Chromosome image enhancement method, system, equipment and medium

Abstract

The invention discloses a chromosome image enhancement method, system and device and a medium. The method comprises the following steps: acquiring a chromosome grayscale image; extracting a foreground image of the chromosome region-of-interest; the method comprises the following steps: initializing five control points and node vectors, and generating a cubic clared B spline curve; three middle control points of the five control points are dynamic control points; constructing an image gray mapping table based on a cubic classed B spline curve; mapping the foreground image of the region of interest of the chromosome according to an image gray mapping table to obtain an enhanced chromosome image; and acquiring the real-time positions of the three dynamic control points, updating the compressed B spline curve and the image gray mapping table for three times, and updating the enhanced chromosome image. According to the method, the calculation complexity is low, the positions of the three dynamic control points can be adjusted in real time, the enhanced chromosome image can be synchronously updated so that a user can confirm the chromosome image in time, and the efficiency is improved on the premise that the enhancement quality of the chromosome image is guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a chromosome image enhancement method, system, device and medium. Background Art

[0002] Chromosome images are captured using microscopes and electronic imaging systems. The quality of these images affects the difficulty of subsequent chromosome karyotype analysis. To improve the quality of chromosome images, image enhancement technology is generally used to enhance chromosome images.

[0003] The paper "Comparison of Image ENHANCEMENT Methods for Chromosome Karyotype Image ENHANCEMENT" comprehensively compares several chromosome enhancement methods. It analyzes histogram equalization (HE), contrast-limited adaptive histogram equalization (CLAHE), histogram equalization combined with 3D block matching (HE+BM3D), and unsharp masking. The performance of these algorithms is evaluated using peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). Experiments show that HE+BM3D performs better for noisy chromosome images, while CLAHE achieves better enhancement results for noise-free chromosome images. The noisy images analyzed in the experimental section of the paper were simulated. Chromosome images captured by current microscopy techniques typically do not contain significant noise. Therefore, this paper focuses on the comparative analysis of the CLAHE method.

[0004] Histogram equalization (HE) redistributes the grayscale distribution of an image by calculating the cumulative distribution probability of the image's histogram, resulting in a uniform distribution of grayscale values across the entire grayscale range. Adaptive histogram equalization (AHE) is an improvement on traditional histogram equalization (HE). AHE divides the image into many small blocks (for example, a 3x3 grid) and performs histogram equalization on each block to enhance the contrast of the local area, better adapting to the grayscale distribution characteristics of different regions in the image. However, in some cases, AHE is prone to over-enhancement of local areas, resulting in noise or artifacts. To address this issue, CLAHE introduces a contrast limiting strategy. Specifically, a threshold is given. When calculating the histogram of each block, if the frequency of a grayscale level exceeds the threshold, the excess frequency is redistributed to other grayscale levels to ensure that the total frequency of the histogram remains unchanged. This prevents over-enhancement of a single grayscale level during the equalization process.

[0005] From this, we can see that the parameters that affect the CLAHE enhancement effect are mainly the number of blocks and the contrast limit threshold. These two parameters are usually selected based on empirical values. Too small a number of blocks will lead to noise amplification, while too large a number will lose the local contrast enhancement effect. Furthermore, after completing histogram equalization for each block, linear interpolation is required to solve the grayscale continuity problem of pixel boundaries between blocks, which makes the entire process computationally complex. If the image size of a single chromosome is small, using the CLAHE method is prone to local over-enhancement.

[0006] In addition, the patent application with publication number CN114155162A discloses a method for enhancing chromosome banding images. A grayscale mapping table is constructed according to the gamma transformation function using the thresholds and preset values corresponding to the deep and light banding of the chromosomes. Finally, the chromosome image after grayscale mapping is subjected to USM sharpening processing to highlight the texture boundaries of the chromosome image.

