Method and device for segmenting colon polyp based on CT image and storage medium

Abstract

The invention discloses a colon polyp segmentation method and device based on a CT image and a storage medium. The method comprises the following steps: carrying out initial segmentation on an intestinal CT image to obtain an initial segmentation result containing a colon wall; performing geometric analysis on the initial segmentation result to extract target geometric features related to the colon wall; marking a target colon wall seed voxel in the initial segmentation result based on the target geometric feature; growing according to the target colon wall seed voxels to obtain all suspected polyp blocks; and calculating the center coordinates of the suspected polyp blocks and sorting the center coordinates to segment the colon polyp. By means of the scheme, the polyp segmentation efficiency and segmentation precision can be improved.

Description

Technical Field

[0001] This application generally relates to the field of image processing technology. More specifically, this application relates to a method, device, and computer-readable storage medium for segmenting colonic polyps based on CT images. Background Art

[0002] With the development of medical image processing and three-dimensional visualization technologies, virtual endoscopy has been widely used in many clinical experiments and various medical diagnoses, such as colon examinations, due to its obvious advantages such as non-invasiveness and repeatability. Virtual endoscopy first obtains tomographic scan data of the human body through medical scanning devices such as computed tomography ("CT") and magnetic resonance imaging ("MRI"), and then uses image processing technology to reconstruct three-dimensional images and form virtual human tissues.

[0003] There are mainly two types of existing methods. One is to identify based on complete CT data, but this method has low processing speed and lacks quantitative analysis of the position of polyps in the intestinal wall. The other is to identify based on colorectal curved surface data, but this method does not consider the influence of CT values on polyp identification and has low accuracy.

[0004] In view of this, there is an urgent need to provide a solution for segmenting colonic polyps based on CT images. First, an initial segmentation is performed on the intestinal CT image to obtain an initial segmentation result containing the colon wall, which avoids the possibility of identifying polyps on the wrong organ and improves the efficiency of polyp identification. Then, geometric features are analyzed on the initial segmentation result and target colon wall seed voxels are marked, while considering both the geometric shape and the colon wall seed voxels (i.e., CT values) to perform identification from two dimensions, thereby enhancing the accuracy of polyp identification. Summary of the Invention

[0005] In order to solve at least one or more of the above-mentioned technical problems, this application proposes a solution for segmenting colonic polyps based on CT images in multiple aspects.

[0006] In a first aspect, this application provides a method for segmenting colonic polyps based on CT images, including: performing an initial segmentation on an intestinal CT image to obtain an initial segmentation result containing the colon wall; performing geometric analysis on the initial segmentation result to extract target geometric features related to the colon wall; marking target colon wall seed voxels in the initial segmentation result based on the target geometric features; obtaining all suspected polyp blocks by growing according to the target colon wall seed voxels; and calculating the central coordinates of each of the suspected polyp blocks and sorting the central coordinates to segment colonic polyps.

[0007] In one embodiment, the target geometric features at least include the shape index and / or curvature of the colon wall.

[0008] In another embodiment, the shape index is calculated by the following formula: , where , represents the principal curvature of the colon wall.

[0009] In another embodiment, the curvature is calculated by the following formula: , where , represents the principal curvature of the colon wall.

[0010] In another embodiment, marking the target colon wall seed voxels based on the target geometric features in the initial segmentation result includes: marking the voxels in the initial segmentation result whose shape index or curvature satisfies the corresponding preset threshold range as the target colon wall seed voxels; or marking the voxels in the initial segmentation result whose shape index and curvature simultaneously satisfy the corresponding preset threshold range as the target colon wall seed voxels.

[0011] In another embodiment, obtaining all suspected polyp blocks by growing based on the target colon wall seed voxels includes: using the target colon wall seed voxels as the initial seed voxels; and performing clustering growth on the initial seed voxels to obtain all suspected polyp blocks.

[0012] In another embodiment, calculating the central coordinates of each of the suspected polyp blocks is performed by: calculating the voxel mean of all voxels within each of the suspected polyp blocks to obtain the central coordinates of each of the suspected polyp blocks.

[0013] In another embodiment, sorting the central coordinates is performed by: determining the polyp diameter sizes of each of the suspected polyp blocks; and sorting the central coordinates according to the polyp diameter sizes of each of the suspected polyp blocks.

