A medical image segmentation method, device, equipment and storage medium

Abstract

The present invention discloses a medical image segmentation method, device, equipment and storage medium, the method comprising: obtaining an image of interest in an initial segmented image corresponding to a medical image to be processed, and determining a first center point parameter corresponding to a center point in the image of interest; determining a scaled image corresponding to the image of interest based on a preset scaling parameter; determining image distances between each image point and the center point based on the first center point parameter and image point parameters corresponding to at least one image point in the scaled image; determining an updated image of interest based on at least one image distance, and determining a target segmented image corresponding to the medical image to be processed based on the updated image of interest. The present invention solves the problem of poor accuracy of segmented images obtained by existing image segmentation algorithms, improves the post-processing algorithm of segmented images, and improves the segmentation accuracy of the corrected segmented images.

Description

Technical Field

[0001] The present invention relates to the field of image segmentation technology, and in particular to a medical image segmentation method, device, equipment and storage medium. Background Art

[0002] Image segmentation is a technique and process to divide an image into several specific regions with unique properties and propose targets of interest. It is a key step from image processing to image segmentation. Especially in the medical industry, extracting precise regions of interest (such as lesions) from inspection images plays a vital role in doctors' diagnosis results and even treatment results.

[0003] There are many image segmentation algorithms currently available, such as threshold-based segmentation algorithms, region-based segmentation algorithms, and neural network segmentation models. In real application scenarios, most of the above image segmentation results are directly put into use, or some conventional post-processing operations are performed on the above image segmentation results.

[0004] However, any image segmentation algorithm has certain segmentation errors. Conventional post-processing operations cannot effectively improve the accuracy of image segmentation results, especially cannot meet the requirements of the medical industry for image segmentation accuracy, and have poor practicality. Summary of the invention

[0005] The present invention provides a medical image segmentation method, device, equipment and storage medium to solve the problem of poor accuracy of existing image segmentation results.

[0006] According to one aspect of the present invention, a medical image segmentation method is provided, comprising:

[0007] Acquire an image of interest in an initial segmented image corresponding to the medical image to be processed, and determine a first center point parameter corresponding to the center point in the image of interest;

[0008] Based on preset scaling parameters, determining a scaled image corresponding to the image of interest;

[0009] Determine the image distance between each of the image points and the center point based on the first center point parameter and the image point parameter corresponding to at least one image point in the zoomed image;

[0010] Based on at least one image distance, an updated image of interest is determined, and based on the updated image of interest, a target segmented image corresponding to the medical image to be processed is determined.

[0011] According to another aspect of the present invention, there is provided a medical image segmentation device, comprising:

[0012] A first center point parameter determination module, used to obtain an image of interest in an initial segmented image corresponding to the medical image to be processed, and determine a first center point parameter corresponding to the center point in the image of interest;

[0013] A zoom image determination module, used to determine the zoom image corresponding to the image of interest based on preset zoom parameters;

[0014] An image distance determination module, configured to determine the image distance between each of the image points and the center point based on the first center point parameter and image point parameters respectively corresponding to at least one image point in the zoomed image;

[0015] The target segmentation image determination module is used to determine an updated image of interest based on at least one image distance, and determine a target segmentation image corresponding to the medical image to be processed based on the updated image of interest.

[0016] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0017] at least one processor; and

[0018] a memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the medical image segmentation method described in any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to implement the medical image segmentation method described in any embodiment of the present invention when executed by a processor.

[0021] The technical solution of the embodiment of the present invention obtains the first center point parameter corresponding to the center point in the image of interest in the initial segmented image and the scaled image corresponding to the image of interest, determines the image distance between each of the image points and the center point based on the first center point parameter and the image point parameter corresponding to at least one image point in the scaled image, determines an updated image of interest based on at least one image distance, and determines a target segmented image corresponding to the medical image to be processed based on the updated image of interest, thereby solving the problem of poor accuracy of the segmented image obtained by the existing image segmentation algorithm, improving the post-processing algorithm of the segmented image, improving the segmentation accuracy of the corrected segmented image and the practicality of the segmented image, and providing an effective and accurate reference value for subsequent diagnosis and treatment.

