Bone marrow smear identification method and system, readable storage medium and computer
The method improves leukemia diagnosis by digitizing bone marrow smears, performing image processing, and using a classification model to accurately identify white blood cells, addressing the limitations of manual inspection.
Patent Information
- Application Number
- CN202411296168.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-18
- Publication Date
- 2024-12-06
AI Technical Summary
Manual inspection of bone marrow smears for leukemia diagnosis is subjective and lacks accuracy due to reliance on personal experience, failing to fully utilize image information for early detection.
A method involving digital image processing, including segmentation, multi-scale clustering, and conversion to HIS space model, followed by classification using a bone marrow cell classification model to identify white blood cells accurately.
Enhances the accuracy and efficiency of bone marrow smear analysis, enabling rapid and precise identification of white blood cell types and numbers.
Smart Images

Figure CN119091440A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of image processing technology, and in particular to a bone marrow smear recognition method, system, readable storage medium and computer. Background Art
[0002] Leukemia is a fatal disease caused by abnormal proliferation of white blood cells in the human bone marrow and hematopoietic tissue. With the advancement of modern medicine, the mortality rate of leukemia is gradually decreasing. However, the natural course of leukemia is short and the onset is rapid. Therefore, rapid and accurate testing of bone marrow smears is particularly important for the treatment of leukemia.
[0003] At present, the clinical diagnosis of leukemia is usually carried out by manual inspection of microscope images from a morphological perspective. The clinical diagnosis plan and the development trend of the lesion are determined by analyzing whether different types of white blood cells in the bone marrow smear have lesions in quantity and morphology. Although the cost of manual inspection is low, there are many disadvantages. Manual inspection will make the results more dependent on personal experience and cannot make accurate judgments. Secondly, the image information and features cannot be fully utilized through naked eye observation, which is not conducive to early diagnosis trends. Summary of the invention
[0004] Based on this, the object of the present invention is to provide a bone marrow smear identification method, system, readable storage medium and computer to at least solve the deficiencies in the above-mentioned technology.
[0005] The present invention provides a bone marrow smear identification method, comprising: Obtaining a bone marrow smear to be tested, converting the bone marrow smear to be tested into a digital image, and preprocessing the digital image to segment a regional image of bone marrow cells in the digital image; Extracting RBG component information of the regional image of the bone marrow cells, and decomposing the RGB component information by multi-scale to optimize the clustering center of the regional image of the bone marrow cells, and obtaining the corresponding bone marrow cell image and its cytoplasm information; Constructing an RBG component model of the bone marrow cell image, converting the RBG component model into a HIS space model, and performing image processing on the bone marrow cell image using the RBG component model and the HIS space model to extract a white blood cell image from the bone marrow cell image; A bone marrow cell classification model is constructed, and the bone marrow cell classification model is used to classify and identify the white blood cell image in the bone marrow cell image to obtain a corresponding classification result.
[0006] Furthermore, the step of preprocessing the digital image to segment the regional image of bone marrow cells in the digital image includes: Acquire all pixel points of the digital image, and perform first-order derivative on each pixel point to determine edge points in each pixel point; Performing a second-order derivative on the edge point, and determining edge pixel points of a bone marrow cell region in the digital image according to the second-order derivative result; The edge pixels of the bone marrow cell region in the digital image are connected to segment the regional image of the bone marrow cells in the digital image.
[0007] Further, the steps of extracting RBG component information of the regional image of the bone marrow cells and decomposing the RGB component information by multi-scale to optimize the cluster center of the regional image of the bone marrow cells to obtain the corresponding bone marrow cell image and its cytoplasm information include: Extracting R component information, G component information, and B component information of the regional image of the bone marrow cells, and setting an initial clustering center of the regional image according to the R component information, the G component information, and the B component information; Extract any pixel point in the area image , and calculate the pixel The distance between the pixel point and the G component information of the initial cluster center is used to cluster the pixel point to the cluster center with the nearest distance to obtain a new cluster center, where the pixel point middle, , ; The new cluster center is updated by using a multi-scale classification algorithm until the RBG component information of the new cluster center no longer changes, so as to obtain the corresponding bone marrow cell image and cytoplasm information thereof.
