Colon bag segmentation method, image processing device, storage medium and program product

Abstract

The invention provides a colon bag segmentation method and device, image processing equipment, a storage medium and a computer program product, and the method comprises the steps: obtaining a plurality of transverse slices of a to-be-segmented colon, and enabling the plurality of transverse slices to be arranged in the walking direction of the to-be-segmented colon; determining the sizes of the plurality of transverse slices; and selecting a target transverse section serving as the boundary of the colon bag according to the size change of the plurality of transverse sections to obtain a segmentation result of the colon bag.

Description

Technical Field

[0001] This application belongs to the technical field of image recognition, and particularly relates to a method and device for colon bag segmentation, an image processing device, a storage medium, and a computer program product. Background Art

[0002] Colon bags are the constituent units of the colon, formed by the shortening of the taenia coli compared to the length of the intestinal tube, causing the intestinal tube to shrink. Correct parameters of colon bags, such as the number of colon bags and the depth of colon bags, play a crucial role in assisting doctors in evaluating colon function. Calculating the number of colon bags and the depth of colon bags is a prerequisite for correct colon bag segmentation. Summary of the Invention

[0003] Embodiments of this application provide a method and device for colon bag segmentation, an image processing device, a storage medium, and a computer program product, which can solve the problem of inability to segment colon bags in related technologies.

[0004] In a first aspect, embodiments of this application provide a method for colon bag segmentation, including: obtaining a plurality of transverse slices of the colon to be segmented, where the plurality of transverse slices are arranged along the running direction of the colon to be segmented; determining the sizes of the plurality of transverse slices; and selecting target transverse slices that serve as the boundaries of the colon bags according to the size changes of the plurality of transverse slices to obtain the segmentation result of the colon bags.

[0005] In a possible implementation manner of the first aspect, selecting target transverse slices that serve as the boundaries of the colon bags according to the size changes of the plurality of transverse slices includes: determining extreme value transverse slices among the plurality of transverse slices according to the size changes of the plurality of transverse slices, where the sizes of the extreme value transverse slices are minimum values; and selecting target transverse slices from the extreme value transverse slices.

[0006] In a possible implementation manner of the first aspect, the size includes first size data and second size data, the extreme value transverse slices include first extreme value transverse slices and second extreme value transverse slices, the first size data of the first extreme value transverse slices is a minimum value, and the second size data of the second extreme value transverse slices is a minimum value. Selecting target transverse slices from the extreme value transverse slices includes: determining the target transverse slices according to the information of the second extreme value transverse slices in the adjacent slices of the first extreme value transverse slices and the information of the first extreme value transverse slices in the adjacent slices of the second extreme value transverse slices. The adjacent slices of the first extreme value transverse slices include the transverse slices between the first extreme value transverse slices and the adjacent extreme value transverse slices of the same type, and the adjacent slices of the second extreme value transverse slices include the transverse slices between the second extreme value transverse slices and the adjacent extreme value transverse slices of the same type.

[0007] In a possible implementation of the first aspect, determining the target cross-section based on the information of the second extreme cross-section in the neighboring slices of the first extreme cross-section and the information of the first extreme cross-section in the neighboring slices of the second extreme cross-section includes: screening out the error extreme cross-sections from the first extreme cross-sections, where the error extreme cross-sections include the first extreme cross-sections with the number of second extreme cross-sections in their neighboring slices being 0; selecting the target extreme cross-sections from the remaining first extreme cross-sections, where the target extreme cross-sections are the first extreme cross-sections closest to the second extreme cross-section in the neighboring slices of the second extreme cross-section; and determining the target cross-section based on the target extreme cross-sections.

[0008] In a possible implementation of the first aspect, determining the target cross-section based on the target extreme cross-sections includes: screening out the target extreme cross-sections with multiple second extreme cross-sections in the neighboring slices to obtain the target cross-section.

[0009] In a possible implementation of the first aspect, the first dimension data is the minor axis length, and the second dimension data is the major axis length.

[0010] In a possible implementation of the first aspect, the dimension includes the third dimension data, the extreme cross-section includes the third extreme cross-section, and the method further includes: correcting the segmentation result of the colonic pouch according to the distribution of the third extreme cross-section.

[0011] In a possible implementation of the first aspect, the third dimension data includes at least one of the equivalent radius, equivalent diameter, and area.

[0012] In a possible implementation of the first aspect, after obtaining the segmentation result of the colonic pouch, it further includes: correcting the segmentation result of the colonic pouch according to the dimension similarity between adjacent colonic pouches.

