A method and system for three-dimensional model reconstruction and visualization of pancreatic lesions

Abstract

The present invention relates to a three-dimensional model reconstruction and visualization method and system for pancreatic lesions, including layered collection of abdominal enhanced grayscale image data from CT data information of a target object and noise reduction and smoothing optimization processing to obtain the boundaries of each layer of pancreatic necrotic tissue, effusion and pancreas and their corresponding adjacent organs; outline the boundary contours of each layer of pancreatic necrotic tissue, effusion and pancreas, and calculate the three-dimensional data information of the pancreatic necrotic tissue, effusion and pancreas; repeat the above steps for the organs adjacent to the area where the pancreatic necrotic tissue, effusion and pancreas are located, and obtain the three-dimensional data information of the corresponding adjacent organs; reconstruct the three-dimensional model of the pancreatic necrotic tissue, effusion and pancreas of the target object and their corresponding adjacent organs and visualize them. By restoring the three-dimensional model of the pancreatic necrotic tissue, effusion and pancreas and their corresponding adjacent organs, accurate judgments can be made during surgery, which is convenient for medical staff to perform precise and individualized treatment.

Description

Technical Field

[0001] The present invention relates to the field of medical technology, and in particular to a method and system for three-dimensional model reconstruction and visualization of pancreatic lesions. Background Art

[0002] In order to understand the patient's condition more accurately, medical imaging equipment is usually used to obtain the patient's two-dimensional tomographic image information, but this method is not conducive to clearly observing the complete lesion information of a certain organ and the relative position between different organs, and cannot meet the requirements of accurate and individualized analysis of lesions. In clinical practice, when lesions occur in the abdominal organs of the human body, it often involves the interrelationship between multiple organs, especially pancreatic lesions. The anatomical location of the pancreas is deep, and necrotizing pancreatitis will produce more necrotic effusions, which is quite unfavorable for accurate understanding of the condition. In actual clinical applications, a common method is to perform abdominal enhanced CT examinations on patients, and radiologists will give examination reports after reading the films, which depends entirely on the doctor's professional knowledge and experience. Clinicians only obtain limited information through reports or reading the films themselves, which leads to the inability of clinicians to accurately judge the overall situation of the lesions, and it is not convenient for doctors to perform precise and individualized treatment for different lesions. Clinicians rely on their own clinical experience and the three-dimensional images subjectively constructed by the brain to easily have cognitive biases in the patient's condition, resulting in misjudgment of the patient's condition. In addition, due to the complex anatomical structure of the pancreas, the long-term corrosion and destruction of necrotic substances in pancreatic infection have changed the original normal anatomical structure of the pancreas and its surroundings. The necrotic material during surgery seriously affects the exposure of the surgical field, making it difficult for clinicians to correctly choose the surgical method and plan the surgical path, which will increase the incidence of complications related to pancreatic necrotic tissue removal surgery. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a method and system for three-dimensional model reconstruction and visualization of pancreatic lesions in view of the deficiencies of the above-mentioned prior art.

[0004] The technical solution of the present invention to solve the above technical problem is as follows: A three-dimensional model reconstruction and visualization method for pancreatic lesions comprises the following steps:

[0005] S1: collecting abdominal enhanced grayscale image data in layers from the CT data information of the target object according to the preset layer thickness;

[0006] S2: using a fuzzy filtering algorithm to perform noise reduction, smoothing and optimization processing on each layer of the abdominal enhanced grayscale image data, so as to obtain the boundaries of each layer of pancreatic necrotic tissue, effusion and pancreas and its corresponding adjacent organs;

[0007] S3: outlining the boundary contours of each layer of pancreatic necrotic tissue, effusion and pancreas respectively, and calculating the three-dimensional data information of the pancreatic necrotic tissue, effusion and pancreas according to the boundary contours of the pancreatic necrotic tissue, effusion and pancreas;

[0008] S4: repeating S2 and S3 for the organs adjacent to the pancreatic necrotic tissue, effusion and the area where the pancreas is located, respectively, to obtain three-dimensional data information of the organs adjacent to the pancreatic necrotic tissue, effusion and the pancreas;

[0009] S5: Reconstruct a three-dimensional model of the pancreatic necrotic tissue, effusion and pancreas and their corresponding adjacent organs of the target object according to the three-dimensional data information of the pancreatic necrotic tissue, effusion and pancreas and their corresponding adjacent organs, and perform visual display.

