CN110838126B - Cell image segmentation method, cell image segmentation device, computer equipment and storage medium - Google Patents
Cell image segmentation method, cell image segmentation device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110838126B CN110838126B CN201911044681.0A CN201911044681A CN110838126B CN 110838126 B CN110838126 B CN 110838126B CN 201911044681 A CN201911044681 A CN 201911044681A CN 110838126 B CN110838126 B CN 110838126B
- Authority
- CN
- China
- Prior art keywords
- image
- cell
- segmentation
- cells
- morphological
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 83
- 238000003709 image segmentation Methods 0.000 title claims abstract description 56
- 238000003860 storage Methods 0.000 title claims abstract description 14
- 230000011218 segmentation Effects 0.000 claims abstract description 78
- 230000000877 morphologic effect Effects 0.000 claims abstract description 58
- 238000012545 processing Methods 0.000 claims abstract description 38
- 238000003708 edge detection Methods 0.000 claims abstract description 23
- 230000001464 adherent effect Effects 0.000 claims description 39
- 230000009466 transformation Effects 0.000 claims description 34
- 238000004590 computer program Methods 0.000 claims description 25
- 239000003550 marker Substances 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 18
- 238000012216 screening Methods 0.000 claims description 15
- 230000008859 change Effects 0.000 claims description 12
- 238000011426 transformation method Methods 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 230000001413 cellular effect Effects 0.000 claims description 9
- 210000004027 cell Anatomy 0.000 description 477
- 238000010586 diagram Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 11
- 239000002609 medium Substances 0.000 description 11
- 239000000853 adhesive Substances 0.000 description 5
- 230000001070 adhesive effect Effects 0.000 description 5
- 238000013135 deep learning Methods 0.000 description 5
- 210000004978 chinese hamster ovary cell Anatomy 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 102000004169 proteins and genes Human genes 0.000 description 3
- 108090000623 proteins and genes Proteins 0.000 description 3
- 230000021164 cell adhesion Effects 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 238000005315 distribution function Methods 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000001629 suppression Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 241000699802 Cricetulus griseus Species 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000004956 cell adhesive effect Effects 0.000 description 1
- 230000032823 cell division Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000010339 dilation Effects 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000005530 etching Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000013604 expression vector Substances 0.000 description 1
- 239000001963 growth medium Substances 0.000 description 1
- 230000002401 inhibitory effect Effects 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 210000001672 ovary Anatomy 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
- 239000011800 void material Substances 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
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration by the use of local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration by the use of histogram techniques
-
- G06T5/90—
-
- 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
- G06T7/12—Edge-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
- G06T7/155—Segmentation; Edge detection involving morphological operators
-
- 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
- G06T2207/20036—Morphological image processing
- G06T2207/20041—Distance transform
-
- 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
- G06T2207/20112—Image segmentation details
- G06T2207/20152—Watershed segmentation
Abstract
The application relates to a cell image segmentation method, a cell image segmentation device, a computer device and a storage medium. The method comprises the following steps: reading a cell gray level image; performing histogram equalization operation on the cell gray level image to obtain an equalized image; performing morphological operation on the equalized image to obtain a morphological image; the morphological operations comprise a top hat operation and a gradient operation; detecting the cell edge in the morphological image through an edge detection algorithm to obtain a cell edge image; carrying out binarization processing on the cell edge image to obtain a binarized cell image; and carrying out cell segmentation according to the binary cell image to obtain a cell segmentation image. By adopting the method, the accuracy of cell image segmentation can be improved.
Description
Technical Field
The present application relates to the field of image processing, and in particular, to a cell image segmentation method, apparatus, computer device, and storage medium.
Background
The stable cell strain screening has important significance in the field of biotechnology. The traditional stable cell strain screening method is to detect the total amount of target protein secreted by cells into a culture medium, screen high-yield cell strains according to the protein expression amount, and can improve the screening efficiency and obtain the stable production cell strains with high single cell yield by methods such as expression vector optimization, cell modification and the like, but the method has the defects of complex operation, long time consumption and the like. With the development of artificial intelligence technology, people begin to shoot cell strain images by means of high power microscope, and screen the cell strain images by methods such as deep learning, etc. to overcome the above disadvantages, so that an image segmentation method capable of rapidly and accurately segmenting single cells from the cell images is needed.
Traditional cell image segmentation is realized based on a threshold method, however, the threshold method is greatly influenced by threshold setting, which easily causes inaccuracy of image segmentation and cannot deal with cell adhesion.
Therefore, the traditional cell image segmentation method has the problem of low image segmentation accuracy.
Disclosure of Invention
In view of the above, it is necessary to provide a cell image segmentation method with high accuracy, a cell image segmentation apparatus, a computer device and a computer readable storage medium.
A method of cellular image segmentation, comprising:
reading a cell gray level image;
performing histogram equalization operation on the cell gray level image to obtain an equalized image;
performing morphological operation on the equalized image to obtain a morphological image; the morphological operations comprise a top hat operation and a gradient operation;
detecting the cell edge in the morphological image through an edge detection algorithm to obtain a cell edge image;
carrying out binarization processing on the cell edge image to obtain a binarized cell image;
and carrying out cell segmentation according to the binary cell image to obtain a cell segmentation image.
In one embodiment, the performing cell segmentation according to the binarized cell image to obtain a cell segmentation image includes:
when the adhesion cells exist in the binarized cell image, calculating the number of the cells in the adhesion cells by a chain code method;
obtaining an optimal minimum value point in an H-minima transformation method according to the number of the cells in the adhesion cells;
according to the optimal minimum value point, performing distance transformation on the binary cell image to obtain a distance transformation image;
and segmenting the distance transformation image by using a watershed algorithm to obtain the cell segmentation image.
In one embodiment, when adherent cells exist in the binarized cell image, calculating the number of cells in the adherent cells by a chain code method includes:
marking the chain code initial position of the binary cell image to obtain a chain code initial mark;
marking the position of the chain code with changed direction in the binary cell image to obtain a chain code change mark;
marking the chain code ending position of the binary cell image to obtain a chain code ending mark;
and calculating the cell number in the adherent cells according to the chain code starting marker, the chain code change marker and the chain code ending marker.
