MPI image segmentation method, system and device based on local maximum point threshold expansion

Abstract

The present invention belongs to the field of MPI image segmentation, and specifically relates to an MPI image segmentation method, system and device based on local maximum point threshold expansion, and aims to solve the problem. The present invention includes: based on the threshold segmentation method, distinguishing the foreground signal and the background signal of the MPI image to be segmented; clustering the foreground MPI image signal by the K-means clustering method to obtain clusters of different categories; selecting the neighborhood pixels of the set area of ​​each cluster center, and obtaining the location of the local maximum signal intensity point of each cluster; based on the location of the local maximum signal intensity point of each cluster, combined with the signal intensity corresponding to each location, performing a threshold expansion operation to obtain the expansion area of ​​each cluster; merging the expansion areas of each cluster to obtain the segmentation result of the MPI image to be segmented. The present invention realizes a robust and accurate MPI image segmentation based on the threshold expansion method of the local maximum point, and reduces the influence of the selective bias existing in the MPI image segmentation.

Description

Background Art

[0002] Magnetic particle imaging (MPI) is an emerging method for directly detecting the magnetization of iron oxide nanoparticles, with advantages such as high specificity and sensitivity, linear quantitative ability, and high clinical translation potential. In various fields of biomedical research, this relatively novel imaging method has triggered scientific exploration in the new advanced field of molecular imaging and analysis, and has shown significant progress in the development of therapeutics and precision medicine. It relies on superparamagnetic iron oxide (SPIO) nanoparticle signals to produce positive contrast images, setting a new standard for quantitative biological imaging.

[0003] However, since MPI imaging is a new imaging modality, it is difficult to define a clear boundary for the region of interest (ROI) in MPI scanning, which leads to selective bias in imaging data segmentation and makes it difficult to robustly analyze and quantify imaging signals.

[0004] Therefore, it is crucial to combine the field of MPI with machine learning, which is capable of analyzing data systems and structures quickly and with high throughput. Through the analysis of regions of interest (ROIs) in preclinical and clinical scans, researchers have shown that machine learning can address the obstacles faced in biomedical image quantification. This makes it possible to use machine learning to address the problem of poor segmentation quality in MPI images. Summary of the invention

[0005] In order to solve the above-mentioned problem in the prior art, that is, the existing MPI image segmentation has a selective bias, resulting in the problem of poor MPI image segmentation quality, the present invention provides an MPI image segmentation method based on local maximum point threshold expansion, the MPI image segmentation method comprises:

[0006] Based on the threshold segmentation method, the foreground image signal and the background signal are distinguished to obtain the foreground MPI image signal of the MPI image to be segmented;

[0007] Clustering the foreground MPI image signal by a K-means clustering method to obtain cluster centers of different categories;

[0008] Select the neighborhood pixels of the set area of ​​each cluster center, and obtain the location of the local maximum signal intensity point of each cluster;

[0009] Based on the location of the local maximum signal strength point of each cluster and the signal strength corresponding to each location, a threshold expansion operation is performed to obtain the expansion area of ​​each cluster;

[0010] The dilated regions of each cluster are merged to obtain the segmentation result of the MPI image to be segmented.

[0011] In some preferred embodiments, the threshold segmentation method is:

[0012]

[0013] Among them, 0 and 1 represent the results of threshold segmentation, 0 represents the background signal, 1 represents the foreground MPI image signal, and x i，j represents the MPI signal intensity of the pixel in the i-th row and j-th column of the MPI image to be segmented, θ 1 is the preset threshold, θ 2 is the preset percentage threshold, and max(X) represents the maximum signal intensity of the MPI image to be segmented.

[0014] In some preferred embodiments, the K-means clustering method is:

[0015]

[0016]

[0017] Among them, x i Represents the horizontal and vertical coordinates of the i-th foreground MPI image signal, u k Represents the average horizontal and vertical coordinate values ​​within the k-th category cluster, C k represents the set of MPI signal points of the k-th cluster, K is the number of clustered categories, n is the number of pixels in the foreground MPI image signal, r i，k It is used to indicate whether the i-th foreground MPI image signal belongs to the k-th category cluster. If so, r i，k =1, otherwise r i，k =0.