[0010] The beneficial effects of the present invention are as follows: the three-dimensional model reconstruction and visualization method for pancreatic lesions of the present invention performs layered sampling on CT data, and combines a fuzzy filtering algorithm to perform noise reduction, smoothing and optimization processing on each layer of abdominal enhanced grayscale image data, thereby obtaining the boundaries of each layer of pancreatic necrotic tissue, effusion and pancreas and their corresponding adjacent organs, and then delineates the boundaries of each layer of pancreatic necrotic tissue, effusion and pancreas, and calculates and obtains the three-dimensional data information of each layer of pancreatic necrotic tissue, effusion and pancreas, and the three-dimensional data information of the adjacent organs can be obtained in the same way, and finally the three-dimensional model of the pancreatic necrotic tissue, effusion and pancreas and their corresponding adjacent organs is obtained through the three-dimensional data information restoration, thereby being able to clearly and accurately restore the pancreatic lesions, and facilitating the precise and individualized treatment of medical staff.

[0011] On the basis of the above technical solution, the present invention can also be improved as follows:

[0012] Further: In S2, the fuzzy filtering algorithm is used to perform noise reduction, smoothing and optimization processing on each layer of the abdominal enhanced grayscale image data, which specifically includes the following steps:

[0013] Creating a blank mask, extracting and processing each layer of the abdominal enhanced grayscale image data using a threshold segmentation method, and obtaining image pixels of organ tissues corresponding to different threshold ranges;

[0014] The region growing method is used to enhance the image pixels with similar regional types corresponding to each layer of pancreatic necrotic tissue, effusion and pancreas, and obtain the heat map of each layer of pancreatic necrotic tissue, effusion and pancreas;

[0015] The boundaries of each layer of pancreatic necrotic tissue, effusion and pancreas and their adjacent organs were determined based on the heat map of each layer of pancreatic necrotic tissue, effusion and pancreas.

[0016] The beneficial effect of the above further scheme is that: the enhanced grayscale image data of each layer of the abdomen can be extracted by the threshold segmentation method, and the pixels within the set threshold range can be extracted, so that the image pixels of the corresponding organ tissue can be obtained, and the image pixels of the similar regional types corresponding to each layer of pancreatic necrotic tissue, effusion and pancreas are enhanced by the region growing method, so that the image pixels of the pancreatic necrotic tissue, effusion and pancreas and the adjacent organs are more obviously distinguished, so that each layer of pancreatic necrotic tissue, effusion and pancreas can be easily separated from the boundaries of the adjacent organs, thereby facilitating the subsequent calculation to obtain the three-dimensional data information of the pancreatic necrotic tissue, effusion and the organs adjacent to the pancreas.

[0017] Further: In S3, outlining the border contours of each layer of pancreatic necrotic tissue, effusion and pancreas specifically includes the following steps:

[0018] The preset grayscale values ​​of normal tissues and organs are compared with the grayscale values ​​of each layer of pancreatic necrotic tissue, effusion and pancreas, and the boundary contours of pancreatic necrotic tissue and effusion are outlined according to the comparison results;

[0019] The border outline of the pancreas was determined based on the border outlines of pancreatic necrotic tissue and effusion.

[0020] The beneficial effect of the above further scheme is: by comparing the grayscale values ​​of the image pixels corresponding to each layer of pancreatic necrotic tissue, effusion and pancreas with the preset grayscale values ​​of normal tissue organs, the boundary contours of the pancreatic necrotic tissue and effusion can be determined, and then combined with the boundaries of each layer of pancreatic necrotic tissue, effusion and pancreas and their corresponding adjacent organs obtained previously, the boundary contour of the pancreas can be obtained.

[0021] Further: the three-dimensional model reconstruction and visualization method for pancreatic lesions also includes the following steps:

[0022] S6: performing triangular facet optimization processing on the three-dimensional model of the pancreatic necrotic tissue, effusion, pancreas and its corresponding adjacent organs, removing the nail-like objects on the surface, obtaining an optimized three-dimensional model of the pancreatic necrotic tissue, effusion, pancreas and its corresponding adjacent organs, and exporting and saving it.

[0023] The beneficial effect of the above further solution is that by performing triangular facet optimization processing on the three-dimensional model of the pancreatic necrotic tissue, effusion and pancreas and its corresponding adjacent organs, the nail-like objects on the surface can be removed and the smoothness of the model surface can be improved.