[0007] The patent uses gamma transform as a grayscale mapping method. The shape of the gamma transform function curve is primarily determined by the gamma value, making it incapable of constructing a flexible and diverse curve shape. Furthermore, unsharp masking (USM) enhances the high-frequency regions of chromosomes. If the weights of the high-frequency overlay components are inappropriate, artifacts can easily appear, leading to distortion of chromosome banding information. Summary of the Invention

[0008] In view of the above-mentioned deficiencies in the prior art, the object of the present invention is to provide a chromosome image enhancement method, system, device and medium to solve the problems of high computational complexity and poor image enhancement quality in the prior art.

[0009] In a first aspect, a chromosome image enhancement method is provided, comprising the following steps:

[0010] Obtain chromosome grayscale image;

[0011] Extract the foreground image of the chromosome region of interest from the chromosome grayscale image;

[0012] Initialize five control points and knot vectors, and generate a cubic clamped B-spline curve based on the control points and knot vectors. The first and last two control points of the five control points are fixed control points, and the three control points in the middle are dynamic control points with adjustable positions.

[0013] Construct an image grayscale mapping table based on a cubic clamped B-spline curve;

[0014] Mapping the grayscale value of the foreground image of the chromosome region of interest to the enhanced grayscale value according to the image grayscale mapping table to obtain the enhanced chromosome image;

[0015] The real-time positions of the three dynamic control points are obtained, the cubic clamped B-spline curve and the image grayscale mapping table are updated, and then the enhanced chromosome image is updated.

[0016] Furthermore, after extracting the foreground image of the chromosome region of interest in the chromosome grayscale image, the method further includes the following steps:

[0017] The foreground image of the chromosome region of interest is subtracted from the global minimum grayscale value of the region to update the foreground image of the chromosome region of interest.

[0018] Furthermore, the initialization of the five control points specifically includes:

[0019] Based on the foreground image of the chromosome region of interest, the multi-level Otsu method is used to segment the image and obtain three grayscale thresholds, which are denoted as t1, t2, and t3 from small to large;

[0020] Initialize the coordinates of the five control points as follows: P0=(0, 0), P1=(t1, k×t1), P2=(t2, (k×t1 +M) / 2), P3=(t3, M), P4=(255, 255); P0 and P4 are the first and last fixed control points, and P1, P2, and P3 are the three dynamic control points; the coordinates of the five control points satisfy the order of P0, P1, P2, P3, and P4 in non-decreasing order; k is a non-negative coefficient, and the value range of M is [235, 250].

[0021] Furthermore, the three dynamic control points can only move in the y-axis direction, and the coordinates of the five control points must be in a non-decreasing order from the first to the last.

[0022] Furthermore, the three dynamic control points can be moved arbitrarily, but the coordinates of the five control points must be in a non-decreasing order from the first to the last.

[0023] Furthermore, constructing an image grayscale mapping table based on a cubic clamped B-spline curve specifically includes:

[0024] The coordinates of the points on the cubic clamped B-spline curve on the x-axis and y-axis components are:

[0025]

[0026] Where, and Represent the x-axis component and the y-axis component respectively, for Sub-B-spline basis functions, and are the horizontal and vertical coordinates of the ith control point, n+1 is the number of control points, and is the node vector, ,and ; ,and For consecutive floating point numbers;

[0027] The image grayscale mapping table is obtained by discrete sampling of the cubic clamped B-spline curve. For integer coordinates that do not exist, the following interpolation method is used to calculate:

[0028]

[0029] Where, ,and for Positive integers within With the horizontal axis The corresponding vertical coordinate is is the rounding operator; To convert the value to integer operators within ranges; and They are the cubic clamped B-spline curve and Two points that are close to each other, and On the cubic clamped B-spline curve and

[0030] and The corresponding vertical coordinate.

[0031] Furthermore, it also includes:

[0032] The enhanced chromosome image, the cubic clamped B-spline curve shape and the five control points are visualized;

[0033] The system receives the drag command issued by the user through the mouse to move the positions of the three dynamic control points, and updates the displayed cubic clamped B-spline curve shape in real time, and synchronously updates the displayed enhanced chromosome image, so that the user can confirm it in time.

