Medical test-based blood smear evaluation method, device and system

Abstract

The application relates to the technical field of medical image processing, in particular to a blood smear evaluation method, device and system based on medical examination. The method adopts a traversal scanning mode to obtain blood cell images of all regions of a blood smear, and constructs an image set in column units. By screening a red blood cell central region and determining a first blood cell region and a second blood cell region, analysis is jointly performed, so that the cell aggregation degree of each blood cell image can be accurately and effectively quantified. A cell aggregation degree sequence is constructed, and uniformity in the sequence is analyzed, so that the observation difficulty of each image set is obtained, an observable region can be screened, and accurate blood smear quality evaluation is realized. The application effectively quantifies the cell aggregation degree in the image through the image acquisition mode of traversal scanning, divides a correct observable region through the special morphology of the blood smear, and then realizes accurate blood smear quality evaluation.

Description

Technical Field

[0001] This invention relates to the field of medical image processing technology, specifically to a method, apparatus, and system for evaluating blood smears based on medical testing. Background Technology

[0002] Microscopic examination is a fundamental method for examining the morphology of blood cells, primarily used for the morphology of red blood cells, white blood cells, and platelets. It can also be used to assess the quantity of white blood cells and platelets, and to detect potential parasites in the blood. By observing changes in cell morphology, abnormal cells can be identified, thus confirming certain blood disorders. However, blood smears are artificially prepared, resulting in inconsistent quality, which significantly impacts subsequent testing.

[0003] Blood smears are typically prepared by using a glass slide to quickly and steadily move a blood droplet to the other end of the slide. The resulting blood film varies in thickness, with one side thicker than the other. Thicker areas show higher cell aggregation, while thinner areas have fewer cells. The quality assessment of a blood smear should focus on areas where blood cells are easily observed, rather than evaluating the overall uniformity of the smear. Current techniques for selecting observable areas in blood smears primarily rely on manual standard comparisons under a microscope, which is prone to misjudgments and omissions, thus affecting the quality assessment results. Summary of the Invention

[0004] To address the technical problem of inaccurate localization of observable areas in blood smears in existing technologies, which affects the quality assessment results of blood smears, the present invention aims to provide a blood smear assessment method, device, and system based on medical testing. The specific technical solution adopted is as follows:

[0005] This invention proposes a blood smear evaluation method based on medical testing, the method comprising:

[0006] The blood smear is scanned vertically from tail to head. The blood cell images captured in each vertical scan during the process are arranged in sequence to form an image set; thus, a set of all images of the blood region on the blood smear is obtained.

[0007] A threshold segmentation algorithm is used to obtain suspected nucleus regions and suspected cytoplasm regions in blood cell images; the red blood cell center region is selected based on the size and edge curvature of the suspected nucleus regions; the red blood cell center region and adjacent suspected cytoplasm regions are merged into a first blood cell region, and other suspected cytoplasm regions are designated as second blood cell regions; the degree of cell aggregation in each blood cell image is obtained based on the edge length and grayscale value of the first and second blood cell regions.

[0008] The degree of cell aggregation in each image set constitutes a cell aggregation degree sequence based on the positional order of blood cell images; the uniformity of cell aggregation degree in the cell aggregation degree sequence is obtained; the observation difficulty of each image set is obtained based on the uniformity of cell aggregation degree and the degree of cell aggregation; and observable areas are selected in the scanning area based on the observation difficulty.

[0009] The quality of a blood smear is determined by the area of ​​the observable region and the shape integrity of the blood cell region within the observable region.

[0010] Furthermore, the acquisition of suspected hematopoietic nucleus regions and suspected cytoplasmic regions in the hematopoietic cell image includes:

[0011] A threshold segmentation algorithm is used to process blood cell images to obtain binary images. In the binary images, the connected regions composed of the pixel type with the highest gray level are suspected cell nucleus regions, and the connected regions composed of the pixel type are suspected cytoplasm regions.