[0024] The present invention also provides a three-dimensional model reconstruction and visualization system for pancreatic lesions, comprising an acquisition module, a preprocessing module, a delineation calculation module and a reconstruction module;

[0025] The acquisition module is used to acquire abdominal enhanced grayscale image data in layers from the CT data information of the target object according to a preset layer thickness;

[0026] The preprocessing module is used to perform noise reduction, smoothing and optimization processing on each layer of the abdominal enhanced grayscale image data using a fuzzy filtering algorithm to obtain the boundaries of each layer of pancreatic necrotic tissue, effusion and pancreas and corresponding adjacent organs;

[0027] The delineation calculation module is used to delineate the border contours of each layer of pancreatic necrotic tissue, effusion and pancreas respectively, and calculate the three-dimensional data information of the pancreatic necrotic tissue, effusion and pancreas according to the border contours of the pancreatic necrotic tissue, effusion and pancreas;

[0028] The preprocessing module is further used to perform noise reduction, smoothing and optimization processing on each layer of the abdominal enhanced grayscale image data using a fuzzy filtering algorithm to obtain the boundaries of organs adjacent to the pancreatic necrotic tissue, effusion and the area where the pancreas is located;

[0029] The delineation calculation module is further used to respectively delineate the boundary contours of each layer of organs adjacent to the pancreatic necrotic tissue, effusion and the region where the pancreas is located, and calculate the three-dimensional data information of the organs adjacent to the pancreatic necrotic tissue, effusion and the region where the pancreas is located based on the boundary contours of the organs adjacent to the pancreatic necrotic tissue, effusion and the region where the pancreas is located;

[0030] The reconstruction module is used to reconstruct a three-dimensional model of the pancreatic necrotic tissue, effusion and pancreas and its corresponding adjacent organs of the target object based on the three-dimensional data information of the pancreatic necrotic tissue, effusion and pancreas and its corresponding adjacent organs, and perform visual display.

[0031] This three-dimensional model reconstruction and visualization system for pancreatic lesions performs layered sampling of CT data and combines fuzzy filtering algorithm to perform noise reduction, smoothing and optimization processing on each layer of abdominal enhanced grayscale image data, thereby obtaining the boundaries of each layer of pancreatic necrotic tissue, effusion and pancreas and their corresponding adjacent organs, and then outlines the boundaries of each layer of pancreatic necrotic tissue, effusion and pancreas, and calculates the three-dimensional data information of each layer of pancreatic necrotic tissue, effusion and pancreas. The three-dimensional data information of the adjacent organs can be obtained in the same way, and finally the three-dimensional model of the pancreatic necrotic tissue, effusion and pancreas and their corresponding adjacent organs is restored through the three-dimensional data information, so that the pancreatic lesions can be clearly and accurately restored, which is convenient for medical staff to perform precise and individualized treatment.

[0032] On the basis of the above technical solution, the present invention can also be improved as follows:

[0033] Further: the specific implementation of the pre-processing module using the fuzzy filtering algorithm to perform noise reduction, smoothing and optimization processing on each layer of the abdominal enhanced grayscale image data is as follows:

[0034] Creating a blank mask, extracting and processing each layer of the abdominal enhanced grayscale image data using a threshold segmentation method, and obtaining image pixels of organ tissues corresponding to different threshold ranges;

[0035] The region growing method is used to enhance the image pixels with similar regional types corresponding to each layer of pancreatic necrotic tissue, effusion and pancreas, and obtain the heat map of each layer of pancreatic necrotic tissue, effusion and pancreas;

[0036] The boundaries of each layer of pancreatic necrotic tissue, effusion, and the pancreas and its adjacent organs were determined based on the heat map of each layer of pancreatic necrotic tissue, effusion, and pancreas.

[0037] The beneficial effect of the above further scheme is that: the enhanced grayscale image data of each layer of the abdomen can be extracted by the threshold segmentation method, and the pixels within the set threshold range can be extracted, so that the image pixels of the corresponding organ tissue can be obtained, and the image pixels of the similar regional types corresponding to each layer of pancreatic necrotic tissue, effusion and pancreas are enhanced by the region growing method, so that the image pixels of the pancreatic necrotic tissue, effusion and pancreas and the adjacent organs are more obviously distinguished, so that each layer of pancreatic necrotic tissue, effusion and pancreas can be easily separated from the boundaries of the adjacent organs, thereby facilitating the subsequent calculation to obtain the three-dimensional data information of the pancreatic necrotic tissue, effusion and the organs adjacent to the pancreas.

