CN113470028A - Chromosome karyotype image quality evaluation method, chromosome analyzer, and storage medium - Google Patents
Chromosome karyotype image quality evaluation method, chromosome analyzer, and storage medium Download PDFInfo
- Publication number
- CN113470028A CN113470028A CN202111029680.6A CN202111029680A CN113470028A CN 113470028 A CN113470028 A CN 113470028A CN 202111029680 A CN202111029680 A CN 202111029680A CN 113470028 A CN113470028 A CN 113470028A
- Authority
- CN
- China
- Prior art keywords
- chromosome
- image
- cluster
- karyotype
- chromosomes
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- 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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10056—Microscopic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Quality & Reliability (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The application provides a chromosome karyotype image quality evaluation method, a chromosome analyzer and a storage medium, wherein a chromosome contour is extracted from a chromosome karyotype image according to a preset contour detection algorithm; carrying out dispersion analysis on each chromosome contour to obtain a first number of various cluster chromosomes and a second number of non-cluster chromosomes, and carrying out banding definition analysis on each non-cluster chromosome to obtain the banding definition of the chromosome karyotype image; and determining the quality of the chromosome karyotype image according to the banding definition of the chromosome karyotype image. The method and the device realize the acquisition of the number of various cluster chromosomes and the banding definition of the chromosome karyotype image in the chromosome karyotype image by adopting an image processing technology, further evaluate the quality of the chromosome karyotype image according to the number of various cluster chromosomes and the banding definition of the chromosome karyotype image, and can effectively reduce the difficulty of subsequent chromosome karyotype analysis and improve the accuracy of the analysis.
Description
Technical Field
The application relates to the technical field of chromosome analysis, in particular to a chromosome karyotype image quality evaluation method, a chromosome analyzer and a storage medium.
Background
Since chromosomes are important carriers of human genetic information, chromosome analysis is the most important and important approach for the diagnosis of congenital genetic diseases. At present, the conventional karyotype analysis mainly includes that after a cell image of metaphase chromosomes is shot through an electron microscope, the chromosome image is segmented to obtain 46 chromosome examples, and finally, the obtained chromosome examples are classified to generate a cell chromosome karyotype chart. However, due to the non-rigid nature of chromosomes, chromosomes in cell images are different in posture and shape and randomly overlapped and crossed together, so that great challenges are brought to chromosome karyotype analysis, and currently, in the process of chromosome karyotype analysis, image quality is mainly evaluated according to personal experience of analysts, so that the accuracy of karyotype analysis results is improved, and the difficulty of subsequent analysis is increased.
Disclosure of Invention
The application provides a chromosome karyotype image quality evaluation method, a device and a storage medium, aiming at obtaining the number of various cluster chromosomes in a chromosome karyotype image and the banding resolution of the chromosome karyotype image through an image processing technology, further realizing evaluation on the chromosome karyotype image quality according to the number of various cluster chromosomes and the banding resolution of the chromosome karyotype image, and effectively reducing the difficulty of subsequent chromosome karyotype analysis and improving the accuracy of analysis.
In a first aspect, an embodiment of the present application provides a method for evaluating quality of a karyotype image, including:
obtaining a chromosome karyotype image, and extracting a chromosome contour from the chromosome karyotype image according to a preset contour detection algorithm;
performing dispersion degree analysis on each chromosome contour to obtain a first number of various cluster chromosomes and a second number of non-cluster chromosomes;
carrying out banding definition analysis on each non-cluster chromosome to obtain the banding definition of the chromosome karyotype image;
and determining the quality of the chromosome karyotype image according to the number of various cluster chromosomes and the banding definition of the chromosome karyotype image.
In a second aspect, the present application provides a chromosome analyzer, which includes a memory and a processor;
the memory is used for storing a computer program;
the processor is configured to execute the computer program and, when executing the computer program, implement the steps of the karyotype image quality assessment method according to the first aspect.
In a third aspect, embodiments of the present application further provide a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the computer program causes the processor to implement the steps of the karyotype image quality assessment method according to the first aspect.
