CN115641294A - Method and system for screening positive mutant cells based on perimeter-area ratio - Google Patents
Method and system for screening positive mutant cells based on perimeter-area ratio Download PDFInfo
- Publication number
- CN115641294A CN115641294A CN202211100186.9A CN202211100186A CN115641294A CN 115641294 A CN115641294 A CN 115641294A CN 202211100186 A CN202211100186 A CN 202211100186A CN 115641294 A CN115641294 A CN 115641294A
- Authority
- CN
- China
- Prior art keywords
- perimeter
- cell
- cells
- area ratio
- processing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention provides a method and a system for screening positive mutant cells based on perimeter-area ratio, belonging to the technical field of biological information processing based on computers and obtaining slice images of the cells; detecting all cells in the slices by using a YOLOv5 target detection algorithm; respectively acquiring single cells in the slice images of each cell; carrying out gray level processing on the single cell picture; denoising by Gaussian filtering; carrying out binarization processing on the image subjected to Gaussian filtering processing; carrying out contour scanning on the image subjected to binarization processing to obtain a cell boundary, and calculating the perimeter and the area of the cell; and calculating the perimeter area ratio, and judging whether the cells are mutation positive cells. The method screens the positive mutant cells of the urothelial cells in the section image based on the technologies of gray processing, gaussian blur, binarization processing and the like, thereby realizing the rapid screening of the cancer, saving manpower, material resources and financial resources and having higher application value.
Description
Technical Field
The invention relates to the technical field of computer-based biological information processing, in particular to a method and a system for screening positive mutant cells based on a perimeter-to-area ratio.
Background
Cancer is one of the highest mortality diseases worldwide. The rapid screening of the positive mutant cells related to the cancer can accelerate the diagnosis speed of the cancer. Malignant mutations in intracellular genomes are a major cause of cancer. The existing medical technology generally performs the steps of staining a cell section of a patient and manually screening positive mutant cells. This method is time consuming and labor consuming, inefficient, and costly.
In recent years, with the development of computer technology, the use of computer technology in combination with the biological and medical fields has become a research focus. Various cells in the cell slice image can be detected by using target detection algorithms such as YOLO, DETR and the like, but the methods can only detect the cells generally and cannot accurately judge the cell types (such as inflammatory cells, negative cells, positive cells and atypical cells).
Disclosure of Invention
The invention aims to provide a method and a system for screening positive mutant cells based on perimeter-area ratio, so as to solve at least one technical problem in the background technology.
In order to achieve the purpose, the invention adopts the following technical scheme:
in one aspect, the invention provides a method for screening positive mutant cells based on perimeter-to-area ratio, comprising:
acquiring a slice image of the cell;
detecting all cells in the slices by using a YOLOv5 target detection algorithm;
respectively acquiring single cells in the slice images of each cell;
carrying out gray level processing on the single cell picture;
denoising by Gaussian filtering;
carrying out binarization processing on the picture subjected to Gaussian filtering processing;
carrying out contour scanning on the image subjected to binarization processing to obtain a cell boundary, and calculating the perimeter and the area of the cell;
calculating the area ratio of the perimeter;
and judging whether the cells are mutation positive cells or not according to the calculated perimeter area ratio.
Preferably, the individually acquiring the single cell in the slice image of each urothelial cell includes:
intercepting an area containing corresponding cells from an original urothelial cell section image according to a target frame, and respectively restoring the central coordinates (x, y) of the unitized target frame and the width, height w and height h of the unitized target frame in order to restore a real scale, wherein the specific formula is as follows:
wherein, W and H are respectively the height and width of the original urothelial cell section image.
Preferably, the gray processing is performed on the single cell picture, and the gray processing comprises the following steps:
converting three channels of the image of the RGB color space, wherein the Gray value Gray of the corresponding pixel after conversion is shown as the following formula:
in the formula, R, G and B respectively represent values of red, green and blue color channels.
