Medical image segmentation method, system, electronic device and medium

Abstract

The application provides a medical image segmentation method, system, electronic equipment and storage medium, the medical image segmentation method comprises the following steps: carrying out preliminary segmentation on the to-be-segmented medical image according to a preset pixel threshold, and carrying out edge detection and feature enhancement on the medical image obtained through preliminary segmentation to extract a first medical segmentation image; and the first medical segmentation image is optimized according to a preset optimization target to obtain an image of a target organ tissue. The medical image segmentation method, system, electronic equipment and storage medium provided by the application not only have strong universality, reduce the tedious man-machine interaction operation, but also have high segmentation precision, and can better assist doctors to improve the diagnosis efficiency and accuracy.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, and in particular to a medical image segmentation method and system, an electronic device and a medium. BACKGROUND

[0002] At present, cardiovascular disease is the highest mortality disease in the world, and the incidence and mortality are increasing year by year, which seriously threatens human life and health. Therefore, it is of great significance to quantitatively assist in the diagnosis and interventional treatment of cardiovascular disease for improving human health. The heart is a key organ of the human cardiovascular system, and modern medical imaging technology can provide rich structural and functional information. Therefore, in the treatment process, doctors can rely on medical images of the heart to assist in the diagnosis of various heart-related diseases, such as calcification, aortic dissection, aneurysm, etc.

[0003] However, due to the complex structure of the heart, different parts of the heart have different characteristics, and the medical image not only includes heart tissue but also other tissues around the heart, which brings great difficulty to doctors in analyzing the heart structure of the patient's medical image. Therefore, it is particularly important to accurately segment the heart medical image, which can provide high-quality heart structure information for doctors and help them quickly and accurately diagnose.

[0004] At present, the commonly used segmentation methods for heart medical images include manual segmentation method, model matching based method, variable model based method and deep learning based segmentation method. The above methods are roughly described as follows:

[0005] 1. Manual segmentation method: relying on experienced medical experts to manually segment. In clinical practice, manual segmentation by doctors not only takes time and effort, but also depends on the experience of doctors, and the segmentation results of different doctors or even the same doctor at different times have great variability. Therefore, the manual segmentation method for heart medical images has the defects of great variability and the need for a large amount of time and effort.

[0006] 2. Model matching based method: a set of CT image sequences are matched with an average heart model through adaptive shape matching to complete the segmentation of the heart. Although this method can reduce user interaction, the shape and dynamics of the heart of different people (including normal people and patients with heart disease) are diverse, and the complex structure of the heart makes different parts of the heart have different characteristics. Therefore, it is difficult to establish a general model containing all possible shapes of the heart chamber, and the accuracy of segmentation using a unified heart template is low, and there are problems of poor model universality and generalization performance.

[0007] 3. Variable model-based method: This method requires user interaction to complete segmentation, and requires manual confirmation of segmentation results and adjustment of labeling results. Therefore, it has poor robustness and low segmentation accuracy.

[0008] In addition, although there are many blood vessel image segmentation technologies at present, as mentioned above, due to the complex structure of the heart, the medical image segmentation technology applied to conventional blood vessels is difficult to be directly applied to the segmentation of heart medical images.

[0009] Although the above is illustrated by taking the segmentation of heart medical images as an example, it is not difficult for those skilled in the art to understand that the medical image segmentation method of other organ tissues also has similar defects.

[0010] Therefore, how to provide a medical image segmentation method has become one of the technical problems to be solved by those skilled in the art.

[0011] It should be noted that the information disclosed in the background section of the present application is only intended to deepen the understanding of the general background of the present application, and should not be regarded as acknowledging or implying in any form that the information constitutes prior art known to those skilled in the art. SUMMARY

[0012] The purpose of the present application is to provide a medical image segmentation method, system, electronic device and medium to reduce the tedious human-computer interaction operation, improve the segmentation accuracy of medical images, and better assist doctors to improve the diagnosis efficiency and accuracy, in view of the deficiencies in the related art.

[0013] To achieve the above-mentioned purpose, the present application is realized by the following technical scheme: a medical image segmentation method, comprising:

[0014] preliminarily segmenting the to-be-segmented medical image according to a preset pixel threshold, performing edge detection and feature enhancement on the preliminarily segmented medical image, and extracting a first medical segmentation image;

[0015] optimizing the first medical segmentation image according to a preset optimization target to obtain an image of a target organ tissue.

[0016] Optionally, the preliminary segmentation of the to-be-segmented medical image according to the preset pixel threshold, the edge detection and the feature enhancement on the preliminarily segmented medical image, and the extraction of the first medical segmentation image, comprise:

[0017] segmenting the to-be-segmented medical image according to a preset first upper limit threshold and a preset first lower limit threshold to obtain a second medical segmentation image;

[0018] performing edge detection on the to-be-segmented medical image to obtain a third medical segmentation image; and enhancing edges of the to-be-segmented medical image by using a Hessian matrix eigenvalue enhancement operator to obtain a fourth medical segmentation image after edge enhancement;

[0019] performing a logic regression transformation on strong edge pixel points and weak edge pixel points in the fourth medical segmentation image after edge enhancement to obtain a fifth medical segmentation image;

[0020] performing a logic AND operation on the second medical segmentation image and the fifth medical segmentation image to obtain a sixth medical segmentation image;

[0021] performing a morphological connected domain operation on the sixth medical segmentation image to retain a region with a maximum connected domain volume to obtain a seventh medical segmentation image;

[0022] retaining a connected domain result corresponding to the seventh medical segmentation image in the third medical segmentation image to obtain the first medical segmentation image.

[0023] Optionally, before the performing edge detection on the to-be-segmented medical image to obtain a third medical segmentation image, the method further includes:

[0024] performing truncation processing on the second medical segmentation image according to a preset truncation pixel threshold to obtain a second medical segmentation image after truncation;

[0025] performing linear scaling on pixel values of the second medical segmentation image after truncation to scale the pixel values of the second medical segmentation image to a range of 0-255.

[0026] Optionally, the performing edge detection on the to-be-segmented medical image to obtain a third medical segmentation image includes:

[0027] detecting and connecting edges of the second medical segmentation image by using a Canny operator according to a preset second upper threshold and a second lower threshold;

[0028] segmenting to obtain a third medical segmentation image according to edges of the to-be-segmented medical image.