[0012] Furthermore, the screening method for the central region of the red blood cells includes:

[0013] The suspected cell nucleus region smaller than the preset area threshold is designated as the second suspected cell nucleus region. The curvature of the second suspected cell nucleus region is obtained and compared with the curvature of the standard circle. The second suspected cell nucleus region whose curvature error with the standard circle is within the preset error range is designated as the red blood cell center region.

[0014] Furthermore, the method for obtaining the degree of cell aggregation includes:

[0015] The first blood cell region and the second blood cell region are taken as the regions to be analyzed. The gray-scale mean of the regions to be analyzed in the blood cell image is obtained. The gray-scale mean is negatively correlated and then multiplied by the edge length of the regions to be analyzed to obtain the initial degree of aggregation of each region to be analyzed. The initial degree of aggregation of all regions to be analyzed in the blood cell image is summed as the degree of cell aggregation.

[0016] Furthermore, the method for obtaining the uniformity of cell aggregation includes:

[0017] The comparison element value is obtained based on the element value at the center position of the cell aggregation degree sequence. The difference in cell aggregation degree between the comparison element value and each element in the cell aggregation degree sequence is obtained. The cell aggregation degree differences of all elements are negatively correlated and then summed to obtain the uniformity of cell aggregation degree.

[0018] Furthermore, the method for obtaining the observation difficulty includes:

[0019] The observation difficulty is obtained by normalizing the product of the uniformity of cell aggregation and the average cell aggregation in the image set.

[0020] Furthermore, the method for obtaining the shape integrity of the blood cell region within the observable area includes:

[0021] The first and second blood cell regions within the observable area are taken as the regions to be analyzed. Convex hull detection is performed on each region to obtain the convex hull edge of each region. Edge points in the convex hull edge that are not edges of the region to be analyzed are taken as differential edge points. The ratio between the number of differential edge points and the number of edge points of the region to be analyzed is taken as the incompleteness. The incompleteness is negatively correlated and mapped to obtain the initial shape completeness of each region to be analyzed. Regions to be analyzed with an initial shape completeness greater than a preset first completeness threshold are taken as complete blood cell regions. The proportion of complete blood cell regions in all regions to be analyzed is taken as the shape completeness of the blood cell regions within the observable area.

[0022] Furthermore, the method for obtaining the quality of the blood smear includes:

[0023] The area ratio of the observable region to the blood region is obtained. If the area ratio is less than a preset area ratio threshold, the blood smear quality is determined to be substandard.

[0024] If the area ratio is not less than a preset area ratio threshold, the shape integrity of the blood cell region within the observable area is obtained. If the shape integrity is greater than a preset second integrity threshold, the blood smear quality is determined to be up to standard. If the shape integrity is not greater than the preset second integrity threshold, the blood smear quality is determined to be down to standard.

[0025] This invention also proposes a blood smear evaluation device based on medical testing, the device comprising:

[0026] The image acquisition module is used to scan blood smears vertically and from tail to head. During the scanning process, the blood cell images scanned vertically each time are arranged in sequence to form an image set; thus, a set of all images of the blood region on the blood smear is obtained.

[0027] The cell aggregation degree acquisition module is used to obtain suspected blood cell nucleus regions and suspected cytoplasm regions in blood cell images using a threshold segmentation algorithm; the red blood cell center region is selected based on the size and edge curvature of the suspected nucleus region, and the red blood cell center region and the adjacent suspected cytoplasm region are merged as the blood cell region; the cell aggregation degree of each blood cell image is obtained based on the edge length and gray value of the blood cell region.

[0028] The observable region localization module is used to construct a cell aggregation degree sequence based on the positional order of blood cell images in each image set; obtain the uniformity of cell aggregation degree in the cell aggregation degree sequence; obtain the observation difficulty of each image combination based on the uniformity of cell aggregation degree and the cell aggregation degree; and filter out observable regions in the scanning area based on the observation difficulty.

[0029] The blood smear quality assessment module is used to obtain the quality of blood smears based on the area of ​​the observable region and the shape integrity of the blood cell regions within the observable region.

[0030] The present invention also proposes a blood smear evaluation system based on medical testing, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of any one of the blood smear evaluation methods based on medical testing.