In one embodiment, the obtaining the optimal minimum point in the H-minima transformation method according to the number of the cells in the adherent cells includes:
acquiring an H-minima transformation threshold;
obtaining the number of minimum value points according to the H-minima conversion threshold;
and comparing the number of the minimum value points with the number of the cells in the adherent cells to obtain the optimal minimum value points.
In one embodiment, the binarizing the cell edge image to obtain a binarized cell image includes:
carrying out threshold processing on the cell edge image to obtain a thresholded image;
removing a non-cell area in the thresholding image background through an opening operation to obtain an opening operation image;
removing the inner edge of the cell in the opening operation image through closing operation to obtain a closing operation image;
and when the internal edges of the cells still exist in the closed operation image, filling holes in the closed operation image to obtain the binary cell image.
In one embodiment, the performing cell segmentation according to the binarized cell image to obtain a cell segmentation image includes:
searching a cell contour in the binary cell image to obtain cell contour information;
and acquiring a minimum rectangle containing the cell outline according to the cell outline information to obtain the cell segmentation image.
In one embodiment, the step of performing cell segmentation according to the binarized cell image to obtain a cell segmentation image includes:
collecting cell information from the cell segmentation image; the cellular information includes cell size and cell internal structure;
obtaining training sample data according to the cell information; the training sample data is used for cell feature recognition and cell screening.
A cell image segmentation apparatus comprising:
the input module is used for reading the cell gray level image;
the equalization module is used for carrying out histogram equalization operation on the cell gray level image to obtain an equalized image;
the morphological module is used for performing morphological operation on the equalized image to obtain a morphological image; the morphological operations comprise a top hat operation and a gradient operation;
the edge detection module is used for detecting the cell edges in the morphological image through an edge detection algorithm to obtain a cell edge image;
the binarization module is used for carrying out binarization processing on the cell edge image to obtain a binarization cell image;
and the segmentation module is used for carrying out cell segmentation according to the binary cell image to obtain a cell segmentation image.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
reading a cell gray level image;
performing histogram equalization operation on the cell gray level image to obtain an equalized image;
performing morphological operation on the equalized image to obtain a morphological image; the morphological operations comprise a top hat operation and a gradient operation;
detecting the cell edge in the morphological image through an edge detection algorithm to obtain a cell edge image;
carrying out binarization processing on the cell edge image to obtain a binarized cell image;
and carrying out cell segmentation according to the binary cell image to obtain a cell segmentation image.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
reading a cell gray level image;
performing histogram equalization operation on the cell gray level image to obtain an equalized image;
performing morphological operation on the equalized image to obtain a morphological image; the morphological operations comprise a top hat operation and a gradient operation;
detecting the cell edge in the morphological image through an edge detection algorithm to obtain a cell edge image;
carrying out binarization processing on the cell edge image to obtain a binarized cell image;
and carrying out cell segmentation according to the binary cell image to obtain a cell segmentation image.
According to the cell image segmentation method, the cell image segmentation device, the computer equipment and the computer readable storage medium, the histogram equalization operation is performed on the read cell gray level image, the image contrast can be enhanced, and the cell edge can be clarified so as to accurately detect the cell edge. Morphological operation is carried out on the equalized image, so that the cell edge can be further clarified, and the detected cell edge is more accurate. And detecting the cell edge in the morphological image by an edge detection algorithm to obtain a cell edge image, wherein the cell edge image not only contains the cell outline, but also contains the cell internal outline, and the cell edge image is further subjected to binarization processing to remove the cell internal outline. The cell segmentation is carried out according to the obtained binary cell image, and the cell segmentation image with higher accuracy can be obtained due to no interference of the internal outline of the cell, so that the accurate segmentation of the single cell image is realized, a large amount of high-quality training samples can be provided in the subsequent deep learning process, and the accuracy of cell feature identification and cell screening is improved.
Drawings
FIG. 1 is a schematic flow chart of a cell image segmentation method according to an embodiment;
FIG. 2 is a diagram of an application environment of a cell image segmentation method according to an embodiment;
FIG. 3A/B/C/D/E is a diagram illustrating the result of image processing at each step of a cell image segmentation method according to an embodiment;
FIG. 4 is a graph of image segmentation results of a cell image segmentation method according to an embodiment;
FIG. 5A/B is a schematic diagram of a chain code method of a cell image segmentation method according to an embodiment;
FIG. 6 is a graph of the results of distance transformation for a method of cellular image segmentation, according to an embodiment;
FIG. 7 is a schematic diagram of a watershed algorithm of a cell image segmentation method according to an embodiment;
fig. 8 is a block diagram showing a configuration of a cell image segmentation apparatus according to an embodiment;
FIG. 9 is an internal block diagram of a computer device of an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In one embodiment, as shown in FIG. 1, a method of cellular image segmentation is provided. The cell image segmentation method provided by this embodiment can be applied to the application environment shown in fig. 2. In this application environment, a user terminal 202 and a cell image segmentation server 204 are included. The user terminal 202 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices capable of acquiring high-power cell images, and the cell image segmentation server 204 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices having an image processing function. The above-mentioned cell image segmentation method is described by taking the cell image segmentation server 204 in fig. 2 as an example, and may include the following steps:
step S102, reading the cell gray level image.
The cell grayscale image may be an image of a cell taken by a microscope and having only grayscale values. For example, the cell grayscale images may be grayscale images of CHO (Chinese Hamster ovaries) cell images at different periods.
In a specific implementation, CHO cell images of different times are captured in an observation period, the cell images are stored in the cell image segmentation server 204, and when image segmentation processing is required, a gray scale map of the CHO cell images is read from the cell image segmentation server 204.
For example, 5 time points are selected during the culture of the cell line, images of CHO cells are taken by a high power microscope to obtain 5 cell grayscale images, the images are stored in the cell image segmentation server 204, and when cell image segmentation is required, one cell grayscale image is read from the cell image segmentation server 204.
And step S104, carrying out histogram equalization operation on the cell gray level image to obtain an equalized image.