[0014] In a second aspect, the present application provides a device for segmenting colon polyps based on CT images, including: a processor; and a memory, where program instructions for segmenting colon polyps based on CT images are stored. When the program instructions are executed by the processor, the device implements one or more of the embodiments in the foregoing first aspect.

[0015] In a third aspect, the present application provides a computer-readable storage medium, on which computer-readable instructions for segmenting colon polyps based on CT images are stored. When the computer-readable instructions are executed by one or more processors, one or more of the embodiments in the foregoing first aspect are implemented.

[0016] Through the solution for segmenting colon polyps based on CT images provided above, in the embodiments of the present application, first, an initial segmentation result including the colon wall is obtained by initially segmenting the intestinal CT image, then geometric analysis is performed on the initial segmentation result to extract target geometric features, and target colon wall seed voxels are marked. All suspected polyp blocks are obtained by growing the target colon wall seed voxels, the central coordinates of each suspected polyp block are calculated and sorted by the central coordinates to segment the colon polyps. Based on this, first, the colon and rectum are considered for segmentation, which avoids the possibility of identifying polyps on the wrong organ and improves the efficiency of polyp identification. At the same time, the geometric shape and colon wall seed voxels (i.e., CT values) are considered to identify from two dimensions, thereby enhancing the accuracy of polyp identification. Description of the Drawings

[0017] By referring to the accompanying drawings and reading the following detailed description, the above and other objects, features, and advantages of the exemplary embodiments of the present application will become readily understood. In the drawings, several embodiments of the present application are shown in an exemplary rather than restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 is an exemplary flowchart showing the method for segmenting colon polyps based on CT images according to the embodiments of the present application; Figure 2 is an exemplary schematic diagram showing the normal curvature of the colon wall surface according to the embodiments of the present application; Figure 3 is an exemplary schematic diagram showing the principal curvature of the colon wall surface according to the embodiments of the present application; Figure 4 is an exemplary flowchart showing the overall process of segmenting colon polyps based on CT images according to the embodiments of the present application; Figure 5 is an exemplary structural block diagram showing the device for segmenting colon polyps based on CT images according to the embodiments of the present application. Detailed Embodiments

[0018] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts fall within the scope of protection of the present application.

[0019] It should be understood that the terms "including" and "comprising" used in the specification and claims of the present application indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0020] It should also be understood that the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. As used in the specification and claims of this application, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include the plural forms. It should be further understood that the term "and / or" used in the specification and claims of this application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0021] As used in this specification and the claims, the term "if" can be interpreted as "when...", "once", "in response to determining", or "in response to detecting" depending on the context. Similarly, the phrase "if determined" or "if [the described condition or event] is detected" can be interpreted as meaning "once determined", "in response to determining", "once [the described condition or event] is detected", or "in response to detecting [the described condition or event]" depending on the context.

[0022] The specific embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0023] Figure 1 It is an exemplary flowchart showing a method 100 for segmenting colon polyps based on CT images according to an embodiment of this application. As Figure 1 shown, at step S101, the intestinal CT image is initially segmented to obtain an initial segmentation result including the colon wall. In some embodiments, the aforementioned intestinal CT image can be acquired by an acquisition device such as a CT scanning device. In some implementation scenarios, the aforementioned initial segmentation can be achieved by an image segmentation method. Based on this, the remaining interfering organs or tissues (such as the lungs, small intestine, etc.) in the intestinal CT image can be filtered out to obtain an initial segmentation result including the colon wall. In particular, an initial segmentation result including colon wall voxel data is obtained. Among them, the aforementioned image segmentation method can include but is not limited to methods such as the GraphCut algorithm, edge detection algorithms (such as the differential method, Sobel operator, Canny operator, etc.), deep learning (such as using a segmentation model), etc., and this application does not limit in this regard.

[0024] Based on the above-obtained initial segmentation result including the colon wall, at step S102, geometric analysis is performed on the initial segmentation result to extract target geometric features related to the colon wall. In one embodiment, the aforementioned target geometric features can include but are not limited to the shape index and / or curvature of the colon wall. By extracting the shape, curvature, etc. of the colon wall, it can be used to identify polyps.

[0025] In an implementation scenario, the above-mentioned shape index can be calculated and obtained through the following formula: (1) Wherein, , represents the principal curvature of the colon wall.