[0018] In some preferred embodiments, the neighborhood pixels within the set range of each cluster center are selected, and the location of the local maximum signal intensity point of each cluster is obtained, and the method is:

[0019] Obtain the two-dimensional spatial position of each cluster center respectively;

[0020] Use a rectangular box of a set size with the cluster center as the center point to select the MPI signal points in the neighborhood of each cluster center as the set area for calculating the local maximum signal strength point;

[0021] The maximum value point of the foreground MPI image signal in each set area is obtained respectively, and the two-dimensional spatial position of the maximum value point is used as the position of the local maximum signal intensity point of each cluster.

[0022] In some preferred embodiments, based on the location of the local maximum signal strength point of each cluster and the signal strength corresponding to each location, a threshold expansion operation is performed to obtain the expansion area of ​​each cluster, and the method is as follows:

[0023] Generate K all-0 images of the same size as the original MPI image to be segmented; where K is the number of clustering categories;

[0024] Assign the element at the position of the corresponding local maximum signal intensity point in each all-0 image to the MPI signal intensity value of the local maximum signal intensity point;

[0025] A threshold dilation operation is performed on each local maximum signal intensity point to obtain the dilation area of ​​each cluster.

[0026] In some preferred embodiments, the threshold dilation operation is performed by:

[0027]

[0028] Among them, x i，k represents the signal strength of the node in the neighborhood of the node 8 in the i-th row and j-th column at the same position in the original MPI image to be segmented, θ is the preset percentage threshold, and x local_max Represents the MPI signal strength value of the current local maximum signal strength point.

[0029] In some preferred embodiments, the segmentation result of the MPI image to be segmented is expressed as:

[0030] P=P 1 ∪P 2 ∪…P i …∪P K

[0031] Among them, P i represents the dilated area obtained by performing a threshold dilation operation on the local maximum signal intensity point of the ith cluster, ∪ represents the dilated area merging operation, K is the number of cluster categories, and P is the segmentation result of the MPI image to be segmented.

[0032] In another aspect of the present invention, an MPI image segmentation system based on local maximum point threshold expansion is proposed, and the MPI image segmentation system includes the following modules:

[0033] A threshold segmentation module is configured to distinguish a foreground image signal from a background signal based on a threshold segmentation method, and obtain a foreground MPI image signal of the MPI image to be segmented;

[0034] A clustering module, configured to cluster the foreground MPI image signal by a K-means clustering method to obtain cluster centers of different categories;

[0035] A local maximum signal extraction module is configured to select the neighborhood pixels of the set area of ​​each cluster center and obtain the location of the local maximum signal intensity point of each cluster;

[0036] An expansion module is configured to perform a threshold expansion operation based on the location of the local maximum signal strength point of each cluster and the signal strength corresponding to each location to obtain an expansion area of ​​each cluster;

[0037] The segmentation result acquisition module is configured to merge the expansion regions of each cluster to obtain the segmentation result of the MPI image to be segmented.

[0038] According to a third aspect of the present invention, an electronic device is provided, comprising:

[0039] at least one processor;

[0040] and a memory communicatively coupled to at least one of the processors;

[0041] The memory stores instructions that can be executed by the processor, and the instructions are used to be executed by the processor to implement the above-mentioned MPI image segmentation method based on local maximum point threshold expansion.

[0042] In a fourth aspect of the present invention, a computer-readable storage medium is proposed, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to be executed by the computer to implement the above-mentioned MPI image segmentation method based on local maximum point threshold expansion.

[0043] Beneficial effects of the present invention:

[0044] (1) The MPI image segmentation method based on local maximum point threshold expansion of the present invention uses an unsupervised K-means clustering method to preprocess the MPI image, which provides an effective solution for MPI image segmentation and effectively improves the accuracy and precision of subsequent MPI image segmentation results.