[0022] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 A flowchart of a medical image segmentation method is provided for the first embodiment of the present invention;

[0025] Figure 2 A flowchart of a medical image segmentation method provided in Embodiment 2 of the present invention;

[0026] Figure 3 is a flowchart of a specific example of a medical image segmentation method provided in Embodiment 2 of the present invention;

[0027] Figure 4 A schematic diagram of the structure of a medical image segmentation device provided in Embodiment 3 of the present invention;

[0028] Figure 5 It is a structural schematic diagram of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first", "second", "initial", "target", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] Embodiment 1

[0032] Figure 1 A flowchart of a medical image segmentation method is provided for the first embodiment of the present invention. This embodiment is applicable to the case of segmenting medical images. The method can be performed by a medical image segmentation device. The medical image segmentation device can be implemented in the form of hardware and / or software. The medical image segmentation device can be configured in a smart terminal such as a laptop computer, a mobile terminal, a desktop computer, and a tablet computer. Figure 1 As shown, the method includes:

[0033] S110, obtaining an image of interest in an initial segmented image corresponding to the medical image to be processed, and determining a first center point parameter corresponding to the center point in the image of interest.

[0034] Specifically, the medical image to be processed may be a three-dimensional image or a two-dimensional image. Exemplarily, the image type of the medical image to be processed may be a CT (Computed Tomography) image, a DR (digital radiography) image, an MRI (Magnetic Resonance Imaging) image, an ultrasound image or a PET (positron emission tomography) image, etc., and the image type of the medical image to be processed is not limited here.

[0035] The embodiment of the present invention is explained by taking the type of medical image as MRI image as an example. MRI imaging is an imaging method that uses the magnetic resonance phenomenon to obtain electromagnetic signals from the human body and reconstruct human body information. Specifically, when the detection object is a brain area, before obtaining the image of interest in the initial segmented image corresponding to the medical image to be processed, the method also includes: performing a preprocessing operation on the medical image to be processed to obtain a corrected medical image to be processed. Exemplarily, the preprocessing operation includes at least one of an image registration operation, a skull removal operation, and a denoising operation.

[0036] In one embodiment, the initial segmented image can be a segmented image obtained by segmenting the medical image to be processed using a preset segmentation algorithm. Exemplarily, the preset segmentation algorithm includes but is not limited to a threshold-based segmentation algorithm, a region-based segmentation algorithm, an edge-based segmentation algorithm, a morphological watershed algorithm, and a neural network segmentation model, etc. The preset segmentation algorithm is not limited here.

[0037] Specifically, the image of interest is an image obtained by segmenting the initial segmented image based on a preset segmentation algorithm. For example, in the field of medical images, the initial segmented image includes a background image and a lesion image, wherein the lesion image is the image of interest in this embodiment.

[0038] In one embodiment, optionally, the method further includes: obtaining boundary points corresponding to the image of interest, and determining the center point in the image of interest based on the boundary point coordinates of the boundary points. Exemplarily, assuming that the medical image to be processed is a three-dimensional image, the boundary point coordinates include (x1, y1, z1), (x2, y2, z2)…(x n ,y n ,z n ), then the coordinates (X, Y, Z) of the center point satisfy the formula:

[0039]

[0040] In another embodiment, optionally, the method further includes: taking each image point in the image of interest as the image point to be tested in turn; determining the sum of image distances between the image point to be tested and other image points based on the image point coordinates of each image point in the image of interest, and taking the image point to be tested with the smallest sum of image distances as the center point. Exemplarily, the type of image distance may be Euclidean distance, Manhattan distance, Chebyshev distance, Mahalanobis distance, Minkowski distance, etc., and the type of image distance is not limited here.

[0041] In one embodiment, optionally, the first center point parameters include first center point coordinates and first center point grayscale values.

[0042] S120: Determine a zoomed image corresponding to the image of interest based on preset zoom parameters.

[0043] In one embodiment, optionally, the preset zoom parameters include the number of zoom circles and the zoom direction. Specifically, the zoom direction includes a reduction direction and an expansion direction. The zoom direction can be used to describe the relationship between the zoomed image and the image of interest. Exemplarily, when the zoom direction is a reduction direction, the zoomed image belongs to a part of the edge image in the image of interest, and when the zoom direction is an expansion direction, the zoomed image belongs to a part of the edge image outside the image of interest.