[0029] Optionally, the optimizing the first medical segmentation image according to a preset optimization target to obtain an image of a target organ tissue includes:

[0030] performing hole filling on the first medical segmentation image to obtain a first medical segmentation image after hole filling;

[0031] performing a morphological opening operation on the first medical segmentation image after hole filling according to preset morphological opening operation information to obtain a first medical segmentation image after morphological opening operation;

[0032] performing a connected domain operation on the first medical segmentation image after the morphological opening operation to obtain an image of the target organ tissue.

[0033] Optionally, the method further comprises obtaining the image of the medical region of interest on the target organ tissue by:

[0034] selecting a plurality of seed points in the medical region of interest of the medical image to be segmented according to a preset pixel threshold of the medical region of interest; and extracting the image of the medical region of interest by using an adaptive region growing method according to the seed points.

[0035] Optionally, the extracting the image of the medical region of interest by using the adaptive region growing method according to the seed points comprises:

[0036] respectively taking each seed point as a starting point of growth, comparing a pixel point adjacent to the seed point with the seed point, and merging the adjacent pixel point meeting a preset segmentation condition to a region where the seed point is located until all pixel points meeting the preset segmentation condition are merged to the region where the seed point is located, to obtain a plurality of region growing results;

[0037] adding the region growing results to obtain the image of the medical region of interest.

[0038] Optionally, the preset segmentation condition comprises that a value of the adjacent pixel point is between a third upper limit threshold and a third lower limit threshold.

[0039] Before the extracting the image of the medical region of interest by using the adaptive region growing method, the method further comprises determining the third upper limit threshold and the third lower limit threshold according to pixel values of the plurality of seed points.

[0040] Optionally, the determining the third upper limit threshold and the third lower limit threshold according to the pixel values of the plurality of seed points comprises:

[0041] counting the pixel values of the plurality of seed points to determine a maximum pixel value and a minimum pixel value;

[0042] determining the third upper limit threshold and the third lower limit threshold according to the maximum pixel value and the minimum pixel value;

[0043] wherein, the third upper limit threshold and the third lower limit threshold are calculated according to the following formula:

[0044] T max = P max *(1+β)

[0045] T min = Pmin (1-β)

[0046] wherein, T max is a third upper limit threshold, P max is a maximum pixel value, T min is a third lower limit threshold, P min is a minimum pixel value, and β is an adjustment factor, wherein β is in a range of 0 to 1.

[0047] According to another aspect of the present application, the present application also provides a medical image segmentation system, comprising:

[0048] an image segmentation unit configured to preliminarily segment a to-be-segmented medical image according to a preset pixel threshold, and perform edge detection and feature enhancement on the preliminarily segmented medical image to extract a first medical segmentation image;

[0049] an image optimization unit configured to optimize the first medical segmentation image according to a preset optimization target to obtain an image of a target organ tissue.

[0050] According to still another aspect of the present application, the present application also provides a medical image acquisition system, comprising:

[0051] a medical image acquisition device configured to acquire a to-be-segmented medical image;

[0052] a medical image segmentation device configured to segment the to-be-segmented medical image;

[0053] wherein the medical image segmentation device comprises an image segmentation unit and an image optimization unit;

[0054] the image segmentation unit is configured to preliminarily segment the to-be-segmented medical image according to a preset pixel threshold, and perform edge detection and feature enhancement on the preliminarily segmented medical image to extract a first medical segmentation image;

[0055] the image optimization unit is configured to optimize the first medical segmentation image according to a preset optimization target to obtain an image of a target organ tissue.

[0056] According to another aspect of the present application, the present application also provides an electronic device, comprising a processor and a memory, wherein the memory has stored thereon a computer program, and the computer program, when executed by the processor, implements the medical image segmentation method according to any one of the above aspects.

[0057] According to another aspect of the present invention, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the medical image segmentation method described in any of the preceding claims.

[0058] Compared with the prior art, the medical image segmentation method, system, electronic device, and storage medium provided by the present invention have the following beneficial effects:

[0059] The medical image segmentation method provided by this invention performs preliminary segmentation of the medical image to be segmented based on a preset pixel threshold, and then performs edge detection and feature enhancement on the preliminarily segmented medical image to extract a first medical segmented image. The first medical segmented image is then optimized according to a preset optimization target to obtain an image of the target organ or tissue. Therefore, the medical image segmentation method, system, electronic device, and storage medium provided by this invention not only reduce the number of interactions and improve overall segmentation efficiency, but also improve the segmentation accuracy of medical images, thereby better assisting doctors in improving diagnostic efficiency and accuracy, effectively balancing segmentation efficiency and accuracy. Furthermore, the medical image segmentation method provided by this invention is applicable to different target organs and tissues and CTA images from different manufacturers' equipment, demonstrating strong versatility. Attached Figure Description

[0060] Figure 1 A flowchart illustrating a medical image segmentation method according to an embodiment of the present invention;

[0061] Figure 2 This is a cross-sectional schematic diagram of a preprocessed medical image to be segmented (taking the aortic valve as an example) in a specific example of the present invention.

[0062] Figure 3 for Figure 1 A detailed flowchart of step S1 is shown below;

[0063] Figure 4 This is a cross-sectional schematic diagram of a second medical segmentation image in a specific example of the present invention;

[0064] Figure 5 This is a cross-sectional schematic diagram of a third medical segmentation image in a specific example of the present invention;

[0065] Figure 6 This is a cross-sectional schematic diagram of the fifth medical segmentation image in a specific example of the present invention;

[0066] Figure 7 This is a cross-sectional schematic diagram of the sixth medical segmentation image in a specific example of the present invention;

[0067] Figure 8A cross-sectional view of a seventh medical segmentation image in one embodiment of the present application;

[0068] Figure 9 A cross-sectional view of a first medical segmentation image in one embodiment of the present application;

[0069] Figure 10 An image of a target organ tissue in one embodiment of the present application;

[0070] Figure 11 An image of a target organ tissue and a medical region of interest (lesion tissue) in one embodiment of the present application;

[0071] Figure 12 A block diagram of a medical image acquisition system in one embodiment of the present application;

[0072] In the drawings, the following reference numerals are used:

[0073] 100 - medical image acquisition apparatus, 200 - medical image segmentation apparatus, 210 - image segmentation unit, 220 - image optimization unit;

[0074] A1 - aortic vessel, A2 - aortic valve, A3 - valve calcification, A4 - ventricular blood pool. DETAILED DESCRIPTION