[0045] (2) The MPI image segmentation method based on local maximum point threshold expansion of the present invention solves the selective bias problem of MPI image segmentation by combining the local maximum point of the MPI image with the threshold expansion operation on the basis of K-means clustering, and realizes objective, effective and robust MPI image segmentation. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0047] Figure 1 It is a flow chart of the MPI image segmentation method based on local maximum point threshold expansion of the present invention;

[0048] Figure 2The invention discloses an MPI image segmentation example based on a threshold expansion of a local maximum point in an embodiment of the MPI image segmentation method based on a threshold expansion of a local maximum point. DETAILED DESCRIPTION

[0049] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings.

[0050] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0051] The present invention provides an MPI image segmentation method based on local maximum point threshold expansion, which realizes MPI image segmentation based on local maximum points and can effectively alleviate the selective bias problem of MPI image segmentation, thereby realizing robust and accurate MPI image segmentation.

[0052] The present invention provides an MPI image segmentation method based on local maximum point threshold expansion, the MPI image segmentation method comprising:

[0053] Based on the threshold segmentation method, the foreground image signal and the background signal are distinguished to obtain the foreground MPI image signal of the MPI image to be segmented;

[0054] Clustering the foreground MPI image signal by a K-means clustering method to obtain cluster centers of different categories;

[0055] Select the neighborhood pixels of the set area of ​​each cluster center, and obtain the location of the local maximum signal intensity point of each cluster;

[0056] Based on the location of the local maximum signal strength point of each cluster and the signal strength corresponding to each location, a threshold expansion operation is performed to obtain the expansion area of ​​each cluster;

[0057] The dilated regions of each cluster are merged to obtain the segmentation result of the MPI image to be segmented.

[0058] In order to more clearly illustrate the MPI image segmentation method based on local maximum point threshold expansion of the present invention, the following is combined with Figure 1 Each step in the embodiment of the present invention is described in detail.

[0059] The MPI image segmentation method based on local maximum point threshold expansion according to the first embodiment of the present invention includes steps S10 to S50, each of which is described in detail as follows:

[0060] Step S10: based on the threshold segmentation method, distinguish the foreground image signal from the background signal to obtain the foreground MPI image signal of the MPI image to be segmented.

[0061] The threshold segmentation method is shown in formula (1):

[0062]

[0063] Among them, 0 and 1 represent the results of threshold segmentation, 0 represents the background signal, 1 represents the foreground MPI image signal, and x i，j represents the MPI signal intensity of the pixel in the i-th row and j-th column of the MPI image to be segmented, θ 1 is the preset threshold, θ 2 is the preset percentage threshold, and max(X) represents the maximum signal intensity of the MPI image to be segmented.

[0064] That is, when the MPI signal intensity x of the pixel i，j Less than the preset threshold value θ 1 When the pixel’s MPI signal intensity x i，j Less than max(X) and θ 2 When the product of is obtained, it is also classified as background signal, and the remaining pixels are classified as foreground MPI image signals.

[0065] like Figure 2 As shown, an example of MPI image segmentation based on threshold expansion of local maximum points according to an embodiment of the MPI image segmentation method based on threshold expansion of local maximum points of the present invention is shown, wherein in the image before position-based K-means clustering is performed, the dark area is the segmented background area, and the light area is the foreground MPI image signal area.

[0066] Step S20: clustering the foreground MPI image signal by using a K-means clustering method to obtain cluster centers of different categories.

[0067] K-means clustering, the method is shown in formula (2) and formula (3):

[0068]

[0069]

[0070] Among them, x i Represents the horizontal and vertical coordinates of the i-th foreground MPI image signal, u k Represents the average horizontal and vertical coordinate values ​​within the k-th category cluster, C k represents the set of MPI signal points of the k-th cluster, K is the number of clustered categories, n is the number of pixels in the foreground MPI image signal, ri，k It is used to indicate whether the i-th foreground MPI image signal belongs to the k-th category cluster. If so, r i，k =1, otherwise r i，k =0.