[0031] The present invention has the following beneficial effects:

[0032] This invention employs a traversal scanning method to obtain blood cell images of all regions of a blood smear, and constructs an image set in columns. Considering that observable areas should exhibit low blood cell aggregation and easy observation of blood cells, this invention quantifies the degree of cell aggregation in each blood cell image. Given that red blood cells have a concave center and convex periphery, resulting in significantly lower gray values ​​in the center compared to the periphery, directly using a threshold segmentation algorithm to determine cell regions would lead to a lack of information about the central location of the determined red blood cells. Therefore, this invention, by selecting the central region of red blood cells and analyzing the first and second blood cell regions together, can accurately and effectively quantify the degree of cell aggregation in each blood cell image. Because blood smears have a specific coating pattern during application, resulting in a unique blood film thickness distribution, this invention further constructs a cell aggregation degree sequence and analyzes its uniformity to obtain the observation difficulty of each image set, allowing for the selection of observable areas—regions with suitable blood aggregation and uniformity. This achieves accurate blood smear quality assessment. Attached Figure Description

[0033] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0034] Figure 1A flowchart of a blood smear evaluation method based on medical testing provided in one embodiment of the present invention;

[0035] Figure 2 This is a grayscale illustration of a blood cell image provided in one embodiment of the present invention;

[0036] Figure 3 A method provided in one embodiment of the present invention Figure 2 A binary image;

[0037] Figure 4 This is a schematic diagram illustrating the direction of blood diffusion during a blood coating process according to an embodiment of the present invention;

[0038] Figure 5 This is a schematic diagram of the observable area of ​​a blood smear provided in one embodiment of the present invention. Detailed Implementation

[0039] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a blood smear evaluation method, apparatus, and system based on medical testing proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0040] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0041] The following description, in conjunction with the accompanying drawings, details a specific scheme for a blood smear evaluation method, apparatus, and system based on medical testing provided by the present invention.

[0042] Please see Figure 1 The diagram illustrates a flowchart of a blood smear evaluation method based on medical testing, according to an embodiment of the present invention. The method includes:

[0043] Step S1: Scan the blood smear vertically from tail to head. During the scanning process, the blood cell images scanned vertically each time are arranged in sequence to form an image set; obtain the image set of all blood regions on the blood smear.

[0044] In this embodiment of the invention, the blood smear is a blood smear processed by an automated smear machine after venous blood collection, and then placed under a microscope to acquire images. A camera specifically designed for microscopes is used, and after attaching an eyepiece, the image is captured through the microscope's eyepiece to form a real-time image. In this embodiment, the image is scanned vertically from top to bottom along the tail of the blood smear, each vertical scan ending at the edge of the blood membrane, forming a set of blood cell images. The images in the set are arranged according to the order in which the blood cells were acquired, i.e., their position on the smear. After each scan, the image is moved 3mm towards the head of the blood smear and continues to be acquired vertically. This S-shaped vertical scan obtains a set of all images of the blood region on the blood smear. Each image set can be considered as information about a column of areas within the blood region.

[0045] It should be noted that when scanning blood smears, areas where no blood is present do not need to be scanned. The method for obtaining the blood area includes: acquiring the overall image of the blood smear, performing Otsu thresholding on the R channel of the overall image, and the resulting area is the blood area.

[0046] Step S2: Use a threshold segmentation algorithm to obtain suspected nucleus regions and suspected cytoplasm regions in the blood cell image; filter out the red blood cell center region based on the size and edge curvature of the suspected nucleus region; merge the red blood cell center region and the adjacent suspected cytoplasm region as the first blood cell region, and the other suspected cytoplasm regions as the second blood cell region; obtain the degree of cell aggregation in each blood cell image based on the edge length and gray value of the first and second blood cell regions.