The histogram equalization operation may be an operation of equalizing the contrast of different elements in the image through a histogram algorithm.
In specific implementation, histogram equalization operation can be performed on the cell gray level image, the number of each gray level value in a pixel is counted, the probability of occurrence of each gray level value is calculated, and the gray level value is mapped according to the probability. Through histogram equalization operation, the method can play a role in enhancing image contrast and clarifying cell edges so as to accurately detect the cell edges.
In practical applications, the histogram equalization operation can be implemented by the following formula:
wherein the round () function represents the rounding operation, rounding the decimal place number of the argument in brackets, M and N are the number of pixels of length and width in the cell grayscale image, L represents the number of grayscale levels, v is the pixel value in the cell grayscale image, cdfminThe cumulative distribution function cdf is calculated by the following equation for the minimum value of the cumulative distribution function
Wherein p isx(j) Representing the probability of occurrence of a pixel with a gray level j, i.e. the histogram of the image with a pixel value j, normalized to 0,1]。
For example, for a cell grayscale image of 400 × 300 pixels, M is 400, N is 300, 8-bit depth is adopted, L is 2^8 is 256, and v is a specific grayscale value of each pixel point, and any value between 0 and 255 can be taken. And aiming at each pixel point in the cell gray image, carrying out improved histogram equalization operation according to a formula to obtain an equalized image.
And step S106, performing morphological operation on the equalized image to obtain a morphological image.
Wherein the morphological operation is an operation of connecting adjacent elements or separating adjacent elements into independent elements, and the morphological operation may specifically include a top hat operation and a gradient operation.
In specific implementation, the morphological top cap operation can be adopted to highlight the cell outline under the large background of the cell image, then the morphological gradient operation is adopted to search the cell edge, and the morphological top cap operation and the gradient operation are combined to ensure that the cell edge can be accurately extracted in the subsequent edge detection process.
In practical application, src can be used for representing an equalized image, element can be used for representing a structural element, and the formula for performing top hat operation on the equalized image is
dst＝tophat(src,element)＝src-open(src,element)＝src-dilate(erode(src,element))；
Here, open (src, element) represents a morphological open operation, src is subjected to an erosion-before-dilation operation, and dilate (src, element) represents a dilation operation.
Then, the image dst is subjected to gradient operation, and the formula is
dst′＝morphgrad(dst,element)＝dilate(dst,element)-erode(dst,element)；
Wherein, the anode (dst, element) represents that the dst is subjected to the etching operation, and the obtained image dst' is a morphological image.
And S108, detecting the cell edges in the morphological image through an edge detection algorithm to obtain a cell edge image.
The edge detection algorithm is an algorithm capable of identifying an optimal cell contour in the morphological image, and can be a Canny method.
In the specific implementation, the Canny method firstly carries out noise reduction processing on a morphological image through a Gaussian smoothing filter, then calculates the gradient strength and direction of each pixel point in the image, eliminates stray response through a Non-Maximum Suppression (Non-Maximum Suppression) method, eliminates Non-edge pixels, reserves a candidate edge, and finally determines the cell edge through Double-Threshold (Double-Threshold). The Canny method is not easily interfered by noise, strong edges and weak edges can be detected respectively by using double thresholds, and when the weak edges are connected with the strong edges, the output image contains the weak edges, so that the accuracy of the obtained edge detection result is high.
In practical applications, the Canny method may perform the following steps:
(1) smoothing the morphological image by using a Gaussian filter to filter noise, wherein the Gaussian filter kernel with the size of (2k +1) × (2k +1) has a generation formula of
(2) Calculating the gradient strength and direction of each pixel point in the morphological image;
(3) eliminating stray response caused by edge detection by a non-maximum value inhibition method;
(4) determining real and potential edges in the morphological image by dual threshold detection;
(5) and (4) finishing edge detection by inhibiting isolated weak edges to obtain a cell edge image.
And step S110, carrying out binarization processing on the cell edge image to obtain a binarized cell image.
The binarization processing may be to perform binarization processing on the cell edge image, so that the output image only contains two colors, namely black and white, and may include threshold processing, opening operation, closing operation and void filling.
In specific implementation, due to the relatively complicated interior of the CHO cell, the obtained cell edge image not only contains the outline of the cell, but also contains the internal contour of the cell. In order to perform cell segmentation according to the cell outline, a threshold processing is first performed on the cell edge image to obtain a thresholded image, for example, the threshold is set to be 100, the gray value of a pixel point with a gray value higher than 100 in the cell edge image is 255, and the gray value of a pixel point with a gray value lower than or equal to 100 is 0. And performing open operation on the thresholded image, removing non-cell areas in the background to obtain an open operation image, then performing close operation on the open operation image, and removing the inner edges of the cells in the open operation image to obtain a closed operation image. When the internal edges of the cells do not exist in the closed operation image, the closed operation image is used as a binary cell image, when the internal edges of the cells still exist in the closed operation image, hole filling can be carried out on the closed operation image to obtain the binary cell image, and the formula of the hole filling is as follows
Wherein, X0An image which is completely black and has a white pixel at the hole, B represents a structural element, AcRepresenting the complement of the closed-operation image,
represents B structural element pair Xk-1Performing an expansion operation.
And step S112, carrying out cell segmentation according to the binary cell image to obtain a cell segmentation image.
The cell segmentation method comprises the steps of segmenting a whole single cell according to a cell outline in a binary cell image, and obtaining a cell segmentation image which can be a minimum rectangle containing the outline of the whole single cell.
In specific implementation, a findContours function in an opencv library can be called to obtain a cell outline, a boundingRec function is called to obtain an external rectangle with the minimum outline, the cell area is judged, and a cell segmentation image is stored.