[0038] Further: the delineation calculation module delineates each layer of pancreatic necrotic tissue, effusion and pancreatic boundary contour respectively, and the specific implementation is:

[0039] The preset grayscale values ​​of normal tissues and organs were compared with the grayscale values ​​of each layer of pancreatic necrotic tissue, effusion and pancreas, and the boundary contours of pancreatic necrotic tissue, effusion and pancreas were outlined based on the comparison results.

[0040] The beneficial effect of the above further scheme is: by comparing the grayscale values ​​of the image pixels corresponding to each layer of pancreatic necrotic tissue, effusion and pancreas with the preset grayscale values ​​of normal tissue organs, the boundary contours of the pancreatic necrotic tissue and effusion can be determined, and then combined with the boundaries of each layer of pancreatic necrotic tissue, effusion and pancreas and their corresponding adjacent organs obtained previously, the boundary contour of the pancreas can be obtained.

[0041] Further: The three-dimensional model reconstruction and visualization system for pancreatic lesions also includes an optimization module, which is used to perform triangular facet optimization processing on the three-dimensional model of the pancreatic necrotic tissue, effusion, pancreas and its corresponding adjacent organs, remove the nail-like objects on the surface, obtain the optimized three-dimensional model of the pancreatic necrotic tissue, effusion, pancreas and its corresponding adjacent organs, and export and save it.

[0042] The beneficial effect of the above further solution is that by performing triangular facet optimization processing on the three-dimensional model of the pancreatic necrotic tissue, effusion and pancreas and its corresponding adjacent organs, the nail-like objects on the surface can be removed and the smoothness of the model surface can be improved.

[0043] The present invention also provides a three-dimensional model reconstruction and visualization device for pancreatic lesions, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method when executing the computer program.

[0044] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described are implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A schematic diagram of a process for a three-dimensional model reconstruction and visualization method of a pancreatic lesion according to an embodiment of the present invention;

[0046] Figure 2 A schematic diagram of a layer of pancreatic necrotic tissue, effusion, and the boundaries of the pancreas and its corresponding adjacent organs according to an embodiment of the present invention;

[0047] Figure 3 A schematic diagram of outlining a certain layer of pancreatic necrotic tissue, effusion and the border contour of the pancreas according to an embodiment of the present invention;

[0048] Figure 4 A schematic diagram of pancreatic necrotic tissue, effusion and a three-dimensional model of the pancreas and its corresponding adjacent organs according to an embodiment of the present invention;

[0049] Figure 5 The figure is a schematic diagram of the structure of a three-dimensional model reconstruction and visualization system for pancreatic lesions according to an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The principles and features of the present invention are described below in conjunction with the accompanying drawings. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0051] like Figure 1 As shown, a three-dimensional model reconstruction and visualization method for pancreatic lesions includes the following steps:

[0052] S1: collecting abdominal enhanced grayscale image data in layers from the CT data information of the target object according to the preset layer thickness;

[0053] In practice, the CT data information of the target object obtained from the imaging department, which is mainly the enhanced grayscale image data information of the patient's abdomen, can be imported into the mimi CS software, and layered acquisition can be performed according to the preset layer thickness (such as 1mm) to obtain the enhanced grayscale image data of each layer of the abdomen.

[0054] S2: using a fuzzy filtering algorithm to perform noise reduction, smoothing and optimization processing on each layer of the abdominal enhanced grayscale image data, so as to obtain the boundaries of each layer of pancreatic necrotic tissue, effusion and pancreas and its corresponding adjacent organs;

[0055] S3: outlining the boundary contours of each layer of pancreatic necrotic tissue, effusion and pancreas respectively, and calculating the three-dimensional data information of the pancreatic necrotic tissue, effusion and pancreas according to the boundary contours of the pancreatic necrotic tissue, effusion and pancreas;

[0056] S4: repeating S2 and S3 for the organs adjacent to the pancreatic necrotic tissue, effusion and the area where the pancreas is located, respectively, to obtain three-dimensional data information of the organs adjacent to the pancreatic necrotic tissue, effusion and the pancreas;

[0057] S5: Reconstruct a three-dimensional model of the pancreatic necrotic tissue, effusion and pancreas and their corresponding adjacent organs of the target object according to the three-dimensional data information of the pancreatic necrotic tissue, effusion and pancreas and their corresponding adjacent organs, and perform visual display.