The embodiment of the application provides a chromosome karyotype image quality evaluation method, a chromosome analyzer and a storage medium, wherein a chromosome contour is extracted from a chromosome karyotype image according to a preset contour detection algorithm; carrying out dispersion analysis on each chromosome contour to obtain a first number of various cluster chromosomes and a second number of non-cluster chromosomes, and carrying out banding definition analysis on each non-cluster chromosome to obtain the banding definition of the chromosome karyotype image; and determining the quality of the chromosome karyotype image according to the number of various cluster chromosomes and the banding definition of the chromosome karyotype image. The method and the device realize the acquisition of the number of various cluster chromosomes and the banding definition of the chromosome karyotype image in the chromosome karyotype image by adopting an image processing technology, further evaluate the quality of the chromosome karyotype image according to the number of various cluster chromosomes and the banding definition of the chromosome karyotype image, and can effectively reduce the difficulty of subsequent chromosome karyotype analysis and improve the accuracy of the analysis.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure of the embodiments of the application.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, 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 some embodiments of the present application, 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 flow chart of an implementation of a chromosome karyotype image quality assessment method according to an embodiment of the present application;
FIG. 2a is a schematic block diagram of a first image provided in an embodiment of the present application;
FIG. 2b is a schematic block diagram of a second image provided by an embodiment of the present application;
FIG. 2c is a schematic structural view of a third image;
FIG. 2d is a schematic illustration of the effect of the third image after erosion dilation;
FIG. 2e is a schematic representation of a chromosome contour provided in an embodiment of the present application;
FIG. 3 is a flowchart illustrating an implementation of S102 in FIG. 1;
FIG. 4 is a schematic structural diagram of various types of cluster chromosomes and non-cluster chromosomes provided in the examples of the present application;
FIG. 5a is a flowchart of a specific implementation of S103 in FIG. 1;
FIG. 5b is a schematic diagram of a non-cluster chromosome provided in an embodiment of the present application;
FIG. 5c is a schematic diagram of edge information of non-cluster chromosomes according to an embodiment of the present application;
FIG. 5d is a schematic diagram of texture information of non-clustered chromosomes according to an embodiment of the present application;
fig. 6 is a schematic block diagram of a chromosome analyzer provided in an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The flow diagrams depicted in the figures are merely illustrative and do not necessarily include all of the elements and operations/steps, nor do they necessarily have to be performed in the order depicted. For example, some operations/steps may be decomposed, combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
Referring to fig. 1, fig. 1 is a schematic flow chart illustrating an implementation of a chromosome karyotype image quality assessment method according to an embodiment of the present application. The chromosome karyotype image quality evaluation method provided by this embodiment may be executed by a chromosome analyzer, which includes but is not limited to a single server, a server cluster or a personal computer, and other electronic devices with higher computing power. The details are as follows:
s101, obtaining a chromosome karyotype image, and extracting a chromosome contour from the chromosome karyotype image according to a preset contour detection algorithm.
The chromosome karyotype image is a chromosome metaphase cell image shot by a camera, and the magnification of chromosomes in the shot chromosome metaphase cell image is different along with the difference of the magnification of the selected camera, for example, a camera with the magnification of 100 of an objective lens can be selected to shoot the chromosome metaphase image with the magnification of 100.
In the embodiment of the application, the chromosome karyotype image is preprocessed through a preset contour detection algorithm, and a chromosome contour is extracted. Specifically, the preset contour detection algorithm comprises an image binarization algorithm and an edge detection algorithm; by carrying out binarization processing on the chromosome karyotype image, the gray value of the pixel points on the chromosome karyotype image can be set to be 0 or 255, so that the whole chromosome karyotype image has a black-and-white effect, the data volume in the chromosome karyotype image is greatly reduced, and a clear target contour, namely a chromosome contour, can be highlighted after edge detection is carried out.
Illustratively, the extracting a chromosome contour from the chromosome karyotype image according to a preset contour detection algorithm may include: carrying out gray level processing on the chromosome karyotype image to obtain a first image; carrying out binarization processing on the first image to obtain a second image, wherein the second image comprises a foreground area and a background area; and carrying out foreground region detection on the second image based on an edge detection algorithm, and extracting the chromosome outline from the chromosome karyotype image.
Specifically, the karyotype image may be subjected to Gray processing by Gray =0.299R +0.587G +0.114B, so as to convert the three-channel RGB karyotype image into a single-channel Gray map, that is, the first image. Exemplarily, as shown in fig. 2a, it is a schematic structural diagram of a first image provided in the embodiment of the present application. As can be seen from fig. 2a, the first image obtained after performing the gray scale processing on the chromosome karyotype image, specifically, the first image includes a gray background 201 and a chromosome 202.
In addition, in the embodiment of the present application, the process of performing binarization processing on the first image to obtain a second image may include: and carrying out binarization processing on the first image by using an Otsu algorithm OTSU to obtain a binarized image with black background and white chromosome, namely the second image. Specifically, the background region of the second image is displayed in black, and the foreground region, that is, the included chromosome, is displayed in white.
Specifically, the OTSU algorithm calculates an intra-class variance and an inter-class variance of two types of pixels respectively by assuming that a first image includes two types of pixels, specifically, a foreground pixel and a background pixel, finds a gray level that minimizes the intra-class variance and maximizes the inter-class variance, and converts the first image into a second image by using the gray level as a threshold of the OTSU, where the second image includes a black background region (a gray value of a pixel is 0) and a white target region (a gray value of a pixel is 255); in this example, the white target region is a chromosome. Exemplarily, as shown in fig. 2b, it is a schematic structural diagram of the second image provided in the embodiment of the present application.
It should be noted that, due to the fact that the selected camera parameters are different and problems such as light difference or hand shake exist in the shooting process, the photographed chromosome karyotype image may have the problem of inconsistent lines, and the like, the first image is subjected to binarization processing to obtain a second image, and the first image is subjected to normalization processing before the second image comprises a foreground region and a background region, so that the problem of inconsistent image lines caused in the shooting process is solved, and a third image after the normalization processing is obtained; correspondingly, the binarizing processing is performed on the first image to obtain a second image, and the second image includes a foreground region and a background region, including: and carrying out binarization processing on the third image to obtain a second image, wherein the second image comprises a foreground area and a background area. Illustratively, the first image may be normalized by means of minimum and maximum MINMAX, and the gray value of the first image is normalized to [0,255] so that the chromosome texture on the chromosome karyotype image is consistent. Illustratively, as shown in fig. 2c, the schematic structure diagram of the third image obtained after the second image shown in fig. 2b is subjected to the normalization process.