[0044] In one embodiment, the number of zoom circles and the zoom direction can be personalized according to actual needs. For example, the number of zoom circles is 5 circles and the zoom direction is expansion. The specific parameter values ​​of the number of zoom circles and the zoom parameters are not limited here.

[0045] In another embodiment, optionally, the method further includes: obtaining the image size of the medical image to be processed, and determining the number of zooming circles corresponding to the medical image to be processed based on a preset mapping relationship; wherein the preset mapping relationship is used to describe the mapping relationship between the number of zooming circles and the image size. Specifically, in the preset mapping relationship, there may be a positive correlation between the number of zooming circles and the image size, that is, when the image size is larger, the number of zooming circles is larger, and when the image size is smaller, the number of zooming circles is smaller.

[0046] Specifically, the relationship type of the preset mapping relationship may be a linear relationship, an exponential relationship, a sinusoidal relationship, a discrete relationship, etc., and the specific relationship type is not limited here.

[0047] In one embodiment, the preset mapping relationship can be used to describe the mapping relationship between the number of zooming circles and the overall image size of the medical image to be processed. Exemplarily, in the preset mapping relationship, the number of zooming circles corresponding to the overall image size of 512*512*200 is 10, and the number of zooming circles corresponding to the overall image size of 128*128*100 is 5. In this embodiment, the number of zooming circles of the zoomed image in each coordinate axis dimension is the same.

[0048] In another embodiment, a preset mapping relationship can be used to describe the mapping relationship between the number of zooming circles and the image size corresponding to a single coordinate axis dimension of the medical image to be processed. Exemplarily, in the preset mapping relationship, the number of zooming circles corresponding to the image size corresponding to the single coordinate axis dimension of [400,512] is 10, the number of zooming circles corresponding to the image size corresponding to the single coordinate axis dimension of [128,200] is 5, and the number of zooming circles corresponding to the image size corresponding to the single coordinate axis dimension of [50,100] is 2. Assuming that the overall image size of the medical image to be processed is 425*137*80, the number of zooming circles on the X-axis, Y-axis and Z-axis are 10, 5 and 2 respectively. In this embodiment, the number of zooming circles of the zoomed image on each coordinate axis dimension may be different.

[0049] In the field of medical technology, the acquired medical images to be processed usually have a small image dimension in the z-axis direction. If the image is scaled based on the same number of zooms in the three coordinate axes, it is easy to cause program errors (for example, if the image size is 1028*1028*20 and the number of zooms is 30, the Z-axis zoom operation will fail) and the image segmentation effect will be reduced. Setting the number of zooms based on the image size of a single coordinate axis can avoid program errors and improve the image segmentation effect.

[0050] S130 , determining image distances between each image point and the center point based on the first center point parameter and image point parameters corresponding to at least one image point in the zoomed image.

[0051] In one embodiment, optionally, the image point parameters include the image point coordinates and the image point grayscale value. Exemplarily, the first center point parameters are (x0, y0, z0, g0), and the image point parameters are (x i ,y i ,z i ,g i ), where i represents the i-th image point in the scaled image.

[0052] Exemplarily, the type of image distance may be Euclidean distance, Manhattan distance, Chebyshev distance, Mahalanobis distance, Minkowski distance, etc., and the type of image distance is not limited here.

[0053] S140. Determine an updated image of interest based on at least one image distance, and determine a target segmented image corresponding to the medical image to be processed based on the updated image of interest.

[0054] In one embodiment, optionally, based on at least one image distance, determining an updated image of interest includes: taking an image point in the scaled image corresponding to an image distance within a preset distance range as a target image point, or, based on at least one image distance, sorting the image points in the scaled image, and determining the target image point in the scaled image according to the sorting result and a preset selection number; and determining an updated image of interest based on the target image point.

[0055] In one embodiment, exemplarily, the preset distance range may be less than a preset distance threshold. In another embodiment, optionally, the method further includes: determining a preset number of selections based on the image size of the scaled image. Among them, exemplarily, the product of the number of image points in the scaled image and the image point size may be used as the image size of the scaled image. Of course, the number of image points in the scaled image may also be used as the image size of the scaled image. The method for calculating the image size of the scaled image is not limited here. Specifically, there is a positive correlation between the image size of the scaled image and the preset number of selections, that is, when the image size is larger, the preset number of selections is larger, and conversely, when the image size is smaller, the preset number of selections is smaller. The specific correlation between the image size and the preset number of selections is not limited here, and the user can set it according to actual needs.