[0034] In a second aspect, a chromosome image enhancement system is provided, comprising:

[0035] An image acquisition module, used for acquiring chromosome grayscale images;

[0036] A region of interest extraction module is used to extract a foreground image of a chromosome region of interest in a chromosome grayscale image;

[0037] The spline curve initialization module is used to initialize five control points and knot vectors, and generate a cubic clamped B-spline curve based on the control points and knot vectors. The first and last two control points of the five control points are fixed control points, and the three control points in the middle are dynamic control points with adjustable positions.

[0038] An image grayscale mapping table construction module is used to construct an image grayscale mapping table based on a cubic clamped B-spline curve;

[0039] An image enhancement module is used to map the grayscale value of the foreground image of the chromosome region of interest to the enhanced grayscale value according to the image grayscale mapping table to obtain an enhanced chromosome image;

[0040] The dynamic image enhancement module is used to obtain the real-time positions of the three dynamic control points, update the cubic clamped B-spline curve and the image grayscale mapping table, and then update the enhanced chromosome image.

[0041] According to a third aspect, an electronic device is provided, including:

[0042] a memory having a computer program stored thereon;

[0043] Processor; used to implement the chromosome image enhancement method as described above when executing the computer program;

[0044] a display connected to the processor and configured to visually display the enhanced chromosome image, the shape of the cubic clamped B-spline curve, and the five control points;

[0045] The mouse is connected to the processor and is used to generate a drag instruction according to a user's operation to move the positions of the three dynamic control points.

[0046] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a computer, the computer implements the chromosome image enhancement method as described above.

[0047] The present invention proposes a chromosome image enhancement method, system, device, and medium, which have the following advantages over the prior art:

[0048] (1) Compared with the CLAHE method, the present invention has low computational complexity. The present invention is a global enhancement method. The constructed mapping curve is monotonic, and the enhancement process will not affect the light and dark rules of the bands that are closely related to the chromosome structure information. The CLAHE method is a block histogram equalization method. If the number of blocks is not selected properly, it is easy to cause excessive noise enhancement. Although both the present invention and the CLAHE method involve interpolation processes, the CLAHE method uses bilinear interpolation on a two-dimensional scale to solve the grayscale continuity of the block region boundary, while the present invention only performs linear interpolation on a one-dimensional scale. In addition, each time a new image is given, the CLAHE method needs to re-execute the histogram equalization process for each block region. After the B-spline basis function node vector is given, the present invention can pre-store the basis function as an array table in advance, avoiding each recursive operation. In the subsequent process of updating the control point, it is only necessary to look up the table to update the control point, thereby improving processing efficiency.

[0049] (2) Compared with the prior art method of using the gamma function to construct an image grayscale mapping table, the present invention uses the more flexible B-spline function, and can construct a more diverse and flexible mapping function curve. The first-order gradient of the gamma transformation function curve is determined only by the gamma parameter. The gradient of each interval segment of the B-spline function curve is affected by the position of the control point. The user can change the gradient of any interval segment by adjusting the position of the control point, and thus can directionally enhance any grayscale interval segment, thereby achieving the desired effect.

[0050] (3) Among the five control points in the present invention, there are three dynamic control points. The positions of the three dynamic control points can be adjusted in real time, and the enhanced chromosome image can be updated synchronously so that the user can confirm in time and quickly find a chromosome image with better quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0052] Figure 1 is a flow chart of a chromosome image enhancement method provided by an embodiment of the present invention;

[0053] Figure 2 is a chromosome grayscale image provided by an embodiment of the present invention;

[0054] Figure 3 is a foreground image of a chromosome region of interest provided by an embodiment of the present invention;

[0055] Figure 4 is an updated chromosome region of interest foreground image provided by an embodiment of the present invention;

[0056] Figure 5 is a schematic diagram of a cubic clamped B-spline curve provided by an embodiment of the present invention;

[0057] Figure 6 is an enhanced chromosome image provided by an embodiment of the present invention;

[0058] Figure 7 It is a schematic diagram of a visualization interface provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0059] To make the objectives, technical solutions, and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail below. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other implementations obtained by those of ordinary skill in the art without inventive effort are within the scope of protection of the present invention.

