging method based on fluorescence imaging |
| CN112184696A (en) * | 2020-10-14 | 2021-01-05 | 中国科学院近代物理研究所 | Method and system for counting cell nucleus and cell organelle and calculating area of cell nucleus and cell organelle |
| CN112581391A (en) * | 2020-12-14 | 2021-03-30 | 佛山科学技术学院 | Image denoising method based on PCNN |
| CN112819795A (en) * | 2021-02-05 | 2021-05-18 | 复旦大学附属中山医院 | Cell number and area statistical method based on multicolor fluorescence picture |
| CN113096095A (en) * | 2021-04-12 | 2021-07-09 | 江苏理工学院 | Machine vision-based adhesive tablet counting method and counting system |
| CN113139953A (en) * | 2021-05-10 | 2021-07-20 | 宁波永新光学股份有限公司 | Method for detecting and identifying particle pollutants in image and computer readable storage medium |
| CN114563869A (en) * | 2022-01-17 | 2022-05-31 | 中国地质大学（武汉） | Surface mount type mobile phone microscope detection system and microscopic result obtaining method thereof |
| CN115170555A (en) * | 2022-08-04 | 2022-10-11 | 格物致和(北京)生物科技有限公司 | Counting method and system based on images |
| CN116124754A (en) * | 2023-04-17 | 2023-05-16 | 山东省中源联科生物工程集团有限公司 | Method for detecting residual quantity of cross-linking agent in sodium hyaluronate gel through image analysis |
| CN116189178A (en) * | 2022-12-30 | 2023-05-30 | 广州市明美光电技术有限公司 | Identification method, equipment and storage medium for microscopic cell image |
| CN116342432A (en) * | 2023-05-22 | 2023-06-27 | 华侨大学 | Non-labeled cell microscopic image enhancement method and system |
| CN116645390A (en) * | 2023-07-27 | 2023-08-25 | 吉林省星博医疗器械有限公司 | Fluorescent image cell rapid segmentation method and system |
| CN116740332A (en) * | 2023-06-01 | 2023-09-12 | 南京航空航天大学 | Method for positioning center and measuring angle of space target component on satellite based on region detection |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2385494C1 (en) * | 2008-10-22 | 2010-03-27 | Государственное образовательное учреждение высшего профессионального образования Московский инженерно-физический институт (государственный университет) | Method for recognition of cell texture image |
| CN104651462A (en) * | 2015-01-29 | 2015-05-27 | 华南农业大学 | Method for detecting magnaporthe grisea spore based on microscopic image analysis |
| CN110956612A (en) * | 2019-10-31 | 2020-04-03 | 华侨大学 | Cell rapid counting method, computer equipment and readable storage medium |
-
2020
- 2020-05-08 CN CN202010382639.6A patent/CN111583227B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2385494C1 (en) * | 2008-10-22 | 2010-03-27 | Государственное образовательное учреждение высшего профессионального образования Московский инженерно-физический институт (государственный университет) | Method for recognition of cell texture image |
| CN104651462A (en) * | 2015-01-29 | 2015-05-27 | 华南农业大学 | Method for detecting magnaporthe grisea spore based on microscopic image analysis |
| CN110956612A (en) * | 2019-10-31 | 2020-04-03 | 华侨大学 | Cell rapid counting method, computer equipment and readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 王娅: "血液红细胞图像自适应标记分水岭分割算法", 《中国图象图形学报》 * |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112037217A (en) * | 2020-09-09 | 2020-12-04 | 南京诺源医疗器械有限公司 | Intraoperative blood flow imaging method based on fluorescence imaging |
| CN112184696A (en) * | 2020-10-14 | 2021-01-05 | 中国科学院近代物理研究所 | Method and system for counting cell nucleus and cell organelle and calculating area of cell nucleus and cell organelle |
| CN112184696B (en) * | 2020-10-14 | 2023-12-29 | 中国科学院近代物理研究所 | Cell nucleus and organelle counting and area calculating method and system thereof |
| CN112581391A (en) * | 2020-12-14 | 2021-03-30 | 佛山科学技术学院 | Image denoising method based on PCNN |
| CN112819795B (en) * | 2021-02-05 | 2023-03-31 | 复旦大学附属中山医院 | Cell number and area statistical method based on multicolor fluorescence picture |
| CN112819795A (en) * | 2021-02-05 | 2021-05-18 | 复旦大学附属中山医院 | Cell number and area statistical method based on multicolor fluorescence picture |
| CN113096095A (en) * | 2021-04-12 | 2021-07-09 | 江苏理工学院 | Machine vision-based adhesive tablet counting method and counting system |
| CN113096095B (en) * | 2021-04-12 | 2023-07-25 | 江苏理工学院 | Adhesion tablet counting method and counting system based on machine vision |
| CN113139953A (en) * | 2021-05-10 | 2021-07-20 | 宁波永新光学股份有限公司 | Method for detecting and identifying particle pollutants in image and computer readable storage medium |