Alternatively, as can be seen from fig. 2c, in the third image, there are slight conglutinations between chromosomes and objects with a small area around each chromosome, in this embodiment, the objects with an area smaller than the preset area are called as impurities or noise, and before the third image is subjected to binarization processing to obtain the second image, the third image may be subjected to erosion dilation to break the slight conglutinations between chromosomes and remove the impurities without significantly changing the area shape of each chromosome. Exemplarily, as shown in fig. 2d, it is a schematic diagram of the effect of the third image in fig. 2c after erosion expansion.
Specifically, the process of performing binarization on the third image to obtain the second image is the same as the process of performing binarization on the first image to obtain the second image, and details are not repeated here.
In addition, in an embodiment of the present application, performing foreground region detection on the second image based on an edge detection algorithm, and extracting the chromosome contour from the chromosome karyotype image may include: aiming at any first pixel point with the gray value of 255 in the second image, determining second pixel points adjacent to the first pixel point and the gray value of each second pixel point; if the number of the second pixel points with the gray value of 255 is larger than or equal to the preset number, determining that the first pixel point is a point inside the chromosome, and setting the gray value of the first pixel point to be 0; if the number of the second pixel points with the gray value of 255 is smaller than the preset number, determining that the first pixel point is a point on the chromosome contour, and keeping the gray value of the first pixel point unchanged; and connecting all the first pixel points with the gray value of 255 to obtain the chromosome contour. Exemplarily, as shown in fig. 2e, the chromosome contour diagram is obtained by performing foreground region detection on the second image shown in fig. 2 b.
S102, carrying out dispersion degree analysis on each chromosome contour to obtain a first number of various cluster chromosomes and a second number of non-cluster chromosomes.
In an embodiment of the present application, the process of performing the dispersion analysis on each of the chromosome profiles includes: and calculating the perimeter of each chromosome contour, the first area surrounded by each chromosome contour, and the ratio of each perimeter to each first area, and further determining the number of various cluster chromosomes and non-cluster chromosomes by combining the second area of the chromosome image. Specifically, the circumference of each chromosome contour is equal to the number of first pixel points included in each chromosome contour; the first area enclosed by each chromosome contour is equal to the number of second pixel points enclosed by each chromosome contour.
Wherein, each cluster chromosome comprises a small cluster chromosome, a middle cluster chromosome and a large cluster chromosome; specifically, a minicluster chromosome refers to a cluster of chromosomes having 2 to 3 crossover overlaps; the cluster chromosomes refer to chromosome clusters with 3 to 4 crossed and overlapped chromosomes; large clusters of chromosomes refer to clusters of chromosomes having more than 4 crossover overlaps. Furthermore, non-cluster chromosomes refer to independent chromosomes that do not cross or overlap.
Illustratively, as shown in fig. 3, fig. 3 is a flowchart of a specific implementation of S102 in fig. 1. As shown in fig. 3, in the present embodiment, S102 includes S1021 to S1024, which are detailed as follows:
s1021, obtaining a target chromosome contour, wherein the target chromosome contour is any chromosome contour in all chromosome contours.
It is to be understood that, in the present embodiment, the process of determining a chromosome cluster in a chromosome contour is described by taking any chromosome contour of all the chromosome contours as an example. The arbitrary chromosome contour refers to a target chromosome contour composed of continuous pixels with a pixel value of 255, and the target chromosome contour may include any number of connected or crossed chromosomes or independent chromosomes.
S1022, calculating a first perimeter of the target chromosome contour and a first area enclosed by the target chromosome contour.
In this embodiment, the first perimeter of the target chromosome contour is equal to the number of first pixel points (the gray value of the pixel point is 255) on the target chromosome contour, and the first area enclosed by the target chromosome contour is equal to the number of second pixel points (the gray value of the pixel point is 0) enclosed in the target chromosome contour.
S1023, determining a preset cluster-like chromosome or non-cluster chromosome included by the target chromosome contour according to the first area and the second area of the chromosome karyotype image.
Specifically, the proportion of the first area to the second area is calculated, and a preset cluster-like chromosome or a non-cluster chromosome included in the target chromosome profile is determined according to the proportion of the first area to the second area. Illustratively, if the ratio of the first area to the second area is between 1/4000 and 1/400, determining that the target chromosome profile includes a non-cluster chromosome; determining that the target chromosome profile includes a small cluster chromosome if the ratio of the first area to the second area is between 1/400 and 1/230; determining that the target chromosome profile includes a middle cluster chromosome if the first area is between 1/230 and 1/120 in proportion to the second area; and if the proportion of the first area to the second area is greater than 1/120, determining that the target chromosome contour comprises a large cluster of chromosomes.
And S1024, obtaining a first number of the cluster chromosomes and a second number of the non-cluster chromosomes according to the determined preset cluster chromosomes and non-cluster chromosomes corresponding to the target chromosomes.
Specifically, the number of different cluster chromosomes and the number of non-cluster chromosomes are respectively counted to obtain a first number of the cluster chromosomes of each type and a second number of the non-cluster chromosomes.
It should be noted that, in the chromosome karyotype image, the chromosome karyotype image may include other impurities besides the chromosome due to the unstable parameters or the influence of the surrounding environment during the shooting process, which is referred to as noise in the present application. Correspondingly, in order to remove noise in the karyotype image, in an alternative implementation, before determining the preset cluster-like chromosome or non-cluster chromosome included in the target chromosome profile according to the first area and the second area of the karyotype image, the following steps a1 to A3 are further included for determining noise in the karyotype image, which are described in detail as follows:
a1, determining a first ratio of a first perimeter of the target chromosome contour to a first area encompassed by the target chromosome contour.
A2, determining a first noise in the karyotype image based on the first area, the second area, and the first ratio.