[0056] Specifically, based on the target image point, an updated image of interest is determined, including: when the zoom direction is an expansion direction, the target image point in the zoomed image is divided into the image of interest to obtain an updated image of interest; when the zoom direction is a reduction direction, the image points other than the target image point in the zoomed image (which is a part of the image of interest) are divided into the background image in the initial segmented image to obtain an updated image of interest.

[0057] In this embodiment, the updated initial segmented image corresponding to the image of interest is the target segmented image corresponding to the medical image to be processed.

[0058] The technical solution of this embodiment obtains the first center point parameter corresponding to the center point in the image of interest in the initial segmented image and the scaled image corresponding to the image of interest, determines the image distance between each image point and the center point based on the first center point parameter and the image point parameter corresponding to at least one image point in the scaled image, determines an updated image of interest based on at least one image distance, and determines a target segmented image corresponding to the medical image to be processed based on the updated image of interest, thereby solving the problem of poor accuracy of the segmented image obtained by the existing image segmentation algorithm, improving the post-processing algorithm of the segmented image, improving the segmentation accuracy of the corrected segmented image and the practicality of the segmented image, and providing an effective and accurate reference value for subsequent diagnosis and treatment.

[0059] Embodiment 2

[0060] Figure 2 A flowchart of a medical image segmentation method provided in Embodiment 2 of the present invention, this embodiment further refines the step of "determining a target segmentation image corresponding to the medical image to be processed based on the updated image of interest" in the above embodiment, optionally, determining the target segmentation image corresponding to the medical image to be processed based on the updated image of interest, including: determining a second center point parameter corresponding to the center point in the updated image of interest; judging whether the second center point coordinates in the second center point parameter are the same as the previous center point coordinates in the previous center point parameter corresponding to the second center point parameter; if not, repeating the operation of determining the scaled image corresponding to the image of interest based on the preset scale parameter based on the second center point parameter; if yes, determining the target segmentation image corresponding to the medical image to be processed based on the updated image of interest corresponding to the second center point parameter.

[0061] The specific implementation steps of this embodiment include:

[0062] S210, obtaining an image of interest in an initial segmented image corresponding to the medical image to be processed, and determining a first center point parameter corresponding to a center point in the image of interest.

[0063] Based on the above embodiments, optionally, the method further includes: inputting the medical image to be processed into at least two target image segmentation models respectively; and determining an initial segmented image corresponding to the medical image to be processed based on the segmentation results output by each target image segmentation model and a voting mechanism.

[0064] Specifically, the target image segmentation model includes a neural network model trained based on sample medical images, and exemplary model types of the target image segmentation model include but are not limited to a fully convolutional network model (FCN), a semantic segmentation model (SegNet), and a dilated convolution model, etc. Specifically, different target image segmentation models have different model structures and / or different sample medical images for training.

[0065] Specifically, the voting mechanism includes a soft voting mechanism or a hard voting mechanism.

[0066] In one embodiment, if the target image segmentation model outputs a segmentation label result, i.e., 0 or 1, the corresponding voting mechanism is a hard voting mechanism. The hard voting mechanism selects the most classification labels output by different target image segmentation models as the final classification label.

[0067] In another embodiment, if the target image segmentation model outputs the probability of the segmentation label, that is, 0-1, the corresponding voting mechanism is a soft voting mechanism. The soft voting mechanism determines the final classification label based on the probability of the classification labels output by different target image segmentation models. Specifically, each target image segmentation model can be evaluated based on the test medical image, and the evaluation results can be used as the voting weights corresponding to each target image segmentation model; based on the segmentation results and the voting weights, the final segmentation label is determined.

[0068] Based on the above embodiments, optionally, the method further includes: acquiring a sample medical image, and performing a slicing operation on the sample medical image based on at least two slicing size standards to obtain a plurality of slicing medical images; and training at least two initial image segmentation models based on the plurality of slicing medical images to obtain a trained target image segmentation model.