Preferably, the noise reduction using gaussian filtering includes:
wherein (u, v) is the center point coordinate, σ 2 Is the variance.
Carrying out binarization processing on the image after Gaussian filtering processing:
preferably, the image after binarization processing is subjected to contour scanning to obtain a cell boundary, and the perimeter and the area of the cell are calculated, wherein the contour approximation calculation by using a Ramer-Douglas-Peucker (RDP) algorithm comprises the following steps: given the starting and ending points of the curve, first find the vertex of the maximum distance from the line connecting the two reference points, called max _ point; if the max _ point distance is smaller than the threshold value, ignoring all vertexes between the starting point and the end point, and enabling the curve to be a straight line; if max _ point exceeds the threshold value, the algorithm is repeated recursively to obtain the perimeter of the cell;
the area within the contour is calculated using the Green formula as follows:
preferably, the perimeter area ratio is calculated to judge whether the cells are positive mutant cells, and the method comprises the following steps:
by using pairsCalculating the perimeter-to-area ratio Rate from the perimeter periodimeter and the area of the cell pixel P-A The formula is as follows:
in a second aspect, the present invention provides a system for screening positive mutant cells based on perimeter to area ratio, comprising:
the acquisition module is used for acquiring a slice image of the cell;
the detection module is used for detecting all cells in the slice by using a YOLOv5 target detection algorithm;
the extraction module is used for respectively acquiring single cells in the slice images of each cell;
the processing module is used for carrying out gray processing on the single cell picture, carrying out noise reduction by Gaussian filtering and carrying out binarization processing on the picture after the Gaussian filtering processing;
the calculation module is used for carrying out contour scanning on the image after binarization processing to obtain a cell boundary and calculating the perimeter and the area of the cell; calculating the area ratio of the perimeter;
and the judging module is used for judging whether the cells are mutation positive cells or not according to the calculated perimeter area ratio.
In a third aspect, the present invention provides a non-transitory computer readable storage medium for storing computer instructions which, when executed by a processor, implement a method for screening for positively mutated cells based on perimeter-to-area ratio as described above.
In a fourth aspect, the invention provides a computer program product comprising a computer program which, when run on one or more processors, is for implementing a method for screening for positively mutated cells based on perimeter to area ratio as described above.
In a fifth aspect, the present invention provides an electronic device, comprising: a processor, a memory, and a computer program; wherein a processor is connected to the memory, a computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory to cause the electronic device to execute instructions to implement the method for screening positively mutated cells based on perimeter-to-area ratio as described above.
The invention has the beneficial effects that: screening the positive mutant cells of the urothelial cells in the section image based on technologies such as gray processing, gaussian blur, binarization processing and the like, so that the rapid screening of the cancers is realized, manpower, material resources and financial resources are saved, and the method has a high application value.
Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic diagram illustrating the implementation of the method for screening positive mutant cells based on perimeter-to-area ratio according to the embodiment of the present invention.
Fig. 2 is an exemplary diagram of a urothelial cell slice image according to an embodiment of the present invention.
FIG. 3 is a diagram of an example of a single cell obtained according to the detection result of the YOLOv5 target according to the embodiment of the present invention.
FIG. 4 is a diagram of an example of a single cell after gray scale processing according to an embodiment of the present invention.
FIG. 5 is a diagram illustrating a single cell after the Gaussian filter blur noise reduction process according to an embodiment of the present invention.
FIG. 6 is a diagram illustrating an example of a single cell after binarization processing according to an embodiment of the invention.
FIG. 7 is a diagram of an example of a single cell after contour scanning according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative only and should not be construed as limiting the invention.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
For the convenience of understanding, the present invention will be further explained by the following embodiments with reference to the drawings, and the embodiments are not to be construed as limiting the embodiments of the present invention.
It will be appreciated by those skilled in the art that the drawings are merely schematic representations of embodiments and that the elements in the drawings are not necessarily required to practice the present invention.