[0075] To make the objects, advantages and features of the present application more clearly, the medical image segmentation method, system, electronic device and storage medium proposed by the present application are further described in detail below in combination with the drawings. It should be noted that the drawings are very simplified and all use non-precise proportions, only to facilitate and clearly assist the purpose of explaining the embodiments of the present application. It should be understood that the drawings of the specification do not necessarily show the specific structure of the present application in proportion, and the illustrative features used to explain some principles of the present application in the drawings of the specification will also be slightly simplified. The specific design features of the present application disclosed herein include, for example, specific sizes, directions, positions and shapes, which will be determined in part by the specific application and use environment to be applied and used. In the following described embodiments, the same reference numerals are sometimes used in different drawings to represent the same parts or parts with the same function, and the repeated description is omitted. In this specification, similar numbers and letters are used to represent similar items, so once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0076] These terms used in this way can be replaced under appropriate circumstances. Similarly, if the method described herein includes a series of steps, and the order of the steps presented herein is not necessarily the only order in which the steps can be performed, and some of the described steps can be omitted and / or some other steps not described herein can be added to the method.

[0077] The core idea of the present application is to provide a medical image segmentation method, system, electronic device and storage medium, so as to effectively reduce the cumbersome operation of human-computer interaction and improve the medical image segmentation efficiency.

[0078] It should be noted that the electronic device of the present application includes but is not limited to personal computers, mobile terminals and the like, which can be mobile phones, tablet computers and the like with various operating systems.

[0079] In particular, in order to facilitate understanding of the present application, each embodiment provided in the present application is mainly taken as an example of segmenting an aortic valve image, and more specifically, the aortic valve image to be segmented is a CTA (Computed Tomography Angiography) volume data (for example, three-dimensional data of an image) image. According to the content disclosed in each embodiment of the present application, it is not difficult for those skilled in the art to understand that the aortic valve image can also be an MRA (Magnetic Resonance Angiography) image or a medical image obtained by other image devices; further, the medical image to be segmented can be collected by an image acquisition device, such as a CT, MRI and the like, or can be collected by other means (such as the Internet), and of course can also be scanned by a scanning device, and the size of the aortic valve image to be segmented can be set according to specific conditions, which is not limited by the present application; further, although the present application is taken as an example of segmenting an aortic valve image, obviously, the medical image segmentation method provided by the present application can also be used for segmentation of other organ tissues, such as vascular tissues, including but not limited to segmentation of neural vessels, radial artery vessels and the like; and segmentation of other organ tissues, such as liver, lung, brain and the like, which will not be described one by one.

[0080] The medical image segmentation method, system, electronic device and storage medium provided by the present application will be exemplarily described below.

[0081] Embodiment one

[0082] The present embodiment provides a medical image segmentation method, please refer to Figure 1 , which schematically shows the flow chart of the medical image segmentation method provided by one of the embodiments of the present embodiment, as shown in Figure 1 , the medical image segmentation method comprises:

[0083] Step S1: performing preliminary segmentation on the medical image to be segmented according to a preset pixel threshold, and performing edge detection and feature enhancement on the medical image obtained by preliminary segmentation to extract a first medical segmentation image.

[0084] Specifically, those skilled in the art can understand that the preset pixel threshold can be determined according to the calibration value of the target organ tissue in the to-be-segmented medical image. For example, the to-be-segmented medical image is a CT image, and generally, the pixel value of the CT image is calibrated to represent different regions / tissues. If the target organ tissue is lung tissue, the preset pixel threshold should be the maximum and minimum values of the pixel value of the calibrated lung tissue. For example, in the CT image, the calibration value of water is 0, so the pixel value of 0 represents water, the calibration value of lung tissue is -600 to -400, so the pixel value of -600 to -400 represents lung tissue, and the pixel value of 0-100 is myocardial tissue. Therefore, the present application preliminarily segments the to-be-segmented medical image according to the preset pixel threshold, and performs edge detection and feature enhancement on the preliminarily segmented medical image to extract the image of the target organ tissue region, which not only reduces the number of interactions, but also improves the overall segmentation efficiency.

[0085] Step S2: optimizing the first medical segmentation image according to a preset optimization target to obtain the image of the target organ tissue. Therefore, by optimizing the first medical segmentation image extracted in step S1, the segmentation accuracy of the medical image can be improved, thereby better assisting doctors to improve the diagnosis efficiency and accuracy.

[0086] Therefore, the medical image segmentation method provided by the present application preliminarily segments the to-be-segmented medical image according to the preset pixel threshold, and performs edge detection and feature enhancement on the preliminarily segmented medical image to extract the first medical segmentation image; and optimizes the first medical segmentation image according to a preset optimization target to obtain the image of the target organ tissue. In this way, the medical image segmentation method provided by the present application not only reduces the number of interactions and improves the overall segmentation efficiency, but also improves the segmentation accuracy of the medical image, thereby better assisting doctors to improve the diagnosis efficiency and accuracy, and well balancing the segmentation efficiency and segmentation accuracy. Further, the medical image segmentation method provided by the present application can be applied to different target tissues and organs and CTA images of different manufacturers' devices, and has strong universality.

[0087] In one preferred embodiment, before performing step S1 to preliminarily segment the to-be-segmented medical image according to the preset pixel threshold, the method further comprises: acquiring the to-be-segmented medical image, and pre-processing the to-be-segmented medical image in the following manner. Specifically as follows:

[0088] S01: normalizing the size of the to-be-segmented medical image according to a preset image normalization rule to obtain a normalized to-be-segmented medical image.

[0089] Specifically, in one embodiment, the to-be-segmented medical image is a CTA (Computed Tomography Angiography) volume data (e.g., three-dimensional data of an image) image, for example, with a size of 512x512x130, and of course the size can be selected according to the specific image in actual implementation. With such a configuration, by normalizing the size of the to-be-segmented medical image, the segmentation effect and efficiency of the medical image can be further improved.