In practical application, the findContours function carries out contour search by adopting the principle of traversing the pixel value of each pixel point, and the formula is
Wherein cv2 is the abbreviation of opencv, image is the input binary cell image, cv2 retr _ TREE is a pattern for retrieving contour-establishing a contour of a hierarchical TREE structure, cv2 channel _ APPROX _ SIMPLE represents an approximation method of contour-compressing elements in horizontal direction, vertical direction and diagonal direction, only the end point coordinates of the direction are kept, for example, only 4 points are needed for storing contour information for a rectangular contour, the point vector of each contour stored by the constants [ i ] represents the ith contour, hierarchy represents the topology information of the contour, the corresponding topology information of the contours [ i ] is hierarchy [ i ] [0] to hierarchy [ i ] [3], respectively represents the next contour, the previous contour, the parent contour and the index of the embedded contour, if no corresponding item exists, the corresponding hierarchy [ i ] is set as a negative number. Then the contour contours [ i ] is traversed.
The formula of the boundingRec function is
x,y,w,h＝cv2.boundingRect(contours[i])；
Wherein x and y are respectively the coordinates of the upper left fixed point pixel of the minimum outline bounding rectangle, w and h are respectively the width and height of the rectangle, the part is intercepted, the number of pixels with the pixel value of 255 in the area is traversed to be used as the area of the outline, then a proper outline picture of the cell is screened out according to the area of the cell, and the minimum cell bounding rectangle picture is stored.
It should be understood that, although the steps in the flowchart of fig. 1 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in fig. 1 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
According to the cell image segmentation method, histogram equalization operation is performed on the read cell gray level image, so that the image contrast can be enhanced, and the cell edge can be clarified, so that the cell edge can be accurately detected. Morphological operation is carried out on the equalized image, so that the cell edge can be further clarified, and the detected cell edge is more accurate. And detecting the cell edge in the morphological image by an edge detection algorithm to obtain a cell edge image, wherein the cell edge image not only contains the cell outline, but also contains the cell internal outline, and the cell edge image is further subjected to binarization processing to remove the cell internal outline. Cell segmentation is carried out according to the obtained binary cell image, and a cell segmentation image with high accuracy can be obtained because the interference of the internal contour of the cell is avoided.
FIG. 3A/B/C/D/E is a diagram illustrating the result of image processing at each step of a cell image segmentation method according to an embodiment, wherein FIG. 3A is a gray scale image of the cell read at step S102; fig. 3B is an equalized image obtained by the histogram equalization processing in step S104; fig. 3C is a cell edge image obtained by the edge detection in step S108; fig. 3D and 3E are a closed operation image and a binarized cell image obtained in the binarization processing in step S110, respectively.
Fig. 4 is a diagram of an image segmentation result of a cell image segmentation method according to an embodiment, for each single cell in fig. 3A, a minimum external rectangle containing a contour of the single cell is obtained by segmentation, a cell area can be calculated according to the result, and the segmentation result is stored in a cell image segmentation server and can be used for cell feature recognition and cell screening in deep learning.
In another embodiment, the step S112 may specifically include: when adherent cells exist in the binarized cell image, calculating the number of cells in the adherent cells by a chain code method; obtaining an optimal minimum value point in the H-minima transformation method according to the number of cells in the adherent cells; according to the optimal minimum value point, performing distance transformation on the binary cell image to obtain a distance transformation image; and (4) segmenting the distance transformation image by using a watershed algorithm to obtain a cell segmentation image.
Wherein, the adherent cells are two or more single cells adhered to each other in the binary cell image.
The chain code method is a method for labeling a cell adhesion image based on a Freeman chain code, and a schematic diagram of the chain code when two single cells are adhered is shown in FIG. 5B.
Wherein, the optimal minimum value point is the minimum value point when the number of the minimum value points is equal to the number of the adhesion cells in the H-minima transformation method.
In specific implementation, when adhesive cells exist, the Freeman chain codes of cell adhesive parts in the binary cell image are obtained, according to FIG. 5A, when 8-way chain codes are adopted, 8 directions of pixel points start counting from the positive right direction to 0, the count is increased in sequence in a counterclockwise direction, and the Freeman chain codes in FIG. 5B are 455677567011231233 in sequence.
The Freeman chain code is improved, and the steps are as follows:
(1) selecting a starting position, and adding a mark 'B' as shown in FIG. 5B;
(2) traversing in the counterclockwise direction, when the directions of two adjacent chain codes are different, for example, the direction of the former chain code is upper left, right left and lower left, the direction of the latter chain code is upper right, right and lower right, or the direction of the former chain code is upper left, right upper right and upper right, and the direction of the next chain code is lower left, right lower right and lower right, inserting 'C' into the two chain codes, as shown by the gray dots in fig. 5B;
(3) the mark 'E' is added after traversing to the end of the chain code, as shown in FIG. 5B.
Based on the modified Freeman chain code, the chain code output of FIG. 5B is B4556C77C56C70112C3C12C33E, and experiments show that for every additional adherent cell between 'B' and 'E', the number of labeled 'C' is increased by 4, so that N is enabledCFor the number of ` C ` in the modified Freeman chain code, the number of cells in adherent cells can be calculated as
Determining H thresholds in H-minima transformation according to the obtained number of the adhesion cells, randomly selecting the H thresholds, wherein each H threshold corresponds to an image of a minimum value point, when the number of the minimum value points in the image is equal to the number of the adhesion cells, determining the H thresholds as the currently selected H thresholds, obtaining the optimal minimum value points according to the determined H thresholds, and then generating a minimum value pixel point set.
Next, the binarized cell image is converted into a distance-converted image by distance conversion. Calculating the minimum distance from a non-zero pixel point to a minimum value point in a binary cell image by Euclidean distance transformation, wherein the minimum distance is used as a value after the point is transformed, and the distance formula is as follows:
where (x, y) is the coordinate of the pixel value non-zero point and (i, j) is the minimum point coordinate. The distance transformed image obtained by distance transformation is a gray scale image, as shown in fig. 6, where the black part is two cells and the white area is the edge of the "basin", and the two cells can be divided.
And finally, segmenting the distance conversion image by adopting a watershed algorithm, acquiring a mask label of the distance conversion image by calling a connected components function in opencv, wherein a foreground (cell part) label is 1, a background is 0, flooding water from the position with the label of 1, enabling the water to be flooded to find a final boundary, storing the boundary as data, and segmenting the adhered cells according to the data to obtain the cell segmentation image shown in the figure 7.