[0026] In another implementation scenario, the above-mentioned curvature can be calculated and obtained through the following formula: (2) Wherein, , represents the principal curvature of the colon wall.

[0027] It can be understood that the principal curvature is the maximum and minimum values of the normal curvatures along all directions at a point on the surface, and the aforementioned normal curvature is the curvature of the projected curve on the plane formed by the tangent vector and the normal vector of the curve on the surface at a certain point. In the embodiments of the present application, the aforementioned surface is the colon wall surface, and the above , are the maximum normal curvature and the minimum normal curvature among the principal curvatures of the colon wall. Further, the shape index and the curvature of the colon wall can be calculated based on the principal curvature.

[0028] Next, at step S103, target colon wall seed voxels are marked in the initial segmentation result based on the target geometric features. In one embodiment, voxels in the initial segmentation result whose shape index or curvature satisfies the corresponding preset threshold range can be marked as target colon wall seed voxels. Alternatively, voxels in the initial segmentation result whose shape index and curvature simultaneously satisfy the corresponding preset threshold range are marked as target colon wall seed voxels. That is to say, in the embodiments of the present application, corresponding preset threshold ranges can be set respectively for the shape index or the curvature. For the case of only extracting the shape index or the curvature as the target geometric feature, colon wall voxels whose shape index or curvature conform to the corresponding preset threshold range are marked as target colon wall seed voxels. For the case of simultaneously extracting the shape index and the curvature as the target geometric feature, colon wall voxels whose shape index and curvature simultaneously conform to the corresponding preset threshold range are marked as target colon wall seed voxels.

[0029] In some embodiments, the preset threshold ranges corresponding to the above shape index or curvature can be set according to the actual segmentation requirements, and the present application does not impose any restrictions thereon. Preferably, the preset threshold range corresponding to the foregoing shape index can be set to [0, 0.09], and the preset threshold range corresponding to the foregoing curvature can be set to [0, 0.15]. In this scenario, the colon wall voxels with the shape index within [0, 0.09] are marked as target colon wall seed voxels; or the colon wall voxels with the curvature within [0, 0.15] are marked as target colon wall seed voxels; or the colon wall voxels with the shape index within [0, 0.09] and the curvature within [0, 0.15] are marked as target colon wall seed voxels.

[0030] Further, at step S104, all suspected polyp masses are obtained by growing based on the target colon wall seed voxels. In one embodiment, all suspected polyp masses can be obtained by using the target colon wall seed voxels as the initial seed voxels and performing clustering growth on the initial seed voxels. That is, the embodiments of the present application can find all suspected polyp masses through the clustering growth method. Specifically, all suspected polyp masses can be determined by the distance-based clustering growth method. As an example, the clustering growth can be achieved through the shortest Euclidean distance, and the voxels with the closest Euclidean distance are regarded as one class, that is, the voxels with the closest Euclidean distance are regarded as a polyp mass. In some embodiments, other methods such as the centroid method, the group average method, or the method of sum of squared deviations can also be used to achieve the foregoing clustering growth. In addition, all suspected polyp masses can also be obtained by methods such as region-based growth, and the present application does not impose any restrictions in this regard.

[0031] After all suspected polyp masses are obtained, at step S105, the central coordinates of each suspected polyp mass are calculated and sorted to segment the colon polyps. In some embodiments, the central coordinates of each suspected polyp mass can be obtained by calculating the voxel mean of all voxels within each suspected polyp mass. In some embodiments, the polyp diameter size of each suspected polyp mass can be determined, and then the central coordinates are sorted according to the polyp diameter size of each suspected polyp mass. Among them, the polyp diameter size of the suspected polyp mass is determined by the distance between the two voxels with the largest position distance among all voxels in each suspected polyp mass. In some implementation scenarios, based on the determined polyp diameter size, the coordinate information of all suspected polyp masses is arranged in ascending or descending order of the diameter to segment the colon polyps. In other embodiments, in addition to sorting by the diameter size as described above, sorting can also be performed according to the distance from the anus. Alternatively, sorting can also be performed according to the detected default order, and the present application does not impose any restrictions in this regard.