[0069] Specifically, when the image type of the sample medical image is a three-dimensional image, the block size standard may be 4*4*4, 8*8*4, 16*16*1, etc. When the image type of the sample medical image is a two-dimensional image, the block size standard may be 4*4, 4*8, 32*6, etc.

[0070] Taking the sample medical image as a three-dimensional image as an example, the cut medical image is classified, and the classification result includes a three-dimensional data set of three-dimensional cut medical images and / or a two-dimensional data set of two-dimensional cut medical images. Among them, the z parameter in the cut size standard corresponding to the cut medical image in the three-dimensional data set is not 1, and the z parameter in the cut size standard corresponding to the cut medical image in the two-dimensional data set is 1. In this embodiment, the initial image segmentation model includes a three-dimensional initial image segmentation model and / or a two-dimensional initial image segmentation model.

[0071] Furthermore, the three-dimensional data set and / or the two-dimensional data set can be divided based on the block size standard to obtain at least one of a first three-dimensional sub-dataset corresponding to block medical images of the same size, a second three-dimensional sub-dataset corresponding to block medical images of different sizes, a first two-dimensional sub-dataset corresponding to block medical images of the same size, and a second two-dimensional sub-dataset corresponding to block medical images of different sizes. Exemplarily, the image size of the block medical images in the first three-dimensional sub-dataset can be 4*4*2; the image size of the block medical images in the second three-dimensional sub-dataset includes 4*4*2, 4*4*3, and 8*8*2; the image size of the block medical images in the first two-dimensional sub-dataset can be 4*4*1 or 4*4; the image size of the block medical images in the second two-dimensional sub-dataset includes 4*4*1, 4*2*1, and 8*8*1, or the image size of the block medical images in the second two-dimensional sub-dataset includes 4*4, 4*2, and 8*8. In this embodiment, the initial image segmentation model includes at least one of a first three-dimensional initial image segmentation model, a second three-dimensional initial image segmentation model, a first two-dimensional initial image segmentation model, and a second two-dimensional initial image segmentation model.

[0072] The advantage of this setting is that the sample size of sample images used for model training can be increased, thereby improving the training effect of the model.

[0073] S220: Determine a zoomed image corresponding to the image of interest based on preset zoom parameters.

[0074] Based on the above embodiments, optionally, the method also includes: inputting the verification image into at least two target image segmentation models respectively, and determining the predicted image of interest corresponding to the verification image based on the segmentation results and voting mechanism output by each target image segmentation model respectively; comparing the image size of the predicted image of interest with the image size of the verification image of interest corresponding to the verification image, and determining the number of zoom circles and / or zoom direction corresponding to the medical image to be processed based on the comparison result.

[0075] Specifically, if the image size of the predicted image of interest is smaller than the image size of the verified image of interest, the scaling direction is the expansion direction; if the image size of the predicted image of interest is larger than the image size of the verified image of interest, the scaling direction is the reduction direction.

[0076] Specifically, the number of zooming circles of the medical image to be processed is determined based on the size difference between the image size of the predicted image of interest and the image size of the verified image of interest. There is a positive correlation between the size difference and the number of zooming circles, that is, when the size difference is large, the number of zooming circles is large, and vice versa, when the size difference is small, the number of zooming circles is small. The specific mapping relationship between the size difference and the number of zooming circles is not limited here, and the user can set it according to actual needs.

[0077] S230 : Determine image distances between each image point and the center point based on the first center point parameter and image point parameters corresponding to at least one image point in the zoomed image.

[0078] S240: Determine an updated image of interest based on at least one image distance, and determine a second center point parameter corresponding to the center point in the updated image of interest.

[0079] S250, determine whether the coordinates of the second center point are the same as the coordinates of the previous center point, if yes, execute S260, if not, execute S220.

[0080] Specifically, when the number of iterations is 0, the previous center point parameter corresponding to the second center point parameter determined by S240 is the first center point parameter; when the number of iterations is n (n≥1), the previous center point parameter corresponding to the second center point parameter determined by S240 is the second center point parameter corresponding to the n-1th iteration.

[0081] S260 . Determine a target segmented image corresponding to the medical image to be processed based on the updated image of interest corresponding to the second center point parameter.