[0090] S02: filtering the normalized to-be-segmented medical image to obtain a to-be-segmented medical image with noise information removed. Those skilled in the art can understand that the present application does not limit the specific method of removing noise information. For example, in one exemplary embodiment, a three-dimensional Gaussian filter is used to filter out noise information in the normalized to-be-segmented medical image; in another embodiment, a non-local average denoising method is used to remove noise information in the normalized to-be-segmented medical image; in yet another embodiment, a three-dimensional block matching filter is used, and the like, which will not be exemplified one by one. See Figure 2 , Figure 2 is a cross-sectional schematic view of the to-be-segmented medical image (taking the aortic valve as an example) after preprocessing in one specific embodiment of the present application. In the figure, A1 indicates the region of the aortic blood vessel, A2 indicates the region of the aortic valve, A3 indicates the region of the valve calcification, and A4 indicates the region of the ventricular blood pool. From Figure 2 It can be seen that the medical image segmentation method provided by the present application can remove noise information on the to-be-segmented medical image, maintain the integrity of the original information (i.e., the main features), and remove useless information in the signal, thereby laying a good foundation for the quality and segmentation efficiency of subsequent extraction of the first medical segmentation image. It can be understood that, as a preferred embodiment, the to-be-segmented medical image used in step S1 is the to-be-segmented medical image obtained after preprocessing.

[0091] Preferably, in one preferred embodiment, please refer to Figure 3 which schematically shows a specific flowchart of step S1. As shown in Figure 3 In step S1, the to-be-segmented medical image is preliminarily segmented according to a preset pixel threshold value, and the preliminarily segmented medical image is subjected to edge detection and feature enhancement to extract a first medical segmentation image, including the following steps:

[0092] S11: segmenting the to-be-segmented medical image according to a preset first upper limit threshold value and a preset first lower limit threshold value to obtain a second medical segmentation image.

[0093] Specifically, in one of the exemplary embodiments, still taking the aortic valve segmentation as an example, in one of the exemplary CT images, the first upper threshold is preset as 1500, and the first lower threshold is preset as 200. As understood by those skilled in the art, this is only an exemplary description, not a limitation of the present application, and the first upper threshold and the first lower threshold should be reasonably set according to the pixel value range of the target organ tissue to be segmented in the CT image. The first upper threshold and the first lower threshold of different organ tissues, or even the same organ tissue on different calibrated CT images may be different.

[0094] In one of the preferred embodiments, referring to Figure 4 , Figure 4 is obtained by Figure 2 The cross-sectional schematic view of the second medical segmentation image obtained by the preliminary segmentation with the adaptive threshold. According to the first upper threshold and the first lower threshold, the pixel points with pixel values between the first upper threshold and the first lower threshold in the medical image to be segmented are set as white (i.e. pixel value is 1), and the pixel points with pixel values less than the first lower threshold or greater than the first upper threshold are set as black (i.e. pixel value is 0), so that the first medical segmentation image with black background and white target region (including aortic valve region) can be obtained more simply and efficiently.

[0095] In addition, it should be noted that the first upper threshold and the first lower threshold are the pixel values of the target organ tissue in the medical image to be segmented. For example, when the medical image to be segmented is a CTA image, the first upper threshold and the first lower threshold refer to the CT values (i.e. HU values) of the first upper threshold and the first lower threshold in the CTA image.

[0096] S12: performing edge detection on the medical image to be segmented to obtain a third medical segmentation image; and enhancing the edge of the medical image to be segmented by using a Hessian matrix eigenvalue enhancement operator to obtain a fourth medical segmentation image with enhanced edge.

[0097] Preferably, in one of the preferred embodiments, the edge detection on the medical image to be segmented to obtain a third medical segmentation image comprises:

[0098] S121: detecting and connecting the edge of the medical image to be segmented by using a Canny operator according to a preset second upper threshold and a second lower threshold.

[0099] Specifically, in one implementation, the Canny operator is used to detect and connect the edges of the medical image to be segmented, including: first, smoothing the medical image to be segmented using a Gaussian filter; then, calculating the magnitude and direction of the gradient on the smoothed medical image using the finite difference of the first-order partial derivative; next, performing non-maximum suppression on the gradient magnitude to obtain a non-maximum suppressed image; finally, detecting and connecting the edges using a double threshold algorithm.

[0100] Preferably, the specific process of edge detection and connection using the dual-threshold algorithm is as follows: A second upper threshold and a second lower threshold (the second upper threshold is greater than the second lower threshold), i.e., a high threshold and a low threshold, are applied to distinguish edge pixels. If the gradient value of an edge pixel is greater than the second upper threshold, it is considered a strong edge point; if the edge gradient value is less than the second upper threshold but greater than the second lower threshold, it is marked as a weak edge point. Points less than the second lower threshold are suppressed. Thus, strong edge points can be considered true edges. Weak edge points may be true edges, or they may be caused by noise or color changes. It is generally believed that weak edge points caused by true edges are connected to strong edge points, while weak edge points caused by noise are not. Those skilled in the art should understand that the second upper threshold and the second lower threshold should be determined based on the pixel values ​​of the target organ tissue; in this embodiment, they are determined based on the pixel values ​​of the aortic valve. Then, hysteresis boundary tracking is performed. The so-called hysteresis boundary tracking algorithm checks the 8-connected neighborhood pixels of a weak edge point; if a strong edge point exists, the weak edge point is considered a true edge and preserved. Search for all connected weak edges. If any point of a connected weak edge is connected to a point of a strong edge, then retain the weak edge; otherwise, suppress the weak edge. The search can be performed using either breadth-first search or depth-first search algorithms; this invention does not impose any restrictions on either.

[0101] S122: Based on the edges of the medical image to be segmented, a third medical segmentation image is obtained.

[0102] Please refer to Figure 5 , Figure 5 This is a schematic diagram of a cross-section of the third medical segmentation image, such as... Figure 5 As shown, by detecting and connecting the edges of the medical image to be segmented, the contour of the aortic valve can be effectively identified, thereby enabling the aortic valve to be distinguished from the ventricular blood pool.

[0103] Furthermore, for details regarding the use of the Hessian matrix eigenvalue enhancement operator to enhance the edges of the medical image to be segmented, resulting in a fourth medical segmented image with enhanced edges, please refer to the relevant descriptions in the prior art regarding the use of the Hessian matrix eigenvalue enhancement operator to enhance image edges, which will not be repeated here.

[0104] S13: performing a logistic regression transformation on the strong edge pixel points and the weak edge pixel points in the fourth medical segmentation image after edge enhancement to obtain a fifth medical segmentation image.

[0105] By performing a regression processing on the strong blood vessel features and the weak features in the fourth medical segmentation image after edge enhancement, i.e., setting the strong edge pixel points to black (i.e., pixel value is 0) and setting the weak edge pixel points to white (i.e., pixel value is 1), the fifth medical segmentation image is obtained. As shown in Figure 6 Figure 6 Fig. 6 is a cross-sectional schematic view of the fifth medical segmentation image according to one specific example of the present application. As can be seen from Figure 6 , by performing a logistic regression transformation on the fourth medical segmentation image, the contour boundary information of the aortic valve region can be further enhanced.