[0032] As described above, in the embodiment of the present application, first, the intestinal CT image is initially segmented to obtain an initial segmentation result including the colon wall, so as to avoid the possibility of identifying polyps on wrong organs and improve the efficiency of polyp segmentation. Then, geometric analysis is performed on the initial segmentation result to extract target geometric features, and the target colon wall seed voxels are marked for identification from two dimensions of geometric shape and voxels. By growing the target colon wall seed voxels, all suspected polyp blocks are obtained, and the central coordinates of each suspected polyp block are calculated and sorted to accurately segment colon polyps.

[0033] Figure 2 is an exemplary schematic diagram showing the normal curvature of the colon wall surface according to an embodiment of the present application. As Figure 2 shown, it is assumed that 201 in the figure represents a partial colon wall surface, where df(X) represents the tangent vector of the curve C on the colon wall surface at point P, N represents the normal vector of the curve C on the colon wall surface at point P, and the normal curvature is the curvature K(X) of the projection curve of the curve C on the plane formed by the tangent vector df(X) and the normal vector N at point P. It should be understood that there is a normal curvature in each direction of the surface, so there are a maximum normal curvature and a minimum normal curvature, and the maximum normal curvature and the minimum normal curvature are the principal curvatures of the colon wall surface.

[0034] Figure 3 is an exemplary schematic diagram showing the principal curvature of the colon wall surface according to an embodiment of the present application. As Figure 3 shown, 201 in the figure represents a partial colon wall surface, where df(X) represents the tangent vector of the curve C on the colon wall surface at point P, and N represents the normal vector of the curve C on the colon wall surface at point P. Further, the curvatures K1 and K2 of the projection curves in two directions on the plane formed by the tangent vector df(X) and the normal vector N of the curve C at point P are exemplarily shown in the figure. It is assumed that K1 and K2 are the maximum normal curvature and the minimum normal curvature respectively, and the K1 and K2 (corresponding to the above , ) are the principal curvatures of the colon wall surface. As described above, according to the principal curvature of the colon wall surface, the shape and curvature of the colon wall can be calculated (see the above formulas (1) and (2)).

[0035] Figure 4 is an exemplary flowchart showing the overall process of segmenting colon polyps based on CT images according to an embodiment of the present application. It should be understood that Figure 4 is a specific embodiment of the method 100 described above, so the description made above regarding Figure 1 also applies to Figure 1 . Figure 4 .

[0036] As Figure 4As shown in the figure, at step S401, intestinal CT images are collected. In some embodiments, the aforementioned intestinal CT images can be obtained by collection devices such as CT scanning devices. Based on the collected intestinal CT images, at step S402, an image segmentation operation is performed, and at step S403, colon wall voxel data is generated. In some implementation scenarios, methods such as the GraphCut algorithm, edge detection algorithm, deep learning, etc. can be used to perform the image segmentation operation to generate an initial segmentation result containing colon wall voxel data.

[0037] Next, at step S404, the target geometric features of the colon wall are extracted. In one embodiment, the target geometric features can be at least the shape index and / or curvature, etc. Specifically, the aforementioned shape index can be calculated based on obtained. The aforementioned curvature can be calculated by obtained, where , represents the principal curvature of the colon wall.

[0038] Based on the extracted target geometric features, at step S405, the target colon wall seed voxels are marked. In some embodiments, the colon wall voxels whose shape index or curvature meets the corresponding preset threshold range can be marked as target colon wall seed voxels, or the colon wall voxels whose shape index and curvature both meet the corresponding preset threshold range can be marked as target colon wall seed voxels. Preferably, the preset threshold range corresponding to the shape index can be set to [0, 0.09], and the preset threshold range corresponding to the curvature can be set to [0, 0.15].

[0039] Next, at step S406, using the target colon wall seed voxels as the initial seed voxels, all suspected polyp blocks are determined by the clustering growth method. In some embodiments, methods such as the shortest Euclidean distance, centroid method, group average method, or method of sum of squared deviations can also be used to implement the aforementioned clustering growth. Additionally, all suspected polyp blocks can also be obtained by methods such as region-based growth.

[0040] Furthermore, at step S407, the central coordinates of each suspected polyp block are calculated. In some embodiments, the voxel mean of all voxels within each suspected polyp block can be calculated to obtain the central coordinates of each suspected polyp block. After obtaining the central coordinates of each suspected polyp block, at step S408, the central coordinate sorting is performed to segment the colon polyps. In some embodiments, the polyp diameter size of each suspected polyp block can be determined, and then the central coordinate sorting can be performed according to the polyp diameter size of each suspected polyp block.