[0058] The three-dimensional model reconstruction and visualization method for pancreatic lesions of the present invention performs layered sampling on CT data and performs noise reduction, smoothing and optimization processing on each layer of abdominal enhanced grayscale image data in combination with a fuzzy filtering algorithm, thereby obtaining the boundaries of each layer of pancreatic necrotic tissue, effusion and pancreas and their corresponding adjacent organs, and then delineates the boundaries of each layer of pancreatic necrotic tissue, effusion and pancreas, and calculates and obtains the three-dimensional data information of each layer of pancreatic necrotic tissue, effusion and pancreas, and the three-dimensional data information of the adjacent organs can be obtained in the same way, and finally the three-dimensional model of the pancreatic necrotic tissue, effusion and pancreas and their corresponding adjacent organs is restored through the three-dimensional data information, thereby being able to clearly and accurately restore the pancreatic lesions, and facilitating the precise and individualized treatment of medical staff.

[0059] In one or more embodiments of the present invention, in S2, the step of performing noise reduction, smoothing and optimization processing on each layer of the abdominal enhanced grayscale image data using a fuzzy filtering algorithm specifically includes the following steps:

[0060] S21: creating a blank mask, extracting and processing each layer of the abdominal enhanced grayscale image data by using a threshold segmentation method, and obtaining image pixels of organ tissues corresponding to different threshold ranges;

[0061] S22: using the region growing method to enhance the image pixels of similar region types corresponding to each layer of pancreatic necrotic tissue, effusion and pancreas, respectively, to obtain a heat map of each layer of pancreatic necrotic tissue, effusion and pancreas;

[0062] S23: Determine the boundaries of each layer of pancreatic necrotic tissue, effusion and pancreas and their adjacent organs according to the heat map of each layer of pancreatic necrotic tissue, effusion and pancreas.

[0063] The threshold segmentation method can be used to extract the enhanced grayscale image data of each layer of the abdomen, and the pixels within the set threshold range can be extracted, so that the image pixels of the corresponding organ tissue can be obtained, and the region growing method is used to enhance the image pixels of each layer of pancreatic necrotic tissue, effusion and pancreas corresponding to the region type similar to each other, so that the image pixels of the pancreatic necrotic tissue, effusion and pancreas and the adjacent organs are more clearly distinguished. In this way, each layer of pancreatic necrotic tissue, effusion and pancreas can be easily separated from the boundaries of the adjacent organs, so as to facilitate the subsequent calculation of the three-dimensional data information of the pancreatic necrotic tissue, effusion and the adjacent organs of the pancreas. Figure 2 Shown are necrotic tissue and fluid accumulation in the pancreatic organ, as well as the boundaries between the pancreas and its adjacent organs. The white strip is the pancreas, the gray parts on both sides of the white strip are pancreatic fluid accumulation, and the dark area on the far right is the spleen. No necrotic tissue was found in this case.

[0064] In one or more embodiments of the present invention, in S3, outlining the border contours of each layer of pancreatic necrotic tissue, effusion and pancreas specifically comprises the following steps:

[0065] S31: comparing the preset grayscale values ​​of normal tissues and organs with the grayscale values ​​of each layer of pancreatic necrotic tissue, effusion and pancreas, and outlining the boundary contours of the pancreatic necrotic tissue and effusion according to the comparison results;

[0066] S32: Determine the border contour of the pancreas according to the border contours of the pancreatic necrotic tissue and the effusion.

[0067] By comparing the grayscale values ​​of the image pixels corresponding to each layer of pancreatic necrotic tissue, effusion and pancreas with the preset grayscale values ​​of normal tissues and organs, the boundary contours of the pancreatic necrotic tissue and effusion can be determined. Combined with the boundaries of each layer of pancreatic necrotic tissue, effusion and pancreas and their corresponding adjacent organs obtained above, the boundary contour of the pancreas can be obtained. Figure 3 Shown are necrotic tissue and effusion of the pancreatic organ, as well as the boundaries of the pancreas and its adjacent organs. The white long strip boundary outline is the boundary outline of the pancreas, the gray border outlines on both sides of the long strip are the boundary outlines of the pancreatic effusion, and the dark area boundary outline on the far right is the boundary outline of the spleen. In this case, there is no boundary outline of necrotic tissue.