[0013] In a possible implementation of the first aspect, before selecting the target cross-section serving as the boundary of the colonic pouch according to the dimension changes of multiple cross-sections, the method further includes: preprocessing the dimension, and the preprocessing includes at least one of filtering out the burrs and smoothing.

[0014] In a possible implementation of the first aspect, obtaining multiple cross-sections of the colon to be segmented includes: determining the running direction of the colon to be segmented; and cutting the colon to be segmented along the running direction at a set interval in a direction perpendicular to the running direction to obtain the cross-sections.

[0015] In a possible implementation of the first aspect, determining the running direction of the colon to be segmented includes: obtaining the centerline of the colon to be segmented as the running direction.

[0016] In a possible implementation of the first aspect, the colon to be segmented includes at least one of a complete colon, ascending colon, transverse colon, descending colon, and sigmoid colon.

[0017] In a second aspect, an embodiment of the present application provides a colon pouch segmentation device, including: an acquisition module for acquiring a plurality of transverse slices of the colon to be segmented, the plurality of transverse slices being arranged along the running direction of the colon to be segmented; a determination module for determining the sizes of the plurality of transverse slices; and a selection module for selecting, according to the size changes of the plurality of transverse slices, target transverse slices serving as the boundaries of the colon pouch to obtain the segmentation result of the colon pouch.

[0018] In a third aspect, an embodiment of the present application provides an image processing device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that when the processor executes the computer program, the colon pouch segmentation method described in any one of the above first aspects is implemented.

[0019] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the colon pouch segmentation method described in any one of the above first aspects is implemented.

[0020] In a fifth aspect, an embodiment of the present application provides a computer program product, which when running on an image processing device, causes the image processing device to execute the colon pouch segmentation method described in any one of the above first aspects.

[0021] The beneficial effects of the embodiments of the present application compared with the prior art are as follows: By acquiring a plurality of transverse slices of the colon to be segmented, the plurality of transverse slices being arranged along the running direction of the colon to be segmented; determining the sizes of the plurality of transverse slices; and selecting, according to the size changes of the plurality of transverse slices, target transverse slices serving as the boundaries of the colon pouch to obtain the segmentation result of the colon pouch. The colon pouch is formed by the colon band being shorter than the length of the intestinal tube, causing the intestinal tube to shrink. Therefore, the sizes of the transverse slices in different regions of the colon pouch generally change according to a fixed rule. For example, the size of the transverse slice is small at the edge of the same colon pouch and large in the middle. According to this rule, the target transverse slice serving as the boundary of the colon pouch can be selected from the transverse slices to achieve the segmentation of the colon pouch. Description of the Drawings

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0023] Figure 1It is a schematic structural diagram of an image processing device provided by an embodiment of the present application;

[0024] Figure 2 It is a schematic flowchart of a colon bag segmentation method provided by an embodiment of the present application;

[0025] Figure 3 It is a schematic diagram of a colon three-dimensional model provided by a specific embodiment of the present application;

[0026] Figure 4 It is Figure 2 The specific flowchart of S1 in

[0027] Figure 5 It is a schematic diagram of a cross-section of an obvious bending part of the colon provided by a specific embodiment of the present application;

[0028] Figure 6 It is a schematic diagram of a cross-sectional diameter-length change curve provided by a specific embodiment of the present application;

[0029] Figure 7 It is Figure 2 The specific flowchart of S4 in

[0030] Figure 8 It is Figure 7 The specific flowchart of S42 in

[0031] Figure 9 It is a schematic structural diagram of a colon bag segmentation device provided by an embodiment of the present application. Detailed implementation manners

[0032] In the following description, for the purpose of illustration rather than limitation, specific details such as specific system structures and technologies are put forward in order to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0033] It should be understood that when used in the specification of the present application and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0034] It should also be understood that the term "and / or" used in the specification of the present application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0035] As used in the description of the present application and the appended claims, the term "if" can be construed as "when" or "once" or "in response to determining" or "in response to detecting" depending on the context. Similarly, the phrases "if determined" or "if [the described condition or event] is detected" can be construed as meaning "once determined" or "in response to determining" or "once [the described condition or event] is detected" or "in response to detecting [the described condition or event]" depending on the context.

[0036] In addition, in the description of the present application and the appended claims, the terms "first", "second", "third", etc. are only used for differential description and cannot be construed as indicating or implying relative importance.