According to the cell image segmentation method, aiming at the condition that adhesive cells exist in a binary cell image, the number of the cells in the adhesive cells is accurately obtained through a chain code method, an optimal minimum value point in an H-minima transformation method is determined according to the number of the cells, distance transformation is carried out on the binary cell image according to the optimal minimum value point to obtain a distance transformation image, separation of the adhesive cells is achieved through the distance transformation image, the distance transformation image is segmented through a watershed algorithm, and a single cell image can be accurately segmented from the adhesive cell image.
In another embodiment, the step S112 may further include: marking the chain code initial position of the binary cell image to obtain a chain code initial mark; marking the position of the chain code with changed direction in the binary cell image to obtain a chain code change mark; marking the chain code ending position of the binary cell image to obtain a chain code ending mark; and calculating the cell number in the adherent cells according to the chain code initial marker, the chain code change marker and the chain code end marker.
In specific implementation, as shown in fig. 5, on the basis of a conventional Freeman chain code method, a chain code start position is determined first, a marker 'B' is introduced to the chain code start position, then counterclockwise traversal is performed, when two adjacent chain codes are different in direction, a position where the chain code direction changes can be determined, the position is marked as 'C', and finally, when traversal is performed to the chain code end, a chain code end position is determined, and a marker 'E' is added. Counting the number N of ' C's between ' B ' and ' ECSince the number of labeled ` C ` is increased by 4 for every one adherent cell, the number of cells in the adherent cells can be calculated as
Since the above processing procedure of step S112 has been described in detail in the foregoing embodiments, it is not described herein again.
The method marks the chain code starting position, the chain code direction changing position and the chain code ending position of the binary cell image respectively, calculates the number of cells in the adherent cells according to the marks, is convenient for separating the adherent cells by using a distance conversion method in the subsequent steps, and accurately segments the single cell image from the adherent cell image by using a watershed algorithm.
In another embodiment, the step S112 may further include: acquiring an H-minima transformation threshold; obtaining the number of minimum value points according to the H-minima conversion threshold; and comparing the number of the minimum value points with the number of cells in the adherent cells to obtain the optimal minimum value points.
Wherein the H-minima transformation threshold is the H threshold in the H-minima transformation method.
In the specific implementation, h thresholds can be randomly selected, each h threshold corresponds to an image of a minimum value point, when the number of the minimum value points in the image is equal to the number of the adherent cells, the h thresholds can be determined to be the currently selected h thresholds, the optimal minimum value points are obtained according to the determined h thresholds, and then a minimum value pixel point set is generated. Since the above processing procedure of step S112 has been described in detail in the foregoing embodiments, it is not described herein again.
The method obtains the optimal minimum value point according to the H-minima transformation threshold, is convenient for separating the adhesion cells by using a distance transformation method in the subsequent steps, and accurately segments the single cell image from the adhesion cell image by using a watershed algorithm.
In another embodiment, the step S110 may specifically include: carrying out threshold processing on the cell edge image to obtain a thresholded image; removing a non-cell area in the thresholding image background through an opening operation to obtain an opening operation image; removing the inner edge of the cell in the opening operation image through closing operation to obtain a closing operation image; and when the internal edges of the cells still exist in the closed operation image, filling holes in the closed operation image to obtain a binary cell image.
In a specific implementation, a threshold is set to perform binarization processing on the cell edge image, for example, the threshold is set to 100, the gray value of a pixel in the cell edge image with a gray value higher than 100 is 255, and the gray value of a pixel with a gray value lower than or equal to 100 is 0. Then, an open operation is performed to remove non-cell areas in the background, and a close operation is performed to remove cell internal edges in the open operation image, so as to obtain an image like a closed operation image shown in fig. 3D, and when the cell internal edges still exist in the closed operation image, for example, black dot areas in the cell of fig. 3D, the closed operation image is hole-filled, so as to obtain a binary cell image shown in fig. 3E. Since the above processing procedure of step S110 has been described in detail in the foregoing embodiments, it is not described herein again.
According to the method, the cells in the cell edge image are distinguished from the background through threshold processing, so that the cell image can be conveniently divided subsequently, the open operation can remove the non-cell area in the background area, the false division of the background is avoided, the closed operation can remove the inner edge of the cells, when the inner edge of the cells still exists in the closed operation image, the hole filling is carried out on the closed operation image, and the accurate cell division image can be conveniently obtained aiming at the outer edge of the cells subsequently.
In another embodiment, the step S112 may further include: searching a cell contour in a binary cell image to obtain cell contour information; and acquiring a minimum rectangle containing the cell outline according to the cell outline information to obtain a cell segmentation image.
In specific implementation, for the binarized cell image shown in fig. 3E, a findContours function in an opencv library may be called, contour search is performed by traversing the pixel value of each pixel point to obtain cell contour information, then, a boundingget function is used to obtain the minimum external rectangle of the contour, determine the cell area, and store the cell segmentation image. Since the above processing procedure of step S112 has been described in detail in the foregoing embodiments, it is not described herein again.
According to the method, the cell contour is searched in the binary cell image, the obtained cell contour information is accurate, the minimum rectangle containing the cell contour is obtained according to the cell contour information, and the obtained cell segmentation image is high in accuracy.
In another embodiment, after the step S112, the method may further include: collecting cell information from the cell segmentation image; cellular information includes cell size and cell internal structure; obtaining training sample data according to the cell information; training sample data is used for cell feature recognition and cell screening.
The cell information is information such as the size and internal structure of a single cell.
In specific implementation, the size of each single cell, protein expression parameters and other information may be acquired from the cell segmentation image shown in fig. 4, the acquired information may be sorted to obtain training sample data, when cell feature recognition or cell screening needs to be performed by using methods such as deep learning, training may be performed based on the training sample data, and according to different functions that need to be implemented, a cell feature recognition model or a cell screening model may be established, and cell feature recognition or cell screening may be performed based on the established model.
The method collects the cell information from the cell segmentation image, and the collected cell information has higher accuracy due to higher accuracy of the cell segmentation image, and the information is used as a training sample, and cell feature recognition and cell screening are carried out by using deep learning based on the training sample, so that the result has higher accuracy and lower operation time.