[0008] Furthermore, the calculation formula of the multi-scale classification algorithm is: ; In the formula, , , Indicates The number of class sets, express The value of the R, G, and B component information contained in the cluster center before the cycle in the class, Indicates the pixel value updated iteratively after the loop.
[0009] Further, the steps of converting the RBG component model into a HIS space model, and performing image processing on the bone marrow cell image using the RBG component model and the HIS space model to extract the white blood cell image from the bone marrow cell image include: Extracting the S parameter component in the HIS space model, and performing linear contrast processing on the extracted S parameter component and the G component information of the bone marrow cell image; The S parameter component and G component information after the linear contrast processing are converted by using an image conversion algorithm, and grayscale processing is performed based on the conversion result to extract the white blood cell image in the bone marrow cell image.
[0010] The present invention also provides a bone marrow smear identification system, comprising: An image preprocessing module is used to obtain a bone marrow smear to be tested, convert the bone marrow smear to be tested into a digital image, and preprocess the digital image to segment a regional image of bone marrow cells in the digital image; A clustering optimization module, used for extracting RBG component information of the regional image of the bone marrow cells, and decomposing the RGB component information by multi-scale to optimize the clustering center of the regional image of the bone marrow cells, and obtaining the corresponding bone marrow cell image and its cytoplasm information; An image processing module, used for constructing an RBG component model of the bone marrow cell image, converting the RBG component model into a HIS space model, and performing image processing on the bone marrow cell image using the RBG component model and the HIS space model to extract a white blood cell image from the bone marrow cell image; The classification and recognition module is used to construct a bone marrow cell classification model, and use the bone marrow cell classification model to classify and recognize the white blood cell image in the bone marrow cell image to obtain a corresponding classification result.
[0011] Furthermore, the image preprocessing module includes: A first-order derivative unit, used to obtain all pixel points of the digital image and perform first-order derivative on each pixel point to determine an edge point in each pixel point; A second-order derivative unit, used for performing a second-order derivative on the edge point, and determining edge pixel points of the bone marrow cell region in the digital image according to the second-order derivative result; The image segmentation unit is used to connect the edge pixel points of the bone marrow cell area in the digital image to segment the regional image of the bone marrow cells in the digital image.
[0012] Furthermore, the clustering optimization module includes: A cluster center setting unit, used for extracting R component information, G component information and B component information of the regional image of the bone marrow cells, and setting an initial cluster center of the regional image according to the R component information, the G component information and the B component information; A cluster center updating unit, used to extract any pixel point in the regional image , and calculate the pixel The distance between the pixel point and the G component information of the initial cluster center is used to cluster the pixel point to the cluster center with the nearest distance to obtain a new cluster center, where the pixel point middle, , ; The cluster center optimization unit is used to update the new cluster center by using a multi-scale classification algorithm until the RBG component information of the new cluster center no longer changes, so as to obtain the corresponding bone marrow cell image and its cytoplasm information.
[0013] Furthermore, the image processing module includes: A contrast processing unit, used for extracting the S parameter component in the HIS space model, and performing linear contrast processing on the extracted S parameter component and the G component information of the bone marrow cell image; The image conversion unit is used to convert the S parameter component and G component information after the linear contrast processing by using an image conversion algorithm, and perform grayscale processing based on the conversion result to extract the white blood cell image in the bone marrow cell image.
[0014] The present invention also provides a readable storage medium on which a computer program is stored. When the program is executed by a processor, the above-mentioned bone marrow smear identification method is implemented.
[0015] The present invention also provides a computer, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned bone marrow smear identification method when executing the computer program.