[0106] S14: performing a logical AND operation on the second medical segmentation image and the fifth medical segmentation image to obtain a sixth medical segmentation image.

[0107] Specifically, as shown in Figure 7 Figure 7 Fig. 7 is a cross-sectional schematic view of the sixth medical segmentation image according to one specific example of the present application. As can be seen from Figure 7 , by performing a logical AND operation on the second medical segmentation image (preferably the second medical segmentation image after the processing in steps S1201 and S1202 below) and the fifth medical segmentation image (i.e., multiplying the pixel value of each pixel point in the second medical segmentation image by the pixel value of the corresponding pixel point in the fifth medical segmentation image), the non-aortic valve region can be further removed.

[0108] S15: performing a morphological connected domain operation on the sixth medical segmentation image to retain the region with the largest connected domain volume to obtain a seventh medical segmentation image.

[0109] Preferably, in one exemplary embodiment, the specific steps of the morphological connected domain operation are as follows: scanning the sixth medical segmentation image, selecting a seed point from any of the sixth medical segmentation image, judging whether the pixel of the seed point and the adjacent pixels are the same, if yes, considering that they are in the same region, otherwise, determining that they are in different regions; taking the pixel points in different regions as a new seed point, repeatedly performing the above steps to obtain the connected domain where the new seed point is located, until all the pixel points of the sixth medical segmentation image are scanned; then calculating the volumes of all the connected domains and retaining the region with the largest connected domain volume. Figure 8 Figure 8 Fig. 8 is a cross-sectional schematic view of the seventh medical segmentation image according to one specific example of the present application. As can be seen from​​​Figure 8 As shown, performing a morphological connected domain operation on the sixth medical segmentation image, retaining the region with the largest connected domain volume, can further remove the non-aortic valve region and only retain the aortic valve region.

[0110] S16: retaining the connected result in the third medical segmentation image corresponding to the seventh medical segmentation image, to obtain the first medical segmentation image.

[0111] Specifically, referring to Figure 9 , Figure 9 is a cross-sectional schematic view of the first medical segmentation image in a specific example of the present application. From Figure 10 It can be seen that retaining the connected result in the third medical segmentation image corresponding to the seventh medical segmentation image can further remove the non-aortic valve region, thereby further improving the segmentation effect of the medical image segmentation method provided by the present application and laying a good foundation for obtaining high-quality aortic valve images.

[0112] Preferably, in one preferred embodiment, before step S12: performing edge detection on the to-be-segmented medical image to obtain a third medical segmentation image, it further includes:

[0113] S1201: performing truncation processing on the second medical segmentation image according to a preset truncation pixel threshold to obtain a truncated second medical segmentation image;

[0114] S1202: performing linear scaling on the pixel values of the truncated second medical segmentation image to scale the pixel values of the second medical segmentation image to the range of 0-255.

[0115] Thus, by performing truncation processing on the to-be-segmented medical image, the pixel values of each pixel point in the second medical segmentation image can be adjusted to a preset range, for example, the range of 0-800. In specific operation, the pixel value of a pixel point with a pixel value in the range of 0-800 can be kept unchanged, the pixel value of a pixel point with a pixel value less than 0 can be set to 0, and the pixel value of a pixel point with a pixel value greater than 800 can be set to 800. Finally, by performing linear scaling on the pixel values of the second medical segmentation image after truncation processing, the pixel values of each pixel point in the second medical segmentation image can be scaled to the range of 0-255. Specifically, linear scaling of the pixel values can be performed using the following formula:

[0116] P′ i = (P i / 800) * 255

[0117] In the formula, P′ i is the pixel value of pixel point i in the second medical segmentation image after truncation processing, Pi a pixel value of the pixel point i in the second medical segmentation image after linear scaling.

[0118] Preferably, in one of the exemplary embodiments, in step S2, the first medical segmentation image is optimized according to a preset optimization target to obtain an image of the target organ tissue, including:

[0119] S21: performing hole filling on the first medical segmentation image to obtain a first medical segmentation image after hole filling;

[0120] S22: performing a morphological opening operation on the first medical segmentation image after hole filling according to preset morphological opening operation information to obtain a first medical segmentation image after morphological opening operation;

[0121] S23: performing a connected domain operation on the first medical segmentation image after morphological opening operation to obtain the image of the target organ tissue.

[0122] Since there are some abnormal areas inside the blood vessels, some hole areas will appear, and thus the hole filling algorithm can fill these holes not connected to the boundary. By performing a morphological opening operation on the first medical segmentation image after hole filling, some boundary interference objects can be effectively removed. The specific parameters of the morphological opening operation can be set according to specific conditions, for example, set to 1. See Figure 10 , Figure 10 is the image of the target organ tissue in the specific example of the present application. From Figure 10 It can be seen that by performing a connected domain analysis, such as a maximum connected domain method, on the first medical segmentation image after morphological opening operation, small target region interference regions (non-aortic valve regions) can be effectively removed, for example, the bone region close to the common iliac artery blood vessels is removed, so that a more pure and accurate aortic valve image is obtained.

[0123] In summary, the medical image segmentation method provided by the present application not only reduces the number of interactions and improves the overall segmentation efficiency, but also improves the segmentation accuracy of medical images, so as to better assist doctors to improve the diagnosis efficiency and accuracy, and well balance the segmentation efficiency and segmentation accuracy. Further, the medical image segmentation method provided by the present application can be applied to different target tissues and organs and CTA images of different manufacturers' devices, and has strong universality.

[0124] Embodiment Two

[0125] The present embodiment provides a medical image segmentation method for obtaining an image of a medical region of interest on the target organ tissue, including:

[0126] S3: selecting a plurality of seed points in the medical region of interest of the medical image to be segmented according to a preset pixel threshold of the medical region of interest; and extracting the image of the medical region of interest according to the seed points by using an adaptive region growing method.

[0127] For the convenience of understanding, the following will take the diseased tissue on the target organ tissue as an example to illustrate the medical region of interest, which is obviously not a limitation of the present application. As understood by those skilled in the art, whether in the field of clinical medicine or in the field of medical research, the diseased tissue is typically an example of the medical region of interest in most cases.