[0047] During the preparation of blood smears, the slide is pushed from one end of the blood droplet to the other. The thickness of the blood film varies from thick to thin. An excessively thick blood film can easily cause cell adhesion, while an excessively thin blood film can lead to misinterpretation. Furthermore, it is difficult to ensure that the amount of blood droplet and the force applied during preparation are completely consistent for each smear, resulting in variations in the thickness of the blood film. It is necessary to determine, based on the inherent characteristics of the blood smear, whether there are areas where blood cells are evenly distributed and easily observed. In high-quality blood film areas, blood cells are evenly distributed with less cell aggregation and adhesion, allowing for clear observation of cell morphology; conversely, in other areas, the distribution of blood cells is uneven. Because the blood droplet diffuses laterally under the shear force of the coverslip, in a uniform distribution, the sides are slightly higher than the center. However, if the blood film is too thick, causing a higher degree of red blood cell aggregation in the center compared to the sides, the uniformity of cell distribution in that location is lower, making it less suitable as a high-quality observation area. Since each blood cell image can be considered a local area in a smear, in order to assess the observable high-quality area, it is first necessary to obtain the degree of cell aggregation in each blood cell image, and then analyze whether the distribution of cell aggregation degree in the vertical direction belongs to the situation of high on both sides and low in the middle as reflected in the high-quality area.

[0048] Firstly, considering the significant grayscale difference between the background and cellular regions in the smear, a threshold segmentation algorithm can be used to segment the blood cell image. However, red blood cells have a unique morphology: a concave center and convex edges, resulting in a low-grayscale area at the center of the red blood cell region. During threshold segmentation, this area might be identified as background, leading to the loss of grayscale information in the central region during subsequent analysis. Therefore, this embodiment of the invention divides the region into suspected blood cell nuclei and suspected cytoplasm after threshold segmentation. The suspected blood cell nuclei region is a connected component formed by background information, while the suspected cytoplasm region is a connected component formed by foreground information. If the suspected blood cell nuclei region is the central region of the red blood cell, it will appear small and highly rounded. Therefore, this embodiment of the invention can filter out the central region of the red blood cell based on the size and edge curvature of the suspected nuclei region.

[0049] Preferably, in this embodiment of the invention, a threshold segmentation algorithm is used to process the blood cell image to obtain a binary image; in the binary image, the connected region composed of the pixel type with the highest grayscale is the suspected cell nucleus region, and the connected region composed of the pixel type is the suspected cytoplasm region. Please refer to [link to relevant documentation]. Figure 2 This illustrates a grayscale diagram of a blood cell image provided in one embodiment of the present invention. Please refer to the corresponding example. Figure 3 This illustrates an embodiment of the present invention. Figure 2 The binary image, by Figure 2 and Figure 3 It can be seen that, Figure 3The black foreground region in the image forms a suspected cytoplasmic region, which is either a complete cell region or a region containing only cytoplasm. The connected domain formed by the white background region is either the central region of the red blood cell or the background region.

[0050] It should be noted that the threshold segmentation algorithm in this embodiment of the invention is the Otsu thresholding algorithm, which is an automatic threshold segmentation algorithm that can obtain a binary image by processing the grayscale image of the blood cell image. The suspected nucleus region and the suspected cytoplasm region are determined using a connected component algorithm, specifically the two-pass algorithm.

[0051] Preferably, the screening method for the central region of red blood cells in this embodiment of the invention includes:

[0052] The suspected cell nucleus region smaller than the preset area threshold is designated as the second suspected cell nucleus region. The curvature of the second suspected cell nucleus region is obtained and compared with the curvature of the standard circle. The second suspected cell nucleus region whose curvature error with the standard circle is within the preset error range is designated as the red blood cell center region.

[0053] It should be noted that the area threshold setting is related to the microscope's magnification. A higher magnification results in larger cell shapes in the image, leading to more pixels in the central region of the red blood cells, i.e., a larger area. In this embodiment, the microscope magnification is 100x, and at an image resolution of 1920×1080, the area threshold is set to 16, equivalent to 16 pixels. In this embodiment, the curvature error range is set to 10%. Circular fitting can be achieved using the least squares method, a technique well-known to those skilled in the art and will not be elaborated upon here.

[0054] Once the central region of the red blood cell is determined, it can be combined with adjacent suspected cytoplasmic regions to form the first blood cell region. This first blood cell region may be a single mature red blood cell region or a superimposed cell region containing mature red blood cell regions. Other suspected cytoplasmic regions are designated as the second blood cell region, which can be a superimposed region of other blood cell regions or a single region.