In one embodiment, as shown in fig. 8, there is provided a cell image segmentation apparatus 800, including: an input module 802, an equalization module 804, a morphology module 806, an edge detection module 808, a binarization module 810, and a segmentation module 812, wherein:
an input module 802 for reading a cell grayscale image;
the equalization module 804 is used for performing histogram equalization operation on the cell gray level image to obtain an equalized image;
a morphology module 806, configured to perform a morphology operation on the equalized image to obtain a morphology image;
the edge detection module 808 is configured to detect a cell edge in the morphological image through an edge detection algorithm to obtain a cell edge image;
a binarization module 810, configured to perform binarization processing on the cell edge image to obtain a binarized cell image;
and a segmentation module 812, configured to perform cell segmentation according to the binarized cell image to obtain a cell segmentation image.
In one embodiment, the segmentation module 812 includes: when adherent cells exist in the binarized cell image, calculating the number of cells in the adherent cells by a chain code method; obtaining an optimal minimum value point in the H-minima transformation method according to the number of cells in the adherent cells; according to the optimal minimum value point, performing distance transformation on the binary cell image to obtain a distance transformation image; and (4) segmenting the distance transformation image by using a watershed algorithm to obtain a cell segmentation image.
In one embodiment, the segmentation module 812 further includes: marking the chain code initial position of the binary cell image to obtain a chain code initial mark; marking the position of the chain code with changed direction in the binary cell image to obtain a chain code change mark; marking the chain code ending position of the binary cell image to obtain a chain code ending mark; and calculating the cell number in the adherent cells according to the chain code initial marker, the chain code change marker and the chain code end marker.
In one embodiment, the segmentation module 812 further includes: acquiring an H-minima transformation threshold; obtaining the number of minimum value points according to the H-minima conversion threshold; and comparing the number of the minimum value points with the number of cells in the adherent cells to obtain the optimal minimum value points.
In one embodiment, the binarization module 810 includes: carrying out threshold processing on the cell edge image to obtain a thresholded image; removing a non-cell area in the thresholding image background through an opening operation to obtain an opening operation image; removing the inner edge of the cell in the opening operation image through closing operation to obtain a closing operation image; and when the internal edges of the cells still exist in the closed operation image, filling holes in the closed operation image to obtain a binary cell image.
In one embodiment, the segmentation module 812 further includes: searching a cell contour in a binary cell image to obtain cell contour information; and acquiring a minimum rectangle containing the cell outline according to the cell outline information to obtain a cell segmentation image.
In one embodiment, the segmentation module 812 further includes: collecting cell information from the cell segmentation image; cellular information includes cell size and cell internal structure; obtaining training sample data according to the cell information; training sample data is used for cell feature recognition and cell screening.
For the specific definition of the cell image segmentation apparatus, reference may be made to the above definition of the cell image segmentation method, which is not described herein again. The respective modules in the cell image segmentation apparatus described above may be implemented in whole or in part by software, hardware, and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
The cell image segmentation device provided by the above can be used for executing the cell image segmentation method provided by any of the above embodiments, and has corresponding functions and beneficial effects.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 9. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of indoor positioning of an air sensor. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 9 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
reading a cell gray level image;
carrying out histogram equalization operation on the cell gray level image to obtain an equalized image;
performing morphological operation on the equalized image to obtain a morphological image;
detecting the cell edge in the morphological image through an edge detection algorithm to obtain a cell edge image;
carrying out binarization processing on the cell edge image to obtain a binarized cell image;
and performing cell segmentation according to the binary cell image to obtain a cell segmentation image.
In one embodiment, the processor, when executing the computer program, further performs the steps of: when adherent cells exist in the binarized cell image, calculating the number of cells in the adherent cells by a chain code method; obtaining an optimal minimum value point in the H-minima transformation method according to the number of cells in the adherent cells; according to the optimal minimum value point, performing distance transformation on the binary cell image to obtain a distance transformation image; and (4) segmenting the distance transformation image by using a watershed algorithm to obtain a cell segmentation image.
In one embodiment, the processor, when executing the computer program, further performs the steps of: marking the chain code initial position of the binary cell image to obtain a chain code initial mark; marking the position of the chain code with changed direction in the binary cell image to obtain a chain code change mark; marking the chain code ending position of the binary cell image to obtain a chain code ending mark; and calculating the cell number in the adherent cells according to the chain code initial marker, the chain code change marker and the chain code end marker.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring an H-minima transformation threshold; obtaining the number of minimum value points according to the H-minima conversion threshold; and comparing the number of the minimum value points with the number of cells in the adherent cells to obtain the optimal minimum value points.
In one embodiment, the processor, when executing the computer program, further performs the steps of: carrying out threshold processing on the cell edge image to obtain a thresholded image; removing a non-cell area in the thresholding image background through an opening operation to obtain an opening operation image; removing the inner edge of the cell in the opening operation image through closing operation to obtain a closing operation image; and when the internal edges of the cells still exist in the closed operation image, filling holes in the closed operation image to obtain a binary cell image.
In one embodiment, the processor, when executing the computer program, further performs the steps of: searching a cell contour in a binary cell image to obtain cell contour information; and acquiring a minimum rectangle containing the cell outline according to the cell outline information to obtain a cell segmentation image.
In one embodiment, the processor, when executing the computer program, further performs the steps of: collecting cell information from the cell segmentation image; cellular information includes cell size and cell internal structure; obtaining training sample data according to the cell information; training sample data is used for cell feature recognition and cell screening.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
reading a cell gray level image;
carrying out histogram equalization operation on the cell gray level image to obtain an equalized image;
performing morphological operation on the equalized image to obtain a morphological image;
detecting the cell edge in the morphological image through an edge detection algorithm to obtain a cell edge image;
carrying out binarization processing on the cell edge image to obtain a binarized cell image;
and performing cell segmentation according to the binary cell image to obtain a cell segmentation image.