[0016] The bone marrow smear recognition method, system, readable storage medium and computer of the present invention convert the bone marrow smear to be tested into a digital image, and perform image segmentation on the digital image to obtain a regional image of bone marrow cells, thereby improving the accuracy of cell recognition and the efficiency of feature analysis, extracting RGB component information of the regional image, and using multi-scale decomposition component information to optimize the clustering center of the regional image to obtain the bone marrow cell image, converting the RGB component model into a HIS space model, using the RBG component model and the HIS space model to perform image processing on the bone marrow cell image to obtain the corresponding white blood cell image, constructing a conversion image using the difference information of the two color components to highlight the cell nuclei of the white blood cells, extracting the corresponding white blood cell image using threshold segmentation binarization processing, and classifying and identifying the white blood cell image using the constructed bone marrow cell classification model to quickly and accurately identify the type and number of white blood cells, thereby achieving classification of bone marrow cells. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] Figure 1 is a flow chart of a bone marrow smear identification method in a first embodiment of the present invention; Figure 2 for Figure 1 Detailed flow chart of step S101; Figure 3 for Figure 1 Detailed flow chart of step S102; Figure 4 for Figure 1 Detailed flow chart of step S103; Figure 5 is a structural block diagram of a bone marrow smear recognition system in a second embodiment of the present invention; Figure 6 FIG. 4 is a structural block diagram of a computer in a third embodiment of the present invention.
[0018] The following specific implementation manner will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION
[0019] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.
[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.
[0021] Embodiment 1 See also Figure 1 , which shows a bone marrow smear identification method in a first embodiment of the present invention, and the method specifically includes steps S101 to S104: S101, obtaining a bone marrow smear to be tested, converting the bone marrow smear to be tested into a digital image, and preprocessing the digital image to segment a regional image of bone marrow cells in the digital image; For further information, see Figure 2 , the step S101 specifically includes steps S1011 to S1013: S1011, acquiring all pixel points of the digital image, and performing first-order derivative on each pixel point to determine edge points in each pixel point; S1012, performing a second-order derivative on the edge point, and determining edge pixel points of a bone marrow cell region in the digital image according to the second-order derivative result; S1013, connecting edge pixel points of the bone marrow cell region in the digital image to segment a regional image of the bone marrow cells in the digital image.
[0022] In a specific implementation, a bone marrow smear to be tested is obtained and converted into a digital image, all pixel points of the digital image are extracted, a first-order derivative is performed on each pixel point, and the maximum value of the first-order derivative in the first-order derivative result is screened out, and the pixel point corresponding to the maximum value is the edge point, a second-order derivative is performed on the edge point, and the edge pixel points of the bone marrow cell area in the digital image are determined according to the zero-crossing point of the calculated second-order derivative, and the edge pixel points are connected to obtain the edge information of the bone marrow cell area in the digital image, so as to segment the regional image of the bone marrow cells in the digital graphic.
[0023] In this embodiment, the first-order derivative operator includes but is not limited to the Sobel operator, the Prewitt operator, etc., and the second-order derivative operator includes but is not limited to the Canny operator, the Log operator, etc.
[0024] S102, extracting RBG component information of the regional image of the bone marrow cells, and decomposing the RGB component information by multi-scale to optimize the cluster center of the regional image of the bone marrow cells, and obtaining the corresponding bone marrow cell image and cytoplasm information thereof; For further information, see Figure 3 , the step S102 specifically includes steps S1021 to S1023: S1021, extracting R component information, G component information, and B component information of the regional image of the bone marrow cells, and setting an initial clustering center of the regional image according to the R component information, the G component information, and the B component information; S1022, extracting any pixel point in the regional image , and calculate the pixel The distance between the pixel point and the G component information of the initial cluster center is used to cluster the pixel point to the cluster center with the nearest distance to obtain a new cluster center, where the pixel point middle, , ; S1023, using a multi-scale classification algorithm to update the new cluster center until the RBG component information of the new cluster center no longer changes, so as to obtain the corresponding bone marrow cell image and cytoplasm information thereof.