[0128] Preferably, as can be understood by those skilled in the art, the seed points should be selected according to the specific characteristics of the diseased tissue. For example, calcification, aortic dissection, aneurysm, etc. When the diseased tissue to be segmented is aortic valve calcification, in order to achieve better segmentation results and improve segmentation efficiency, appropriate seed points (at least two) and positions should be selected in the aortic valve calcification region according to the characteristics of the aortic valve calcification, rather than randomly selected. Further, the present application does not limit the specific method of selecting the seed points. The seed points can be manually selected according to the visual display of the medical image to be segmented on a display device (including but not limited to a display, a projection screen, etc.), or automatically selected by a machine according to a preset pixel threshold of the diseased tissue, or dynamically obtained according to a preset selection algorithm, which is not limited by the present application. As mentioned earlier, the preset pixel threshold can be determined according to the calibration value of the diseased tissue in the medical image to be segmented, which will not be described here. Thus, by selecting a plurality of seed points at one time, the present application extracts the image of the diseased tissue region, which not only reduces the number of interactions, but also improves the overall segmentation efficiency.

[0129] Since the image of the target organ tissue and the image of the diseased tissue on the target organ tissue are both based on the medical image to be segmented, different segmentation methods are used according to the characteristics of the target organ tissue and the characteristics of the diseased tissue. Therefore, in specific implementation, the image of the diseased tissue on the target organ tissue can be obtained first, and then the image of the target organ tissue can be obtained; or the image of the target organ tissue can be obtained first, and then the image of the diseased tissue on the target organ tissue can be obtained; or if the computing resources are sufficient, the image of the target organ tissue and the image of the diseased tissue can be obtained in parallel. In order to further improve the segmentation efficiency of the medical image.

[0130] Preferably, in one exemplary embodiment, it further includes merging the image of the diseased tissue and the image of the target organ tissue to obtain a target medical image.

[0131] Referring to Figure 11 , Figure 11 For the images of the target organ tissue and the lesion tissue in the specific example of the present application, the contrast Figure 11 and Figure 10 It is not difficult to find that the valve calcification region (medical interest region, lesion tissue) in Figure 10 is more fine compared with Figure 11 The medical image segmentation method provided by the present application can significantly improve the segmentation efficiency and accuracy of medical images by obtaining the image of the target organ tissue and the image of the lesion tissue respectively, and then combining the image of the target organ tissue and the image of the lesion tissue, thereby better assisting doctors to improve the diagnostic accuracy.

[0132] As can be seen, the medical image segmentation method provided by the present embodiment can segment the CTA aortic valve and calcification through at least two points, which not only improves the overall segmentation algorithm accuracy, but also reduces the tedious interactive operation. Further, the medical image segmentation algorithm provided by the present application is highly versatile and suitable for CTA aortic valve images of different manufacturers' devices, which can better assist doctors to improve the diagnostic accuracy. Further, those skilled in the art can understand that, although the present application takes the valve calcification as an example to illustrate the way of segmenting the lesion tissue, it is also applicable to other disease tissues such as aortic dissection and aneurysm, and will not be repeated here.

[0133] Preferably, in one preferred embodiment, the image of the medical interest region is extracted by using an adaptive region growing method according to the seed points, comprising:

[0134] S31: Each of the seed points is taken as a starting point of growth, and the pixel points adjacent to the seed points are compared with the seed points, and the adjacent pixel points meeting the preset segmentation condition are merged into the region where the seed point is located, until all the pixel points meeting the preset segmentation condition are merged in, to obtain a plurality of region growing results.

[0135] S32: The region growing results are added to obtain the image of the medical interest region.

[0136] Specifically, region growing refers to the process of developing groups of pixels or regions into larger regions, that is, starting from a set of seed points, the region growing from these points is achieved by merging adjacent pixels with similar attributes such as intensity, gray level, texture color, etc. to this region.

[0137] Preferably, in one preferred embodiment, the preset segmentation condition comprises that the value of the adjacent pixel points is between a third upper limit threshold and a third lower limit threshold.

[0138] Before the image of the diseased tissue is extracted by using the adaptive region growing method, the method further comprises: determining the third upper limit threshold and the third lower limit threshold according to the pixel values of the plurality of seed points.

[0139] Specifically, in one exemplary embodiment, the second upper limit threshold and the second lower limit threshold can be determined by the following method:

[0140] statistically analyzing the pixel values of the plurality of seed points to determine a maximum pixel value and a minimum pixel value;

[0141] determining the third upper limit threshold and the third lower limit threshold according to the maximum pixel value and the minimum pixel value;

[0142] wherein the calculation formulae of the third upper limit threshold and the third lower limit threshold are as follows:

[0143] T max = P max *(1+β)

[0144] T min = P min *(1-β)

[0145] wherein T max is the third upper limit threshold, P max is the maximum pixel value, T min2 is the third lower limit threshold, P min2 is the minimum pixel value, and β is an adjustment factor, and the value of β is 0-1.

[0146] Therefore, by calculating the third upper limit threshold and the third lower limit threshold according to the pixel values of the plurality of seed points, and then respectively merging the region between each two adjacent seed points of the medical image to be segmented by using the region growing method according to the third upper limit threshold and the third lower limit threshold (i.e. merging the pixel points with pixel values between the third upper limit threshold and the third lower limit threshold together), the region growing method can be used to more simply and efficiently merge the region between each two adjacent seed points of the medical image to be segmented.

[0147] Further, as can be understood by those skilled in the art, the value of β can be set according to specific circumstances. For example, when the medical image to be segmented is a CTA image, the value of β is 0.2. In addition, it should be noted that in the calculation formula of the third upper threshold and the third lower threshold, the pixel value of the seed point refers to the pixel value of the seed point in the medical image to be segmented. For example, when the medical image to be segmented is a CTA image, the pixel value of the seed point refers to the CT value, i.e. the HU value, of the seed point in the CTA image.

[0148] Based on the same inventive concept, a further embodiment of the present application provides a medical image segmentation system, comprising an image segmentation unit and an image optimization unit.

[0149] Specifically, the image segmentation unit is configured to preliminarily segment the medical image to be segmented according to a preset pixel threshold, and perform edge detection and feature enhancement on the preliminarily segmented medical image to obtain a first medical segmentation image. The image optimization unit is configured to optimize the first medical segmentation image according to a preset optimization target to obtain an image of a target organ tissue.