[0071] By minimizing J, each signal point is clustered into K categories, and the average horizontal and vertical coordinates of the cluster center are updated according to the clustering results. Stable clustering results are obtained through iterative updates. Figure 2 In the example, set the number of cluster categories K to 2, from Figure 2 It can be observed that the foreground MPI image signal is clustered into two different areas, upper and lower.

[0072] Step S30, select the neighborhood pixels of the set area of ​​each cluster center, and obtain the location of the local maximum signal strength point of each cluster:

[0073] Step S31, respectively obtaining the two-dimensional spatial position of each cluster center;

[0074] Step S32, using a rectangular frame of a set size with the cluster center as the center point, to select the MPI signal points in the vicinity of each cluster center as the set area for calculating the local maximum signal strength point;

[0075] In one embodiment of the present invention, the size of the rectangular frame is N*N, where N is the pixel side length of the rectangular frame. Figure 2 In the example shown, N is taken as 60 pixels;

[0076] Step S33, respectively obtaining the maximum value point of the foreground MPI image signal in each set area, and using the two-dimensional spatial position of the maximum value point as the position of the local maximum signal intensity point of each cluster.

[0077] Step S40, based on the location of the local maximum signal strength point of each cluster and the signal strength corresponding to each location, a threshold expansion operation is performed to obtain the expansion area of ​​each cluster:

[0078] Step S41, generating K all-0 images of the same size as the original MPI image to be segmented; wherein K is the number of clustering categories;

[0079] Step S42, assigning the element at the position of the corresponding local maximum signal intensity point in each all-0 image to the MPI signal intensity value of the local maximum signal intensity point;

[0080] Step S43: Perform a threshold dilation operation on each local maximum signal strength point to obtain a dilated area of ​​each cluster.

[0081] In one embodiment of the present invention, a set record is used as an expansion point. The set is initially a single local maximum point. Each time the expansion is performed, a point is selected from the set without replacement to perform a threshold expansion operation, as shown in formula (4):

[0082]

[0083] Among them, x i，j represents the signal strength of the node in the neighborhood of the node 8 in the i-th row and j-th column at the same position in the original MPI image to be segmented, θ is the preset percentage threshold, and x local_max Represents the MPI signal strength value of the current local maximum signal strength point.

[0084] That is, if the signal point has not been expanded and the signal strength of the signal point is greater than the θ percentage threshold (that is, θ*x local_max ), then the element at that position is assigned the value x i，j And add it to the expansion set. Otherwise, no operation is performed.

[0085] exist Figure 2 In the example shown, θ is taken as 0.7.

[0086] Step S50, merging the expansion regions of each cluster to obtain the segmentation result of the MPI image to be segmented, as shown in formula (5):

[0087] P=P 1 ∪P 2 ∪…P i …∪P K (5)

[0088] Among them, P i represents the dilated area obtained by performing a threshold dilation operation on the local maximum signal intensity point of the ith cluster, ∪ represents the dilated area merging operation, K is the number of cluster categories, and P is the segmentation result of the MPI image to be segmented.

[0089] like Figure 2 As shown, the regional images obtained by dilating the upper and lower local maximum points are taken as a union to obtain the final image, which is the segmentation result of the MPI image to be segmented.

[0090] In summary, the present invention is a threshold expansion MPI image segmentation method based on local maximum points. It is an objective, accurate and robust MPI image segmentation method, which can effectively alleviate the selective bias problem of MPI image segmentation, thereby facilitating the study of the distribution of iron nanoparticles in vivo and has great significance for MPI imaging research.

[0091] Although the various steps in the above embodiment are described in the above-mentioned order, those skilled in the art can understand that in order to achieve the effect of this embodiment, different steps do not have to be executed in such an order. They can be executed simultaneously (in parallel) or in a reverse order. These simple changes are within the scope of protection of the present invention.