[0037] The reference to "one embodiment" or "some embodiments" or the like described in the description of the present application means that a specific feature, structure, or characteristic described in connection with that embodiment is included in one or more embodiments of the present application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in another way. The terms "comprising", "including", "having", and their variants all mean "including but not limited to", unless otherwise specifically emphasized in another way.

[0038] The colon bag segmentation method provided by the embodiments of the present application can be applied to an image processing device, specifically including but not limited to electronic devices with computing functions such as servers, server clusters, workstations, laptops, and desktop computers. The embodiments of the present application do not impose any restrictions on the specific type of the image processing device.

[0039] Figure 1 Shown is a block diagram of a part of the structure of the image processing device provided by the embodiments of the present application. Refer to Figure 1 , the image processing device includes: a processor 10, a memory 20, a bus 30, an input device 40, an output device 50, and a communication device 60. The processor 10 and the memory 20 are connected to each other through the bus 30, and the input device 40, the output device 50, and the communication device 60 are also connected to the bus 30. Those skilled in the art can understand that Figure 1 the structure of the image processing device shown in

[0040] does not constitute a limitation on the image processing device, and may include more or fewer components than shown in the figure, or combine some components, or have different component arrangements. Figure 1 The following specifically introduces each component of the image processing device:

[0041] Processor 10 is the control center of the image processing device and can execute various functions and process data by running programs stored in the memory 20. Processor 10 can be a Central Processing Unit (CPU), and this processor 10 can also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or this processor can also be any conventional processor, etc. In some embodiments, processor 10 can include an AI (Artificial Intelligence) processor, which is used to process computational operations related to machine learning.

[0042] Memory 20 is used to store the operating system, application programs, BootLoader, data, and other programs, such as program codes of computer programs, etc. Memory 20 can also be used to temporarily store data required for and generated during the execution of programs. Memory 20 can include high-speed random access memory and can also include non-volatile memory, such as flash memory, hard disks, multimedia cards, card-type memories, etc. Memory 20 can include storage units provided inside the image processing device, such as the hard disk of the image processing device, and / or removable external storage units, such as external hard disks, USB flash drives, Smart Media Cards (SMCs), Secure Digital (SD) cards, etc.

[0043] The input device 40 can include at least one of a keyboard, a mouse, a touch panel, a joystick, etc., and is used to collect user input operations to generate corresponding input signals.

[0044] The output device 50 is used to output information to be provided to the user. The output device 50 generally includes a display, and optionally, a Liquid Crystal Display (LCD), an Organic Light-Emitting Diode (OLED), etc. can be used. In addition, the output device can further include a speaker.

[0045] The communication device 60 can include a modem, a network card, etc., and is used to establish a network connection with other devices and communicate with each other.

[0046] The colon bag segmentation method provided by the embodiments of the present application can be implemented as a computer software program. For example, an embodiment of the present application provides a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program codes for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 60, and / or installed from a removable external storage unit. When the computer program is executed by a processor 10, various functions defined in the colon bag segmentation method provided by the embodiments of the present application are implemented.

[0047] To facilitate understanding of the colon bag segmentation method provided by the embodiments of the present application, the colon will be specifically described below.

[0048] The colon is a part of the large intestine, and the large intestine is a part of the lower digestive tract, including the cecum, colon, and rectum. The cecum is the starting part of the large intestine, located in the right iliac fossa, connected to the ileum on the left, and communicating with the ascending colon above. The colon surrounds the jejunum and ileum and can be divided into four intestinal segments: the ascending colon, transverse colon, descending colon, and sigmoid colon. The ascending colon is the part that continues upward from the cecum and bends to the left below the right lobe of the liver to form the transverse colon. The part of the transverse colon from the left end to the lower part of the spleen that bends downward to the left iliac crest is called the descending colon. The part of the colon below the plane of the left iliac crest is located in the lower abdomen and the small pelvic cavity, and the intestinal tube is curved, called the sigmoid colon, which continues into the rectum at the level of the 3rd sacral vertebra. The rectum is located in the pelvic cavity, and the part below the pelvic diaphragm is also called the anal canal. The turning part between the ascending colon and the transverse colon is the right colic flexure, also called the hepatic flexure. The turning part between the transverse colon and the descending colon is the left colic flexure, also called the splenic flexure. The colon has a characteristic structure called the haustra of colon, which are sac-like protrusions where the intestinal wall is separated by transverse grooves and bulges outward. This is mainly because the teniae coli are shorter than the colon tube, resulting in the folding of the colon tube.

[0049] Figure 2 The flowchart of the colon bag segmentation method provided by an embodiment of the present application is shown. By way of example and not limitation, this method can be applied to the above-mentioned image processing device.