[0150] Since the medical image segmentation system provided by the present application and the medical image segmentation method provided by the present application belong to the same inventive concept, they at least have the same beneficial effects, which will not be repeated here.

[0151] Based on the same inventive concept, a further embodiment of the present application also provides a medical image acquisition system, as shown in Figure 12 , the medical image acquisition system comprises a medical image acquisition device 100 and a medical image segmentation device 200.

[0152] Specifically, the medical image acquisition device 100 is configured to acquire a medical image to be segmented. The medical image acquisition device 100 is configured to acquire a medical image to be optimized. The medical image acquisition device 100 includes but is not limited to an imaging device such as CT, MRI, an electronic device connected to the Internet and capable of acquiring a medical image to be optimized from the Internet, or a scanning device capable of acquiring the medical image to be optimized. The medical image segmentation device is configured to segment the medical image to be segmented.

[0153] The medical image segmentation device 200 comprises an image segmentation unit 210 and an image optimization unit 220. The image segmentation unit 210 is configured to preliminarily segment the to-be-segmented medical image according to a preset pixel threshold, and perform edge detection and feature enhancement on the preliminarily segmented medical image to obtain a first medical segmentation image. The image optimization unit 220 is configured to optimize the first medical segmentation image according to a preset optimization target to obtain an image of a target organ tissue.

[0154] Since the medical image acquisition system provided by the present application and the medical image segmentation method provided by the present application belong to the same inventive concept, they at least have the same beneficial effects, which will not be repeated here.

[0155] In addition, the terms "first", "second", "third", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the technical features indicated. Therefore, the features defined as "first", "second", etc. can explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "a plurality of" is at least two, for example, two, three, etc., unless otherwise specifically limited.

[0156] It should be noted that the systems and methods disclosed in the embodiments herein can also be implemented in other ways. The above-described device embodiments are only illustrative, for example, the flowcharts and block diagrams in the drawings show the possible implementation architecture, function and operation of the devices, methods and computer program products according to the embodiments herein. In this regard, each block in the flowchart or block diagram can represent a module, program segment or part of code containing one or more executable instructions for implementing the specified logic function, and each block in the flowchart or block diagram can represent a module, program segment or part of code containing one or more executable instructions for implementing the specified logic function. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur in different orders from those shown in the drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and sometimes they can be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0157] In addition, the functional modules in each of the embodiments herein can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0158] Based on the same inventive concept, another embodiment of the present application further provides an electronic device, which comprises a processor and a memory, and the memory stores a computer program, and the computer program is executed by the processor to implement the medical image segmentation method according to any one of the above embodiments.

[0159] Still another embodiment of the present application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the medical image segmentation method described above.

[0160] The readable storage medium of the embodiments of the present application can adopt any combination of one or more computer readable media. The readable medium can be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, device or apparatus, or any combination thereof. More specific examples (non-exhaustive list) of the computer readable storage medium include an electrical connection having one or more wires, a portable computer hard disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this paper, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or apparatus.

[0161] The computer readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, in which a computer readable program code is carried. Such a propagated data signal can take various forms, including but not limited to an electromagnetic signal, an optical signal or any suitable combination thereof. The computer readable signal medium can also be any computer readable medium other than the computer readable storage medium, which can send, propagate or transmit a program for use by or in combination with an instruction execution system, device or apparatus.

[0162] Note that computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0163] Therefore, the medical image segmentation method, system, electronic device and storage medium provided by the present application not only reduce the number of interactions and improve the overall segmentation efficiency, but also improve the segmentation accuracy of the medical image, thereby better assisting doctors to improve the diagnosis efficiency and accuracy, and well balancing the segmentation efficiency and segmentation accuracy. Further, the medical image segmentation method provided by the present application can be applied to different target tissues and organs and CTA images of different manufacturers, and has strong versatility.

[0164] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, the person skilled in the art can combine and combine the different embodiments or examples described in the present specification and the features of the different embodiments or examples without contradiction.

[0165] In summary, the above embodiments describe the different configurations of the medical image segmentation method, system, electronic device and storage medium provided by the present application in detail. Of course, the above description is only a description of the preferred embodiments of the present application, and does not limit the scope of the present application in any way. The present application includes but is not limited to the configurations listed in the above embodiments. The person skilled in the art can easily deduce other configurations from the above embodiments. Any modification or modification of the present application made by the person skilled in the art according to the above disclosure is within the scope of protection of the claims.

Claims

1. A medical image segmentation method characterized by, The method comprises the following steps: performing preliminary segmentation on the to-be-segmented medical image according to a preset pixel threshold value, performing edge detection and feature enhancement on the medical image obtained through the preliminary segmentation, and extracting a first medical segmentation image; optimizing the first medical segmentation image according to a preset optimization target to obtain an image of a target organ tissue; wherein the first medical segmentation image is extracted through a first mode and the image of the target organ tissue is obtained through a second mode: the first mode is: segmenting the to-be-segmented medical image according to a preset first upper limit threshold value and a preset first lower limit threshold value to obtain a second medical segmentation image; performing edge detection on the to-be-segmented medical image to obtain a third medical segmentation image; enhancing the edge of the to-be-segmented medical image by using a Hessian matrix eigenvalue enhancement operator to obtain a fourth medical segmentation image after edge enhancement; performing a logistic regression transformation on strong edge pixel points and weak edge pixel points in the fourth medical segmentation image after edge enhancement to obtain a fifth medical segmentation image; performing a logical AND operation on the second medical segmentation image and the fifth medical segmentation image to obtain a sixth medical segmentation image; performing a morphological connected domain operation on the sixth medical segmentation image to retain a region with the largest connected domain volume to obtain a seventh medical segmentation image; retaining a connected domain result corresponding to the seventh medical segmentation image in the third medical segmentation image to obtain the first medical segmentation image; the second mode is: performing hole filling on the first medical segmentation image to obtain a first medical segmentation image after hole filling; performing a morphological opening operation on the first medical segmentation image after hole filling according to preset morphological opening operation information to obtain a first medical segmentation image after morphological opening operation; performing a connected domain operation on the first medical segmentation image after morphological opening operation to obtain the image of the target organ tissue.

2. The medical image segmentation method according to claim 1, characterized in that, Before the step of performing edge detection on the to-be-segmented medical image to obtain a third medical segmentation image, the method further comprises: performing truncation processing on the second medical segmentation image according to a preset truncation pixel threshold value to obtain a second medical segmentation image after truncation; performing linear scaling on pixel values of the second medical segmentation image after truncation to scale the pixel values of the second medical segmentation image to a range of 0-255.

