A method and system for marking tumor boundary of digestive tract submucosal tumors

Abstract

The present invention discloses a method and system for marking the boundaries of submucosal tumors of the digestive tract. This method addresses the existing problem of difficulty distinguishing the boundaries of submucosal tumors of the digestive tract due to the invasive growth of tumor cells, which causes the boundaries of tumor cells to merge with surrounding normal tissue. By using a "region segmentation-tumor region identification-tumor region accuracy analysis" approach, tumor regions are determined, thereby facilitating the marking of tumor focus boundaries. This method improves the accuracy of tumor region boundary determination, ensures the correctness of tumor focus boundary marking, and provides reliable support for subsequent diagnosis and treatment by doctors.

Description

Technical Field

[0001] The present invention belongs to the field of image processing and relates to a method and system for marking tumor foci boundaries of digestive tract submucosal tumors. Background Art

[0002] Gastrointestinal submucosal tumors are common lesions of the digestive system, and their diagnosis and treatment are crucial for patient prognosis. With the increasing sophistication of endoscopic treatment techniques, resection of submucosal tumors has become an important treatment option. Tumor boundary marking can clearly define the tumor's boundaries, helping surgeons accurately identify and resect tumor tissue during surgery, avoiding omission or accidental injury to normal tissue. Therefore, the development and application of an effective method for marking the boundaries of submucosal tumors of the digestive tract is of great clinical significance.

[0003] When marking the tumor boundary of a submucosal tumor in the digestive tract, the invasive growth of tumor cells causes the tumor boundary of the tumor cell foci to merge with the surrounding normal tissue, making it difficult to directly distinguish the tumor boundary, thereby affecting the doctor's tumor boundary marking effect of the patient's submucosal tumor in the digestive tract, and further affecting the subsequent treatment plan. Summary of the Invention

[0004] The present invention aims to address the existing problem of difficulty in directly distinguishing the boundaries of submucosal tumors of the digestive tract due to the invasive growth of tumor cells, which causes the boundaries of tumor cells to merge with surrounding normal tissue. A method and system for marking the boundaries of submucosal tumors of the digestive tract is provided. The method analyzes the collected local CT images of the patient and combines the grayscale and positional representations of the pixels on the CT images to perform regional segmentation of the CT images. The location of the tumor region is then determined based on the characteristic representations of the tumor. Further, the tumor region is accurately analyzed to accurately determine the boundaries of the tumor, thereby improving the accuracy of tumor boundary marking.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] A method for marking the tumor boundary of a digestive tract submucosal tumor comprises the following steps:

[0007] Acquire local CT images;

[0008] Performing regional segmentation on the local CT image to obtain the segmented CT image, performing feature analysis on different regions of the segmented CT image to obtain the region where the tumor is located;

[0009] Pixel count is performed based on the tumor area, and the tumor area is divided into several sub-areas based on the pixel count results. Based on the sub-areas, the average gray value and regional edge shape are calculated, and the tumor area is obtained based on the calculation results;

[0010] Perform boundary analysis on the tumor area to obtain the actual location of the tumor area;

[0011] The edge pixels of the actual position of the tumor area are marked to obtain the tumor lesion boundary.

[0012] A further improvement of the present invention is:

[0013] The performing of regional segmentation on the local CT image to obtain the segmented CT image, and performing feature analysis on different regions of the segmented CT image to obtain the region where the tumor is located, includes:

[0014] The local CT image is segmented by using the threshold segmentation method;

[0015] Based on the CT image after threshold segmentation, a coordinate system is constructed with the center of the image as the origin;

[0016] Based on the constructed coordinate system, starting from the origin, the two sides of the X-axis are judged in sequence. Specifically, it is judged whether there are pixels with a gray value of 1 continuously distributed on both sides of the X-axis in the Y-axis direction;

[0017] If it exists, the pixel point is regarded as the area where the tumor may exist on the CT image;

[0018] If there are no continuous pixels with a grayscale value of 1 on both sides of the X-axis within the set threshold range, the subsequent judgment in the Y-axis direction will be stopped, and the area that has been judged is the area where the tumor may exist.