[0050] S1: Obtain a plurality of transverse slices of the colon to be segmented.

[0051] These transverse slices are arranged along the running direction of the colon to be segmented. The colon to be segmented is part or all of a colon three-dimensional model, and specifically may include at least one of a complete colon, ascending colon, transverse colon, descending colon, and sigmoid colon. This also means that the colon bag segmentation method provided by the embodiments of the present application can be applied to a complete colon or a single intestinal segment thereof.

[0052] The running direction can also be referred to as the long-axis direction, that is, the direction in which the long axis of the colon to be segmented extends. The running directions of different intestinal segments of the colon are different. In some embodiments, the centerline of the colon to be segmented can be obtained as the running direction. This method has higher accuracy and is applicable not only to intestinal segments with obvious curvature and multiple intestinal segments, but also to a single intestinal segment with less obvious curvature. The centerline can also be referred to as the skeleton, which has the same topological structure as the original object and a width of a single pixel / voxel. The specific extraction algorithm is not limited here. For example, it can be obtained through morphological processing.

[0053] The shape of the colon is tubular, and its length is much greater than its diameter. The original intention of a transverse section refers to a section obtained by cutting perpendicular to the long axis direction of the tissue. In the embodiments of the present application, a transverse section refers to a cross-sectional image obtained by cutting the colon to be segmented perpendicular to the running direction of the colon.

[0054] The three-dimensional colon model can be obtained based on three-dimensional medical images obtained by non-invasive examinations. Specifically, for three-dimensional medical images such as computed tomography (CT) and magnetic resonance imaging (MRI), the colon therein can be segmented, and the segmentation result is the three-dimensional colon model. Alternatively, the three-dimensional colon model can be obtained by three-dimensional reconstruction based on the colon video obtained by endoscopic examination. Specifically, the colon video includes multiple colon images, and these images are reconstructed from multiple perspectives to obtain the three-dimensional colon model.

[0055] As an alternative embodiment of the present application, methods such as CT and MRI that are not affected by foreign objects inside the colon and can accurately scan the outer diameter of the colon pouch can be used to scan the colon and obtain the required medical images, thereby improving the accuracy of obtaining the outer diameter data of the colon, and further enhancing the accuracy of the final colon pouch segmentation and the credibility of the segmentation result.

[0056] The three-dimensional colon model is a three-dimensional image composed of multiple voxels (Volume Pixel, Voxel). The voxel value of each voxel is used to indicate whether the voxel belongs to the colon. The voxels belonging to the colon can be referred to as the foreground, and the voxels not belonging to the colon can be referred to as the background. For example, in a specific embodiment of the present application, the three-dimensional colon model is as Figure 3 shown.

[0057] As Figure 4 shown, in a specific embodiment of the present application, S1 includes the following parts.

[0058] S11: Determine the running direction of the colon to be segmented.

[0059] For a single intestinal segment with insignificant curvature, such as the ascending colon or descending colon, to simplify the calculation, the curvature can be ignored, and the overall direction vector of the long axis of this intestinal segment can be directly calculated as the running direction. For a single intestinal segment with more obvious curvature, such as the transverse colon and sigmoid colon, as well as the colon to be segmented that includes multiple intestinal segments, simplified calculation may introduce relatively large errors, and a more accurate method can be adopted, such as calculating the direction vector and centerline in segments to determine the running direction.

[0060] S12: Along the running direction, the colon to be segmented is cut at a set interval in a direction perpendicular to the running direction to obtain transverse slices.

[0061] The unit of the set interval can be a voxel. When the set interval is a single voxel, the obtained transverse slice, or the depth of the cross-sectional image, is 1, that is, the transverse slice is essentially a two-dimensional image. When the set interval is n voxels, n > 1, the obtained transverse slice can be a three-dimensional image with a depth of n obtained by direct cutting, or a two-dimensional image obtained from this three-dimensional image. Specifically, the three-dimensional image can be pooled in the depth dimension to obtain a two-dimensional image as the transverse slice; or, one layer of the three-dimensional image can be selected in the depth dimension as the transverse slice.

[0062] S2: Determine the sizes of multiple transverse slices.