A3, determining a second noise in the karyotype image based on the first area and the second area, or based on the first perimeter and the second perimeter.
Optionally, in step a2, determining a first noise in the karyotype image from the first area, the second area, and the first ratio includes: and calculating the proportion of the first area to the second area, and determining first noise in the chromosome karyotype image according to the proportion of the first area to the second area and the first ratio. Specifically, if the ratio of the first area to the second area of a target contour is greater than 1/300 and the first ratio is greater than 0.025, the target contour is determined to be a first noise; alternatively, the first noise is generated by impurities such as bubbles, dust, and the like.
In step a3, determining a second noise in the karyotype image based on the first area and the second area, or based on the first perimeter and the second perimeter, may include: calculating the proportion of the first area to the second area, and determining second noise in the chromosome karyotype image according to the proportion of the first area to the second area; or calculating the proportion of the first perimeter to the second perimeter, and determining second noise in the chromosome karyotype image according to the proportion of the first perimeter to the second perimeter. Illustratively, if the proportion of the first area of the target contour to the second area is less than 1/4000, the target contour is determined to be the second noise, or if the proportion of the first perimeter of the target contour to the second perimeter is less than 1/100, the target contour is determined to be the second noise. Specifically, the second noise is caused by cell debris.
Illustratively, as shown in fig. 4, is a schematic structural diagram of various cluster chromosomes and non-cluster chromosomes provided in the embodiments of the present application. As can be seen from fig. 4, in the present embodiment, the karyotype chart includes non-cluster chromosomes 401, small cluster chromosomes 402, and medium cluster chromosomes 403, and does not include large cluster chromosomes. It is understood that different chromosome karyotype images contain different cluster chromosome types, and the number of clusters and the number of non-clusters are also different, and will not be described herein again.
S103, carrying out banding definition analysis on each non-cluster chromosome to obtain the banding definition of the chromosome karyotype image.
And performing edge detection on each non-cluster chromosome by adopting an edge detection algorithm, such as a canny algorithm, to obtain texture information of each non-cluster chromosome, and determining the banding definition of the chromosome karyotype image according to the texture information of each non-cluster chromosome.
Illustratively, as shown in fig. 5a, fig. 5a is a flowchart of a specific implementation of S103 in fig. 1. As can be seen from fig. 5a, in the present embodiment, S103 includes S1031 to S1033, which are detailed as follows:
and S1031, obtaining a target non-cluster chromosome, wherein the target non-cluster chromosome is any non-cluster chromosome in all the non-cluster chromosomes.
In the present embodiment, the process of determining the banding definition of the karyotype image is exemplarily described with an arbitrary chromosome of all the non-cluster chromosomes as a target non-cluster chromosome.
S1032, processing the target non-cluster chromosome based on an edge detection algorithm to obtain texture information of the target non-cluster chromosome.
Alternatively, the edge detection algorithm may be any one of Roberts Cross operator, Prewitt operator Sobel operator, Kirsch operator, Canny operator, compass operator, etc., and in this embodiment, the Canny edge detection algorithm is taken as an example for exemplary illustration.
Specifically, the processing of the target non-cluster chromosome based on an edge detection algorithm to obtain texture information of the target non-cluster chromosome includes: performing Gaussian filtering processing on the target non-cluster chromosome to obtain a smooth image of the target non-cluster chromosome; determining the gradient amplitude and the gradient direction of the smooth image, and determining the texture information of the target non-cluster chromosome according to the gradient amplitude and the gradient direction. Determining texture information of the target non-cluster chromosome according to the gradient magnitude and the gradient direction may include: carrying out non-maximum suppression on the gradient amplitude along the gradient direction to obtain edge information of the target non-clustered chromosome; and deleting the edge contour of the edge information to obtain the texture information of the target non-cluster chromosome.
S1033, determining the banding definition of the chromosome karyotype image according to the texture information of each target non-cluster chromosome.
Wherein the texture information includes the number of textures, and determining the banding definition of the chromosome karyotype image according to the texture information of each target non-cluster chromosome includes: and calculating the mean value of the texture numbers of all the non-cluster chromosomes, and determining the banding definition of the chromosome karyotype image according to the mean value of the texture numbers and a preset texture number threshold value. For example, the texture number threshold includes a first threshold and a second threshold, and the first threshold is greater than the second threshold; if the mean value of the texture numbers is larger than a first threshold value (3 are assumed), determining that the banding definition of the chromosome karyotype image is equal to a first definition value; if the mean value of the texture numbers is smaller than a first threshold value and larger than a second threshold value (assumed to be 1), determining that the banding definition of the chromosome karyotype image is equal to a second definition value; and if the mean value of the texture numbers is smaller than a first threshold value, determining that the banding definition of the chromosome karyotype image is equal to a third definition value. Wherein the first articulation value is greater than the second articulation value, which is greater than the third articulation value. Illustratively, a first sharpness value represents sharpness, a second sharpness value represents slight blurring, and a third sharpness value represents blurring.
Exemplarily, as shown in fig. 5b to 5d, fig. 5b is a schematic diagram of a non-cluster chromosome provided in an embodiment of the present application; FIG. 5c is a schematic diagram of edge information of non-cluster chromosomes according to an embodiment of the present application; fig. 5d is a schematic diagram of texture information of non-cluster chromosomes according to an embodiment of the present application.
And S104, determining the quality of the chromosome karyotype image according to the number of various cluster chromosomes and the banding definition of the chromosome karyotype image.