Example 1
This example 1 provides a system for screening positive mutant cells based on perimeter-to-area ratio, comprising:
the acquisition module is used for acquiring a slice image of the cell;
the detection module is used for detecting all cells in the slice by using a YOLOv5 target detection algorithm;
the extraction module is used for respectively acquiring single cells in the slice image of each cell;
the processing module is used for carrying out gray processing on the single cell picture, carrying out noise reduction by Gaussian filtering and carrying out binarization processing on the picture after the Gaussian filtering processing;
the calculation module is used for carrying out contour scanning on the image after the binarization processing to obtain a cell boundary and calculating the perimeter and the area of the cell; calculating the area ratio of the perimeter;
and the judging module is used for judging whether the cells are mutation positive cells or not according to the calculated perimeter area ratio.
In example 1, the above system was used to realize a method for screening positive mutant cells based on perimeter-to-area ratio, comprising:
acquiring a slice image of the cell;
detecting all cells in the slices by using a YOLOv5 target detection algorithm;
respectively acquiring single cells in the slice images of each cell;
carrying out gray level processing on the single cell picture;
denoising by Gaussian filtering;
carrying out binarization processing on the image subjected to Gaussian filtering processing;
carrying out contour scanning on the image subjected to binarization processing to obtain a cell boundary, and calculating the perimeter and the area of the cell;
calculating the area ratio of the perimeter;
and judging whether the cells are mutation positive cells or not according to the calculated perimeter area ratio.
The individual cells in the slice image of each urothelial cell obtained separately include:
intercepting an area containing corresponding cells in an original urothelial cell slice image according to a target frame, and respectively restoring the central coordinates (x, y) of the unitized target frame and the width, height w and height h of the unitized target frame in order to restore a real scale, wherein the specific formula is as follows:
wherein, W and H are respectively the height and width of the original urothelial cell section image.
Carrying out gray processing on the single cell picture, comprising the following steps:
converting three channels of the image of the RGB color space, wherein the Gray value Gray of the corresponding pixel after conversion is shown as the following formula:
in the formula, R, G and B respectively represent values of red, green and blue color channels.
Denoising with gaussian filtering includes:
wherein (u, v) is the center point coordinate, σ 2 Is the variance.
Carrying out binarization processing on the picture subjected to Gaussian filtering processing:
performing contour scanning on the image after binarization processing to obtain a cell boundary, and calculating the perimeter and the area of the cell, wherein the contour approximation calculation perimeter is performed by using a Ramer-Douglas-Peucker (RDP) algorithm: giving a starting point and an end point of a curve, firstly finding a vertex with the maximum distance from a line connecting two reference points, and calling the vertex with the maximum distance as max _ point; if the max _ point distance is smaller than the threshold value, ignoring all vertexes between the starting point and the end point, and enabling the curve to be a straight line; if max _ point exceeds the threshold value, the algorithm is repeated recursively to obtain the perimeter of the cell;
the area within the contour is calculated using the Green formula as follows:
calculating the area ratio of the perimeter, and judging whether the cells are positive mutant cells or not, wherein the method comprises the following steps:
using the perimeter and area of the pixel of the corresponding cell, the perimeter area ratio RateP-a is calculated as follows:
example 2
The positive mutant cell is round in shape, so that the perimeter area is small, and the screening can be rapidly and directly carried out through the bottom layer characteristics of the image. Therefore, in this embodiment 2, all cells in the urothelial cell slice image are detected by using the YOLOv5 target detection algorithm, and then positive mutant cells are screened out based on the perimeter-to-area ratio for different types of cells, so that the rapid screening of cancer is realized, the manpower, material resources and financial resources are saved, and the application value is high.