[0063] The size of the transverse slice, that is, the size of the cross-section of the colon, can be obtained by counting the foreground pixels / voxels in the image. Since the shape of the transverse slice of the colon is often not a regular geometric shape, a single piece of data may not be able to completely represent the size of the transverse slice. To better segment the haustra of the colon, multiple pieces of data can be used to represent the size of the transverse slice. In some embodiments, the size can include at least one of the short diameter length, long diameter length, equivalent radius, equivalent diameter, and area, where the diameter length can be the radius or diameter. The center point of the foreground part in the transverse slice can be calculated first, and then the diameter lengths passing through the center point in multiple directions can be calculated. The minimum value among them is the short diameter length, and the maximum value is the long diameter length. The number of pixels / voxels included in the foreground part of the transverse slice can be counted to obtain the area, and then the radius / diameter of a circle with the same area as the foreground part of the transverse slice can be calculated as the equivalent radius / diameter of the transverse slice.

[0064] S3: Preprocess the sizes.

[0065] In some embodiments, this step may be omitted. The preprocessing may specifically include at least one of filtering out burrs and smoothing, and may be performed on a curve (hereinafter referred to as the curve) drawn according to the size of transverse slices arranged along the running direction of the colon to be segmented. The abscissa of the curve is the serial number of the transverse slice, and the ordinate is the size. The curve is a visual representation of an array formed by arranging the sizes of the transverse slices in sequence, and the two are substantially equivalent. If there are more than one type of size, curves may be drawn separately for each size.

[0066] For parts of the colon with obvious bends, such as the left colic flexure and the right colic flexure, the shape of the transverse slices in the bent parts may be irregular, resulting in obvious mutations in the sizes of their transverse slices, which are manifested as burrs in the continuously recorded sizes of the transverse slices. For example, as Figure 5 shown, the bent part on the left side of the figure is more complex. The shape of the foreground part in the transverse slice obtained at this position is irregular, resulting in an obvious difference between the size of this transverse slice and the sizes of adjacent transverse slices. In the cross-sectional diameter-length change curve as Figure 6 shown, it is manifested as obvious outlier noise points, which can also be called burrs.

[0067] The method for filtering out burrs is not limited herein and may be a time-domain or frequency-domain signal processing method, such as wavelet transform, low-pass filtering, removing after identifying burr signals, etc. Still taking Figure 6 as an example, after identifying 2 noise points therein, these 2 noise points can be removed to achieve burr filtering.

[0068] The sizes of adjacent transverse slices may have discontinuous changes, resulting in the curve possibly fluctuating up and down. Especially when the cutting interval is greater than 1 voxel and only single-layer images are selected as transverse slices, adjacent transverse slices are discontinuous in the three-dimensional colon model, and the aforementioned curve fluctuations are more likely to occur.

[0069] The curve can be smoothed to reduce or remove the above-mentioned curve fluctuations. The smoothing algorithm is not limited herein either, such as Gaussian smoothing, exponential smoothing, etc.

[0070] Since the segmentation of the colon pouch refers to the law that the size of the transverse slices is small at the edge and large in the middle of the colon pouch, the extreme points in the curve are required. The abnormal fluctuations of the curve and / or the burrs therein will lead to incorrect extreme points, thereby resulting in incorrect results in the segmentation of the colon pouch. The preprocessing can reduce the errors in the segmentation of the colon pouch caused by the abnormalities of the curve, thereby improving the correct rate of the segmentation of the colon pouch.

[0071] In the case where the preprocessing includes burr filtering and smoothing, if the curve with burrs is directly smoothed, it will cause the horizontal slice sizes before and after the burrs to be incorrectly lifted under the action of the smoothing algorithm, which may affect the subsequent segmentation of the colon pouch. To achieve a better preprocessing effect, the curve can be first subjected to burr filtering and then smoothed.

[0072] S4: Select the target horizontal slices that serve as the boundaries of the colon pouch based on the size changes of multiple horizontal slices to obtain the segmentation result of the colon pouch.

[0073] According to the formation principle of the colon pouch, it can be known that the horizontal slice sizes in different regions of the colon pouch generally change according to a fixed rule. For example, the horizontal slice size is small at the edges of the same colon pouch and large in the middle. According to this rule, the extreme points in the curve can be determined based on the size changes of multiple horizontal slices, and then the target horizontal slices can be selected from the extreme points. The extreme points include minimum values and maximum values. Since the horizontal slice size at the boundary of the colon pouch is generally the smallest among the horizontal slice sizes of the entire colon pouch, the extreme points here generally use the minimum values.

[0074] As Figure 7 shown, in a specific embodiment of the present application, S4 may include the following parts.

[0075] S41: Determine the extreme horizontal slices among multiple horizontal slices based on the size changes of multiple horizontal slices.

[0076] The extreme horizontal slices are the extreme points in the above curve, and their sizes are minimum values.