In one embodiment, the computer program when executed by the processor further performs the steps of: when adherent cells exist in the binarized cell image, calculating the number of cells in the adherent cells by a chain code method; obtaining an optimal minimum value point in the H-minima transformation method according to the number of cells in the adherent cells; according to the optimal minimum value point, performing distance transformation on the binary cell image to obtain a distance transformation image; and (4) segmenting the distance transformation image by using a watershed algorithm to obtain a cell segmentation image.
In one embodiment, the computer program when executed by the processor further performs the steps of: marking the chain code initial position of the binary cell image to obtain a chain code initial mark; marking the position of the chain code with changed direction in the binary cell image to obtain a chain code change mark; marking the chain code ending position of the binary cell image to obtain a chain code ending mark; and calculating the cell number in the adherent cells according to the chain code initial marker, the chain code change marker and the chain code end marker.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring an H-minima transformation threshold; obtaining the number of minimum value points according to the H-minima conversion threshold; and comparing the number of the minimum value points with the number of cells in the adherent cells to obtain the optimal minimum value points.
In one embodiment, the computer program when executed by the processor further performs the steps of: carrying out threshold processing on the cell edge image to obtain a thresholded image; removing a non-cell area in the thresholding image background through an opening operation to obtain an opening operation image; removing the inner edge of the cell in the opening operation image through closing operation to obtain a closing operation image; and when the internal edges of the cells still exist in the closed operation image, filling holes in the closed operation image to obtain a binary cell image.
In one embodiment, the computer program when executed by the processor further performs the steps of: searching a cell contour in a binary cell image to obtain cell contour information; and acquiring a minimum rectangle containing the cell outline according to the cell outline information to obtain a cell segmentation image.
In one embodiment, the computer program when executed by the processor further performs the steps of: collecting cell information from the cell segmentation image; cellular information includes cell size and cell internal structure; obtaining training sample data according to the cell information; training sample data is used for cell feature recognition and cell screening.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method of cell image segmentation, comprising:
reading a cell gray level image;
performing histogram equalization operation on the cell gray level image to obtain an equalized image;
performing morphological operation on the equalized image to obtain a morphological image; the morphological operations comprise a top hat operation and a gradient operation;
detecting the cell edge in the morphological image through an edge detection algorithm to obtain a cell edge image;
performing binarization processing on the cell edge image to obtain a binarized cell image, further comprising: carrying out threshold processing on the cell edge image to obtain a thresholded image; removing a non-cell area in the thresholding image background through an opening operation to obtain an opening operation image; removing the inner edge of the cell in the opening operation image through closing operation to obtain a closing operation image; when the internal edges of the cells do not exist in the closed operation image, taking the closed operation image as the binary cell image; when the internal edges of the cells still exist in the closed operation image, hole filling is carried out on the closed operation image to obtain the binary cell image;
and carrying out cell segmentation according to the binary cell image to obtain a cell segmentation image.
2. The method according to claim 1, wherein said performing cell segmentation based on said binarized cell image to obtain a cell segmentation image comprises:
when the adhesion cells exist in the binarized cell image, calculating the number of the cells in the adhesion cells by a chain code method;
obtaining an optimal minimum value point in an H-minima transformation method according to the number of the cells in the adhesion cells;
according to the optimal minimum value point, performing distance transformation on the binary cell image to obtain a distance transformation image;
and segmenting the distance transformation image by using a watershed algorithm to obtain the cell segmentation image.
3. The method according to claim 2, wherein the calculating the number of cells in the adherent cells by a chain code method when adherent cells are present in the binarized cell image comprises:
marking the chain code initial position of the binary cell image to obtain a chain code initial mark;
marking the position of the chain code with changed direction in the binary cell image to obtain a chain code change mark;
marking the chain code ending position of the binary cell image to obtain a chain code ending mark;
and calculating the cell number in the adherent cells according to the chain code starting marker, the chain code change marker and the chain code ending marker.
4. The method as claimed in claim 2, wherein the obtaining the optimal minimum point in the H-minima transformation method according to the cell number in the adherent cells comprises:
acquiring an H-minima transformation threshold;
obtaining the number of minimum value points according to the H-minima conversion threshold;
and comparing the number of the minimum value points with the number of the cells in the adherent cells to obtain the optimal minimum value points.
5. The method of claim 1, wherein said performing a morphological operation on said equalized image to obtain a morphological image comprises:
firstly, highlighting the cell outline under the large background of the cell image by adopting the top cap operation;
the gradient operation is then used to find the cell edges.
6. The method according to claim 1, wherein said performing cell segmentation based on said binarized cell image to obtain a cell segmentation image comprises:
searching a cell contour in the binary cell image to obtain cell contour information;
and acquiring a minimum rectangle containing the cell outline according to the cell outline information to obtain the cell segmentation image.
7. The method according to claim 1, wherein the step of performing cell segmentation based on the binarized cell image to obtain a cell segmentation image is followed by:
collecting cell information from the cell segmentation image; the cellular information includes cell size and cell internal structure;
obtaining training sample data according to the cell information; the training sample data is used for cell feature recognition and cell screening.