[0060] like Figure 1 As shown, an embodiment of the present invention provides a chromosome image enhancement method, comprising the following steps:

[0061] S1: Get the chromosome grayscale image. Figure 2 Shown is a grayscale image of chromosomes.

[0062] S2: Extract the foreground image of the chromosome region of interest from the chromosome grayscale image.

[0063] In specific implementation, the method for extracting the foreground image of the chromosome region of interest can be based on traditional histogram statistics, threshold segmentation and other methods, or it can be based on semantic segmentation based on deep learning, where the grayscale value of the chromosome background region containing the impurity region is set to 255, and the chromosome region of interest is extracted to obtain the foreground image of the chromosome region of interest. Figure 3 Shown is the Figure 2 The foreground image of the chromosome region of interest is obtained by extracting the chromosome grayscale image shown.

[0064] S3: The foreground image of the chromosome region of interest is subtracted from the global minimum grayscale value of the region to update the foreground image of the chromosome region of interest.

[0065] This step can further enhance the contrast image and improve the effect of subsequent image enhancement. Figure 4 Shown Figure 3The chromosome region of interest foreground image shown is the chromosome region of interest foreground image after being processed and updated in step S3. Of course, in some embodiments, if high-quality chromosome image enhancement can be achieved only through subsequent steps, this step can also be omitted.

[0066] S4: Initialize five control points and knot vectors, and generate a cubic clampedB spline curve based on the control points and knot vectors; the first and last two control points of the five control points are fixed control points, and the middle three control points are dynamic control points with adjustable positions.

[0067] In this embodiment, the initialization of the five control points specifically includes:

[0068] Since chromosome bands contain dark bands, gray bands, and light bands, a multi-level threshold segmentation method is used. Specifically, the multi-level Otsu method is used to segment the foreground image of the chromosome region of interest, and three grayscale thresholds are obtained, which are recorded as t1, t2, and t3 from small to large;

[0069] Initialize the coordinates of the five control points in the two-dimensional coordinate system as follows: P0 = (0, 0), P1 = (t1, k×t1), P2 = (t2, (k×t1+M) / 2), P3 = (t3, M), P4 = (255, 255); P0 and P4 are the first and last fixed control points, and P1, P2, and P3 are the three dynamic control points; the coordinates of the five control points satisfy the order of P0, P1, P2, P3, and P4 in non-decreasing order, that is, 0 < P 1x ≤P 2x ≤ P 3x <255, 0< P 1y ≤ P 2y ≤ P 3y <255, P 1x 、P 2x 、P 3x are the horizontal coordinates of P1, P2, and P3 respectively, 1y 、P 2y 、P 3y are the vertical coordinates of P1, P2, and P3 respectively; k is a non-negative coefficient, which is 2 in this embodiment; M ranges from [235, 250], which is 245 in this embodiment.

[0070] The node vector composed of nodes is , the clamped B-spline curve requires the repetition of the first and last nodes to be ,Right now , In this embodiment, the node vector is initialized . Then according to the control points and node vectors, The formula of the sub-clamped B-spline curve is as follows:

[0071]

[0072] Where, for Points on the clamped B-spline curve, n+1 is the number of control points; ,and For consecutive floating point numbers; ; is the coordinate of the i-th control point; for The sub-B-spline basis function is defined as the following Cox-de Boor recursive formula:

[0073]

[0074]

[0075] make Construct a cubic clamped B-spline curve. Figure 5 As shown, this is a schematic diagram of a cubic clamped B-spline curve.