The method for screening the positive mutant cells based on the manual characteristics, provided by the embodiment 2, is used for rapidly and accurately screening the positive mutant cells according to the urothelial cell section image, and comprises the following steps:
for a urothelial cell section image, firstly, using Yolov5 to detect a target, wherein the labeling form of a target frame bbox of each cell in the image is as follows:
bbox＝{class，x，y，w，h}
in the formula, class represents the category to which the object belongs, (x, y) represents the center coordinates of the unitized object box, and w and h represent the width and height of the unitized object box, respectively.
Calculating the nuclear-to-cytoplasmic ratio of the cells in each target frame, wherein the specific method comprises the following steps:
intercepting an area containing corresponding cells from an original urothelial cell section image according to a target frame, and respectively restoring the central coordinates (x, y) of the unitized target frame and the width, height w and height h of the unitized target frame in order to restore a real scale, wherein the specific formula is as follows:
wherein, W and H are respectively the height and width of the original urothelial cell section image. Coordinates (x) of upper left corner of target frame min ,y min ) And the coordinates of the lower right corner (x) max ,y max ) The calculation formula of (a) is as follows:
and (3) calculating the perimeter area ratio of the cells, wherein the specific method comprises the following steps:
generally, we describe pictures using RGB or BGR color spaces, where R represents red, G represents green, and B represents blue, all between 0-255. The mixing of the three primary colors red, green and blue can form other colors. The Gray level image has only one dimension, three channels of the image of the RGB color space need to be transformed, and the Gray level Gray of the corresponding pixel after the transformation is shown by the following formula:
in the formula, R, G and B respectively represent values of red, green and blue color channels. The value range of each pixel of the gray image is 0-255, and the larger the pixel value is, the whiter the color is, otherwise, the blacker the color is. 255 for white and 0 for black.
The grayscale image is denoised using gaussian filtering, with a one-dimensional gaussian distribution as follows:
the two-dimensional gaussian distribution is as follows:
where u or (u, v) is the center point coordinate and σ is the standard deviation. It is subjected to a filtering process by setting a convolution kernel of k × k.
And (3) carrying out binarization processing on the image, wherein a specific formula is as follows:
cell boundaries were obtained by contour scanning. The perimeter is calculated by contour approximation using the Ramer-Douglas-Peucker (RDP) algorithm. Given the start and end points of the curve, the algorithm will first find the vertex of the maximum distance from the line connecting the two reference points, which will be called max _ point. If the max _ point distance is less than the threshold, all vertices between the start and end points are automatically ignored, making the curve a straight line. If max _ point exceeds the threshold, the algorithm is repeated recursively, resulting in a pixel perimeter of the cell.
The area within the contour is calculated using the Green formula as follows:
calculating a perimeter-to-area ratio Rate using a pixel perimeter periodeter and an area of a corresponding cell P-A The formula is as follows:
example 3
As shown in fig. 1 to 7, this example 3 provides a method for screening positive mutant cells based on perimeter-to-area ratio, which is implemented as a schematic diagram shown in fig. 1, and comprises the following processing steps (fig. 1):
step S1, acquiring a slice image (figure 2) of urothelial cells, wherein 17900 images are obtained;
s2, detecting all cells in the slice by using a YOLOv5 target detection algorithm, wherein the method comprises the following steps:
300 slice images of urothelial cells were manually labeled, as per 7:3, dividing the training set into a training set and a verification set, training 100 rounds based on a YOLOv5x pre-training model, and storing a YOLOv5x _ best. And (4) carrying out target detection on all pictures in the data set by using a YOLOv5x _ best.pt model, and storing the detection result in a YOLO format.
Step S3, obtaining individual cells in the slice image of each urothelial cell (fig. 3), respectively, the method comprising:
intercepting an area containing corresponding cells in an original urothelial cell slice image according to a target frame, and respectively restoring the central coordinates (x, y) of the unitized target frame and the width, height w and height h of the unitized target frame in order to restore a real scale, wherein the specific formula is as follows:
wherein, W and H are respectively the height and width of the original urothelial cell section image. Coordinates (x) of upper left corner of target frame min ,y min ) And the coordinates of the lower right corner (x) max ,y max ) The calculation formula of (c) is as follows:
each original urothelium cell slice image can obtain single cell pictures with different numbers of 0-100.