[0055] In a localized region, a high degree of cell aggregation can result in multiple overlapping cells in the acquired blood cell area, leading to a larger area. Furthermore, this overlap reduces light transmittance, making the area darker and exhibiting a grayscale contrast. Therefore, the degree of cell aggregation in each blood cell image can be determined by the edge lengths and grayscale values ​​of the first and second blood cell regions. A longer edge length indicates a larger blood cell region, while a smaller grayscale value indicates greater overlap and thus a higher degree of cell aggregation.

[0056] Preferably, in this embodiment of the invention, the method for obtaining the degree of cell aggregation includes:

[0057] The first and second blood cell regions are selected as the regions to be analyzed. The mean gray value of each region in the blood cell image is obtained. Since a smaller mean gray value indicates a darker region and a greater degree of cell overlap, the mean gray value is negatively correlated and then multiplied by the edge length of the region to be analyzed to obtain the initial clustering degree of each region. A larger initial clustering degree indicates that multiple cells are superimposed in that region. Because there are multiple regions to be analyzed in the blood cell image, the sum of the initial clustering degrees of all regions in the blood cell image is taken as the cell clustering degree.

[0058] In this embodiment of the invention, the negative correlation mapping method adopts the form of reciprocal, because the gray mean of the region to be analyzed may be 0. Therefore, the reciprocal of the gray mean plus the positive integer 1 is used as the negative correlation mapping result.

[0059] Step S3: The degree of cell aggregation in each image set is used to form a cell aggregation sequence based on the positional order of blood cell images; the uniformity of cell aggregation in the cell aggregation sequence is obtained; the observation difficulty of each image set is obtained based on the uniformity of cell aggregation and the degree of cell aggregation; and observable areas are selected in the scanning area based on the observation difficulty.

[0060] Please see Figure 4This illustration shows a schematic diagram of the blood diffusion direction during a blood smear application process according to an embodiment of the present invention. During the pushing motion of the blood smear, the blood droplets are subjected to shear forces from the coverslip and slide, spreading from the center outwards to form a blood film of a certain width. Since the shear forces on the sides are generally greater than those on the center, the cell aggregation degree of the blood film on the sides is generally slightly higher than that in the center. However, when the blood droplets are too large or the pushing speed is inappropriate, the blood concentration in the center will be higher, resulting in poor uniformity of cell distribution. Therefore, this embodiment of the invention aims to find regions where the cell aggregation degree is high on both sides and low in the center as observable areas. However, observing regions with high cell aggregation degree in the center and low cell aggregation degree on both sides is difficult. Therefore, this embodiment of the invention constructs a cell aggregation degree sequence based on the positional order of the blood cell images in each image set. This sequence represents the degree of cell aggregation in a vertical local region. If the sequence exhibits a large central element and smaller elements on both sides, it indicates that the vertical region is difficult to observe. The uniformity of cell aggregation can be obtained from the cell aggregation degree sequence, and analysis can be performed in conjunction with this uniformity. Based on the uniformity and degree of cell aggregation, the observation difficulty of each image set can be determined. Specifically, within a vertical region, the more uniform the cell aggregation degree, the larger the central element and the smaller the elements on both sides, and the greater the overall degree of cell aggregation, the higher the observation difficulty of that vertical region. Based on the observation difficulty, observable regions can be selected; these observable regions are merged areas of vertical regions with lower observation difficulty.

[0061] Preferably, in this embodiment of the invention, the method for obtaining the uniformity of cell aggregation includes:

[0062] The comparison element value is obtained by taking the element value at the center of the cell aggregation degree sequence. The difference in cell aggregation degree between the comparison element value and each element in the sequence is then calculated. These differences are negatively correlated and summed to obtain the cell aggregation degree uniformity. It should be noted that if the number of elements in the cell aggregation degree sequence is odd, the middle element value can be directly used as the comparison element value; if it is even, the average of the two middle element values ​​is used. The smaller the difference in cell aggregation degree between the comparison element value and other elements, the less pronounced the cell aggregation degree is relative to the center, indicating a distribution characteristic outside the observable area. Therefore, a negative correlation is applied and the differences are summed to obtain the cell aggregation degree uniformity. A higher uniformity indicates greater observation difficulty.