[0082] Figure 3 is a flowchart of a specific example of a medical image segmentation method provided in Embodiment 2 of the present invention. Figure 3 Take the medical image as a brain magnetic resonance image as an example. Specifically, a small number of labeled brain magnetic resonance images are obtained as sample medical images, and preprocessing operations are performed on the brain magnetic resonance images. Exemplarily, the preprocessing operations include registration operations, skull removal operations, and denoising operations. Based on at least two block size standards, the brain magnetic resonance images are cut into blocks to obtain multiple block medical images, and the block medical images are classified. Specifically, the 3D data set contains three-dimensional block magnetic resonance images, and the 2D data set contains two-dimensional block magnetic resonance images. Further, the 3D data set and the 2D data set are classified respectively to obtain 3D sub-datasets of the same size, 3D sub-datasets of different sizes obtained based on mixed sampling, 2D sub-datasets of the same size, and 2D sub-datasets of different sizes obtained based on mixed sampling. Based on each sub-dataset, the initial image segmentation model corresponding to it is trained to obtain multiple target image segmentation models.

[0083] The medical image to be processed is respectively input into a plurality of target image segmentation models, and based on the output results and the voting mechanism, the lesion image (i.e., the image of interest) in the initial segmentation model corresponding to the medical image to be processed is determined, and based on the preset scaling parameters, the scaled image corresponding to the lesion image is determined, and based on the image distance between the image point in the scaled image and the center point in the lesion image, the lesion image is expanded or reduced to obtain an updated lesion image, and based on the updated lesion image, the operation of expanding or reducing the lesion image is repeatedly performed, and when the center point coordinates of the updated lesion image are the same as the center point coordinates of the previous lesion image, a precisely segmented lesion image is obtained, that is, a target segmented image corresponding to the medical image to be processed is obtained.

[0084] The technical solution of this embodiment determines the second center point parameter corresponding to the center point in the updated image of interest, and determines whether the second center point coordinates in the second center point parameter are the same as the previous center point coordinates in the previous center point parameter corresponding to the second center point parameter. If different, based on the second center point parameter, repeatedly executes the operation of determining the scaled image corresponding to the image of interest based on the preset scaling parameter until the second center point coordinates are the same as the previous center coordinates, thereby obtaining the target segmented image. This solves the problem of low accuracy of the segmented image obtained by a single post-processing operation, and further improves the segmentation accuracy of the segmented image finally obtained and the practicality of the segmented image.

[0085] Embodiment 3

[0086] Figure 4 This is a schematic diagram of the structure of a medical image segmentation device provided in Embodiment 3 of the present invention. Figure 4 As shown, the device includes: a first center point parameter determination module 310, a zoom image determination module 320, an image distance determination module 330 and a target segmentation image determination module 340.

[0087] The first center point parameter determination module 310 is used to obtain an image of interest in the initial segmented image corresponding to the medical image to be processed, and determine a first center point parameter corresponding to the center point in the image of interest;

[0088] A zoom image determination module 320, configured to determine a zoom image corresponding to the image of interest based on preset zoom parameters;

[0089] An image distance determination module 330, configured to determine the image distance between each image point and the center point based on the first center point parameter and the image point parameter corresponding to at least one image point in the zoomed image;

[0090] The target segmented image determination module 340 is used to determine an updated image of interest based on at least one image distance, and determine a target segmented image corresponding to the medical image to be processed based on the updated image of interest.

[0091] The technical solution of this embodiment obtains the first center point parameter corresponding to the center point in the image of interest in the initial segmented image and the scaled image corresponding to the image of interest, determines the image distance between each image point and the center point based on the first center point parameter and the image point parameter corresponding to at least one image point in the scaled image, determines an updated image of interest based on at least one image distance, and determines a target segmented image corresponding to the medical image to be processed based on the updated image of interest, thereby solving the problem of poor accuracy of the segmented image obtained by the existing image segmentation algorithm, improving the post-processing algorithm of the segmented image, improving the segmentation accuracy of the corrected segmented image and the practicality of the segmented image, and providing an effective and accurate reference value for subsequent diagnosis and treatment.

[0092] On the basis of the above embodiment, optionally, the first center point parameter includes the first center point coordinates and the first center point grayscale value, and correspondingly, the image point parameter includes the image point coordinates and the image point grayscale value of the image point.