[0041] Figure 5FIG. 0 is an exemplary structural block diagram showing a device 500 for segmenting colon polyps based on CT images according to an embodiment of the present application. It can be understood that the device 500 may include the device of the embodiment of the present application, and the device implementing the solution of the present application may be a single device (such as a computing device) or a multi-functional device including various peripheral devices.

[0042] As Figure 5 shown in FIG. 5, the device of the present application may further include a central processor or central processing unit (“CPU”) 511, which may be a general-purpose CPU, a dedicated CPU, or other information processing and program execution units. Further, the device 500 may further include a mass storage 512 and a read-only memory (“ROM”) 513. The mass storage 512 may be configured to store various types of data, including various intestinal CT images, initial segmentation results, target geometric features, target colon wall seed voxels, all suspected polyp blocks and their coordinate information, algorithm data, intermediate results, and various programs required to run the device 500. The ROM 513 may be configured to store data and instructions for power-on self-test of the device 500, initialization of each functional module in the system, driver programs for basic input / output of the system, and data and instructions required to boot the operating system.

[0043] Optionally, the device 500 may further include other hardware platforms or components, such as the shown tensor processing unit (“TPU”) 514, graphics processing unit (“GPU”) 515, field programmable gate array (“FPGA”) 516, and machine learning unit (“MLU”) 517. It can be understood that although various hardware platforms or components are shown in the device 500, they are merely exemplary rather than restrictive, and those skilled in the art may add or remove corresponding hardware according to actual needs. For example, the device 500 may only include a CPU, related storage devices, and interface devices to implement the method for segmenting colon polyps based on CT images of the present application.

[0044] In some embodiments, to facilitate the transfer and interaction of data with an external network, the device 500 of the present application further includes a communication interface 518, so that it can be connected to a local area network / wireless local area network ("LAN / WLAN") 505 through the communication interface 518, and then can be connected to a local server 506 or the Internet ("Internet") 507 through the LAN / WLAN. Alternatively or additionally, the device 500 of the present application can also be directly connected to the Internet or a cellular network based on wireless communication technology through the communication interface 518, such as based on the 3rd generation ("3G"), 4th generation ("4G") or 5th generation ("5G") wireless communication technology. In some application scenarios, the device 500 of the present application can also access a server 508 and a database 509 of an external network as needed to obtain various known algorithms, data and modules, and can remotely store various data, such as various types of data or instructions for presenting, for example, intestinal CT images, initial segmentation results, target geometric features, target colon wall seed voxels, all suspected polyp blocks and their coordinate information, etc.

[0045] The peripheral devices of the device 500 may include a display device 502, an input device 503 and a data transmission interface 504. In one embodiment, the display device 502 may include, for example, one or more speakers and / or one or more visual displays, which are configured to provide voice prompts and / or image video displays for the colon polyp segmentation based on CT images of the present application. The input device 503 may include, for example, a keyboard, a mouse, a microphone, a gesture capture camera and other input buttons or controls, which are configured to receive the input of audio data and / or user instructions. The data transmission interface 504 may include, for example, a serial interface, a parallel interface or a universal serial bus interface ("USB"), a small computer system interface ("SCSI"), a serial ATA, a FireWire, a PCI Express and a high-definition multimedia interface ("HDMI"), etc., which are configured for data transmission and interaction with other devices or systems. According to the solution of the present application, the data transmission interface 504 can receive intestinal CT images collected by a CT device and transmit intestinal CT images or various other types of data or results to the device 500.

[0046] The above-mentioned CPU 511, large-capacity memory 512, ROM 513, TPU 514, GPU 515, FPGA 516, MLU 517 and communication interface 518 of the device 500 of the present application can be interconnected through a bus 519 and achieve data interaction with the peripheral devices through the bus. In one embodiment, through the bus 519, the CPU 511 can control other hardware components and their peripheral devices in the device 500.

[0047] In combination with the aboveFigure 5 Describes a device that can be used to perform colon polyp segmentation based on CT images in this application. It should be understood that the device structure or architecture here is only exemplary, and the implementation manner and implementation entity of this application are not limited by it, but can be changed without departing from the spirit of this application.