[0063] In this embodiment of the invention, considering the possibility of negative differences in cell aggregation, the differences are mapped using an exponential function with the natural constant as the base. That is, the difference is used as the power of the exponential function, resulting in a positive value. Similar to the negative correlation mapping of the gray-scale mean described above, a reciprocal form can also be used for negative correlation mapping; details will not be elaborated further.

[0064] Preferably, in this embodiment of the invention, the method for obtaining the observation difficulty includes:

[0065] The observation difficulty is obtained by normalizing the product of the uniformity of cell aggregation and the average cell aggregation in the image set.

[0066] The normalization algorithm in this embodiment can be implemented using range standardization. In other embodiments, function mapping methods such as the hyperbolic tangent function can also be used; these are techniques well-known to those skilled in the art and will not be elaborated upon here. In this embodiment, a threshold range of 0.33 to 0.45 is set. The set of images within this threshold range represents the local region of the observable area. Continuously observable local regions are merged, and the largest merged region is taken as the observable area. Please refer to [link / reference]. Figure 5 The diagram shows a schematic of an observable area of ​​a blood smear provided by an embodiment of the present invention. In the observable area, the cells are morphologically intact and are distributed relatively dispersedly and evenly.

[0067] Step S4: Obtain the quality of the blood smear based on the area of ​​the observable region and the shape integrity of the blood cell region within the observable region.

[0068] For the observable area, a larger area indicates a higher quality blood smear; higher integrity of the blood cell regions within the observable area indicates that the smearing process meets the regulations and requirements and does not affect normal cell observation. Therefore, the quality of a blood smear can be determined based on the area of ​​the observable area and the shape integrity of the blood cell regions within it.

[0069] Preferably, in this embodiment of the invention, the complete blood cell connected regions should be non-concave in the image. If cell breakage occurs during the coating process, the connected regions of the broken cells will exhibit an uneven shape. Therefore, the method for obtaining the shape integrity of the blood cell region within the observable area in this embodiment of the invention includes:

[0070] The first and second blood cell regions within the observable area are selected as the regions to be analyzed. Convex hull detection is performed on each region to obtain its convex hull edge. The greater the difference between the convex hull edge and the actual edge of the region, the more likely the corresponding cells are fragmented, and the less complete the shape.

[0071] Edge points within the convex hull that are not edges of the region to be analyzed are designated as differential edge points. The ratio between the number of differential edge points and the number of edge points of the region to be analyzed is used as the incompleteness. A negative correlation is applied to this incompleteness to obtain the initial shape completeness of each region to be analyzed. A higher initial shape completeness indicates that the blood cells corresponding to that region are more likely to be intact blood cell regions.

[0072] The regions to be analyzed with an initial shape integrity greater than a preset first integrity threshold are defined as complete blood cell regions, and the proportion of complete blood cell regions in all regions to be analyzed is defined as the shape integrity of blood cell regions within the observable region.

[0073] In this embodiment of the invention, since the incompleteness value range is between 0 and 1, the difference between the positive integer 1 and the incompleteness can be directly used as the negative correlation mapping result to obtain the initial shape completeness. The first completeness threshold is set to 0.9.

[0074] Furthermore, in this embodiment of the invention, the method for obtaining the quality of blood smears includes:

[0075] The proportion of the observable area to the blood smear area is obtained. If the proportion is less than a preset area proportion threshold, the blood smear quality is deemed substandard. In this embodiment of the invention, the area proportion threshold is set to 0.2.

[0076] If the area proportion is not less than a preset area proportion threshold, the shape integrity of the blood cell region within the observable area is obtained. If the shape integrity is greater than a preset second integrity threshold, the blood smear quality is determined to be up to standard. If the shape integrity is not greater than the preset second integrity threshold, the blood smear quality is determined to be substandard. In this embodiment of the invention, the second integrity threshold is set to 0.9.