[0077] S42: Select the target horizontal slices from the extreme horizontal slices.

[0078] Two types of sizes can be used in combination to screen the target horizontal slices. Specifically, the sizes include first size data and second size data, the extreme horizontal slices include first extreme horizontal slices and second extreme horizontal slices, the first size data of the first extreme horizontal slices is the minimum value, and the second size data of the second extreme horizontal slices is the minimum value. The first extreme horizontal slices and the second extreme horizontal slices can be the same horizontal slice.

[0079] The target cross-section can be determined based on the information of the second extreme-value cross-sections in the adjacent slices of the first extreme-value cross-section and the information of the first extreme-value cross-sections in the adjacent slices of the second extreme-value cross-section. The adjacent slices of the first extreme-value cross-section include the cross-sections between the first extreme-value cross-section and the adjacent extreme-value cross-sections of the same type. The adjacent slices of the second extreme-value cross-section include the cross-sections between the second extreme-value cross-section and the adjacent extreme-value cross-sections of the same type. The adjacent slices can exclude the first / second extreme-value cross-section itself or can include it. Except for the first / second extreme-value cross-sections closest to the endpoints of the centerline, most of the first / second extreme-value cross-sections have adjacent slices in both the front and back directions. When including itself, the two adjacent slices can be combined for description. For example, among the cross-sections numbered 1-20, 2, 10, and 16 are the first extreme-value cross-sections, and 1, 11, and 18 are the second extreme-value cross-sections. Then, for the first extreme-value cross-section numbered 10, its adjacent slices can include the cross-sections numbered 3-15; for the second extreme-value cross-section numbered 11, its adjacent slices can include the cross-sections numbered 2-17.

[0080] As Figure 8 shown, in a specific embodiment of the present application, S42 may include the following parts.

[0081] S421: Screen out the error extreme-value cross-sections from the first extreme-value cross-sections.

[0082] The error extreme-value cross-sections include the first extreme-value cross-sections with the number of second extreme-value cross-sections in their adjacent slices being 0.

[0083] S422: Select the target extreme-value cross-sections from the remaining first extreme-value cross-sections.

[0084] The target extreme-value cross-section is the first extreme-value cross-section closest to the second extreme-value cross-section in the adjacent slices of the second extreme-value cross-section.

[0085] At the boundary of the colonic pouch, different types of sizes all show a narrowing trend, and based on this, the above screening can be performed.

[0086] S423: Determine the target cross-section according to the target extreme-value cross-section.

[0087] Specifically, the target extreme-value cross-sections with multiple second extreme-value cross-sections in their adjacent slices can be screened out to obtain the target cross-section. Since there may be multiple folds in a single colonic pouch, the existence of folds may cause other extreme points to appear in the curve besides the boundary of the colonic pouch. After the above two screenings, the target extreme-value cross-sections with multiple second extreme-value cross-sections in their adjacent slices may be folds. After screening out this part of the target extreme-value cross-sections, the target cross-section can be obtained.

[0088] Optionally, the first dimension data is the short diameter length, and the second dimension data is the long diameter length.

[0089] S5: Correct the segmentation result of the haustra.

[0090] In some embodiments, this step may be omitted.

[0091] The above process of selecting the target transverse slice may miss some correct haustra boundaries. For example, in the screening of the target extreme transverse slices, some correct haustra boundaries may be regarded as folds and screened out. Therefore, the segmentation result of the haustra can be corrected according to the prior knowledge related to the haustra.

[0092] Optionally, it is known that the volumes and lengths of adjacent haustra are generally similar. Accordingly, the segmentation result of the haustra can be corrected according to the size similarity between adjacent haustra. Specifically, the sizes of each haustra can be calculated according to the obtained haustra segmentation result, such as length, volume, etc. If the size of a certain haustra is significantly larger than the size of its adjacent haustra, the ratio of the size of this haustra to the size of its adjacent haustra can be calculated, and according to this ratio, it can be obtained how many actual haustra are spliced together to form this haustra, so as to further segment this haustra.

[0093] Optionally, it is known that the sizes of different types all satisfy the same variation law. Accordingly, other types of dimension data can be introduced to correct the segmentation result of the haustra. Specifically, the segmentation result of the haustra can be corrected according to the distribution of the third extreme transverse slice. The third dimension data of the third extreme transverse slice is a minimum value, and the third dimension data can include at least one of equivalent radius, equivalent diameter, and area. For example, in the obtained haustra segmentation result, if it is found that there are multiple minimum values of the equivalent area diameter in a certain haustra, then these minimum values can be referred to for further segmentation of the haustra.