8. A cell image segmentation apparatus, comprising:
the input module is used for reading the cell gray level image;
the equalization module is used for carrying out histogram equalization operation on the cell gray level image to obtain an equalized image;
the morphological module is used for performing morphological operation on the equalized image to obtain a morphological image; the morphological operations comprise a top hat operation and a gradient operation;
the edge detection module is used for detecting the cell edges in the morphological image through an edge detection algorithm to obtain a cell edge image;
a binarization module, configured to perform binarization processing on the cell edge image to obtain a binarized cell image, and further include: carrying out threshold processing on the cell edge image to obtain a thresholded image; removing a non-cell area in the thresholding image background through an opening operation to obtain an opening operation image; removing the inner edge of the cell in the opening operation image through closing operation to obtain a closing operation image; when the internal edges of the cells do not exist in the closed operation image, taking the closed operation image as the binary cell image; when the internal edges of the cells still exist in the closed operation image, hole filling is carried out on the closed operation image to obtain the binary cell image;
and the segmentation module is used for carrying out cell segmentation according to the binary cell image to obtain a cell segmentation image.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the cell image segmentation method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the cell image segmentation method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911044681.0A CN110838126B (en) | 2019-10-30 | 2019-10-30 | Cell image segmentation method, cell image segmentation device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911044681.0A CN110838126B (en) | 2019-10-30 | 2019-10-30 | Cell image segmentation method, cell image segmentation device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110838126A CN110838126A (en) | 2020-02-25 |
| CN110838126B true CN110838126B (en) | 2020-11-17 |
Family
ID=69575943
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911044681.0A Active CN110838126B (en) | 2019-10-30 | 2019-10-30 | Cell image segmentation method, cell image segmentation device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110838126B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111598029B (en) * | 2020-05-21 | 2021-11-30 | 深圳太力生物技术有限责任公司 | Method, system, server and storage medium for screening target cell strain |
| CN111862071B (en) * | 2020-07-29 | 2024-03-05 | 南通大学 | Method for measuring CT value of lumbar 1 vertebral body based on CT image |
| CN112017730B (en) * | 2020-08-26 | 2022-08-09 | 深圳太力生物技术有限责任公司 | Cell screening method and device based on expression quantity prediction model |
| CN112750118B (en) * | 2021-01-18 | 2022-10-11 | 中南大学 | Novel method and system for identifying cell number in single cell pore plate sequencing based on automatic visual detection |
| CN113286079B (en) * | 2021-05-10 | 2023-04-28 | 迈克医疗电子有限公司 | Image focusing method and device, electronic equipment and readable storage medium |
| CN113537181A (en) * | 2021-09-17 | 2021-10-22 | 北京慧荣和科技有限公司 | CB microkernel microscopic image identification and analysis method and system based on neural network |
| CN115082783A (en) * | 2022-05-30 | 2022-09-20 | 华南农业大学 | Low-contrast fogdrop image identification method |
| CN115546462A (en) * | 2022-12-01 | 2022-12-30 | 南京维拓科技股份有限公司 | Method for extracting shape features of product and counting based on image recognition |
| 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 |
| CN117333929B (en) * | 2023-12-01 | 2024-02-09 | 贵州省公路建设养护集团有限公司 | Method and system for identifying abnormal personnel under road construction based on deep learning |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106295588A (en) * | 2016-08-17 | 2017-01-04 | 电子科技大学 | The automatic identifying method of leukocyte in a kind of leucorrhea micro-image |
| CN106875404A (en) * | 2017-01-18 | 2017-06-20 | 宁波摩视光电科技有限公司 | The intelligent identification Method of epithelial cell in a kind of leukorrhea micro-image |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107316077B (en) * | 2017-06-21 | 2020-09-08 | 上海交通大学 | Automatic adipose cell counting method based on image segmentation and edge detection |
| JP2019058074A (en) * | 2017-09-25 | 2019-04-18 | オリンパス株式会社 | Image processing apparatus, cell cluster recognition apparatus, cell cluster recognition method, and cell cluster recognition program |
-
2019
- 2019-10-30 CN CN201911044681.0A patent/CN110838126B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106295588A (en) * | 2016-08-17 | 2017-01-04 | 电子科技大学 | The automatic identifying method of leukocyte in a kind of leucorrhea micro-image |
| CN106875404A (en) * | 2017-01-18 | 2017-06-20 | 宁波摩视光电科技有限公司 | The intelligent identification Method of epithelial cell in a kind of leukorrhea micro-image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110838126A (en) | 2020-02-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110838126B (en) | Cell image segmentation method, cell image segmentation device, computer equipment and storage medium | |
| CN113160192B (en) | Visual sense-based snow pressing vehicle appearance defect detection method and device under complex background | |
| CN108710866B (en) | Chinese character model training method, chinese character recognition method, device, equipment and medium | |
| WO2019232853A1 (en) | Chinese model training method, chinese image recognition method, device, apparatus and medium | |
| CN109117848B (en) | Text line character recognition method, device, medium and electronic equipment | |
| Shi et al. | Automatic road crack detection using random structured forests | |
| CN107633226B (en) | Human body motion tracking feature processing method | |
| CN109919002B (en) | Yellow stop line identification method and device, computer equipment and storage medium | |
| CN109343920B (en) | Image processing method and device, equipment and storage medium thereof | |
| Zhang et al. | Road recognition from remote sensing imagery using incremental learning | |
| CN109033944B (en) | Method and system for classifying all-sky aurora images and positioning key local structure | |
| WO2019232852A1 (en) | Handwriting training sample obtaining method and apparatus, and device and medium | |
| CN111145209A (en) | Medical image segmentation method, device, equipment and storage medium | |
| CN111539330B (en) | Transformer substation digital display instrument identification method based on double-SVM multi-classifier | |
| WO2019232850A1 (en) | Method and apparatus for recognizing handwritten chinese character image, computer device, and storage medium | |
| CN108734109B (en) | Visual target tracking method and system for image sequence | |
| Tian et al. | Scene text segmentation with multi-level maximally stable extremal regions | |
| CN112270317A (en) | Traditional digital water meter reading identification method based on deep learning and frame difference method | |
| CN110751619A (en) | Insulator defect detection method | |
| CN111523537A (en) | Character recognition method, storage medium and system | |
| CN112749673A (en) | Method and device for intelligently extracting stock of oil storage tank based on remote sensing image | |
| Liang et al. | An extraction and classification algorithm for concrete cracks based on machine vision | |
| CN112818952A (en) | Coal rock boundary recognition method and device and electronic equipment | |
| CN107330434A (en) | Electrical symbol recognition methods in a kind of circuit diagram based on PHOG features | |
| CN113989604A (en) | Tire DOT information identification method based on end-to-end deep learning |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20211201 Address after: 518048 No. 323-m, third floor, comprehensive Xinxing phase I, No. 1, Haihong Road, Fubao community, Fubao street, Futian District, Shenzhen, Guangdong Province Patentee after: Shenzhen Taili Biotechnology Co.,Ltd. Address before: 523560 building 3 and 4, gaobao green technology city, Tutang village, Changping Town, Dongguan City, Guangdong Province Patentee before: DONGGUAN TAILI BIOLOGICAL ENGINEERING CO.,LTD. |
|
| TR01 | Transfer of patent right |