[0077] In summary, this invention employs a traversal scanning method to obtain blood cell images of all regions of a blood smear and constructs an image set in columns. By selecting the central region of red blood cells and analyzing the first and second blood cell regions together, the degree of cell aggregation in each blood cell image can be accurately and effectively quantified. By constructing a sequence of cell aggregation degrees and analyzing its uniformity, the observation difficulty of each image set can be obtained, allowing for the selection of observable areas and thus achieving accurate blood smear quality assessment. This invention effectively quantifies the degree of cell aggregation in images through traversal scanning image acquisition, and delineates the correct observable areas based on the specific morphology of blood smears, thereby achieving accurate blood smear quality assessment.

[0078] Based on the same inventive concept, the present invention also proposes a blood smear evaluation device based on medical testing, the device comprising:

[0079] The image acquisition module is used to scan blood smears vertically and from tail to head. During the scanning process, the blood cell images scanned vertically each time are arranged in sequence to form an image set; thus, a set of all images of the blood region on the blood smear is obtained.

[0080] The cell aggregation degree acquisition module is used to obtain suspected blood cell nucleus regions and suspected cytoplasm regions in blood cell images using a threshold segmentation algorithm; the red blood cell center region is selected based on the size and edge curvature of the suspected nucleus region, and the red blood cell center region and the adjacent suspected cytoplasm region are merged as the blood cell region; the cell aggregation degree of each blood cell image is obtained based on the edge length and gray value of the blood cell region.

[0081] The observable region localization module is used to construct a cell aggregation degree sequence based on the positional order of blood cell images in each image set; obtain the uniformity of cell aggregation degree in the cell aggregation degree sequence; obtain the observation difficulty of each image combination based on the uniformity of cell aggregation degree and the cell aggregation degree; and filter out observable regions in the scanning area based on the observation difficulty.

[0082] The blood smear quality assessment module is used to obtain the quality of blood smears based on the area of ​​the observable region and the shape integrity of the blood cell regions within the observable region.

[0083] The present invention also proposes a blood smear evaluation system based on medical testing, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of any one of the blood smear evaluation methods based on medical testing.

[0084] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0085] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A blood smear evaluation method based on medical testing, characterized in that, The method includes: Starting from the tail of the blood smear, images are scanned vertically from top to bottom. During the scan, the blood cell images captured vertically each time are arranged in sequence to form an image set; thus, a set of all images of the blood region on the blood smear is obtained. The threshold segmentation algorithm is used to obtain suspected nucleus regions and suspected cytoplasm regions in blood cell images; the red blood cell center region is selected based on the size and edge curvature of the suspected nucleus region; the red blood cell center region and the adjacent suspected cytoplasm region are merged into the first blood cell region, and the other suspected cytoplasm regions are the second blood cell regions; the degree of cell aggregation in each blood cell image is obtained based on the edge length and gray value of the first and second blood cell regions. The degree of cell aggregation in each image set constitutes a cell aggregation degree sequence based on the positional order of blood cell images; the uniformity of cell aggregation degree in the cell aggregation degree sequence is obtained by comparing the element at the center position with other elements; the observation difficulty of each image set is obtained based on the uniformity of cell aggregation degree and the degree of cell aggregation; and observable areas are selected in the scanning area based on the observation difficulty. The quality of a blood smear is determined by the area of ​​the observable region and the shape integrity of the blood cell region within the observable region.

2. The blood smear evaluation method based on medical testing according to claim 1, characterized in that, The suspected nucleus region and suspected cytoplasm region in the obtained blood cell image include: A threshold segmentation algorithm is used to process blood cell images to obtain binary images. In the binary images, the connected regions composed of the pixel type with the highest gray level are suspected cell nucleus regions, and the connected regions composed of the pixel type are suspected cytoplasm regions.

3. The blood smear evaluation method based on medical testing according to claim 1, characterized in that, The screening method for the central region of red blood cells includes: The suspected cell nucleus region smaller than the preset area threshold is designated as the second suspected cell nucleus region. The curvature of the second suspected cell nucleus region is obtained and compared with the curvature of the standard circle. The second suspected cell nucleus region whose curvature error with the standard circle is within the preset error range is designated as the red blood cell center region.