[0094] By obtaining multiple transverse slices of the colon to be segmented, the multiple transverse slices are arranged along the running direction of the colon to be segmented; determine the sizes of the multiple transverse slices; according to the size changes of the multiple transverse slices, select the target transverse slices as the boundaries of the haustra to obtain the segmentation result of the haustra. The haustra is formed by the shortening of the taenia coli compared to the length of the intestinal tube, causing the intestinal tube to shrink. Therefore, the sizes of the transverse slices in different regions of the haustra generally change according to a fixed rule. For example, the size of the transverse slice is small at the edge and large in the middle of the same haustra. According to this rule, the target transverse slices as the boundaries of the haustra can be selected from the transverse slices to achieve the segmentation of the haustra.

[0095] Figure 9 The structural schematic diagram of a haustra segmentation device provided by an embodiment of the present application is shown. The haustra segmentation device includes an acquisition module 101, a determination module 102, and a selection module 103.

[0096] An acquisition module 101, configured to acquire a plurality of transverse slices of a colon to be segmented, and the plurality of transverse slices are arranged along the running direction of the colon to be segmented.

[0097] A determination module 102, configured to determine the sizes of the plurality of transverse slices.

[0098] An identification module 103, configured to select target transverse slices serving as boundaries of haustra according to the size changes of the plurality of transverse slices, so as to obtain a segmentation result of the haustra.

[0099] Optionally, the identification module 103 includes a determination unit (not shown in the figure) and a selection unit (not shown in the figure). The determination unit is configured to determine extreme-value transverse slices among the plurality of transverse slices according to the size changes of the plurality of transverse slices, and the sizes of the extreme-value transverse slices are minimum values; the selection unit is configured to select target transverse slices from the extreme-value transverse slices.

[0100] Optionally, the size includes first size data and second size data, the extreme-value transverse slices include first extreme-value transverse slices and second extreme-value transverse slices, the first size data of the first extreme-value transverse slices are minimum values, the second size data of the second extreme-value transverse slices are minimum values, and the selection unit is specifically configured to determine the target transverse slices according to the information of the second extreme-value transverse slices in the adjacent slices of the first extreme-value transverse slices and the information of the first extreme-value transverse slices in the adjacent slices of the second extreme-value transverse slices. The adjacent slices of the first / second extreme-value transverse slices include the transverse slices between the first / second extreme-value transverse slices and the adjacent same-type extreme-value transverse slices.

[0101] Optionally, the selection unit is specifically configured to screen out error extreme-value transverse slices from the first extreme-value transverse slices, where the error extreme-value transverse slices include the first extreme-value transverse slices with the number of the second extreme-value transverse slices in their adjacent slices being 0; select target extreme-value transverse slices from the remaining first extreme-value transverse slices, where the target extreme-value transverse slices are the first extreme-value transverse slices closest to the second extreme-value transverse slices in the adjacent slices of the second extreme-value transverse slices; and determine the target transverse slices according to the target extreme-value transverse slices.

[0102] Optionally, the selection unit is specifically configured to screen out the target extreme-value transverse slices with multiple second extreme-value transverse slices in their adjacent slices to obtain the target transverse slices.

[0103] Optionally, the first size data is the short diameter length, and the second size data is the long diameter length.

[0104] Optionally, the size includes third size data, the extreme-value transverse slices include third extreme-value transverse slices, and the device further includes a correction module (not shown in the figure), and the correction module is configured to correct the segmentation result of the haustra according to the distribution of the third extreme-value transverse slices.

[0105] Optionally, the third dimension data includes at least one of an equivalent radius, an equivalent diameter, and an area.

[0106] Optionally, the correction module is further configured to correct the segmentation result of the colonic pouch according to the dimensional similarity between adjacent colonic pouches.

[0107] Optionally, the device further includes a preprocessing module (not shown in the figure), and the preprocessing module is configured to preprocess the dimensions, and the preprocessing includes at least one of deburring and smoothing.

[0108] Optionally, the obtaining module 101 is specifically configured to determine the running direction of the colon to be segmented; along the running direction, the colon to be segmented is cut at a set interval in a direction perpendicular to the running direction to obtain transverse slices.

[0109] Optionally, the obtaining module 101 is specifically configured to obtain the center line of the colon to be segmented as the running direction.

[0110] Optionally, the colon to be segmented includes at least one of a complete colon, an ascending colon, a transverse colon, a descending colon, and a sigmoid colon.