[0092] The MPI image segmentation system based on local maximum point threshold expansion according to the second embodiment of the present invention comprises the following modules:

[0093] A threshold segmentation module is configured to distinguish a foreground image signal from a background signal based on a threshold segmentation method, and obtain a foreground MPI image signal of the MPI image to be segmented;

[0094] A clustering module, configured to cluster the foreground MPI image signal by a K-means clustering method to obtain cluster centers of different categories;

[0095] A local maximum signal extraction module is configured to select the neighborhood pixels of the set area of ​​each cluster center and obtain the location of the local maximum signal intensity point of each cluster;

[0096] An expansion module is configured to perform a threshold expansion operation based on the location of the local maximum signal strength point of each cluster and the signal strength corresponding to each location to obtain an expansion area of ​​each cluster;

[0097] The segmentation result acquisition module is configured to merge the expansion regions of each cluster to obtain the segmentation result of the MPI image to be segmented.

[0098] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process and related instructions of the system described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0099] It should be noted that the MPI image segmentation system based on local maximum point threshold expansion provided in the above embodiment is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the modules or steps in the embodiments of the present invention can be decomposed or combined. For example, the modules in the above embodiment can be combined into one module, or further divided into multiple sub-modules to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the present invention are only for distinguishing the modules or steps, and are not regarded as improper limitations of the present invention.

[0100] An electronic device according to a third embodiment of the present invention includes:

[0101] at least one processor;

[0102] and a memory communicatively coupled to at least one of the processors;

[0103] The memory stores instructions that can be executed by the processor, and the instructions are used to be executed by the processor to implement the above-mentioned MPI image segmentation method based on local maximum point threshold expansion.

[0104] A fourth embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to be executed by the computer to implement the above-mentioned MPI image segmentation method based on local maximum point threshold dilation.

[0105] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process and related instructions of the storage device and processing device described above can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0106] Those skilled in the art should be able to appreciate that the modules and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software or a combination of the two, and the programs corresponding to the software modules and method steps can be placed in random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in the technical field. In order to clearly illustrate the interchangeability of electronic hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are performed in electronic hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0107] The terms "first", "second", etc. are used to distinguish similar objects rather than to describe or indicate a particular order or sequence.

[0108] The term "comprise" or any other similar term is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus / device that includes a list of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article, or apparatus / device.

[0109] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. An MPI image segmentation method based on local maximum point threshold expansion, characterized in that: The MPI image segmentation method includes: Based on the threshold segmentation method, the foreground image signal and the background signal are distinguished to obtain the foreground MPI image signal of the MPI image to be segmented; Clustering the foreground MPI image signal by a K-means clustering method to obtain cluster centers of different categories; Select the neighborhood pixels of the set area of ​​each cluster center, and obtain the location of the local maximum signal intensity point of each cluster; Based on the location of the local maximum signal strength point of each cluster and the signal strength corresponding to each location, a threshold expansion operation is performed to obtain the expansion area of ​​each cluster: Generate K all-0 images of the same size as the original MPI image to be segmented; where K is the number of clustering categories; Assign the element at the position of the corresponding local maximum signal intensity point in each all-0 image to the MPI signal intensity value of the local maximum signal intensity point; Perform the threshold dilation operation on each local maximum signal strength point to obtain the dilation area of ​​each cluster; The threshold dilation operation is performed as follows: Among them, x i,j represents the signal strength of the node in the neighborhood of the node 8 in the i-th row and j-th column at the same position in the original MPI image to be segmented, θ is the preset percentage threshold, and x local_max The MPI signal strength value representing the current local maximum signal strength point; The dilated regions of each cluster are merged to obtain the segmentation result of the MPI image to be segmented.