4. The blood smear evaluation method based on medical testing according to claim 1, characterized in that, The method for obtaining the degree of cell aggregation includes: The first blood cell region and the second blood cell region are taken as the regions to be analyzed. The gray-scale mean of the regions to be analyzed in the blood cell image is obtained. The gray-scale mean is negatively correlated and then multiplied by the edge length of the regions to be analyzed to obtain the initial degree of aggregation of each region to be analyzed. The initial degree of aggregation of all regions to be analyzed in the blood cell image is summed as the degree of cell aggregation.

5. The blood smear evaluation method based on medical testing according to claim 1, characterized in that, The method for obtaining the uniformity of cell aggregation includes: The comparison element value is obtained based on the element value at the center position of the cell aggregation degree sequence. The difference in cell aggregation degree between the comparison element value and each element in the cell aggregation degree sequence is obtained. The cell aggregation degree differences of all elements are negatively correlated and then summed to obtain the uniformity of cell aggregation degree.

6. The blood smear evaluation method based on medical testing according to claim 1, characterized in that, The methods for obtaining the observation difficulty include: The observation difficulty is obtained by normalizing the product of the uniformity of cell aggregation and the average cell aggregation in the image set.

7. The blood smear evaluation method based on medical testing according to claim 1, characterized in that, The methods for obtaining the shape integrity of the blood cell region within the observable area include: The first and second blood cell regions within the observable area are taken as the regions to be analyzed. Convex hull detection is performed on each region to obtain the convex hull edge of each region. Edge points in the convex hull edge that are not edges of the region to be analyzed are taken as differential edge points. The ratio between the number of differential edge points and the number of edge points of the region to be analyzed is taken as the incompleteness. The incompleteness is negatively correlated and mapped to obtain the initial shape completeness of each region to be analyzed. Regions to be analyzed with an initial shape completeness greater than a preset first completeness threshold are taken as complete blood cell regions. The proportion of complete blood cell regions in all regions to be analyzed is taken as the shape completeness of the blood cell regions within the observable area.

8. The blood smear evaluation method based on medical testing according to claim 7, characterized in that, The method for obtaining the quality of the blood smear includes: The area ratio of the observable region to the blood region is obtained. If the area ratio is less than a preset area ratio threshold, the blood smear quality is determined to be substandard. If the area ratio is not less than a preset area ratio threshold, the shape integrity of the blood cell region within the observable area is obtained. If the shape integrity is greater than a preset second integrity threshold, the blood smear quality is determined to be up to standard. If the shape integrity is not greater than the preset second integrity threshold, the blood smear quality is determined to be down to standard.

9. A blood smear evaluation device based on medical testing, characterized in that, The device includes: The image acquisition module is used to scan images from top to bottom along the vertical direction of the blood smear, starting from the tail of the smear. During the scanning process, the blood cell images scanned vertically each time are arranged in sequence to form an image set; thus obtaining a set of all images of the blood region on the blood smear. The cell aggregation degree acquisition module is used to obtain suspected nucleus regions and suspected cytoplasm regions in blood cell images using a threshold segmentation algorithm; the red blood cell center region is selected based on the size and edge curvature of the suspected nucleus region, and the red blood cell center region and the adjacent suspected cytoplasm region are merged as the blood cell region; the cell aggregation degree of each blood cell image is obtained based on the edge length and gray value of the blood cell region. The observable region localization module is used to construct a cell aggregation degree sequence based on the positional order of blood cell images in each image set; to obtain the uniformity of cell aggregation degree in the cell aggregation degree sequence by comparing the element at the center position with other elements; to obtain the observation difficulty of each image combination based on the uniformity of cell aggregation degree and the cell aggregation degree; and to filter out observable regions in the scanning area based on the observation difficulty. The blood smear quality assessment module is used to obtain the quality of blood smears based on the area of ​​the observable region and the shape integrity of the blood cell regions within the observable region.

10. A blood smear evaluation system based on medical testing, 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, it implements the steps of the blood smear evaluation method based on medical testing as described in any one of claims 1 to 9.

Images