[0111] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not imply the order of execution, and the order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0112] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of the present application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be described herein again.

[0113] The embodiment of the present application also provides a computer-readable storage medium, and the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the foregoing method embodiments can be implemented.

[0114] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above method embodiments of this application, a computer program can be used to instruct relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate forms, etc. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the photographing device / electronic device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk, or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0115] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0116] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians 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 this application.

[0117] In the embodiments provided in this application, it should be understood that the disclosed device / network device and method can be implemented in other ways. For example, the device / network device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical or other forms.

[0118] The unit described as a separation component may or may not be physically separated. The component displayed as a unit may or may not be a physical unit, that is, it may be located in one place or may be distributed over multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0119] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included within the protection scope of the present application.

Claims

1. A method for colon bag segmentation, characterized in that, The method includes: Obtaining a plurality of transverse slices of the colon to be segmented, and arranging the plurality of transverse slices along the running direction of the colon to be segmented; Determining the sizes of the plurality of transverse slices; According to the size changes of the plurality of transverse slices, selecting target transverse slices as the boundaries of the haustra of colon to obtain the segmentation result of the haustra of colon.

2. The method according to claim 1, wherein The obtaining a plurality of transverse slices of the colon to be segmented includes: Determining the running direction of the colon to be segmented; Along the running direction, cutting the colon to be segmented at a set interval in a direction perpendicular to the running direction to obtain the transverse slices.

3. The method according to claim 2, wherein The determining the running direction of the colon to be segmented includes: Obtaining the center line of the colon to be segmented as the running direction.

4. The method according to claim 1, wherein The selecting target transverse slices as the boundaries of the haustra of colon according to the size changes of the plurality of transverse slices includes: Determining extreme value transverse slices among the plurality of transverse slices according to the size changes of the plurality of transverse slices, and the sizes of the extreme value transverse slices are minimum values; Selecting the target transverse slices from the extreme value transverse slices.

5. The method according to claim 4, wherein The sizes include the minor axis length and the major axis length, the extreme value transverse slices include a first extreme value transverse slice and a second extreme value transverse slice, the minor axis length of the first extreme value transverse slice is the minimum value, the major axis length of the second extreme value transverse slice is the minimum value, and the selecting the target transverse slices from the extreme value transverse slices includes: Determining the target transverse slices according to the information of the second extreme value transverse slice in the adjacent slices of the first extreme value transverse slice and the information of the first extreme value transverse slice in the adjacent slices of the second extreme value transverse slice; the adjacent slices of the first extreme value transverse slice include the slices between the first extreme value transverse slice and the adjacent extreme value transverse slices of the same type, and the adjacent slices of the second extreme value transverse slice include the slices between the second extreme value transverse slice and the adjacent extreme value transverse slices of the same type.

6. The method according to claim 5, wherein The determining the target transverse slices according to the information of the second extreme value transverse slice in the adjacent slices of the first extreme value transverse slice and the information of the first extreme value transverse slice in the adjacent slices of the second extreme value transverse slice includes: Screening out error extreme value transverse slices from the first extreme value transverse slices, and the error extreme value transverse slices include the first extreme value transverse slices with the number of the second extreme value transverse slices in their adjacent slices being 0; Selecting target extreme value transverse slices from the remaining first extreme value transverse slices, and the target extreme value transverse slices are the first extreme value transverse slices closest to the second extreme value transverse slice in the adjacent slices of the second extreme value transverse slice; Determining the target transverse slices according to the target extreme value transverse slices.

7. The method according to claim 6, wherein The determining the target transverse slices according to the target extreme value transverse slices includes: Screen out the target extreme cross-section with multiple second extreme cross-sections in adjacent laminae to obtain the target cross-section.

8. The method according to any one of claims 4-7, characterized in that, The dimension includes third dimension data, the extreme cross-section includes a third extreme cross-section, the third dimension data includes at least one of an equivalent radius, an equivalent diameter, and an area, and the method further includes: Correct the segmentation result of the colonic pouch according to the distribution of the third extreme cross-section.

9. The method according to any one of claims 1-7, characterized in that After obtaining the segmentation result of the colonic pouch, the method further includes: Correct the segmentation result of the colonic pouch according to the dimensional similarity between adjacent colonic pouches.

10. An image processing apparatus, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, the method according to any one of claims 1 to 9 is implemented.

11. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

12. A computer program product, characterized in that, When the computer program product runs on an image processing device, the image processing device is caused to execute the method according to any one of claims 1 to 9.

Images