[0025] In the specific implementation, the R (red) component information, G (green) component information and B (blue) component information of the regional image of the bone marrow cells are extracted, and three initial clustering centers are arbitrarily set, and the R (red) component information, G (green) component information and B (blue) component information are used as their corresponding component information respectively; Specifically, the distance from any pixel in the regional image to the initial cluster center is calculated using the G component information as the judgment standard: Extract any pixel point in the area image , and calculate the pixel The distance from the G component information of the initial cluster center is used to cluster the pixel point to the cluster center with the nearest distance to obtain a new cluster center, where the pixel point middle, , ; The new cluster center is updated by using a multi-scale classification algorithm until the RBG component information of the new cluster center no longer changes, so as to obtain the corresponding bone marrow cell image and its cytoplasm information. The calculation formula of the multi-scale classification algorithm is: ; In the formula, , , Indicates The number of class sets, express The value of the R, G, and B component information contained in the cluster center before the cycle in the class, Indicates the pixel value updated iteratively after the loop.
[0026] S103, constructing an RBG component model of the bone marrow cell image, converting the RBG component model into a HIS space model, and performing image processing on the bone marrow cell image using the RBG component model and the HIS space model to extract a white blood cell image from the bone marrow cell image; For further information, see Figure 4 , the step S103 specifically includes steps S1031~S1032: S1031, extracting the S parameter component in the HIS space model, and performing linear contrast processing on the extracted S parameter component and the G component information of the bone marrow cell image; S1032, using an image conversion algorithm to convert the S parameter component and G component information after the linear contrast processing, and performing grayscale processing based on the conversion result to extract the white blood cell image in the bone marrow cell image.
[0027] In the specific implementation, the RGB component model of the bone marrow cell image is constructed, and the RGB component model is converted into the HIS space model. The specific formula is as follows: ; In the formula, R, G, and B represent the red, green, and blue component values in the RGB component model, respectively, and their values are integers between [0, 255]. Indicates finding the minimum value.
[0028] Specifically, according to the difference in staining concentration between leukocyte nuclei and cytoplasm, in order to achieve the location of cell nuclei, the saturation parameter component (S component) that best describes the staining concentration is used. In order to accurately compare the difference characteristics between the S component and the G component of leukocytes, the leukocyte nuclei are extracted by combining the mixed properties of the two color spaces. Since it is necessary to eliminate the influence of uneven cell staining, the extracted S component image is subjected to linear contrast processing to define the saturation component image. Gray value is Between, the processed component map Gray value is Among them, the calculation formula of the linear contrast processing of the saturation component is: ; In the formula, The saturation component map of the white blood cell nucleus is obtained by combining the mixed attributes of the two color spaces. Extracted linear enhancement component map.
[0029] Furthermore, based on the grayscale distribution characteristics of the saturation component and the green component, the conversion image of the two color space components is constructed using the following formula: , in order to highlight the cell nucleus, the gray value of the cell nucleus is larger, and the gray value of other areas is smaller: ; Get ratio converted image The grayscale histogram information of the cell nucleus is obtained, and the trough point in the histogram information is used as the screening threshold of the cell nucleus. The grayscale histogram value of the area where the cell nucleus is located is greater than the trough point, and the other areas are less than the trough point. The threshold segmentation method is used to transform the image Binarization was performed to extract the leukocyte nuclei.
[0030] S104, constructing a bone marrow cell classification model, and using the bone marrow cell classification model to classify and identify the white blood cell image in the bone marrow cell image to obtain a corresponding classification result.