[0019] The pixel calculation is performed based on the region where the tumor is located, and the region where the tumor is located is divided into several sub-regions according to the pixel calculation results, including:

[0020] Construct the gray value data sequence of the tumor area ,in Indicates the area where the tumor is located The gray value of a pixel, ;

[0021] Calculate the Pixels and The probability that the pixels belong to the same area:

[0022] ;

[0023] ;

[0024] Where, Indicates the The coordinates of the pixel points; Indicates the The coordinates of the centroid of the area where the pixel point is located; Indicates the The coordinates of the pixel point to the The distance from the centroid of the area where the pixel is located; Indicates the The average distance from the edge pixels to the centroid of the region where the pixel is located; Indicates the Pixels and The possibility that the pixels belong to the same area;

[0025] Setting judgment thresholds ,when Less than threshold When Pixels and Pixels are divided into the same area;

[0026] Repeat the above calculation to determine The other pixels in the eight neighborhoods of the pixel point and the The possibility that the pixels belong to the same area is calculated after the judgment is completed. The probability that a pixel point and its eight neighboring pixels belong to the same area is calculated until the eight neighboring pixels of the pixel point divided into an area and the surrounding pixels are calculated. When , the judgment of the current area is completed;

[0027] Repeat the above determination method until the tumor area is divided into several sub-areas.

[0028] The method of calculating the average gray value and the regional edge shape based on the plurality of sub-regions and obtaining the tumor region according to the calculation results includes:

[0029] Based on several sub-regions, the The probability that a region belongs to the region where the tumor is located:

[0030] ;

[0031] ;

[0032] Where, Indicates the The average gray value of the region; Indicates that except The average gray value of the remaining area of the region; Indicates the A data sequence constructed by the distance from the edge pixel of a region to the centroid of the region; Indicates in The average value of the difference between the distances of adjacent edge pixels in a region and the centroid of the region; Indicates the The shape of each area; Indicates the The probability that the region belongs to the tumor area;

[0033] Based on the calculation results, select The corresponding area is used as the location of the tumor area in the CT image, and the tumor area is obtained.

[0034] The performing boundary analysis on the tumor region to obtain the actual position of the tumor region includes:

[0035] Select the centroid position of the tumor area and extend it in all directions from the centroid position to obtain the The pixel gray value data sequence in each direction ;

[0036] Calculate the tumor area The trend of wettability change in each direction:

[0037] ;

[0038] ;

[0039] Where, Represents the weight value of the grayscale change of the j-th pixel in the v-th direction; Indicates the distance from the jth pixel to the centroid in the vth direction; Indicates the shortest distance from the jth pixel point to the boundary of other regions in the vth direction; Indicates the number of pixels in the vth direction; The tumor area The trend of infiltration in different directions;

[0040] Select the pixel point that is adjacent to the edge pixel point of the tumor area in the vth direction and analyze the possibility that the pixel point belongs to the tumor area:

[0041] ;

[0042] Where, Indicates the grayscale difference between the edge pixel and the adjacent pixel in the vth direction; It represents the difference between the gray value of the edge pixel in the vth direction and the adjacent pixel in its original area and the average value of the five consecutive adjacent pixels;

[0043] According to the calculation results Judge the pixel points and obtain the actual position of the tumor area.

[0044] According to the calculation results Determine the pixel points and obtain the actual location of the tumor area, including:

[0045] Setting judgment thresholds ,when When , the pixel point is divided into the tumor area;

[0046] Repeat the judgment until the calculated or , stop judging in this direction;

[0047] The other directions are judged in turn until all directions are judged and the actual position of the tumor area is obtained.

[0048] The obtaining of a local CT image comprises:

[0049] Scan and obtain the patient's local chest CT image;

[0050] The patient's local chest CT image is denoised and processed using a histogram equalization method to obtain a processed local CT image.

[0051] A tumor boundary marking system for digestive tract submucosal tumors, comprising:

[0052] An image acquisition module, used for acquiring local CT images;

[0053] A tumor region acquisition module is used to segment the local CT image, obtain the segmented CT image, perform feature analysis on different regions of the segmented CT image, and obtain the tumor region;

[0054] The tumor region acquisition module is used to calculate pixels based on the tumor region, divide the tumor region into several sub-regions based on the pixel calculation results, calculate the average gray value and regional edge shape based on the several sub-regions, and obtain the tumor region based on the calculation results;

[0055] A module for obtaining the actual position of the tumor region is used to perform boundary analysis on the tumor region and obtain the actual position of the tumor region;

[0056] The tumor focus boundary acquisition module is used to mark the edge pixel points of the actual position of the tumor area and obtain the tumor focus boundary of the tumor.

[0057] A terminal device comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any one of the methods of the present invention when executing the computer program.

[0058] A computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of any method described in the present invention.

[0059] Compared with the prior art, the present invention has the following beneficial effects:

[0060] This invention discloses a method for marking the boundaries of submucosal tumors of the digestive tract. This method uses a "region segmentation - tumor region identification - tumor region accuracy analysis" approach to determine the tumor region, thereby facilitating the marking of tumor foci boundaries. This method improves the accuracy of tumor region boundary determination and ensures the correctness of tumor foci boundary marking, providing reliable support for subsequent diagnosis and treatment by physicians. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0062] Figure 1 is a flow chart of the method of the present invention;

[0063] Figure 2 Schematic diagram of an image after threshold segmentation according to the present invention;

[0064] Figure 3 This is a schematic diagram of the regional division of the present invention;

[0065] Figure 4 This is a schematic diagram of the pixel point judgment sequence of the present invention;

[0066] Figure 5 Schematic diagram of density distribution trend of the present invention. DETAILED DESCRIPTION

[0067] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations.

[0068] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but rather merely represents selected embodiments of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without creative effort shall fall within the scope of protection of the present invention.

[0069] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0070] In the description of the embodiments of the present invention, it should be noted that if the terms "upper," "lower," "horizontal," "inner," etc. appear, the orientation or positional relationship indicated is based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship in which the inventive product is typically placed when in use. These terms are merely for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or component referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limitations on the present invention. In addition, the terms "first," "second," etc. are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0071] In addition, if the term "horizontal" appears, it does not mean that the component must be absolutely horizontal, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", and does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0072] In the description of the embodiments of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "disposed," "installed," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to mechanical connections or electrical connections; they can refer to direct connections or indirect connections through an intermediate medium; and they can refer to internal connections between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0073] The present invention is described in further detail below with reference to the accompanying drawings:

[0074] See also Figures 1 to 5 The embodiment of the present invention discloses a method for marking the tumor foci boundary of a gastrointestinal submucosal tumor. First, a local CT image of the patient is collected using a CT scanner, and the collected CT image is preprocessed accordingly. Based on a specific analysis of the collected local CT image of the patient's chest, the CT image is segmented into regions. Then, based on the characteristic performance of different regions, the location of the tumor region is identified, and the tumor region is accurately analyzed to complete the tumor foci boundary calibration. Based on the actual position of the tumor region on the gastrointestinal mucosal CT image analyzed above, the tumor foci boundary marking is completed to help doctors perform corresponding diagnosis and treatment.

[0075] The specific steps include:

[0076] Step S1: First, a local CT image of the patient is acquired by using a CT scanner, and the acquired CT image is preprocessed accordingly.

[0077] The present invention primarily marks the boundaries of submucosal tumors in the digestive tract by analyzing the collected images of the patient's digestive tract mucosa. Due to the invasive growth of the tumor portion in the patient's body, it is difficult to directly distinguish the tumor boundary area based on CT images, which affects the marking of the boundaries of submucosal tumors in the digestive tract. Therefore, the embodiment of the present invention requires specific analysis based on the collected CT images of the patient. The specific steps are as follows:

[0078] Step S1.1: Use a CT scanner to acquire a local chest CT image of the patient. The acquired image should have high resolution and clarity to facilitate subsequent processing and analysis.

[0079] In this step, the acquired image should be scanned with appropriate thickening, and the patient needs to control his or her breathing state to minimize the impact of unstable breathing on the image quality of the acquired patient's local CT image.

[0080] Step S1.2: Preprocess the local chest CT image of the patient acquired in step S1.1, denoise the image using existing technology, and process the image using a histogram equalization method to enhance the contrast of the patient's CT image, thereby obtaining a preprocessed local CT image.

[0081] Step S2: The collected local CT image of the patient's chest is specifically analyzed, the CT image is segmented, and then the location of the tumor area is identified based on the characteristic performance of different areas. The tumor area is accurately analyzed to complete the tumor boundary calibration.

[0082] When edge detection is used directly to segment CT images, the texture of tissues in the human body is relatively similar, resulting in poor segmentation and difficulty in analysis and judgment. In addition, due to the infiltrative growth of the tumor, the tumor lesion boundary segmented by this method is inaccurate, affecting subsequent judgment. Therefore, the embodiment of the present invention is based on the collected local CT image of the patient's chest, and segments different regions based on the grayscale value of the pixel point. The location of the tumor on the CT image is further determined, and the accuracy of the boundary part of the tumor is analyzed, thereby completing the marking of the tumor lesion boundary, making the marked result more accurate.

[0083] Specifically, the steps for marking the tumor boundary of a tumor under the digestive tract mucosa are as follows:

[0084] (1) Based on the collected local CT images of the patient, a specific analysis is performed, the grayscale value and position of the pixel points are used to segment the region, and the location of the tumor region is identified based on the specific characteristics of different regions.

[0085] (2) Based on the location of the tumor area analyzed above, combined with the edge pixels of the area and the specific performance of the surrounding area, the edge of the tumor area is accurately analyzed.

[0086] The specific steps include:

[0087] Step 2.1: Perform specific analysis based on the collected local CT images of the patient, use the grayscale value and position of the pixel points to perform regional segmentation, and identify the location of the tumor area based on the specific characteristics of different areas, that is, the area where the tumor is located.

[0088] First, the embodiments of the present invention require specific analysis based on the patient's local CT images acquired above. A local chest CT image of a patient contains multiple different tissue components, each of which appears differently on the chest CT image. Furthermore, within a chest CT image, the density of the tumor lesion differs from that of other normal tissues. However, due to the invasive nature of the tumor, the embodiments of the present invention identify the tumor's approximate location on the CT image.

[0089] Therefore, the embodiment of the present invention needs to perform a specific analysis in combination with the above-collected local CT image of the patient's chest to complete the preliminary identification of the tumor area on the local CT image of the patient. The specific analysis steps are as follows:

[0090] Step 2.1.1: First, we need to determine the approximate location of the tumor on the CT image. The tumor and other tissue areas should be located in the middle of the patient's chest CT image. There is a clear difference between the tumor and the surrounding (no tissue) area on the CT image. Therefore, we use the threshold segmentation technique to perform image segmentation. Figure 2 .

[0091] Step 2.1.2: Construct a coordinate system on the image after threshold segmentation. With the image center as the origin and the origin as the starting point, continuously determine whether there are pixels with a grayscale value of 1 distributed continuously on both sides of the X-axis in the vertical direction. If so, select the pixels with a grayscale value of 1 that are continuously distributed near the X-axis in the vertical direction as the possible tumor area on the CT image. See Figure 3 .

[0092] For a patient's local chest CT image, various tissues (including tumor tissue) are generally located in the central area. This step is used to screen out the distribution area of the tissue area on the CT image.

[0093] Furthermore, a judgment threshold is set during the judgment. If there are no continuous pixels with a grayscale value of 1 within the 15 pixel position range on both sides of the X-axis, the judgment of the subsequent vertical direction will be stopped. The area before the judgment is stopped is the area where the tumor may exist. The area where the tumor may exist on the CT image is obtained by judgment, that is, the area where the tumor is located.

[0094] Step 2.1.3: Based on the area where the tumor may be located divided on the CT image, the area where the tumor may be located is divided on the original image.

[0095] The area where the tumor may be located divided in the above steps is an entire area. Further, the embodiment of the present invention needs to segment the entire area and then determine the segmented areas to identify the tumor area.

[0096] The details are as follows:

[0097] Step 2.1.3.1: Construct the grayscale value data sequence of the entire area divided on the original image: .in Indicates the overall area The gray value of a pixel, .

[0098] Step 2.1.3.2: Select pixels (the pixels are distributed in ), calculate the distance between the pixel and the The probability that the pixels belong to the same area:

[0099] ;

[0100] ;

[0101] Where, Indicates the The coordinates of the pixel points. Indicates the The coordinates of the centroid of the area where the pixel point is located. Indicates the The coordinates of the pixel point to the The distance from the centroid of the area where the pixel point is located. Indicates the The average distance from the edge pixels to the centroid of the region where the pixel points are located. Indicates the Pixels and The probability that the pixels belong to the same area.

[0102] The calculation formula in this step is mainly based on the grayscale values of adjacent pixels and the position of the pixels in the coordinate system. In the collected digestive tract CT images, the grayscale values of the pixels in each tissue area are close, and the shape of each tissue is close to a circle (including the irregular shape of the tumor). Therefore, when the grayscale values of adjacent pixels in the analyzed digestive tract CT images are closer, and the difference between the distance between the pixel to be judged and the centroid of a certain area and the distance between the pixel on the boundary of the area and the centroid of the area is smaller, it means that the adjacent pixels belong to the same area.

[0103] Furthermore, in the calculation, a threshold is set , when the calculated When Pixels and Pixels are divided into the same area. Indicates the possibility that the i-th pixel and the i+1-th pixel belong to the same region.

[0104] Step 2.1.3.3: After analyzing that adjacent pixels belong to the same area, continue to analyze The other pixels in the eight neighborhoods of the pixel point and the The possibility that the pixels belong to the same area. After eight neighborhoods around the pixel, select the The probability that the eight neighboring pixels of the pixel point belong to the same area is re-analyzed. The judgment is made in order until the eight neighboring pixels of the pixel point divided into one area and the surrounding pixels are calculated. , then the determination of the area is completed, and the undetermined pixels are reselected for area determination, see Figure 4 .

[0105] Step 2.1.3.4: Repeat step 2.1.3.3 to divide the entire area divided in the original image into multiple small areas, i.e., several sub-areas.

[0106] Step 2.1.4: Based on the specific performance of each small area in the sub-areas, the tumor tissue area is analyzed, i.e., the tumor area, as follows:

[0107] Step 2.1.4.1: Analyze The probability that a region belongs to the region where the tumor is located:

[0108] ;

[0109] ;

[0110] Where, Indicates the The average gray value of the region; Indicates that except The average gray value of the remaining area of the region. Indicates the The data sequence is constructed by the distance from the edge pixels of a region to the centroid of the region. Indicates in The average value of the difference between the distances of adjacent edge pixels in a region and the centroid of the region. Indicates the The shape of the area. Indicates the The probability that a region belongs to the region where the tumor is located.

[0111] The formula in this step is primarily based on the average grayscale value between regions and the shape of the region's edges. For tumor regions, due to the invasive growth of the tumor, the grayscale color of the tumor region differs significantly from that of normal tissue, and the shape is relatively irregular. The greater the difference between the average grayscale value of a region and the average grayscale value of the remaining regions, and the more irregular the distance between the edge pixels and the region's centroid, the more likely the region is a tumor.

[0112] Step 2.1.4.2: Based on the calculation results of step 2.1.4.1, the embodiment of the present invention selects The corresponding area is used as the location of the tumor area in the CT image.

[0113] At this point, the embodiment of the present invention obtains the location of the tumor area on the patient's digestive tract mucosa CT image, that is, obtains the tumor area.

[0114] Step 2.2: Based on the tumor area analyzed in step 2.1, combined with the edge pixels of the area and the specific performance of the surrounding area, perform an accurate analysis of the edge of the tumor area.

[0115] In the above process, the embodiment of the present invention obtains the tumor region on the patient's digestive tract mucosa CT image, and based on this, the embodiment of the present invention can complete the marking of the tumor boundary. However, due to the invasive growth of tumors in the human body, the tumor boundary becomes irregular in shape. Since the above process of the embodiment of the present invention uses grayscale value and distance to perform region segmentation, the tumor boundary segmentation may be inaccurate, requiring detailed analysis to determine its accuracy.

[0116] Therefore, the embodiment of the present invention performs accurate boundary analysis of the tumor area based on the pixel distribution performance of the tumor area and the specific performance of the pixel points in the boundary area, thereby helping to complete the marking of the tumor lesion boundary. The specific process is as follows:

[0117] Step 2.2.1: First, the embodiment of the present invention needs to analyze the density distribution trend (i.e., grayscale distribution) of the tumor area, see Figure 5 , as follows:

[0118] Step 2.2.1.1: Select the centroid of the tumor area and extend from the centroid in all directions to obtain the first The pixel gray value data sequence in each direction:

[0119] ;

[0120] Where, Indicates the tumor area The direction of The gray value of a pixel.

[0121] Step 2.2.1.2: Calculate the tumor area The trend of wettability change in each direction:

[0122] ;

[0123] ;

[0124] Where, Represents the weight value of the grayscale change of the j-th pixel in the v-th direction. Indicates the distance from the jth pixel to the centroid in the vth direction. Indicates the shortest distance from the j-th pixel point to the boundary of other regions in the v-th direction. Indicates the number of pixels in the vth direction. The tumor area The trend of wettability change in different directions.

[0125] Among them, the weight value The weight is calculated primarily based on the pixel's position within the region and its distance from other regions. Due to the invasive nature of tumor growth, pixels closer to the edge of a region are more likely to represent areas of recent invasive growth and expansion, and thus should receive a larger weight for invasive trend analysis.

[0126] The calculation is primarily based on the change in grayscale values in each direction (specifically, the change in weight values). The invasive growth of a tumor region manifests differently in different directions. Therefore, based on the grayscale values of consecutive pixels in the same direction, combined with different weight values, we analyze the invasive trend in each direction.

[0127] Step 2.2.2: Then select the pixel points that are adjacent to the edge pixel points of the tumor area in the vth direction and analyze the possibility that they belong to the tumor area:

[0128] ;

[0129] Where, Indicates the grayscale difference between the edge pixel and the adjacent pixel in the vth direction. It represents the difference between the grayscale value of the edge pixel in the vth direction and the adjacent pixel in its original area and the average value of the five consecutive adjacent pixels.

[0130] The calculation formula in this step is mainly based on the grayscale difference between the edge pixel points in a certain direction of the tumor area and the pixels in other areas adjacent to each other. Because the distance factor needs to be taken into account when dividing the area, the pixels with a certain difference in grayscale are divided into normal tissue, which may have already indicated invasive growth. Therefore, when the grayscale difference between the edge pixel point and the adjacent pixel point in the vth direction of the tumor area is closer to the invasive growth in that direction, and the grayscale difference between the pixel point and the adjacent pixel point in the area where it exists is greater, the possibility that it belongs to the tumor area is greater.

[0131] Furthermore, in the judgment, a threshold is set , when the calculated , then the pixel is divided into the tumor area. Then repeat the judgment until the calculated or , stop judging in that direction. Similarly, judge in other directions as well. Obtain the actual position of the tumor area on the patient's digestive tract mucosa CT image.

[0132] Thus, the embodiment of the present invention has obtained the actual position of the tumor area on the patient's digestive tract mucosa CT image.

[0133] Step S3: Based on the actual position of the tumor area on the digestive tract mucosa CT image analyzed in step S2, the tumor focus boundary is marked to help doctors perform corresponding diagnosis and treatment.

[0134] In the above process, the embodiment of the present invention obtains the actual location of the tumor area on the digestive tract mucosa CT image. All edge pixels of the tumor area are selected and marked on the CT image, which is the tumor lesion boundary. This helps doctors make appropriate diagnosis and treatment.

[0135] The embodiment of the present invention discloses a tumor boundary marking system for a submucosal tumor of the digestive tract, comprising:

[0136] An image acquisition module, used for acquiring local CT images;

[0137] A tumor region acquisition module is used to segment the local CT image, obtain the segmented CT image, perform feature analysis on different regions of the segmented CT image, and obtain the tumor region;

[0138] The tumor region acquisition module is used to calculate pixels based on the tumor region, divide the tumor region into several sub-regions based on the pixel calculation results, calculate the average gray value and regional edge shape based on the several sub-regions, and obtain the tumor region based on the calculation results;

[0139] A module for obtaining the actual position of the tumor region is used to perform boundary analysis on the tumor region and obtain the actual position of the tumor region;

[0140] The tumor focus boundary acquisition module is used to mark the edge pixel points of the actual position of the tumor area and obtain the tumor focus boundary of the tumor.

[0141] A schematic diagram of a terminal device provided in one embodiment of the present invention. The terminal device in this embodiment includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of each of the aforementioned method embodiments are implemented. Alternatively, when the processor executes the computer program, the functions of each module / unit in each of the aforementioned device embodiments are implemented.

[0142] The computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to accomplish the present invention.

[0143] The terminal device may be a computing device such as a desktop computer, a notebook computer, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0144] The processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0145] The memory may be used to store the computer programs and / or modules, and the processor implements various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory.

[0146] If the module / unit integrated into the terminal device is implemented as 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, the present invention can implement all or part of the process steps in the above-mentioned method embodiments by using a computer program to instruct the relevant hardware. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium. It should be noted that the content of the computer-readable medium can be appropriately increased or decreased based on the requirements of legislation and patent practice in a jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media does not include electric carrier signals and telecommunication signals.

[0147] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A method for marking the tumor boundary of a digestive tract submucosal tumor, characterized in that: The following steps are involved: Acquire local CT images; Performing regional segmentation on the local CT image to obtain the segmented CT image, performing feature analysis on different regions of the segmented CT image to obtain the region where the tumor is located; Pixel count is performed based on the tumor area, and the tumor area is divided into several sub-areas based on the pixel count results. Based on the sub-areas, the average gray value and regional edge shape are calculated, and the tumor area is obtained based on the calculation results; Perform boundary analysis on the tumor area to obtain the actual location of the tumor area; Mark the edge pixels of the actual location of the tumor area to obtain the tumor lesion boundary; The performing boundary analysis on the tumor region to obtain the actual position of the tumor region includes: Select the centroid position of the tumor area and extend it in all directions from the centroid position to obtain the The pixel gray value data sequence in each direction ; Calculate the tumor area The trend of wettability change in each direction: ； ； Where, Represents the weight value of the grayscale change of the j-th pixel in the v-th direction; Indicates the distance from the jth pixel to the centroid in the vth direction; Indicates the shortest distance from the jth pixel point to the boundary of other regions in the vth direction; Indicates the number of pixels in the vth direction; The tumor area The trend of infiltration in different directions; Select the pixel point that is adjacent to the edge pixel point of the tumor area in the vth direction and analyze the possibility that the pixel point belongs to the tumor area: ； Where, Indicates the grayscale difference between the edge pixel and the adjacent pixel in the vth direction; It represents the difference between the gray value of the edge pixel in the vth direction and the adjacent pixel in its original area and the average value of the five consecutive adjacent pixels; According to the calculation results Judge the pixel points and obtain the actual location of the tumor area; According to the calculation results Determine the pixel points and obtain the actual location of the tumor area, including: Setting judgment thresholds ,when When , the pixel point is divided into the tumor area; Repeat the judgment until the calculated or , stop judging in this direction; The other directions are judged in turn until all directions are judged and the actual position of the tumor area is obtained.

2. A method for marking tumor boundaries of a digestive tract submucosal tumor according to claim 1, characterized in that: The performing of regional segmentation on the local CT image to obtain the segmented CT image, and performing feature analysis on different regions of the segmented CT image to obtain the region where the tumor is located, includes: The local CT image is segmented by using the threshold segmentation method; Based on the CT image after threshold segmentation, a coordinate system is constructed with the center of the image as the origin; Based on the constructed coordinate system, starting from the origin, the two sides of the X-axis are judged in sequence. Specifically, it is judged whether there are pixels with a gray value of 1 continuously distributed on both sides of the X-axis in the Y-axis direction; If it exists, the pixel point is regarded as the area where the tumor may exist on the CT image; If there are no continuous pixels with a grayscale value of 1 on both sides of the X-axis within the set threshold range, the judgment in the subsequent Y-axis direction will be stopped. Before stopping the judgment, the area that has been judged is the area where the tumor may exist.

3. The method for marking tumor boundaries of a digestive tract submucosal tumor according to claim 1, characterized in that: The pixel calculation is performed based on the region where the tumor is located, and the region where the tumor is located is divided into several sub-regions according to the pixel calculation results, including: Construct the gray value data sequence of the tumor area ,in Indicates the entire tumor area The gray value of a pixel, ; Calculate the Pixels and The probability that the pixels belong to the same area: ； ； Where, Indicates the The coordinates of the pixel points; Indicates the The coordinates of the centroid of the area where the pixel points are located; Indicates the The coordinates of the pixel point to the The distance from the centroid of the area where the pixel is located; Indicates the The average distance from the edge pixels to the centroid of the region where the pixel is located; Indicates the Pixels and The possibility that the pixels belong to the same area; Setting judgment thresholds ,when Less than threshold When Pixels and Pixels are divided into the same area; Repeat the above calculation to determine The other pixels in the eight neighborhoods of the pixel point and the The possibility that the pixels belong to the same area is calculated after the judgment is completed. The probability that a pixel point and its eight neighboring pixels belong to the same area is calculated until the eight neighboring pixels of the pixel point divided into an area and the surrounding pixels are calculated. When , the judgment of the current area is completed; Repeat the above determination method until the tumor area is divided into several sub-areas.

4. A method for marking tumor boundaries of a digestive tract submucosal tumor according to claim 3, characterized in that: The method of calculating the average gray value and the regional edge shape based on the plurality of sub-regions and obtaining the tumor region according to the calculation results includes: Based on several sub-regions, the The probability that a region belongs to the region where the tumor is located: ； ； Where, Indicates the The average gray value of the region; Indicates that except The average gray value of the remaining area of the region; Indicates the A data sequence constructed by the distance from the edge pixel of a region to the centroid of the region; Indicates in The average value of the difference between the distances of adjacent edge pixels in a region and the centroid of the region; Indicates the The shape of each area; Indicates the The probability that the region belongs to the tumor area; Based on the calculation results, select The corresponding area is used as the location of the tumor area in the CT image, and the tumor area is obtained.

5. The method for marking tumor boundaries of a digestive tract submucosal tumor according to claim 1, characterized in that: The obtaining of a local CT image comprises: Scan and obtain the patient's local chest CT image; The patient's local chest CT image is denoised and processed using a histogram equalization method to obtain a processed local CT image.

6. A tumor boundary marking system for digestive tract submucosal tumors, characterized in that: include: An image acquisition module, used for acquiring local CT images; A tumor region acquisition module is used to segment the local CT image, obtain the segmented CT image, perform feature analysis on different regions of the segmented CT image, and obtain the tumor region; The tumor region acquisition module is used to calculate pixels based on the tumor region, divide the tumor region into several sub-regions based on the pixel calculation results, calculate the average gray value and regional edge shape based on the several sub-regions, and obtain the tumor region based on the calculation results; A module for obtaining the actual position of the tumor region is used to perform boundary analysis on the tumor region and obtain the actual position of the tumor region; The tumor focus boundary acquisition module is used to mark the edge pixel points of the actual position of the tumor area and obtain the tumor focus boundary; The performing boundary analysis on the tumor region to obtain the actual position of the tumor region includes: Select the centroid position of the tumor area and extend it in all directions from the centroid position to obtain the The pixel gray value data sequence in each direction ; Calculate the tumor area The trend of wettability change in each direction: ； ； Where, Represents the weight value of the grayscale change of the j-th pixel in the v-th direction; Indicates the distance from the jth pixel to the centroid in the vth direction; Indicates the shortest distance from the jth pixel point to the boundary of other regions in the vth direction; Indicates the number of pixels in the vth direction; The tumor area The trend of infiltration in different directions; Select the pixel point that is adjacent to the edge pixel point of the tumor area in the vth direction and analyze the possibility that the pixel point belongs to the tumor area: ； Where, Indicates the grayscale difference between the edge pixel and the adjacent pixel in the vth direction; It represents the difference between the gray value of the edge pixel in the vth direction and the adjacent pixel in its original area and the average value of the five consecutive adjacent pixels; According to the calculation results Judge the pixel points and obtain the actual location of the tumor area; According to the calculation results Determine the pixel points and obtain the actual location of the tumor area, including: Setting judgment thresholds ,when When , the pixel point is divided into the tumor area; Repeat the judgment until the calculated or , stop judging in this direction; The other directions are judged in turn until all directions are judged and the actual position of the tumor area is obtained.

7. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images