Specifically, the association mapping relationship between the quality level of the chromosome karyotype image and the number of each cluster chromosome and the banding definition of the chromosome karyotype image is preset, and the quality of the chromosome karyotype image can be determined according to the association mapping relationship.
Illustratively, the quality of the karyotype image includes four levels, a level a karyotype image, a level B karyotype image, a level C karyotype image, and a level D karyotype image. In an embodiment, it can be determined according to the association mapping relationship that the number of chromosomes correspondingly included in the level-a chromosome karyotype image is greater than or equal to 30, the number of non-cluster chromosomes is greater than or equal to 25, the number of small cluster chromosomes is less than or equal to a third threshold value 3, the number of middle cluster chromosomes is less than or equal to 1, the number of large cluster chromosomes is less than or equal to 0, and the banding definition is a first definition value; the number of chromosomes correspondingly contained in the B-level chromosome karyotype image is more than or equal to 25, the number of non-cluster chromosomes is more than or equal to 18, the number of small cluster chromosomes is less than or equal to 6, the number of middle cluster chromosomes is less than or equal to 3, the number of large cluster chromosomes is less than or equal to 1, and the banding definition is a second definition value; the number of chromosomes correspondingly contained in the C-level chromosome karyotype image is more than or equal to 20, the number of non-cluster chromosomes is more than or equal to 10, the number of small cluster chromosomes is less than or equal to 8, the number of middle cluster chromosomes is less than or equal to 5, the number of large cluster chromosomes is less than or equal to 2, and the banding definition is a second definition value; the D-type chromosome karyotype image corresponds to a chromosome karyotype image that does not satisfy any of the above-described types of chromosome karyotype images.
According to the analysis, the chromosome karyotype image quality evaluation method provided by the embodiment of the application extracts the chromosome contour from the chromosome karyotype image according to the preset contour detection algorithm; carrying out dispersion analysis on each chromosome contour to obtain a first number of various cluster chromosomes and a second number of non-cluster chromosomes, and carrying out banding definition analysis on each non-cluster chromosome to obtain the banding definition of the chromosome karyotype image; and determining the quality of the chromosome karyotype image according to the number of various cluster chromosomes and the banding definition of the chromosome karyotype image. The method and the device realize the acquisition of the number of various cluster chromosomes and the banding definition of the chromosome karyotype image in the chromosome karyotype image by adopting an image processing technology, further evaluate the quality of the chromosome karyotype image according to the number of various cluster chromosomes and the banding definition of the chromosome karyotype image, and can effectively reduce the difficulty of subsequent chromosome karyotype analysis and improve the accuracy of the analysis.
Referring to fig. 6, fig. 6 is a schematic block diagram of a chromosome analyzer according to an embodiment of the present application.
Illustratively, the chromosome analyzer 600 may be a server or a terminal device, and the server may be a single server or a server cluster; the terminal device may be an electronic device of a user, such as a mobile phone, a tablet computer, a notebook computer, a desktop computer, or a personal digital assistant, a wearable device, or the like.
The chromosome analyzer 600 includes an image scanning module 61 and an image analysis module 62.
The image scanning module 61 is configured to scan a sample, such as a metaphase cell sample, and generate an image corresponding to the sample, such as a karyotype image; the image analysis module 62 is used for analyzing the image generated by the image scanning module 61, such as performing chromosome karyotype image quality assessment analysis on the chromosome karyotype image generated by the image scanning module 61.
Illustratively, the image analysis module 61 includes a processor 601 and a memory 602, and the processor 601 and the memory 602 are connected by a bus 603, such as an I2C (Inter-integrated Circuit) bus 603.
Specifically, the Processor 601 may be a Micro-controller Unit (MCU), a Central Processing Unit (CPU), a Digital Signal Processor (DSP), or the like.
Specifically, the Memory 602 may be a Flash chip, a Read-Only Memory (ROM) magnetic disk, an optical disk, a usb disk, or a removable hard disk.
Wherein the processor 601 is configured to run a computer program stored in the memory 602 and to implement the steps of the above-mentioned karyotype image quality assessment method when executing the computer program.
Illustratively, the processor 601 is configured to run a computer program stored in the memory 602 and to implement the following steps when executing the computer program:
obtaining a chromosome karyotype image, and extracting a chromosome contour from the chromosome karyotype image according to a preset contour detection algorithm;
performing dispersion degree analysis on each chromosome contour to obtain a first number of various cluster chromosomes and a second number of non-cluster chromosomes;
carrying out banding definition analysis on each non-cluster chromosome to obtain the banding definition of the chromosome karyotype image;
and determining the quality of the chromosome karyotype image according to the number of various cluster chromosomes and the banding definition of the chromosome karyotype image.
In one embodiment, the extracting a chromosome contour from the chromosome karyotype image according to a preset contour detection algorithm includes:
carrying out gray level processing on the chromosome karyotype image to obtain a first image;
carrying out binarization processing on the first image to obtain a second image, wherein the second image comprises a foreground area and a background area;
and carrying out foreground region detection on the second image based on an edge detection algorithm, and extracting the chromosome outline from the chromosome karyotype image.
In an embodiment, before performing binarization processing on the first image to obtain a second image, where the second image includes a foreground region and a background region, the method further includes:
normalizing the first image to obtain a normalized third image;
the binarization processing is carried out on the first image to obtain a second image, wherein the second image comprises a foreground area and a background area, and the binarization processing method comprises the following steps:
and carrying out binarization processing on the third image to obtain a second image, wherein the second image comprises a foreground area and a background area.