[0031] In the specific implementation, the morphological characteristics, color characteristics and texture characteristics of several bone marrow cells are obtained, wherein the morphological characteristics include information such as cell size, shape and edge, the color characteristics include information such as mean, variance, kurtosis and skewness, and the texture characteristics include frequency and contrast. The above-mentioned characteristic values are calculated, and various types of white blood cells are classified and numbered according to the characteristic data to obtain the corresponding bone marrow cell classification model. The white blood cell image in the bone marrow cell image obtained above is imported into the bone marrow cell classification model for split recognition, so as to quickly identify the white blood cells in the bone marrow cell image and obtain the classification result.
[0032] In summary, the bone marrow smear recognition method in the above embodiment of the present invention converts the bone marrow smear to be tested into a digital image, and performs image segmentation on the digital image to obtain a regional image of bone marrow cells, thereby improving the accuracy of cell recognition and the efficiency of feature analysis, extracting RGB component information of the regional image, and using multi-scale decomposition component information to optimize the clustering center of the regional image to obtain a bone marrow cell image, converting the RGB component model into a HIS space model, using the RBG component model and the HIS space model to perform image processing on the bone marrow cell image to obtain a corresponding white blood cell image, constructing a conversion image using the difference information of the two color components to highlight the cell nuclei of the white blood cells, extracting the corresponding white blood cell image using threshold segmentation binarization processing, and classifying and identifying the white blood cell image using the constructed bone marrow cell classification model to quickly and accurately identify the type and number of white blood cells, thereby achieving classification of bone marrow cells.
[0033] Embodiment 2 Another aspect of the present invention is to provide a bone marrow smear recognition system. Figure 5 , shown is a bone marrow smear identification system in a second embodiment of the present invention, the system comprising: An image preprocessing module 11 is used to obtain a bone marrow smear to be tested, convert the bone marrow smear to be tested into a digital image, and preprocess the digital image to segment a regional image of bone marrow cells in the digital image; Furthermore, the image preprocessing module 11 includes: A first-order derivative unit, used to obtain all pixel points of the digital image and perform first-order derivative on each pixel point to determine an edge point in each pixel point; A second-order derivative unit, used for performing a second-order derivative on the edge point, and determining edge pixel points of the bone marrow cell region in the digital image according to the second-order derivative result; The image segmentation unit is used to connect the edge pixel points of the bone marrow cell area in the digital image to segment the regional image of the bone marrow cells in the digital image.
[0034] The clustering optimization module 12 is used to extract the RBG component information of the regional image of the bone marrow cells, and use multi-scale decomposition of the RGB component information to optimize the cluster center of the regional image of the bone marrow cells to obtain the corresponding bone marrow cell image and its cytoplasm information; Furthermore, the clustering optimization module 12 includes: A cluster center setting unit, used for extracting R component information, G component information and B component information of the regional image of the bone marrow cells, and setting an initial cluster center of the regional image according to the R component information, the G component information and the B component information; A cluster center updating unit, used to extract any pixel point in the regional image , and calculate the pixel The distance between the pixel point and the G component information of the initial cluster center is used to cluster the pixel point to the cluster center with the nearest distance to obtain a new cluster center, where the pixel point middle, , ; The cluster center optimization unit is used to update the new cluster center by using a multi-scale classification algorithm until the RBG component information of the new cluster center no longer changes, so as to obtain the corresponding bone marrow cell image and its cytoplasm information.
[0035] An image processing module 13 is used to construct an RBG component model of the bone marrow cell image, convert the RBG component model into a HIS space model, and perform image processing on the bone marrow cell image using the RBG component model and the HIS space model to extract a white blood cell image from the bone marrow cell image; Furthermore, the image processing module 13 includes: A contrast processing unit, used for extracting the S parameter component in the HIS space model, and performing linear contrast processing on the extracted S parameter component and the G component information of the bone marrow cell image; The image conversion unit is used to convert the S parameter component and G component information after the linear contrast processing by using an image conversion algorithm, and perform grayscale processing based on the conversion result to extract the white blood cell image in the bone marrow cell image.