[0048] According to the above description in combination with the drawings, those skilled in the art can also understand that the embodiments of this application can also be implemented through software programs. Accordingly, this application also provides a computer-readable storage medium, on which computer-readable instructions for colon polyp segmentation based on CT images are stored. When the computer-readable instructions are executed by one or more processors, they can be used to implement the method for colon polyp segmentation based on CT images described in this application in combination with the attached Figure 1 drawings.

[0049] It should be noted that although the operations of the method of this application are described in a specific order in the drawings, this does not require or imply that these operations must be performed in that specific order, or that all the shown operations must be performed to achieve the desired result. On the contrary, the order of execution of the steps depicted in the flowchart can be changed. Additionally or alternatively, some steps can be omitted, multiple steps can be combined into one step for execution, and / or one step can be decomposed into multiple steps for execution.

[0050] It should be understood that when terms such as "first", "second", "third", and "fourth" are used in the claims, the description, and the drawings of this application, they are only used to distinguish different objects, rather than to describe a specific order. The terms "comprising" and "including" used in the description and claims of this application indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0051] It should also be understood that the terms used in the description of this application herein are only for the purpose of describing specific embodiments, and are not intended to limit this application. As used in the description and claims of this application, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms. It should be further understood that the term "and / or" used in the description and claims of this application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0052] Although the embodiments of the present application are as described above, the above content is only an example adopted for the convenience of understanding the present application, and is not intended to limit the scope and application scenarios of the present application. Any person skilled in the art within the technical field of the present application may make any modifications and changes in the form of implementation and details without departing from the spirit and scope disclosed by the present application. However, the scope of patent protection of the present application shall still be subject to the scope defined by the appended claims.

[0053] In addition, the collection and acquisition of various data in the present application comply with relevant laws and regulations and are authorized by the data providers. Any organization or individual that needs to obtain external data shall obtain authorization according to law and ensure data security, and shall not illegally collect, use, process, or transmit unauthorized or unprotected data, nor illegally buy, sell, provide, or disclose unauthorized or unprotected data.

Claims

1. A method for segmenting colon polyps based on CT images, characterized in that, Comprising: Performing initial segmentation on intestinal CT images to obtain an initial segmentation result including the colon wall; Performing geometric analysis on the initial segmentation result to extract target geometric features of the colon wall; Marking target colon wall seed voxels in the initial segmentation result based on the target geometric features; Growing according to the target colon wall seed voxels to obtain all suspected polyp masses; Calculating the central coordinates of each suspected polyp mass and sorting the central coordinates to segment colon polyps.

2. The method according to claim 1, characterized in that Wherein the target geometric features at least include the shape index and / or curvature of the colon wall.

3. The method according to claim 2, wherein Wherein the shape index is calculated by the following formula: Among them, , represents the principal curvature of the colon wall.

4. The method according to claim 2, wherein Wherein the curvature is calculated by the following formula: Among them, , represents the principal curvature of the colon wall.

5. The method according to claim 2, characterized in that Wherein marking target colon wall seed voxels in the initial segmentation result based on the target geometric features includes: Marking the voxels in the initial segmentation result whose shape index or curvature satisfies the corresponding preset threshold range as the target colon wall seed voxels; or Marking the voxels in the initial segmentation result whose shape index and curvature simultaneously satisfy the corresponding preset threshold range as the target colon wall seed voxels.

6. The method according to claim 2 or 5, characterized in that, Wherein growing according to the target colon wall seed voxels to obtain all suspected polyp masses includes: Using the target colon wall seed voxels as initial seed voxels; Performing clustering growth on the initial seed voxels to obtain all suspected polyp masses.

7. The method according to claim 1, characterized in that, Wherein the central coordinates of each suspected polyp mass are calculated by the following operations: Calculating the voxel mean of all voxels in each suspected polyp mass to obtain the central coordinates of each suspected polyp mass.

8. The method according to claim 1, wherein Wherein the central coordinate sorting is performed by the following operations: Determining the polyp diameter size of each suspected polyp mass; Sorting the central coordinates according to the polyp diameter size of each suspected polyp mass.

9. A device for segmenting colonic polyps based on CT images, characterized in that, Comprising: A processor; A memory, in which program instructions for segmenting colon polyps based on CT images are stored, and when the program instructions are executed by the processor, the device realizes the method according to any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, On which computer-readable instructions for segmenting colon polyps based on CT images are stored, and when the computer-readable instructions are executed by one or more processors, the method according to any one of claims 1-8 is realized.

Images