In an embodiment, the performing a dispersion analysis on each chromosome contour to obtain a first number of clustered chromosomes and a second number of non-clustered chromosomes of each class includes:
acquiring a target chromosome contour, wherein the target chromosome contour is any chromosome contour in all chromosome contours;
calculating a first perimeter of the target chromosome contour and a first area encompassed by the target chromosome contour;
determining a preset cluster-like chromosome or a non-cluster chromosome included in the target chromosome contour according to the first area and the second area of the chromosome karyotype image;
and obtaining a first number of various cluster chromosomes and a second number of non-cluster chromosomes according to the determined preset cluster chromosomes and non-cluster chromosomes corresponding to the target chromosomes.
In an embodiment, before the determining, according to the first area and the second area of the chromosome karyotype image, whether the target chromosome contour includes a preset cluster-like chromosome or a non-cluster-like chromosome, the method further includes:
determining a first ratio of a first perimeter of the target chromosome contour to a first area encompassed by the target chromosome contour;
determining a first noise in the karyotype image from the first area, the second area, and the first ratio;
determining a second noise in the karyotype image based on the first area and the second area, or based on the first and second perimeters.
In an embodiment, the performing banding definition analysis on each non-cluster chromosome to obtain the banding definition of the karyotype image includes:
obtaining a target non-cluster chromosome, wherein the target non-cluster chromosome is any non-cluster chromosome in all the non-cluster chromosomes;
processing the target non-cluster chromosome based on an edge detection algorithm to obtain texture information of the target non-cluster chromosome;
and determining the banding definition of the chromosome karyotype image according to the texture information of each target non-cluster chromosome.
In an embodiment, the processing the target non-cluster chromosome based on an edge detection algorithm to obtain texture information of the target non-cluster chromosome includes:
performing Gaussian filtering processing on the target non-cluster chromosome to obtain a smooth image of the target non-cluster chromosome;
determining the gradient amplitude and the gradient direction of the smooth image, and determining the texture information of the target non-cluster chromosome according to the gradient amplitude and the gradient direction.
In one embodiment, the determining texture information of the target non-cluster chromosome according to the gradient magnitude and the gradient direction includes:
carrying out non-maximum suppression on the gradient amplitude along the gradient direction to obtain edge information of the target non-clustered chromosome;
and deleting the edge contour of the edge information to obtain the texture information of the target non-cluster chromosome.
The specific principle and implementation manner of the chromosome analyzer provided in the embodiment of the present application are similar to those of the chromosome karyotype image quality assessment method in the foregoing embodiment, and details are not repeated here.
An embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored, and when executed by a processor, the computer program causes the processor to implement the following steps:
obtaining a chromosome karyotype image, and extracting a chromosome contour from the chromosome karyotype image according to a preset contour detection algorithm;
performing dispersion degree analysis on each chromosome contour to obtain a first number of various cluster chromosomes and a second number of non-cluster chromosomes;
carrying out banding definition analysis on each non-cluster chromosome to obtain the banding definition of the chromosome karyotype image;
and determining the quality of the chromosome karyotype image according to the number of various cluster chromosomes and the banding definition of the chromosome karyotype image.
In one embodiment, the extracting a chromosome contour from the chromosome karyotype image according to a preset contour detection algorithm includes:
carrying out gray level processing on the chromosome karyotype image to obtain a first image;
carrying out binarization processing on the first image to obtain a second image, wherein the second image comprises a foreground area and a background area;
and carrying out foreground region detection on the second image based on an edge detection algorithm, and extracting the chromosome outline from the chromosome karyotype image.
In an embodiment, before performing binarization processing on the first image to obtain a second image, where the second image includes a foreground region and a background region, the method further includes:
normalizing the first image to obtain a normalized third image;
the binarization processing is carried out on the first image to obtain a second image, wherein the second image comprises a foreground area and a background area, and the binarization processing method comprises the following steps:
and carrying out binarization processing on the third image to obtain a second image, wherein the second image comprises a foreground area and a background area.
In an embodiment, the performing a dispersion analysis on each chromosome contour to obtain a first number of clustered chromosomes and a second number of non-clustered chromosomes of each class includes:
acquiring a target chromosome contour, wherein the target chromosome contour is any chromosome contour in all chromosome contours;
calculating a first perimeter of the target chromosome contour and a first area encompassed by the target chromosome contour;
determining a preset cluster-like chromosome or a non-cluster chromosome included in the target chromosome contour according to the first area and the second area of the chromosome karyotype image;
and obtaining a first number of various cluster chromosomes and a second number of non-cluster chromosomes according to the determined preset cluster chromosomes and non-cluster chromosomes corresponding to the target chromosomes.
In an embodiment, before the determining, according to the first area and the second area of the chromosome karyotype image, whether the target chromosome contour includes a preset cluster-like chromosome or a non-cluster-like chromosome, the method further includes:
determining a first ratio of a first perimeter of the target chromosome contour to a first area encompassed by the target chromosome contour;
determining a first noise in the karyotype image from the first area, the second area, and the first ratio;
determining a second noise in the karyotype image based on the first area and the second area, or based on the first and second perimeters.