[0036] The classification and recognition module 14 is used to construct a bone marrow cell classification model, and use the bone marrow cell classification model to classify and recognize the white blood cell image in the bone marrow cell image to obtain a corresponding classification result.
[0037] The functions or operation steps implemented when the above modules and units are executed are generally the same as those in the above method embodiments, and will not be repeated here.
[0038] The bone marrow smear identification system provided in the embodiment of the present invention has the same implementation principle and technical effects as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the system embodiment, reference may be made to the corresponding contents in the aforementioned method embodiment.
[0039] Embodiment 3 The present invention also provides a computer, see Figure 6 , shown is a computer in the third embodiment of the present invention, including a memory 10, a processor 20, and a computer program 30 stored in the memory 10 and executable on the processor 20. When the processor 20 executes the computer program 30, the above-mentioned bone marrow smear identification method is implemented.
[0040] The memory 10 includes at least one type of readable storage medium, which includes a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., an SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 10 may be an internal storage unit of a computer, such as a hard disk of the computer. In other embodiments, the memory 10 may also be an external storage device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card, etc. Further, the memory 10 may also include both an internal storage unit of the computer and an external storage device. The memory 10 may be used not only to store application software and various types of data installed in the computer, but also to temporarily store data that has been output or is to be output.
[0041] Among them, in some embodiments, the processor 20 can be an electronic control unit (Electronic Control Unit, abbreviated as ECU, also known as a vehicle computer), a central processing unit (Central Processing Unit, CPU), a controller, a microcontroller, a microprocessor or other data processing chip, used to run the program code stored in the memory 10 or process data, such as executing access restriction programs, etc.
[0042] It should be pointed out that Figure 6 The structure shown does not constitute a limitation on the computer. In other embodiments, the computer may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.
[0043] The embodiment of the present invention further provides a readable storage medium on which a computer program is stored. When the program is executed by a processor, the above-mentioned bone marrow smear identification method is implemented.
[0044] Those skilled in the art will appreciate that the logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For purposes of this specification, "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.
[0045] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.
[0046] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.
[0047] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0048] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.
Claims
1. A bone marrow smear identification method, characterized in that: include: Obtaining a bone marrow smear to be tested, converting the bone marrow smear to be tested into a digital image, and preprocessing the digital image to segment a regional image of bone marrow cells in the digital image; Extracting RBG component information of the regional image of the bone marrow cells, and decomposing the RGB component information by multi-scale to optimize the clustering center of the regional image of the bone marrow cells, and obtaining the corresponding bone marrow cell image and its cytoplasm information; Constructing an RBG component model of the bone marrow cell image, converting the RBG component model into a HIS space model, and performing image processing on the bone marrow cell image using the RBG component model and the HIS space model to extract a white blood cell image from the bone marrow cell image; A bone marrow cell classification model is constructed, and the bone marrow cell classification model is used to classify and identify the white blood cell image in the bone marrow cell image to obtain a corresponding classification result.
2. The bone marrow smear identification method according to claim 1, characterized in that: The step of preprocessing the digital image to segment the regional image of bone marrow cells in the digital image comprises: Acquire all pixel points of the digital image, and perform first-order derivative on each pixel point to determine edge points in each pixel point; Performing a second-order derivative on the edge point, and determining edge pixel points of a bone marrow cell region in the digital image according to the second-order derivative result; The edge pixels of the bone marrow cell region in the digital image are connected to segment the regional image of the bone marrow cells in the digital image.