S4, carrying out gray processing on the single cell picture, wherein the method comprises the following steps:
three channels of the image in the RGB color space are transformed, and the Gray value Gray of the corresponding pixel after transformation is shown in the following formula:
in the formula, R, G and B respectively represent values of red, green and blue color channels. The value range of each pixel of the gray image is 0-255, and the larger the pixel value is, the whiter the color is, otherwise, the blacker the color is. 255 for white and 0 for black.
S5, denoising by Gaussian filtering, wherein the method comprises the following steps:
wherein (u, v) is the center point coordinate, σ 2 Is the variance.
S6, carrying out binarization processing on the picture subjected to Gaussian filtering processing, wherein the method comprises the following steps:
and S7, carrying out contour scanning on the image subjected to the binarization processing to obtain a cell boundary, and calculating the perimeter and the area of the cell. The method comprises the following steps:
and (3) carrying out contour approximation by using a Ramer-Douglas-Peucker (RDP) algorithm to calculate the perimeter. Given the start and end points of the curve, the algorithm will first find the vertex of the maximum distance from the line connecting the two reference points, which will be called max _ point. If the max _ point distance is less than the threshold, all vertices between the start and end points are automatically ignored, making the curve a straight line. If max _ point exceeds the threshold, the algorithm is repeated recursively, resulting in a pixel perimeter of the cell.
The area within the contour is calculated using the Green formula as follows:
s8, calculating the perimeter area ratio, and judging whether the cells are positive mutant cells or not, wherein the method comprises the following steps:
calculating the perimeter area ratio Rate using the pixel perimeter period and the area of the corresponding cell P-A The formula is as follows:
example 4
Embodiment 4 of the present invention provides a non-transitory computer readable storage medium for storing computer instructions which, when executed by a processor, implement a method for screening positive mutant cells based on perimeter-to-area ratio, the method comprising:
acquiring a slice image of the cell;
detecting all cells in the slices by using a YOLOv5 target detection algorithm;
respectively acquiring single cells in slice images of each cell;
carrying out gray level processing on the single cell picture;
denoising by Gaussian filtering;
carrying out binarization processing on the image subjected to Gaussian filtering processing;
carrying out contour scanning on the image subjected to binarization processing to obtain a cell boundary, and calculating the perimeter and the area of the cell;
calculating the area ratio of the perimeter;
and judging whether the cells are mutation positive cells or not according to the calculated perimeter area ratio.
Example 5
Example 5 of the present invention provides a computer program (product) comprising a computer program for implementing, when running on one or more processors, a method of screening for positively mutated cells based on perimeter to area ratio, the method comprising:
acquiring a slice image of the cell;
detecting all cells in the slices by using a YOLOv5 target detection algorithm;
respectively acquiring single cells in slice images of each cell;
carrying out gray level processing on the single cell picture;
denoising by Gaussian filtering;
carrying out binarization processing on the image subjected to Gaussian filtering processing;
carrying out contour scanning on the image subjected to the binarization processing to obtain a cell boundary, and calculating the perimeter and the area of the cell;
calculating the area ratio of the perimeter;
and judging whether the cells are mutation positive cells or not according to the calculated perimeter area ratio.