In an embodiment, the performing banding definition analysis on each non-cluster chromosome to obtain the banding definition of the karyotype image includes:
obtaining a target non-cluster chromosome, wherein the target non-cluster chromosome is any non-cluster chromosome in all the non-cluster chromosomes;
processing the target non-cluster chromosome based on an edge detection algorithm to obtain texture information of the target non-cluster chromosome;
and determining the banding definition of the chromosome karyotype image according to the texture information of each target non-cluster chromosome.
In an embodiment, the processing the target non-cluster chromosome based on an edge detection algorithm to obtain texture information of the target non-cluster chromosome includes:
performing Gaussian filtering processing on the target non-cluster chromosome to obtain a smooth image of the target non-cluster chromosome;
determining the gradient amplitude and the gradient direction of the smooth image, and determining the texture information of the target non-cluster chromosome according to the gradient amplitude and the gradient direction.
In one embodiment, the determining texture information of the target non-cluster chromosome according to the gradient magnitude and the gradient direction includes:
carrying out non-maximum suppression on the gradient amplitude along the gradient direction to obtain edge information of the target non-clustered chromosome;
and deleting the edge contour of the edge information to obtain the texture information of the target non-cluster chromosome.
The computer-readable storage medium may be an internal storage unit of the chromosome analyzer in any of the foregoing embodiments, for example, a hard disk or a memory of the terminal. The computer-readable storage medium may also be an external storage device of the terminal, such as a plug-in hard disk provided on the chromosome analyzer, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like.
It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.
It should also be understood that the term "and/or" as used in this application and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
While the invention has been described with reference to specific embodiments, the scope of the invention is not limited thereto, and those skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the invention. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A chromosome karyotype image quality assessment method, comprising:
obtaining a chromosome karyotype image, and extracting a chromosome contour from the chromosome karyotype image according to a preset contour detection algorithm;
performing dispersion degree analysis on each chromosome contour to obtain a first number of various cluster chromosomes and a second number of non-cluster chromosomes;
carrying out banding definition analysis on each non-cluster chromosome to obtain the banding definition of the chromosome karyotype image;
and determining the quality of the chromosome karyotype image according to the number of various cluster chromosomes and the banding definition of the chromosome karyotype image.
2. The method for evaluating the quality of the karyotype image according to claim 1, wherein the extracting the chromosome contour from the karyotype image according to a preset contour detection algorithm comprises:
carrying out gray level processing on the chromosome karyotype image to obtain a first image;
carrying out binarization processing on the first image to obtain a second image, wherein the second image comprises a foreground area and a background area;
and carrying out foreground region detection on the second image based on an edge detection algorithm, and extracting the chromosome outline from the chromosome karyotype image.
3. The method for evaluating the quality of the karyotype image according to claim 2, wherein before the binarizing process is performed on the first image to obtain the second image, the second image including the foreground region and the background region, the method further includes:
normalizing the first image to obtain a normalized third image;
the binarization processing is carried out on the first image to obtain a second image, wherein the second image comprises a foreground area and a background area, and the binarization processing method comprises the following steps:
and carrying out binarization processing on the third image to obtain the second image, wherein the second image comprises a foreground area and a background area.
4. The method for quality assessment of karyotype images according to any one of claims 1 to 3, wherein the performing a dispersion analysis on each of the chromosome profiles to obtain the first number of cluster chromosomes and the second number of non-cluster chromosomes comprises:
acquiring a target chromosome contour, wherein the target chromosome contour is any chromosome contour in all chromosome contours;
calculating a first perimeter of the target chromosome contour and a first area encompassed by the target chromosome contour;
determining a preset cluster-like chromosome or a non-cluster chromosome included in the target chromosome contour according to the first area and the second area of the chromosome karyotype image;
and obtaining a first number of various cluster chromosomes and a second number of non-cluster chromosomes according to the determined preset cluster chromosomes and non-cluster chromosomes corresponding to the target chromosomes.
5. The method for quality assessment of a karyotype image according to claim 4, wherein before the determining the predetermined cluster-like chromosome or non-cluster chromosome included in the target chromosome profile based on the first area and the second area of the karyotype image, further comprising:
determining a first ratio of a first perimeter of the target chromosome contour to a first area encompassed by the target chromosome contour;
determining a first noise in the karyotype image from the first area, the second area, and the first ratio;
determining a second noise in the karyotype image based on the first area and the second area, or based on the first and second perimeters.
6. The method for evaluating the quality of the karyotype image according to claim 4, wherein the analyzing the banding definition of each of the non-cluster chromosomes to obtain the banding definition of the karyotype image comprises:
obtaining a target non-cluster chromosome, wherein the target non-cluster chromosome is any non-cluster chromosome in all the non-cluster chromosomes;
processing the target non-cluster chromosome based on an edge detection algorithm to obtain texture information of the target non-cluster chromosome;
and determining the banding definition of the chromosome karyotype image according to the texture information of each target non-cluster chromosome.
7. The chromosome karyotype image quality assessment method according to claim 6, wherein the processing the target non-cluster chromosome based on an edge detection algorithm to obtain texture information of the target non-cluster chromosome includes:
performing Gaussian filtering processing on the target non-cluster chromosome to obtain a smooth image of the target non-cluster chromosome;
determining the gradient amplitude and the gradient direction of the smooth image, and determining the texture information of the target non-cluster chromosome according to the gradient amplitude and the gradient direction.
8. The chromosome karyotype image quality evaluation method according to claim 7, wherein the determining texture information of the target non-cluster chromosome from the gradient magnitude and the gradient direction includes:
carrying out non-maximum suppression on the gradient amplitude along the gradient direction to obtain edge information of the target non-clustered chromosome;
and deleting the edge contour of the edge information to obtain the texture information of the target non-cluster chromosome.