[0076] S5: Constructing an image grayscale mapping table based on a cubic clamped B-spline curve. The specific process includes:

[0077] The coordinates of the points on the above cubic clamped B-spline curve in the x-axis and y-axis components are:

[0078]

[0079] Where, and Represent the x-axis component and the y-axis component respectively, for Sub-B-spline basis functions, and are the horizontal and vertical coordinates of the i-th control point, , is the node vector;

[0080] The grayscale value range of the image is , discrete sampling is performed on the cubic clamped B-spline curve to obtain the image grayscale mapping table. For integer coordinates that do not exist, the following interpolation method is used to calculate:

[0081]

[0082] Where, ,and for Positive integers within With the horizontal axis The corresponding vertical coordinate is is the rounding operator; To convert the value to integer operators within ranges; and They are the cubic clamped B-spline curve and Two points that are close to each other, and On the cubic clamped B-spline curve and

[0083] and The corresponding vertical coordinate. The image grayscale mapping table is an array type with an array length of 256. The subscripts are 0 to 255, which correspond to the values on the horizontal axis of the cubic clamped B-spline curve. The array values are the values on the vertical axis of the corresponding cubic clamped B-spline curve.

[0084] S6: Map the grayscale value of the foreground image of the chromosome region of interest to the enhanced grayscale value according to the image grayscale mapping table to obtain the enhanced chromosome image. Figure 6 Shown Figure 4 The enhanced chromosome image is obtained after mapping through the image grayscale mapping table.

[0085] S7: Since the positions of the three dynamic control points in the middle are dynamically adjustable, users can adjust the positions of the three dynamic control points. Therefore, it is also necessary to obtain the real-time positions of the three dynamic control points, update the cubic clamped B-spline curve and the image grayscale mapping table, and then update the enhanced chromosome image.

[0086] In some embodiments, the three dynamic control points can only move in the y-axis direction, and the coordinates of the five control points must be non-decreasing from the beginning to the end, that is, they must still meet the requirement of 0 <P 1y ≤ P 2y ≤ P 3y <255. The horizontal coordinates of the three dynamic control points are obtained through multi-level Otsu segmentation, corresponding to the grayscale thresholds for segmenting dark, gray, and light bands. Therefore, the horizontal coordinates of the three dynamic control points are already optimal. Limiting the movement of the three dynamic control points to the y-axis can improve optimization efficiency, obtain chromosome images of higher quality more quickly, and achieve a balance between efficiency and quality.

[0087] In other embodiments, the three dynamic control points can be moved arbitrarily, but the coordinates of the five control points must be non-decreasing from the beginning to the end, that is, they must still satisfy 0 < P 1x≤P 2x ≤ P 3x <255, 0< P 1y ≤ P 2y ≤ P 3y <255. The horizontal coordinates of the three dynamic control points obtained by multi-level Otsu method segmentation are better, but not necessarily optimal. Therefore, setting the three dynamic control points to be movable arbitrarily reduces the optimization efficiency but increases the probability of finding the chromosome image with the best quality.

[0088] In some preferred embodiments, the chromosome image enhancement further comprises:

[0089] The enhanced chromosome image, the cubic clamped B-spline curve shape and the five control points are visualized; Figure 7 The figure shows an example of a visualization interface, where the enhanced chromosome image is displayed on the left side of the interface, and the control points and the cubic clamped B-spline curve are displayed on the right side of the interface;

[0090] The system receives the drag command issued by the user through the mouse to move the positions of the three dynamic control points P1, P2, and P3, and updates the displayed cubic clamped B-spline curve shape in real time. It also updates the displayed enhanced chromosome image synchronously, realizing human-computer interaction, facilitating timely confirmation by the user, and improving optimization efficiency.