3. The medical image segmentation method according to claim 1, characterized in that, The step of performing edge detection on the to-be-segmented medical image to obtain a third medical segmentation image comprises: detecting and connecting the edge of the to-be-segmented medical image by using a Canny operator according to a preset second upper limit threshold value and a second lower limit threshold value; segmenting to obtain a third medical segmentation image according to the edge of the to-be-segmented medical image.

4. The medical image segmentation method of claim 1, characterized in that, The method further comprises obtaining an image of a medical region of interest on the target organ tissue by the following method: selecting a plurality of seed points in the medical region of interest of the to-be-segmented medical image according to a preset pixel threshold value of the medical region of interest, and extracting an image of the medical region of interest by using an adaptive region growing method according to the seed points.

5. The medical image segmentation method according to claim 4, characterized in that, The step of extracting an image of a medical region of interest by using an adaptive region growing method according to the seed points comprises: respectively, each of the seed points as a starting point of growth, and comparing the seed points and the adjacent pixel points adjacent to the seed points, merging the adjacent pixel points meeting a preset segmentation condition to a region where the seed points are located, until all the pixel points meeting the preset segmentation condition are merged to the region where the seed points are located, to obtain a plurality of region growth results; adding the region growth results to obtain the medical region of interest image.

6. The medical image segmentation method according to claim 5, characterized in that, The preset segmentation condition includes that a value of the adjacent pixel point is between a third upper limit threshold and a third lower limit threshold; Before the medical region of interest image is extracted by using the adaptive region growing method, the method further includes: determining the third upper limit threshold and the third lower limit threshold according to pixel values of the plurality of seed points.

7. The medical image segmentation method according to claim 6, characterized in that, The third upper limit threshold and the third lower limit threshold are determined according to the pixel values of the plurality of seed points, and include: statistically processing the pixel values of the plurality of seed points to determine a maximum pixel value and a minimum pixel value; determining the third upper limit threshold and the third lower limit threshold according to the maximum pixel value and the minimum pixel value; The calculation formulas of the third upper limit threshold and the third lower limit threshold are as follows: ； ； In the formula, is a third upper threshold value, is a maximum pixel value, is a third lower threshold value, is a minimum pixel value, is an adjustment factor, is a value between 0 and 1.

8. A medical image segmentation system, characterized by, including: The image segmentation unit is configured to preliminarily segment the to-be-segmented medical image according to a preset pixel threshold, and perform edge detection and feature enhancement on the preliminarily segmented medical image to extract a first medical segmentation image; The image optimization unit is configured to optimize the first medical segmentation image according to a preset optimization target to obtain an image of a target organ tissue; The first medical segmentation image is extracted by using a first mode, and the image of the target organ tissue is obtained by using a second mode. The first mode is: segmenting the to-be-segmented medical image according to a preset first upper limit threshold and a preset first lower limit threshold to obtain a second medical segmentation image; performing edge detection on the to-be-segmented medical image to obtain a third medical segmentation image; enhancing edges of the to-be-segmented medical image by using a Hessian matrix eigenvalue enhancement operator to obtain a fourth medical segmentation image after edge enhancement; performing a logistic regression transformation on strong edge pixel points and weak edge pixel points in the fourth medical segmentation image after edge enhancement to obtain a fifth medical segmentation image; performing a logical AND operation on the second medical segmentation image and the fifth medical segmentation image to obtain a sixth medical segmentation image; performing a morphological connected domain operation on the sixth medical segmentation image to retain a region with a maximum connected domain volume to obtain a seventh medical segmentation image; and retaining a connected domain result corresponding to the seventh medical segmentation image in the third medical segmentation image to obtain the first medical segmentation image. The second mode is: performing hole filling on the first medical segmentation image to obtain a first medical segmentation image after hole filling; performing a morphological opening operation on the first medical segmentation image after hole filling according to preset morphological opening operation information to obtain a first medical segmentation image after morphological opening operation; and performing a connected domain operation on the first medical segmentation image after morphological opening operation to obtain the image of the target organ tissue.

9. A medical image acquisition system, characterized by The method comprises: a medical image acquisition device configured to acquire a medical image to be segmented; a medical image segmentation device configured to segment the medical image to be segmented; The medical image segmentation device comprises an image segmentation unit and an image optimization unit. The image segmentation unit is configured to preliminarily segment the medical image to be segmented according to a preset pixel threshold, and perform edge detection and feature enhancement on the preliminarily segmented medical image to obtain a first medical segmentation image. The image optimization unit is configured to optimize the first medical segmentation image according to a preset optimization target to obtain an image of a target organ tissue. The first medical segmentation image is obtained by the following mode one, and the image of the target organ tissue is obtained by the following mode two: The first mode is: segmenting the medical image to be segmented according to a preset first upper threshold and a preset first lower threshold to obtain a second medical segmentation image; performing edge detection on the medical image to be segmented to obtain a third medical segmentation image; enhancing the edges of the medical image to be segmented by using a Hessian matrix eigenvalue enhancement operator to obtain a fourth medical segmentation image after edge enhancement; performing a logistic regression transformation on strong edge pixel points and weak edge pixel points in the fourth medical segmentation image after edge enhancement to obtain a fifth medical segmentation image; performing a logical AND operation on the second medical segmentation image and the fifth medical segmentation image to obtain a sixth medical segmentation image; performing a morphological connected domain operation on the sixth medical segmentation image to retain a region with the largest connected domain volume to obtain a seventh medical segmentation image; and retaining a connected domain result corresponding to the seventh medical segmentation image in the third medical segmentation image to obtain the first medical segmentation image. The second mode is: performing hole filling on the first medical segmentation image to obtain a first medical segmentation image after hole filling; performing a morphological opening operation on the first medical segmentation image after hole filling according to preset morphological opening operation information to obtain a first medical segmentation image after morphological opening operation; and performing a connected domain operation on the first medical segmentation image after morphological opening operation to obtain the image of the target organ tissue.

10. An electronic device, comprising: The computer program is stored in the readable storage medium and is executed by the processor to implement the medical image segmentation method in any one of claims 1 to 7.

11. A readable storage medium, characterized by, The computer program is stored in the readable storage medium and is executed by the processor to implement the medical image segmentation method in any one of claims 1 to 7.

Images