[0093] Based on the above embodiment, optionally, the target segmentation image determination module 340 includes:

[0094] A target segmented image determination unit, used to determine a second center point parameter corresponding to the center point in the updated image of interest;

[0095] Determine whether the second center point coordinates in the second center point parameter are the same as the previous center point coordinates in the previous center point parameter corresponding to the second center point parameter;

[0096] If not, then based on the second center point parameter, repeatedly performing the operation of determining the scaled image corresponding to the image of interest based on the preset scaling parameter;

[0097] If yes, then based on the updated image of interest corresponding to the second center point parameter, a target segmented image corresponding to the medical image to be processed is determined.

[0098] Based on the above embodiment, optionally, the target segmentation image determination module 340 includes:

[0099] an image of interest updating unit, configured to take an image point in the zoomed image corresponding to an image distance within a preset distance range as a target image point, or to sort the image points in the zoomed image based on at least one image distance, and determine the target image point in the zoomed image according to the sorting result and a preset selection number;

[0100] Based on the target image point, an updated image of interest is determined.

[0101] Based on the above embodiment, optionally, the device further includes:

[0102] An initial segmented image determination module, used for inputting the medical image to be processed into at least two target image segmentation models respectively;

[0103] Based on the segmentation results output by each target image segmentation model and the voting mechanism, an initial segmented image corresponding to the medical image to be processed is determined.

[0104] Based on the above embodiment, optionally, the device further includes:

[0105] A target image segmentation model training module is used to obtain a sample medical image and perform a slicing operation on the sample medical image based on at least two slicing size standards to obtain a plurality of slicing medical images;

[0106] Based on a plurality of cut-up medical images, at least two initial image segmentation models are trained respectively to obtain a trained target image segmentation model.

[0107] Based on the above embodiment, optionally, the preset zoom parameters include the number of zoom circles and the zoom direction, and the device further includes:

[0108] A preset scaling parameter determination module is used to input the verification image into at least two target image segmentation models respectively, and determine the predicted image of interest corresponding to the verification image based on the segmentation results respectively output by each target image segmentation model and a voting mechanism;

[0109] The image size of the predicted image of interest is compared with the image size of the verification image of interest corresponding to the verification image, and the number of zoom circles and / or the zoom direction corresponding to the medical image to be processed are determined according to the comparison result.

[0110] The medical image segmentation device provided in the embodiment of the present invention can execute the medical image segmentation method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0111] Embodiment 4

[0112] Figure 5 It is a structural schematic diagram of an electronic device provided in Embodiment 4 of the present invention. Figure 5The electronic device 10 in the figure is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0113] like Figure 5 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0114] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0115] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as a segmentation method for a medical image.

[0116] In some embodiments, the medical image segmentation method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the medical image segmentation method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the medical image segmentation method in any other appropriate manner (e.g., by means of firmware).

[0117] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0118] The computer program for implementing the medical image segmentation method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program can be executed completely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or completely on a remote machine or server.

[0119] Embodiment 5

[0120] Embodiment 5 of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to execute a medical image segmentation method, the method comprising:

[0121] Acquire an image of interest in an initial segmented image corresponding to the medical image to be processed, and determine a first center point parameter corresponding to the center point in the image of interest;

[0122] Based on the preset scaling parameters, determining a scaled image corresponding to the image of interest;

[0123] Determine the image distance between each image point and the center point based on the first center point parameter and the image point parameter corresponding to at least one image point in the zoomed image;

[0124] Based on at least one image distance, an updated image of interest is determined, and based on the updated image of interest, a target segmented image corresponding to the medical image to be processed is determined.

[0125] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer 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 of the foregoing.