[0091] The chromosome image enhancement method provided in the above embodiment has the following advantages: Compared with the CLAHE method, this method has low computational complexity. This method is a global enhancement solution, and the enhancement process does not affect the light and dark patterns of bands that are closely related to chromosome structural information. The CLAHE method is a block histogram equalization method. If the number of blocks is not properly selected, it can easily lead to excessive noise enhancement. Although both this method and the CLAHE method involve interpolation, the CLAHE method uses bilinear interpolation on a two-dimensional scale to address grayscale continuity at the boundaries of the block regions, while the present method only performs linear interpolation on a one-dimensional scale. In addition, each time a new image is given, the CLAHE method needs to re-execute the histogram equalization process for each block region. However, once the B-spline basis function node vectors are given, the B-spline basis functions in this method are fixed. Therefore, the B-spline basis functions can be pre-stored as an array table, avoiding recursive operations each time. When the control points are subsequently updated, only the table needs to be looked up to update the control points, thereby improving processing efficiency. Compared to existing methods that use gamma functions to construct image grayscale mapping tables, this method uses the more flexible B-spline function, allowing for a wider variety of mapping function curves. Three of the five control points in this method are dynamic, allowing for real-time position adjustment of these points through human-computer interaction. The enhanced chromosome image is then updated simultaneously, allowing users to quickly confirm and find a higher-quality chromosome image.

[0092] An embodiment of the present invention further provides a chromosome image enhancement system, comprising:

[0093] An image acquisition module, used for acquiring chromosome grayscale images;

[0094] A region of interest extraction module is used to extract a foreground image of a chromosome region of interest in a chromosome grayscale image;

[0095] The spline curve initialization module is used to initialize five control points and knot vectors, and generate a cubic clamped B-spline curve based on the control points and knot vectors. The first and last two control points of the five control points are fixed control points, and the three control points in the middle are dynamic control points with adjustable positions.

[0096] An image grayscale mapping table construction module is used to construct an image grayscale mapping table based on a cubic clamped B-spline curve;

[0097] An image enhancement module is used to map the grayscale value of the foreground image of the chromosome region of interest to the enhanced grayscale value according to the image grayscale mapping table to obtain an enhanced chromosome image;

[0098] The dynamic image enhancement module is used to obtain the real-time positions of the three dynamic control points, update the cubic clamped B-spline curve and the image grayscale mapping table, and then update the enhanced chromosome image.

[0099] It should be understood that the functional unit modules in various embodiments of the present invention can be concentrated in one processing unit, or each unit module can exist physically separately, or two or more unit modules can be integrated into one unit module, and can be implemented in the form of hardware or software.

[0100] In addition, an embodiment of the present invention further provides an electronic device, including:

[0101] a memory having a computer program stored thereon;

[0102] Processor; used to implement the chromosome image enhancement method as described above when executing the computer program;

[0103] a display connected to the processor and configured to visually display the enhanced chromosome image, the shape of the cubic clamped B-spline curve, and the five control points;

[0104] The mouse is connected to the processor and is used to generate a drag instruction according to a user's operation to move the positions of the three dynamic control points.

[0105] In addition, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a computer, the computer implements the chromosome image enhancement method as described above.

[0106] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0107] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0108] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0109] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0110] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0111] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A chromosome image enhancement method, characterized in that: The steps include: Obtain chromosome grayscale image; Extract the foreground image of the chromosome region of interest from the chromosome grayscale image; Initialize five control points and knot vectors, and generate a cubic clamped B-spline curve based on the control points and knot vectors. The first and last two control points of the five control points are fixed control points, and the three control points in the middle are dynamic control points with adjustable positions. Construct an image grayscale mapping table based on a cubic clamped B-spline curve; Mapping the grayscale value of the foreground image of the chromosome region of interest to the enhanced grayscale value according to the image grayscale mapping table to obtain the enhanced chromosome image; The real-time positions of the three dynamic control points are obtained, the cubic clamped B-spline curve and the image grayscale mapping table are updated, and then the enhanced chromosome image is updated.

2. The chromosome image enhancement method according to claim 1, characterized in that: After extracting the foreground image of the chromosome region of interest in the chromosome grayscale image, the following steps are also included: The foreground image of the chromosome region of interest is subtracted from the global minimum grayscale value of the region to update the foreground image of the chromosome region of interest.