Example 6
An embodiment 6 of the present invention provides an electronic device, including: a processor, a memory, and a computer program; wherein a processor is coupled to the memory, the computer program stored in the memory, and when the electronic device is run, the processor executes the computer program stored in the memory to cause the electronic device to execute instructions to implement a method for screening positively mutated cells based on perimeter to area ratio, the method comprising:
acquiring a slice image of the cell;
detecting all cells in the slices by using a YOLOv5 target detection algorithm;
respectively acquiring single cells in slice images of each cell;
carrying out gray level processing on the single cell picture;
denoising by Gaussian filtering;
carrying out binarization processing on the image subjected to Gaussian filtering processing;
carrying out contour scanning on the image subjected to the binarization processing to obtain a cell boundary, and calculating the perimeter and the area of the cell;
calculating the perimeter area ratio;
and judging whether the cells are mutation positive cells or not according to the calculated perimeter area ratio.
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 the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts based on the technical solutions disclosed in the present invention.
Claims (10)
1. A method for screening positive mutant cells based on perimeter to area ratio, comprising:
acquiring a slice image of the cell;
detecting all cells in the slices by using a YOLOv5 target detection algorithm;
respectively acquiring single cells in slice images of each cell;
carrying out gray level processing on the single cell picture;
denoising by Gaussian filtering;
carrying out binarization processing on the image subjected to Gaussian filtering processing;
carrying out contour scanning on the image subjected to the binarization processing to obtain a cell boundary, and calculating the perimeter and the area of the cell;
calculating the area ratio of the perimeter;
and judging whether the cells are mutation positive cells or not according to the calculated perimeter area ratio.
2. The method for screening positive mutant cells based on perimeter-to-area ratio according to claim 1, wherein separately obtaining individual cells in the slice image of each urothelial cell comprises:
intercepting an area containing corresponding cells from an original urothelial cell section image according to a target frame, and respectively restoring the central coordinates (x, y) of the unitized target frame and the width, height w and height h of the unitized target frame in order to restore a real scale, wherein the specific formula is as follows:
wherein, W and H are respectively the height and width of the original urothelial cell section image.
3. The method for screening positive mutant cells based on perimeter-to-area ratio as claimed in claim 1, wherein the grey scale processing is performed on the single cell picture, comprising:
converting three channels of the image of the RGB color space, wherein the Gray value Gray of the corresponding pixel after conversion is shown as the following formula:
in the formula, R, G and B respectively represent values of red, green and blue color channels.
4. The method of claim 1, wherein the denoising using gaussian filtering comprises:
wherein (u, v) is the center coordinates, σ 2 Is a variance of。
Carrying out binarization processing on the picture subjected to Gaussian filtering processing:
5. the method for screening positive mutant cells based on the perimeter-to-area ratio as claimed in claim 4, wherein the image after binarization processing is subjected to contour scanning to obtain cell boundaries, and the perimeter and the area of the cells are calculated, including calculating the perimeter by contour approximation using Ramer-Douglas-Peucker (RDP) algorithm: given the starting and ending points of the curve, first find the vertex of the maximum distance from the line connecting the two reference points, called max _ point; if the max _ point distance is smaller than the threshold value, ignoring all vertexes between the starting point and the end point, and enabling the curve to be a straight line; if max _ point exceeds the threshold value, the algorithm is repeated recursively to obtain the perimeter of the cell;
the area within the contour is calculated using the Green formula as follows:
6. the method of claim 5, wherein the perimeter-to-area ratio is calculated to determine whether the cell is a positive mutant cell by:
calculating the perimeter area ratio Rate using the pixel perimeter period and the area of the corresponding cell P-A The formula is as follows:
7. a system for screening positive mutant cells based on perimeter to area ratio, comprising:
the acquisition module is used for acquiring a slice image of the cell;
the detection module is used for detecting all cells in the slice by using a YOLOv5 target detection algorithm;
the extraction module is used for respectively acquiring single cells in the slice image of each cell;
the processing module is used for carrying out gray processing on the single cell picture, carrying out noise reduction by using Gaussian filtering and carrying out binarization processing on the picture after the Gaussian filtering processing;
the calculation module is used for carrying out contour scanning on the image after the binarization processing to obtain a cell boundary and calculating the perimeter and the area of the cell; calculating the perimeter area ratio;
and the judging module is used for judging whether the cells are mutation positive cells or not according to the calculated perimeter area ratio.