[0126] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0127] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0128] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0129] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0130] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A medical image segmentation method, characterized in that: include: Acquire an image of interest in an initial segmented image corresponding to the medical image to be processed, and determine a first center point parameter corresponding to the center point in the image of interest; Based on preset scaling parameters, determining a scaled image corresponding to the image of interest; Determine the image distance between each of the image points and the center point based on the first center point parameter and the image point parameter corresponding to at least one image point in the zoomed image; Determining an updated image of interest based on at least one image distance, and determining a target segmented image corresponding to the medical image to be processed based on the updated image of interest; Wherein, determining the target segmented image corresponding to the medical image to be processed based on the updated image of interest includes: Determine a second center point parameter corresponding to the center point in the updated image of interest; Determine whether the second center point coordinates in the second center point parameter are the same as the previous center point coordinates in the previous center point parameter corresponding to the second center point parameter; If not, then based on the second center point parameter, repeatedly performing the operation of determining the scaled image corresponding to the image of interest based on the preset scaling parameter; If yes, determining a target segmented image corresponding to the medical image to be processed based on the updated image of interest corresponding to the second center point parameter; Wherein, the method further comprises: Inputting the medical images to be processed into at least two target image segmentation models respectively; wherein different target image segmentation models have different model structures and / or use different sample medical images for training; Based on the segmentation results respectively output by each of the target image segmentation models and a voting mechanism, determining an image of interest in the initial segmented image corresponding to the medical image to be processed; Wherein, determining the updated image of interest based on at least one image distance comprises: taking an image point in the zoomed image corresponding to an image distance within a preset distance range as a target image point, or, based on at least one image distance, sorting the image points in the zoomed image, and determining the target image point in the zoomed image according to the sorting result and a preset selection number; Based on the target image point, the updated image of interest is determined.

2. The method according to claim 1, characterized in that The first center point parameters include first center point coordinates and first center point grayscale values, and correspondingly, the image point parameters include image point coordinates and image point grayscale values ​​of the image point.

3. The method according to claim 1, characterized in that: The method further comprises: Acquire a sample medical image, and perform a slicing operation on the sample medical image based on at least two slicing size standards to obtain a plurality of slicing medical images; Based on a plurality of cut-up medical images, at least two initial image segmentation models are trained respectively to obtain a trained target image segmentation model.

4. The method according to claim 1, characterized in that The preset zoom parameters include the number of zooming circles and the zooming direction. Accordingly, the method further includes: Inputting the verification image into at least two target image segmentation models respectively, and determining the predicted image of interest corresponding to the verification image based on the segmentation results respectively output by each target image segmentation model and a voting mechanism; The image size of the predicted image of interest is compared with the image size of the verification image of interest corresponding to the verification image, and the number of zoom circles and / or the zoom direction corresponding to the medical image to be processed are determined according to the comparison result.

5. A medical image segmentation device, characterized in that: include: A first center point parameter determination module, used to obtain an image of interest in an initial segmented image corresponding to the medical image to be processed, and determine a first center point parameter corresponding to the center point in the image of interest; A zoom image determination module, used to determine the zoom image corresponding to the image of interest based on preset zoom parameters; An image distance determination module, configured to determine the image distance between each of the image points and the center point based on the first center point parameter and image point parameters respectively corresponding to at least one image point in the zoomed image; a target segmentation image determination module, configured to determine an updated image of interest based on at least one image distance, and determine a target segmentation image corresponding to the medical image to be processed based on the updated image of interest; Wherein, the target segmentation image determination module includes: a target segmented image determination unit, configured to determine a second center point parameter corresponding to the center point in the updated image of interest; determine whether the second center point coordinates in the second center point parameter are the same as the previous center point coordinates in the previous center point parameter corresponding to the second center point parameter; if not, based on the second center point parameter, repeatedly perform the operation of determining the zoomed image corresponding to the image of interest based on the preset zoom parameter; if yes, determine the target segmented image corresponding to the medical image to be processed based on the updated image of interest corresponding to the second center point parameter; Wherein, the device further comprises: An initial segmented image determination module is used to input the medical image to be processed into at least two target image segmentation models respectively; wherein different target image segmentation models have different model structures and / or use different sample medical images for training; based on the segmentation results respectively output by each target image segmentation model and a voting mechanism, determine an image of interest in the initial segmented image corresponding to the medical image to be processed; Wherein, the target segmentation image determination module further includes: The image of interest updating unit is used to take the image point corresponding to the image distance in the zoomed image that meets the preset distance range as the target image point, or, based on at least one image distance, sort the image points in the zoomed image, and determine the target image point in the zoomed image according to the sorting result and a preset selection number; based on the target image point, determine the updated image of interest.

6. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the medical image segmentation method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the medical image segmentation method according to any one of claims 1 to 4 when executed.

Images