9. A chromosome analyzer, comprising:
a memory and a processor;
the memory is used for storing a computer program;
the processor, configured to execute the computer program and, when executing the computer program, implement the steps of the karyotype image quality assessment method according to any one of claims 1 to 8.
10. A computer-readable storage medium, wherein the embodiment further provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and the computer program, when executed by a processor, causes the processor to implement the steps of the chromosome karyotype image quality assessment method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111029680.6A CN113470028A (en) | 2021-09-03 | 2021-09-03 | Chromosome karyotype image quality evaluation method, chromosome analyzer, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111029680.6A CN113470028A (en) | 2021-09-03 | 2021-09-03 | Chromosome karyotype image quality evaluation method, chromosome analyzer, and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113470028A true CN113470028A (en) | 2021-10-01 |
Family
ID=77867345
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111029680.6A Pending CN113470028A (en) | 2021-09-03 | 2021-09-03 | Chromosome karyotype image quality evaluation method, chromosome analyzer, and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113470028A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115220622A (en) * | 2021-12-17 | 2022-10-21 | 深圳市瑞图生物技术有限公司 | Chromosome image editing method, analysis device, and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102156996A (en) * | 2011-04-01 | 2011-08-17 | 上海海事大学 | Image edge detection method |
| CN110659717A (en) * | 2018-07-12 | 2020-01-07 | 赛业（广州）生物科技有限公司 | Method and system for intelligently identifying chromosome number |
| CN112489007A (en) * | 2020-11-26 | 2021-03-12 | 华南师范大学 | System and method for evaluating image quality of metaphase cells of chromosomes |
| CN112785566A (en) * | 2021-01-15 | 2021-05-11 | 湖南自兴智慧医疗科技有限公司 | Chromosome metaphase image scoring method and device, electronic equipment and storage medium |
-
2021
- 2021-09-03 CN CN202111029680.6A patent/CN113470028A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102156996A (en) * | 2011-04-01 | 2011-08-17 | 上海海事大学 | Image edge detection method |
| CN110659717A (en) * | 2018-07-12 | 2020-01-07 | 赛业（广州）生物科技有限公司 | Method and system for intelligently identifying chromosome number |
| CN112489007A (en) * | 2020-11-26 | 2021-03-12 | 华南师范大学 | System and method for evaluating image quality of metaphase cells of chromosomes |
| CN112785566A (en) * | 2021-01-15 | 2021-05-11 | 湖南自兴智慧医疗科技有限公司 | Chromosome metaphase image scoring method and device, electronic equipment and storage medium |
Non-Patent Citations (3)
| Title |
|---|
| 姚景侠: "《小麦细胞与分子遗传研究》", 31 October 2000, 南京出版社 * |
| 李荣江 等: "关于中职卫校人类染色体核型分析实验方法的探讨", 《卫生职业教育》 * |
| 王保华 等: "《生物医学电子学高级教程》", 31 March 2001, 东南大学出版社 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115220622A (en) * | 2021-12-17 | 2022-10-21 | 深圳市瑞图生物技术有限公司 | Chromosome image editing method, analysis device, and storage medium |
| CN115220622B (en) * | 2021-12-17 | 2023-09-05 | 深圳市瑞图生物技术有限公司 | Chromosome image editing method, analysis device, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108229526B (en) | Network training method, network training device, image processing method, image processing device, storage medium and electronic equipment | |
| CN108229490B (en) | Key point detection method, neural network training method, device and electronic equipment | |
| CN110516577B (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| US8805077B2 (en) | Subject region detecting apparatus | |
| JP2010525486A (en) | Image segmentation and image enhancement | |
| CN111462086A (en) | Image segmentation method and device and training method and device of neural network model | |
| US8923610B2 (en) | Image processing apparatus, image processing method, and computer readable medium | |
| CN110415237B (en) | Skin flaw detection method, skin flaw detection device, terminal device and readable storage medium | |
| US11430130B2 (en) | Image processing method and computer-readable recording medium having recorded thereon image processing program | |
| CN111882565B (en) | Image binarization method, device, equipment and storage medium | |
| CN114298985B (en) | Defect detection method, device, equipment and storage medium | |
| CN117496560B (en) | Fingerprint line identification method and device based on multidimensional vector | |
| JP2018185265A (en) | Information processor, method for control, and program | |
| CN113470028A (en) | Chromosome karyotype image quality evaluation method, chromosome analyzer, and storage medium | |
| CN114140481A (en) | Edge detection method and device based on infrared image | |
| CN112822413B (en) | Shooting preview method, shooting preview device, terminal and computer readable storage medium | |
| JP2010204947A (en) | Object detection device, object detection method and program | |
| CN117765330A (en) | MRI image-based data labeling method and system | |
| CN111222446B (en) | Face recognition method, face recognition device and mobile terminal | |
| CN107945186A (en) | Method, apparatus, computer-readable recording medium and the terminal device of segmentation figure picture | |
| JP4967045B2 (en) | Background discriminating apparatus, method and program | |
| CN116342529A (en) | Method and equipment for evaluating definition of base fluorescence image, medium and device | |
| CN110827254A (en) | Method and device for determining image definition | |
| CN112950516B (en) | Method and device for enhancing local contrast of image, storage medium and electronic equipment | |
| CN114418848A (en) | Video processing method and device, storage medium and electronic equipment |
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 |