| CN114563869A (en) * | 2022-01-17 | 2022-05-31 | 中国地质大学（武汉） | Surface mount type mobile phone microscope detection system and microscopic result obtaining method thereof |
| CN115170555A (en) * | 2022-08-04 | 2022-10-11 | 格物致和(北京)生物科技有限公司 | Counting method and system based on images |
| CN116189178A (en) * | 2022-12-30 | 2023-05-30 | 广州市明美光电技术有限公司 | Identification method, equipment and storage medium for microscopic cell image |
| CN116124754A (en) * | 2023-04-17 | 2023-05-16 | 山东省中源联科生物工程集团有限公司 | Method for detecting residual quantity of cross-linking agent in sodium hyaluronate gel through image analysis |
| CN116342432A (en) * | 2023-05-22 | 2023-06-27 | 华侨大学 | Non-labeled cell microscopic image enhancement method and system |
| CN116342432B (en) * | 2023-05-22 | 2023-08-01 | 华侨大学 | Non-labeled cell microscopic image enhancement method and system |
| CN116740332A (en) * | 2023-06-01 | 2023-09-12 | 南京航空航天大学 | Method for positioning center and measuring angle of space target component on satellite based on region detection |
| CN116740332B (en) * | 2023-06-01 | 2024-04-02 | 南京航空航天大学 | Method for positioning center and measuring angle of space target component on satellite based on region detection |
| CN116645390A (en) * | 2023-07-27 | 2023-08-25 | 吉林省星博医疗器械有限公司 | Fluorescent image cell rapid segmentation method and system |
| CN116645390B (en) * | 2023-07-27 | 2023-10-03 | 吉林省星博医疗器械有限公司 | Fluorescent image cell rapid segmentation method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111583227B (en) | 2023-03-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111583227B (en) | Method, device, equipment and medium for automatically counting fluorescent cells | |
| CN107507173B (en) | No-reference definition evaluation method and system for full-slice image | |
| Versari et al. | Long-term tracking of budding yeast cells in brightfield microscopy: CellStar and the Evaluation Platform | |
| CN110956612B (en) | Cell rapid counting method, computer equipment and readable storage medium | |
| GB2478593A (en) | Segmentation of cell nuclei in histological sections | |
| CN110276759B (en) | Mobile phone screen bad line defect diagnosis method based on machine vision | |
| Borges et al. | Region growing for segmenting green microalgae images | |
| CN109544571A (en) | A kind of metallic phase image edge detection method based on mathematical morphology | |
| CN116664452B (en) | Multi-scale enhancement method and system for multi-channel fluorescent image | |
| CN110648312A (en) | Method for identifying wool and cashmere fibers based on scale morphological characteristic analysis | |
| CN111223110A (en) | Microscopic image enhancement method and device and computer equipment | |
| CN109948544B (en) | Automatic positioning and identifying method for target bacterial colony | |
| CN115393375A (en) | Bright field cell image segmentation method and device in fluorescence microscopic imaging | |
| Tse et al. | A combined watershed and level set method for segmentation of brightfield cell images | |
| CN113470041B (en) | Immunohistochemical cell image cell nucleus segmentation and counting method and system | |
| CN113850792A (en) | Cell classification counting method and system based on computer vision | |
| CN112396618B (en) | Grain boundary extraction and grain size measurement method based on image processing | |
| Xiong et al. | Segmentation of drosophila RNAi fluorescence images using level sets | |
| Ma et al. | A counting and segmentation method of blood cell image with logical and morphological feature of cell | |
| CN112184696A (en) | Method and system for counting cell nucleus and cell organelle and calculating area of cell nucleus and cell organelle | |
| Hramm et al. | Configurable Cell Segmentation Solution Using Hough Circles Transform and Watershed Algorithm | |
| Li et al. | Cell image segmentation based on an improved watershed transformation | |
| CN111325706A (en) | Grain boundary extraction and grain boundary extraction model generation method and device | |
| Shao et al. | An improved SVM method for cDNA microarray image segmentation | |
| CN115082379A (en) | Activated sludge phase contrast microscopic image floc and filamentous bacterium segmentation method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |