Automated watershed analysis system and method based on tumor location and safety distance

Abstract

The present invention belongs to the field of computer-aided medical technology, and specifically relates to an automated watershed analysis system and method based on tumor location and safety distance, the method comprising: constructing a 3D model based on acquired image data; the 3D model comprises an organ model, a pipeline model and a tumor model; taking the tumor model as the basic analysis object, the organ model as the boundary, and the pipeline in the organ as the constraint condition; obtaining a tumor safety distance cutting margin ball model based on the input target distance, and performing a logical intersection operation with the pipeline model to obtain simulated resected branches and remaining branches; performing a merging process to obtain a complete cutting pipeline branch; merging all cutting pipeline branches to obtain a total cutting pipeline branch model, combining the remaining cutting branches and the total cutting pipeline branch model, dividing the organ model to obtain a corresponding organ cutting 3D model. The present invention can realize the distance analysis and simulation requirements of quantitative safety cutting margins.

Description

Technical Field

[0001] The present invention relates to the field of computer-aided medical technology, and in particular to an automated watershed analysis system and method based on tumor location and safety distance. Background Art

[0002] At present, in the process of nodule surgery, it is not enough to just remove the nodule. We also need to ensure that there is normal tissue as a buffer around the removed nodule. This buffer area is the cutting edge. The closest distance between the nodule and the boundary of the removed tissue is the cutting edge.

[0003] Adequate margins are the basis for tumor recurrence, but the more you remove, the less tissue is left. Surgeons always strike a balance between adequate margins and retaining as much tissue as possible. The mastery of this balance depends on the surgeon's clinical experience and surgical skills in judging nodules; more importantly, it depends on the quantitative analysis and planning simulation of individualized clinical data and the analysis and summary of large sample data. It is precisely with the support of a large amount of evidence-based medical data that the resection of lung nodules has developed into three main forms: wedge resection, segment resection and lobectomy; the resection of liver tumors has also developed into a precise liver segment-guided resection method. The simulation analysis of tumor safe margins by 3D visualization technology is of great significance and value for preoperative surgical evaluation and planning.

[0004] The distance of the resection margin cannot be evaluated in 3D through preoperative CT images. The only way to measure it is for the surgeon to measure it after the specimen is removed. The tumor diameter can also be measured. Studies have shown that the reconstructed images of liver cancer or lung nodule resection volume and resection margins are accurate, clear, and intuitive when 3D visualization technology is used preoperatively. The simulation results are not much different from the actual results. Before liver cancer resection, the tumor location, the adjacent relationship between the tumor and the surrounding area, and the course of the hepatobiliary duct can be accurately understood, which plays a certain auxiliary role in formulating surgical plans and reducing postoperative complications.

[0005] In a large number of clinical application studies, individualized segmented anatomical structure analysis of different organs (liver, kidney, lung lobe, etc.) has been relatively mature before surgical operations are performed on different organs. However, there is no relatively mature program for safe resection margin assessment and simulation of liver or lung tumors. Whether radical resection has been achieved is diagnosed through postoperative pathological sections.

[0006] In terms of tumor positioning and safe resection margin research, research on tumors of different organs has been ongoing, and corresponding solutions have been proposed from different angles, such as "Method, device, storage medium and electronic equipment for identifying the location of lesion lung segments" (application number: CN202111494117.6), "Segmentation method based on pulmonary bronchial tree and method for locating lesions" (application number: CN202211190905.0), "CT image target lung segment identification method based on pulmonary artery tree grading" (application number: CN202111636037.X), "A method, system and storage medium for generating resection margin path for tumor surgery" (application number: CN202210389690.9), "A system for quantitative determination of intraoperative tumor resection based on image processing" (application number: CN202211455696.8). None of these existing technical solutions solves the quantitative analysis simulation method mentioned in the surgical guidelines for hepatobiliary and thoracic tumors, which requires a safe resection margin of 1 cm or 2 cm. They basically identify the corresponding target segment or area based on segmentation, or determine the range based on the surface fluorescence characteristics in actual clinical surgery, and cannot quantify the safe resection margin distance clearly desired in the guidelines. Some of the work is based on deep learning solutions, which are unexplainable, especially if there are variations in the patient's blood vessels, the individualized liver segmentation may be 7 or 9 segments. If there are variations in the bronchi, the division of the lung segments is not the standard 18 segments, so there is a certain degree of uncertainty. Summary of the invention

[0007] In view of the technical defects mentioned in the background technology, the purpose of the embodiments of the present invention is to provide an automated watershed analysis system and method based on tumor location and safety distance, so as to realize the analysis and simulation of the safe resection margin of tumors in individualized organs.

[0008] To achieve the above objectives, in a first aspect, an embodiment of the present invention provides an automated watershed analysis system based on tumor location and safety distance, the system comprising:

[0009] A reconstruction module, used for performing three-dimensional reconstruction based on the acquired image data to construct a 3D model; wherein the 3D model includes an organ model, a duct model and a tumor model;

[0010] A setting module for analyzing an object based on the tumor model, using the organ model as a boundary, and using the pipes in the organ as constraints;

[0011] A processing module, configured to, based on an input target distance of a safe resection margin, take the tumor model as an initial model, perform isometric expansion on the tumor model according to the target distance, and obtain an initial tumor safety distance model;

[0012] Compute module for:

[0013] Performing a logical intersection operation on the initial tumor safety distance model and the organ model to obtain a tumor safety distance resection margin sphere model inside the solid organ;

[0014] Performing a logical intersection operation on the tumor safety distance cutting margin sphere model and the tube model to obtain the branches to be simulated and the branches remaining after cutting, and recording the remaining branches as TubeR;

[0015] Merging the branch to be simulated and removed with the terminal branch in TubeR to obtain a complete cut pipeline branch;

[0016] Merging all obtained cutting pipeline branches to obtain a total cutting pipeline branch model;

[0017] A simulation module is used to perform Voronoi modeling on the organ model by taking the organ model as the boundary and combining the remaining branches of the cutting and the total cutting pipeline branch model. Figure 3 D division is performed to obtain the organ cutting 3D model corresponding to the cutting pipeline branch, which is used as the simulated resection range of the analyzed organ.

[0018] As a specific implementation of the present application, the image data includes thin-layer CT image DICOM data, which is imported into 3D software for three-dimensional reconstruction.

[0019] As a specific implementation method of the present application, the logical intersection operation of the tumor safety distance cutting margin sphere model and the pipeline model specifically includes: calculating whether all the 3D surface space points on the pipeline model are inside the tumor safety distance cutting margin sphere model; if the point on the pipeline branch is inside the tumor safety distance cutting margin sphere model, it means that the branch is within the safety cutting margin distance and it is necessary to simulate the resection of the branch.

[0020] As a specific implementation of the present application, the branches that need to be simulated and removed are recorded in a marking manner, and different branches are identified by different index values.

[0021] As a specific implementation of the present application, the branch to be simulated cut and the terminal branch in TubeR are merged to obtain a complete cut pipeline branch, and the processing is performed according to the following steps:

[0022] a. Calculate the connectivity of the models in TubeR, count the total number of independent 3D models, find the sub-model with the largest number of vertices, separate the sub-model with the largest number of vertices from other independent 3D models, and the generated sub-model with the largest number of vertices is the main trunk model after cutting, and the remaining 3D models are the remaining terminal branches after cutting;

[0023] b. For each independent model in the trimmed remaining terminal branch obtained in step a, determine whether it is adjacent to the trimmed branch within the cutting edge sphere. If it is adjacent, merge it into the corresponding trimmed branch within the cutting edge sphere and delete it from the trimmed remaining terminal branch;

[0024] c. After step b is completed, the cut pipeline branch includes the cut portion inside the cutting edge ball and the scattered portion of the branch separated by the cutting edge ball, thereby obtaining a complete cut pipeline branch.

[0025] In a second aspect, an embodiment of the present invention further provides an automated watershed analysis method based on tumor location and safety distance, which is applied to the automated watershed analysis system based on tumor location and safety distance described in the first aspect, and the method comprises the following steps:

[0026] Performing three-dimensional reconstruction based on the acquired image data to construct a 3D model; wherein the 3D model includes an organ model, a duct model and a tumor model;

[0027] The tumor model is used as a basic analysis object, the organ model is used as a boundary, and the pipeline in the organ is used as a constraint condition;

[0028] Based on the input target distance of the safe resection margin, the tumor model is used as the initial model, and the tumor model is expanded at equal distances according to the target distance to obtain an initial tumor safety distance model;

[0029] Performing a logical intersection operation on the initial tumor safety distance model and the organ model to obtain a tumor safety distance resection margin sphere model inside the solid organ;

[0030] Performing a logical intersection operation on the tumor safety distance cutting margin sphere model and the tube model to obtain the branches to be simulated and the branches remaining after cutting, and recording the remaining branches as TubeR;

[0031] Merging the branch to be simulated and removed with the terminal branch in TubeR to obtain a complete cut pipeline branch;

[0032] Merging all obtained cutting pipeline branches to obtain a total cutting pipeline branch model;

[0033] Taking the organ model as the boundary, combining the remaining branches of the cutting and the total cutting pipeline branch model, the organ model is subjected to Voronoi Figure 3 D division is performed to obtain the organ cutting 3D model corresponding to the cutting pipeline branch, which is used as the simulated resection range of the analyzed organ.

[0034] The technical solution provided by the embodiment of the present invention establishes a method for importing CT data, performing three-dimensional reconstruction of organs, corresponding tubular tissues and tumors to obtain a 3D model, taking the tumor model as the basic analysis object, the organ model as the boundary, and the pipes in the organ as the constraint condition, and according to the input safety margin distance, calculating, analyzing and simulating the safe margin of the tumor in a 3D mode, thereby realizing the simulation requirements of quantitative safety margin distance analysis and automatic watershed analysis required in precise surgical resection. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the specific implementation of the present invention or the technical solution in the prior art, the drawings required for use in the specific implementation or the description of the prior art are briefly introduced below.

[0036] Figure 1 It is a principle block diagram of an automated watershed analysis system based on tumor location and safety distance provided by an embodiment of the present invention;

[0037] Figure 2 is a display schematic diagram of a three-dimensional reconstruction of the lungs provided by an embodiment of the present invention;

[0038] Figure 3 It is a display schematic diagram of a tumor safety distance resection margin sphere model provided by an embodiment of the present invention;

[0039] Figure 4 This is a schematic diagram of a branch to be simulated and removed provided by an embodiment of the present invention;

[0040] Figure 5 It is a schematic diagram of cutting off the remaining branches provided by an embodiment of the present invention;

[0041] Figure 6 This is a flow chart of an automated watershed analysis method based on tumor location and safety distance provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0044] Please refer to Figure 1 , an embodiment of the present invention provides an automated watershed analysis system based on tumor location and safety distance, the system comprising:

[0045] A reconstruction module, used for performing three-dimensional reconstruction based on the acquired image data to construct a 3D model; wherein the 3D model includes an organ model, a duct model and a tumor model;

[0046] A setting module for analyzing an object based on the tumor model, using the organ model as a boundary, and using the pipes in the organ as constraints;

[0047] A processing module, configured to, based on an input target distance of a safe resection margin, take the tumor model as an initial model, perform isometric expansion on the tumor model according to the target distance, and obtain an initial tumor safety distance model;

[0048] Compute module for:

[0049] Performing a logical intersection operation on the initial tumor safety distance model and the organ model to obtain a tumor safety distance resection margin sphere model inside the solid organ;

[0050] Performing a logical intersection operation on the tumor safety distance cutting margin sphere model and the tube model to obtain the branches to be simulated and the branches remaining after cutting, and recording the remaining branches as TubeR;

[0051] Merging the branch to be simulated and removed with the terminal branch in TubeR to obtain a complete cut pipeline branch;

[0052] Merging all obtained cutting pipeline branches to obtain a total cutting pipeline branch model;

[0053] A simulation module is used to perform Voronoi modeling on the organ model by taking the organ model as the boundary and combining the remaining branches of the cutting and the total cutting pipeline branch model. Figure 3 D division is performed to obtain the organ cutting 3D model corresponding to the cutting pipeline branch, which is used as the simulated resection range of the analyzed organ.

[0054] It should be noted that the present invention is based on some basic and classic processing methods in medical image processing and 3D visualization methods to obtain the basic model required for safe resection margin simulation, and then proceed step by step according to the above scheme, so as to realize the calculation and simulation of safe resection margin of tumors in individualized organs; at the same time, a one-stop processing of visualization rendering is also performed; taking the right upper lobe segmentation as an example, the scheme is described as follows:

[0055] 3D model data preparation. The image data includes thin-layer CT image DICOM data, which is imported into 3D software for 3D reconstruction; by importing 3DVWorks software, 3D models of the left and right lungs, bronchi, pulmonary arteries and pulmonary nodules are reconstructed, such as Figure 2 shown.

[0056] In this embodiment, in order to facilitate the description of the accompanying drawings, the organ model to be analyzed is recorded as Organ; the bronchus or blood vessel is taken as the pipeline target object (the portal vein model is selected in the liver organ, the bronchus or artery is selected in the lung organ, and the artery is selected in the kidney organ), recorded as Tube, and the pipeline model is represented by Tube; the tumor or nodule that needs to be simulated and removed is selected as the analysis object, recorded as Tumor, and the tumor model is represented by Tumor.

[0057] Then input the target distance of the safe resection margin through the input box. For example, input 1cm for tumors in the liver and kidneys, and 2cm for nodules in the lungs. Take the Tumor model as the initial model, and expand the tumor model at equal distances according to the set target distance to obtain the initial tumor safe distance model, recorded as TumorE; perform a logical intersection operation on TumorE and Organ to obtain the tumor safe distance resection margin sphere model inside the solid organ, recorded as TumorT; Figure 3 shown.

[0058] Furthermore, a logical intersection operation is performed on the tumor safety distance cutting margin sphere model and the pipeline model, specifically including: calculating whether all 3D surface space points on the pipeline model are inside the tumor safety distance cutting margin sphere model; if the point on the pipeline branch is inside the tumor safety distance cutting margin sphere model, it means that the branch is within the safety cutting margin distance and it is necessary to simulate the resection of the branch.

[0059] When applied, the branches that need to be simulated resected are recorded by marking, and different branches are identified by different index values; the branches to be simulated resected include branches within the cutting edge ball model.

[0060] Specifically, the branch points to be cut are recorded by marking CutT, and different branches are identified by index values ​​n respectively; Figure 4, calculate that two branches need to be cut off, and record them as CutT1 and CutT2 respectively. The remaining part of Tube after cutting is recorded as TubeR.

[0061] Since the cutting of the cutting edge ball will result in small branches at the end outside the safe cutting edge, it is necessary to find the branches adjacent to the CutTn (n is the index value) model in the previous step and merge them to obtain the complete branches to be removed; that is, merge the branches within the cutting edge ball model and the terminal branches in the remaining branches.

[0062] The branch to be simulated and removed is merged with the terminal branch in TubeR to obtain a complete cut pipeline branch. The processing is performed according to the following steps:

[0063] a. Calculate the connectivity of the models in TubeR, count the total number of independent 3D models, find the sub-model with the largest number of vertices, separate the sub-model with the largest number of vertices from other independent 3D models, and the generated sub-model with the largest number of vertices is the main trunk model after cutting, and the remaining 3D models are the remaining terminal branches after cutting;

[0064] b. For each independent model in the trimmed remaining terminal branch obtained in step a, determine whether it is adjacent to the trimmed branch within the cutting edge sphere. If it is adjacent, merge it into the corresponding trimmed branch within the cutting edge sphere and delete it from the trimmed remaining terminal branch;

[0065] c. After step b is completed, the cut pipeline branch includes the cut portion inside the cutting edge ball and the scattered portion of the branch separated by the cutting edge ball, thereby obtaining a complete cut pipeline branch.

[0066] In this embodiment, the simulation module, when implemented, takes the organ model as the boundary, intersects with the cut trunk model and the total cut pipeline branch model respectively, obtains the vertex set of the trunk model and the total cut pipeline branch model inside the organ model, takes the point set of the trunk model in the organ model and the point set of the total cut pipeline branch model in the organ model as the focus of retention and removal, respectively, and performs Voronoi simulation on the organ model. Figure 3 D division, the organ cutting 3D model corresponding to the cutting pipeline branch is obtained, which is used as the simulated resection range of the analyzed organ, and the complete pipeline structure is also retained in the remaining organ; it should be noted that Voronoi Figure 3 D division is an application of the prior art, and related content can be found in CN114648525A.

[0067] This enables:

[0068] 1. This patent proposes a calculation method for simulating tumor safe resection margins based on 3D visualization, which can solve the problem that safe resection margins cannot be quantitatively analyzed in 2D CT images, and has important guiding significance for the formulation of surgical plans;

[0069] 2. The safe margin simulation calculation method proposed in this patent can adapt to the safe margin calculation operations of the lung, liver, kidney, etc. based on different pipeline branches, and can set the safe distance value according to the actual clinical guidelines and the actual location of the tumor, so as to achieve one-stop processing of multiple parts without the need for multiple software and methods, and has high applicability and versatility;

[0070] 3. The results of this patent can be marked and rendered through 3D visualized results, and can be observed in different directions and angles through operations such as rotation, scaling, and transparency. The simulation calculation results of individual cases can be intuitively evaluated and observed, solving the needs of quantitative simulation analysis in actual clinical analysis;

[0071] 4. The 3D simulation of tumor safety margin analysis simulation process can set different parameters according to different situations and simulate operations repeatedly to meet the actual needs of comparative analysis and surgical procedure selection.

[0072] 5. The simulated safety margin analysis results can be reproduced and saved, which can provide 3D model basic data for teaching and subsequent large-sample scientific research, provide three-dimensional data and parameters for teaching and scientific research, and provide a better data foundation.

[0073] The above scheme establishes a method to import CT image data, reconstruct the organs, corresponding tubular tissues and tumors in three dimensions to obtain a 3D model, uses the tumor model as the basic analysis object, the organ model as the boundary, and the tubes in the organ as constraints, and calculates, analyzes and simulates the safe cutting margin of the tumor in a 3D mode according to the input safe cutting margin distance, thereby realizing the distance analysis and simulation requirements of the quantitative safe cutting margin in precise surgical resection.

[0074] Based on the same inventive concept, an embodiment of the present invention further provides an automated watershed analysis method based on tumor location and safety distance, which is applied to the automated watershed analysis system based on tumor location and safety distance described in the first aspect, and the method comprises the following steps:

[0075] S101, performing three-dimensional reconstruction based on the acquired image data to construct a 3D model; wherein the 3D model includes an organ model, a duct model and a tumor model;

[0076] S102, analyzing an object based on the tumor model, using the organ model as a boundary, and using the pipes in the organ as constraints;

[0077] S103, based on the input target distance of the safe resection margin, taking the tumor model as the initial model, performing isometric expansion on the tumor model according to the target distance to obtain an initial tumor safety distance model;

[0078] S104, performing a logical intersection operation on the initial tumor safety distance model and the organ model to obtain a tumor safety distance resection margin sphere model inside the solid organ;

[0079] S105, performing a logical intersection operation on the tumor safety distance cutting margin sphere model and the tube model to obtain the branches to be simulated and the branches remaining after cutting, and recording the remaining branches as TubeR;

[0080] S106, merging the branch to be simulated cut and the terminal branch in TubeR to obtain a complete cut pipeline branch;

[0081] S107, merging all obtained cutting pipeline branches to obtain a total cutting pipeline branch model;

[0082] S108, taking the organ model as the boundary, combining the remaining branches from the cutting and the total cutting pipeline branch model, and performing Voronoi analysis on the organ model. Figure 3 D division is performed to obtain the organ cutting 3D model corresponding to the cutting pipeline branch, which is used as the simulated resection range of the analyzed organ.

[0083] Furthermore, the logical intersection operation of the tumor safety distance cutting margin sphere model and the pipeline model specifically includes: calculating whether all 3D surface space points on the pipeline model are inside the tumor safety distance cutting margin sphere model; if the point on the pipeline branch is inside the tumor safety distance cutting margin sphere model, it means that the branch is within the safety cutting margin distance and it is necessary to simulate the resection of the branch.

[0084] The branches that need to be simulated and removed are recorded by marking, and different branches are identified by different index values.

[0085] In this embodiment, the branch to be simulated cut and the terminal branch in TubeR are merged to obtain a complete cut pipeline branch, and the processing is performed according to the following steps:

[0086] a. Calculate the connectivity of the models in TubeR, count the total number of independent 3D models, find the sub-model with the largest number of vertices, separate the sub-model with the largest number of vertices from other independent 3D models, and the generated sub-model with the largest number of vertices is the main trunk model after cutting, and the remaining 3D models are the remaining terminal branches after cutting;

[0087] b. For each independent model in the trimmed remaining terminal branch obtained in step a, determine whether it is adjacent to the trimmed branch within the cutting edge sphere. If it is adjacent, merge it into the corresponding trimmed branch within the cutting edge sphere and delete it from the trimmed remaining terminal branch;

[0088] c. After step b is completed, the cut pipeline branch includes the cut portion inside the cutting edge ball and the scattered portion of the branch separated by the cutting edge ball, thereby obtaining a complete cut pipeline branch.

[0089] Merge all obtained cut pipe branches into a 3D model to obtain the total cut pipe branch model, denoted as TubeCut;

[0090] Then, the organ model is used as the boundary to intersect with the cut trunk model and the total cut pipeline branch model, respectively, to obtain the vertex set of the trunk model and the total cut pipeline branch model inside the organ model, and the point set of the trunk model in the organ model and the total cut pipeline branch model in the organ model are used as the focus of retention and removal, respectively, to perform Voronoi on the organ model. Figure 3 D division is performed to obtain the organ cutting 3D model corresponding to the cutting pipeline branch, which is the simulated resection range of the organ, and the complete pipeline structure is retained in the remaining organ.

[0091] It should be noted that for a more specific description of the workflow of the method embodiment, please refer to the aforementioned system embodiment part, which will not be repeated here.

[0092] The entire solution is to import CT data, reconstruct the organs, corresponding tubular tissues and tumors in three dimensions to obtain a 3D model, use the tumor model as the basic analysis object, the organ model as the boundary, and the tubes in the organ as constraints. According to the input safety margin distance, the safe margin of the tumor is calculated, analyzed and simulated in 3D mode, thereby realizing the distance analysis and simulation requirements of quantified safety margins in precise surgical resection.

[0093] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. An automated watershed analysis system based on tumor location and safety distance, characterized in that: The system comprises: A reconstruction module, used for performing three-dimensional reconstruction based on the acquired image data to construct a 3D model; wherein the 3D model includes an organ model, a duct model and a tumor model; A setting module for analyzing an object based on the tumor model, using the organ model as a boundary, and using the pipes in the organ as constraints; A processing module, configured to, based on an input target distance of a safe resection margin, take the tumor model as an initial model, perform isometric expansion on the tumor model according to the target distance, and obtain an initial tumor safety distance model; Compute module for: Performing a logical intersection operation on the initial tumor safety distance model and the organ model to obtain a tumor safety distance resection margin sphere model inside the solid organ; Performing a logical intersection operation on the tumor safety distance cutting margin sphere model and the tube model to obtain the branches to be simulated and the branches remaining after cutting, and recording the remaining branches as TubeR; Merging the branch to be simulated and removed with the terminal branch in TubeR to obtain a complete cut pipeline branch; Merging all obtained cutting pipeline branches to obtain a total cutting pipeline branch model; The simulation module is used to perform Voronoi diagram 3D division on the organ model with the organ model as the boundary, in combination with the remaining branches of the cutting and the total cutting pipeline branch model, to obtain the organ cutting 3D model corresponding to the cutting pipeline branch, and use it as the analyzed organ simulation resection range.

2. The system according to claim 1, characterized in that The image data includes thin-layer CT image DICOM data, which is imported into 3D software for three-dimensional reconstruction.

3. The system according to claim 2, characterized in that The logical intersection operation of the tumor safety distance cutting margin sphere model and the pipeline model specifically includes: calculating whether all 3D surface space points on the pipeline model are inside the tumor safety distance cutting margin sphere model; if the points on the pipeline branch are inside the tumor safety distance cutting margin sphere model, it means that the branch is within the safety cutting margin distance and it is necessary to simulate the resection of the branch.

4. The system according to claim 3, characterized in that The branches that need to be simulated and removed are recorded by marking, and different branches are identified by different index values.

5. The system according to claim 3, characterized in that The branch to be simulated and removed is merged with the terminal branch in TubeR to obtain a complete cut pipeline branch. The processing is performed according to the following steps: a. Calculate the connectivity of the models in TubeR, count the total number of independent 3D models, find the sub-model with the largest number of vertices, separate the sub-model with the largest number of vertices from other independent 3D models, and the generated sub-model with the largest number of vertices is the main trunk model after cutting, and the remaining 3D models are the remaining terminal branches after cutting; b. For each independent model in the trimmed remaining terminal branch obtained in step a, determine whether it is adjacent to the trimmed branch within the cutting edge sphere. If it is adjacent, merge it into the corresponding trimmed branch within the cutting edge sphere and delete it from the trimmed remaining terminal branch; c. After step b is completed, the cut pipeline branch includes the cut portion inside the cutting edge ball and the scattered portion of the branch separated by the cutting edge ball, thereby obtaining a complete cut pipeline branch.

6. An automated watershed analysis method based on tumor location and safety distance, characterized in that: The method for the automated watershed analysis system based on tumor location and safety distance as claimed in claim 1 comprises the following steps: Performing three-dimensional reconstruction based on the acquired image data to construct a 3D model; wherein the 3D model includes an organ model, a duct model and a tumor model; The tumor model is used as a basic analysis object, the organ model is used as a boundary, and the pipeline in the organ is used as a constraint condition; Based on the input target distance of the safe resection margin, the tumor model is used as the initial model, and the tumor model is expanded at equal distances according to the target distance to obtain an initial tumor safety distance model; Performing a logical intersection operation on the initial tumor safety distance model and the organ model to obtain a tumor safety distance resection margin sphere model inside the solid organ; Performing a logical intersection operation on the tumor safety distance cutting margin sphere model and the tube model to obtain the branches to be simulated and the branches remaining after cutting, and recording the remaining branches as TubeR; Merging the branch to be simulated and removed with the terminal branch in TubeR to obtain a complete cut pipeline branch; Merging all obtained cutting pipeline branches to obtain a total cutting pipeline branch model; Taking the organ model as the boundary, combining the remaining branches of the cutting and the total cutting pipeline branch model, the organ model is divided into 3D Voronoi diagrams to obtain the organ cutting 3D model corresponding to the cutting pipeline branch, which is used as the analyzed organ simulation resection range.

7. The method according to claim 6, characterized in that The logical intersection operation of the tumor safety distance cutting margin sphere model and the pipeline model specifically includes: calculating whether all 3D surface space points on the pipeline model are inside the tumor safety distance cutting margin sphere model; if the points on the pipeline branch are inside the tumor safety distance cutting margin sphere model, it means that the branch is within the safety cutting margin distance and it is necessary to simulate the resection of the branch.

8. The method according to claim 7, characterized in that The branches that need to be simulated and removed are recorded by marking, and different branches are identified by different index values.

9. The method according to any one of claims 6 to 8, characterized in that The branch to be simulated and removed is merged with the terminal branch in TubeR to obtain a complete cut pipeline branch. The processing is performed according to the following steps: a. Calculate the connectivity of the models in TubeR, count the total number of independent 3D models, find the sub-model with the largest number of vertices, separate the sub-model with the largest number of vertices from other independent 3D models, and the generated sub-model with the largest number of vertices is the main trunk model after cutting, and the remaining 3D models are the remaining terminal branches after cutting; b. For each independent model in the trimmed remaining terminal branch obtained in step a, determine whether it is adjacent to the trimmed branch within the cutting edge sphere. If it is adjacent, merge it into the corresponding trimmed branch within the cutting edge sphere and delete it from the trimmed remaining terminal branch; c. After step b is completed, the cut pipeline branch includes the cut portion inside the cutting edge ball and the scattered portion of the branch separated by the cutting edge ball, thereby obtaining a complete cut pipeline branch.

Images