2. The MPI image segmentation method based on local maximum point threshold expansion according to claim 1 is characterized in that: The threshold segmentation method is as follows: Among them, 0 and 1 represent the results of threshold segmentation, 0 represents the background signal, 1 represents the foreground MPI image signal, and x i,j represents the MPI signal intensity of the pixel in the i-th row and j-th column of the MPI image to be segmented, θ1 is a preset threshold, θ2 is a preset percentage threshold, and max(X) represents the maximum signal intensity of the MPI image to be segmented.

3. The MPI image segmentation method based on local maximum point threshold expansion according to claim 1, characterized in that: The K-means clustering method is as follows: Among them, x i Represents the horizontal and vertical coordinates of the i-th foreground MPI image signal, u k Represents the average horizontal and vertical coordinate values ​​within the k-th category cluster, C k represents the set of MPI signal points of the k-th cluster, K is the number of clustered categories, n is the number of pixels in the foreground MPI image signal, r i,k It is used to indicate whether the i-th foreground MPI image signal belongs to the k-th category cluster. If so, r i,k =1, otherwise r i,k =0.

4. The MPI image segmentation method based on local maximum point threshold expansion according to claim 1, characterized in that: Select the neighborhood pixels within the set range of each cluster center and obtain the location of the local maximum signal intensity point of each cluster. The method is: Obtain the two-dimensional spatial position of each cluster center respectively; Use a rectangular box of a set size with the cluster center as the center point to select the MPI signal points in the neighborhood of each cluster center as the set area for calculating the local maximum signal strength point; The maximum value point of the foreground MPI image signal in each set area is obtained respectively, and the two-dimensional spatial position of the maximum value point is used as the position of the local maximum signal intensity point of each cluster.

5. The MPI image segmentation method based on local maximum point threshold dilation according to claim 1, characterized in that: The segmentation result of the MPI image to be segmented is expressed as: P=P1∪P2∪…P i …∪P K Among them, P i represents the dilated area obtained by performing a threshold dilation operation on the local maximum signal intensity point of the ith cluster, ∪ represents the dilated area merging operation, K is the number of cluster categories, and P is the segmentation result of the MPI image to be segmented.

6. An MPI image segmentation system based on local maximum point threshold expansion, characterized in that: The MPI image segmentation system includes the following modules: A threshold segmentation module is configured to distinguish a foreground image signal from a background signal based on a threshold segmentation method, and obtain a foreground MPI image signal of the MPI image to be segmented; A clustering module, configured to cluster the foreground MPI image signal by a K-means clustering method to obtain cluster centers of different categories; A local maximum signal extraction module is configured to select the neighborhood pixels of the set area of ​​each cluster center and obtain the location of the local maximum signal intensity point of each cluster; The expansion module is configured to perform a threshold expansion operation based on the location of the local maximum signal strength point of each cluster and the signal strength corresponding to each location to obtain the expansion area of ​​each cluster: Generate K all-0 images of the same size as the original MPI image to be segmented; where K is the number of clustering categories; Assign the element at the position of the corresponding local maximum signal intensity point in each all-0 image to the MPI signal intensity value of the local maximum signal intensity point; Perform the threshold dilation operation on each local maximum signal strength point to obtain the dilation area of ​​each cluster; The threshold dilation operation is performed as follows: Among them, x i,j represents the signal strength of the node in the neighborhood of the node 8 in the i-th row and j-th column at the same position in the original MPI image to be segmented, θ is the preset percentage threshold, and x local_max The MPI signal strength value representing the current local maximum signal strength point; The segmentation result acquisition module is configured to merge the expansion regions of each cluster to obtain the segmentation result of the MPI image to be segmented.

7. An electronic device, characterized in that: include: at least one processor; and a memory communicatively coupled to at least one of the processors; The memory stores instructions executable by the processor, and the instructions are used to be executed by the processor to implement the MPI image segmentation method based on local maximum point threshold dilation as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to be executed by the computer to implement the MPI image segmentation method based on local maximum point threshold dilation according to any one of claims 1 to 5.

Images