3. The chromosome image enhancement method according to claim 1, characterized in that: Initializing the five control points specifically includes: Based on the foreground image of the chromosome region of interest, the multi-level Otsu method is used to segment the image and obtain three grayscale thresholds, which are denoted as t1, t2, and t3 from small to large; Initialize the coordinates of the five control points as follows: P0=(0, 0), P1=(t1, k×t1), P2=(t2, (k×t1 +M) / 2), P3=(t3, M), P4=(255, 255); P0 and P4 are the first and last fixed control points, and P1, P2, and P3 are the three dynamic control points; the coordinates of the five control points satisfy the order of P0, P1, P2, P3, and P4 in non-decreasing order; k is a non-negative coefficient, and the value range of M is [235, 250].

4. The chromosome image enhancement method according to claim 1, characterized in that: The three dynamic control points can only move in the y-axis direction, and the coordinates of the five control points must be in non-decreasing order from the first to the last.

5. The chromosome image enhancement method according to claim 1, characterized in that: The three dynamic control points can be moved arbitrarily, but the coordinates of the five control points must be in non-decreasing order from the first to the last.

6. The chromosome image enhancement method according to claim 1, characterized in that: The constructing of the image grayscale mapping table based on the cubic clamped B-spline curve specifically includes: The coordinates of the points on the cubic clamped B-spline curve on the x-axis and y-axis components are: ； Where, and Represent the x-axis component and the y-axis component respectively, for Sub-B-spline basis functions, and are the horizontal and vertical coordinates of the i-th control point, n+1 is the number of control points, ,and For consecutive floating point numbers, is the node vector; The image grayscale mapping table is obtained by discrete sampling of the cubic clamped B-spline curve. For integer coordinates that do not exist, the following interpolation method is used to calculate: ； Where, ,and for Positive integers within With the horizontal axis The corresponding vertical coordinate is is the rounding operator; To convert the value to integer operators within ranges; and They are the cubic clamped B-spline curve and Two points that are close to each other, and On the cubic clamped B-spline curve and and The corresponding vertical coordinate.

7. The chromosome image enhancement method according to any one of claims 1 to 6, characterized in that: Also includes: The enhanced chromosome image, the cubic clamped B-spline curve shape and the five control points are visualized; The system receives the drag command issued by the user through the mouse to move the positions of the three dynamic control points, and updates the displayed cubic clamped B-spline curve shape in real time, and synchronously updates the displayed enhanced chromosome image, so that the user can confirm it in time.

8. A chromosome image enhancement system, characterized in that: include: An image acquisition module, used for acquiring chromosome grayscale images; A region of interest extraction module is used to extract a foreground image of a chromosome region of interest in a chromosome grayscale image; The spline curve initialization module is used to initialize five control points and knot vectors, and generate a cubic clamped B-spline curve based on the control points and knot vectors. The first and last two control points of the five control points are fixed control points, and the three control points in the middle are dynamic control points with adjustable positions. An image grayscale mapping table construction module is used to construct an image grayscale mapping table based on a cubic clamped B-spline curve; An image enhancement module is used to map the grayscale value of the foreground image of the chromosome region of interest to the enhanced grayscale value according to the image grayscale mapping table to obtain an enhanced chromosome image; The dynamic image enhancement module is used to obtain the real-time positions of the three dynamic control points, update the cubic clamped B-spline curve and the image grayscale mapping table, and then update the enhanced chromosome image.

9. An electronic device, characterized in that: include: a memory having a computer program stored thereon; processor; used for implementing the chromosome image enhancement method according to any one of claims 1 to 7 when executing the computer program; a display connected to the processor and configured to visually display the enhanced chromosome image, the shape of the cubic clamped B-spline curve, and the five control points; The mouse is connected to the processor and is used to generate a drag instruction according to a user's operation to move the positions of the three dynamic control points.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a computer, the computer is enabled to implement the chromosome image enhancement method according to any one of claims 1 to 7.

Images