3. The bone marrow smear identification method according to claim 1, characterized in that: The steps of extracting RBG component information of the regional image of the bone marrow cells and decomposing the RGB component information by multi-scale to optimize the cluster center of the regional image of the bone marrow cells to obtain the corresponding bone marrow cell image and its cytoplasm information include: Extracting R component information, G component information, and B component information of the regional image of the bone marrow cells, and setting an initial clustering center of the regional image according to the R component information, the G component information, and the B component information; Extract any pixel point in the area image , and calculate the pixel The distance between the pixel point and the G component information of the initial cluster center is used to cluster the pixel point to the cluster center with the nearest distance to obtain a new cluster center, where the pixel point middle, , ; The new cluster center is updated by using a multi-scale classification algorithm until the RBG component information of the new cluster center no longer changes, so as to obtain the corresponding bone marrow cell image and cytoplasm information thereof.
4. The bone marrow smear identification method according to claim 3, characterized in that: The calculation formula of the multi-scale classification algorithm is: ; In the formula, , , Indicates The number of class sets, express The value of the R, G, and B component information contained in the cluster center before the cycle in the class, Indicates the pixel value updated iteratively after the loop.
5. The bone marrow smear identification method according to claim 1, characterized in that: The steps of converting the RBG component model into a HIS space model, and performing image processing on the bone marrow cell image using the RBG component model and the HIS space model to extract the white blood cell image from the bone marrow cell image include: Extracting the S parameter component in the HIS space model, and performing linear contrast processing on the extracted S parameter component and the G component information of the bone marrow cell image; The S parameter component and G component information after the linear contrast processing are converted by using an image conversion algorithm, and grayscale processing is performed based on the conversion result to extract the white blood cell image in the bone marrow cell image.
6. A bone marrow smear identification system, characterized in that: include: An image preprocessing module is used to obtain a bone marrow smear to be tested, convert the bone marrow smear to be tested into a digital image, and preprocess the digital image to segment a regional image of bone marrow cells in the digital image; A clustering optimization module, used for extracting RBG component information of the regional image of the bone marrow cells, and decomposing the RGB component information by multi-scale to optimize the clustering center of the regional image of the bone marrow cells, and obtaining the corresponding bone marrow cell image and its cytoplasm information; An image processing module, used for constructing an RBG component model of the bone marrow cell image, converting the RBG component model into a HIS space model, and performing image processing on the bone marrow cell image using the RBG component model and the HIS space model to extract a white blood cell image from the bone marrow cell image; The classification and recognition module is used to construct a bone marrow cell classification model, and use the bone marrow cell classification model to classify and recognize the white blood cell image in the bone marrow cell image to obtain a corresponding classification result.
7. The bone marrow smear identification system according to claim 6, characterized in that: The image preprocessing module comprises: A first-order derivative unit, used to obtain all pixel points of the digital image and perform first-order derivative on each pixel point to determine an edge point in each pixel point; A second-order derivative unit, used for performing a second-order derivative on the edge point, and determining edge pixel points of the bone marrow cell region in the digital image according to the second-order derivative result; The image segmentation unit is used to connect the edge pixel points of the bone marrow cell area in the digital image to segment the regional image of the bone marrow cells in the digital image.
8. The bone marrow smear identification system according to claim 6, characterized in that: The clustering optimization module includes: A cluster center setting unit, used for extracting R component information, G component information and B component information of the regional image of the bone marrow cells, and setting an initial cluster center of the regional image according to the R component information, the G component information and the B component information; A cluster center updating unit, used to extract any pixel point in the regional image , and calculate the pixel The distance between the pixel point and the G component information of the initial cluster center is used to cluster the pixel point to the cluster center with the nearest distance to obtain a new cluster center, where the pixel point middle, , ; The cluster center optimization unit is used to update the new cluster center by using a multi-scale classification algorithm until the RBG component information of the new cluster center no longer changes, so as to obtain the corresponding bone marrow cell image and its cytoplasm information.
9. A readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the bone marrow smear identification method according to any one of claims 1 to 5 is implemented.
10. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the bone marrow smear identification method according to any one of claims 1 to 5 is implemented.
Citation Information
Patent Citations
Bone marrow smear microscopic image analysis method and device, electronic equipment and storage medium
CN112419262A