8. A non-transitory computer-readable storage medium storing computer instructions which, when executed by a processor, implement the method of screening positive mutant cells based on perimeter-to-area ratio according to any one of claims 1-6.
9. A computer program product comprising a computer program which, when run on one or more processors, is for implementing a method for screening positively mutated cells based on perimeter to area ratio as claimed in any one of claims 1 to 6.
10. An electronic device, comprising: a processor, a memory, and a computer program; wherein a processor is connected to the memory, a computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory to cause the electronic device to execute instructions for implementing the method for screening positively mutated cells based on perimeter to area ratio according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211100186.9A CN115641294A (en) | 2022-09-09 | 2022-09-09 | Method and system for screening positive mutant cells based on perimeter-area ratio |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211100186.9A CN115641294A (en) | 2022-09-09 | 2022-09-09 | Method and system for screening positive mutant cells based on perimeter-area ratio |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115641294A true CN115641294A (en) | 2023-01-24 |
Family
ID=84941720
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211100186.9A Pending CN115641294A (en) | 2022-09-09 | 2022-09-09 | Method and system for screening positive mutant cells based on perimeter-area ratio |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115641294A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116109636A (en) * | 2023-04-13 | 2023-05-12 | 北京中超伟业信息安全技术股份有限公司 | Magnetic medium destruction processing method and system based on visual monitoring |
-
2022
- 2022-09-09 CN CN202211100186.9A patent/CN115641294A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116109636A (en) * | 2023-04-13 | 2023-05-12 | 北京中超伟业信息安全技术股份有限公司 | Magnetic medium destruction processing method and system based on visual monitoring |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111814867B (en) | Training method of defect detection model, defect detection method and related device | |
| US10719937B2 (en) | Automated detection and trimming of an ambiguous contour of a document in an image | |
| WO2021109876A1 (en) | Image processing method, apparatus and device, and storage medium | |
| CN112308095A (en) | Picture preprocessing and model training method and device, server and storage medium | |
| CN104966285B (en) | A kind of detection method of salient region | |
| Machairas et al. | Waterpixels: Superpixels based on the watershed transformation | |
| CN107507173A (en) | A kind of full slice image without refer to intelligibility evaluation method and system | |
| CN111680690B (en) | Character recognition method and device | |
| CN104036468B (en) | Single-frame image super-resolution reconstruction method based on the insertion of pre-amplification non-negative neighborhood | |
| CN111489322B (en) | Method and device for adding sky filter to static picture | |
| CN116580028B (en) | Object surface defect detection method, device, equipment and storage medium | |
| CN106447656B (en) | Rendering flaw image detecting method based on image recognition | |
| CN111008642A (en) | High-resolution remote sensing image classification method and system based on convolutional neural network | |
| CN115641294A (en) | Method and system for screening positive mutant cells based on perimeter-area ratio | |
| CN114494739B (en) | Toner mixing effect detection method based on artificial intelligence | |
| CN108171683B (en) | Cell counting method adopting software for automatic identification | |
| CN116758080A (en) | Method and system for detecting screen printing defects of solar cell | |
| CN117809123B (en) | Anomaly detection and reconstruction method and system for double-stage image | |
| CN111553927B (en) | Checkerboard corner detection method, detection system, computer device and storage medium | |
| JP2014106713A (en) | Program, method, and information processor | |
| CN113223098A (en) | Preprocessing optimization method for image color classification | |
| Zhao et al. | Saliency map-aided generative adversarial network for raw to rgb mapping | |
| Ancuti et al. | Image decolorization based on information theory | |
| CN116703744A (en) | Remote sensing image dodging and color homogenizing method and device based on convolutional neural network | |
| Siddiqui et al. | Hierarchical color correction for camera cell phone images |
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 |