[0068] In one or more embodiments of the present invention, the three-dimensional model reconstruction and visualization method for pancreatic lesions further comprises the following steps:

[0069] S6: performing triangular facet optimization processing on the three-dimensional model of the pancreatic necrotic tissue, effusion, pancreas and its corresponding adjacent organs, removing the nail-like objects on the surface, obtaining an optimized three-dimensional model of the pancreatic necrotic tissue, effusion, pancreas and its corresponding adjacent organs, and exporting and saving it.

[0070] By performing triangular facet optimization processing on the three-dimensional model of the pancreatic necrotic tissue, effusion, pancreas and its corresponding adjacent organs, the nail-like objects on the surface can be removed and the smoothness of the model surface can be improved. Figure 4 As shown, the three-dimensional model of pancreatic necrotic tissue, effusion, pancreas and its corresponding adjacent organs after triangular facet optimization processing.

[0071] like Figure 5 As shown, the present invention also provides a three-dimensional model reconstruction and visualization system for pancreatic lesions, including an acquisition module, a preprocessing module, a delineation calculation module and a reconstruction module;

[0072] The acquisition module is used to acquire abdominal enhanced grayscale image data in layers from the CT data information of the target object according to a preset layer thickness;

[0073] The preprocessing module is used to perform noise reduction, smoothing and optimization processing on each layer of the abdominal enhanced grayscale image data using a fuzzy filtering algorithm to obtain the boundaries of each layer of pancreatic necrotic tissue, effusion and pancreas and corresponding adjacent organs;

[0074] The delineation calculation module is used to delineate the border contours of each layer of pancreatic necrotic tissue, effusion and pancreas respectively, and calculate the three-dimensional data information of the pancreatic necrotic tissue, effusion and pancreas according to the border contours of the pancreatic necrotic tissue, effusion and pancreas;

[0075] The preprocessing module is further used to perform noise reduction, smoothing and optimization processing on each layer of the abdominal enhanced grayscale image data using a fuzzy filtering algorithm to obtain the boundaries of organs adjacent to the pancreatic necrotic tissue, effusion and the area where the pancreas is located;

[0076] The delineation calculation module is further used to respectively delineate the boundary contours of each layer of organs adjacent to the pancreatic necrotic tissue, effusion and the region where the pancreas is located, and calculate the three-dimensional data information of the organs adjacent to the pancreatic necrotic tissue, effusion and the region where the pancreas is located based on the boundary contours of the organs adjacent to the pancreatic necrotic tissue, effusion and the region where the pancreas is located;

[0077] The reconstruction module is used to reconstruct a three-dimensional model of the pancreatic necrotic tissue, effusion and pancreas and its corresponding adjacent organs of the target object based on the three-dimensional data information of the pancreatic necrotic tissue, effusion and pancreas and its corresponding adjacent organs, and perform visual display.

[0078] This three-dimensional model reconstruction and visualization system for pancreatic lesions performs layered sampling of CT data and combines fuzzy filtering algorithm to perform noise reduction, smoothing and optimization processing on each layer of abdominal enhanced grayscale image data, thereby obtaining the boundaries of each layer of pancreatic necrotic tissue, effusion and pancreas and their corresponding adjacent organs, and then outlines the boundaries of each layer of pancreatic necrotic tissue, effusion and pancreas, and calculates the three-dimensional data information of each layer of pancreatic necrotic tissue, effusion and pancreas. The three-dimensional data information of the adjacent organs can be obtained in the same way, and finally the three-dimensional model of the pancreatic necrotic tissue, effusion and pancreas and their corresponding adjacent organs is restored through the three-dimensional data information, so that the pancreatic lesions can be clearly and accurately restored, which is convenient for medical staff to perform precise and individualized treatment.

[0079] In one or more embodiments of the present invention, the preprocessing module uses a fuzzy filtering algorithm to perform noise reduction, smoothing and optimization processing on each layer of the abdominal enhanced grayscale image data, specifically implemented as follows:

[0080] Creating a blank mask, extracting and processing each layer of the abdominal enhanced grayscale image data using a threshold segmentation method, and obtaining image pixels of organ tissues corresponding to different threshold ranges;

[0081] The region growing method is used to enhance the image pixels with similar regional types corresponding to each layer of pancreatic necrotic tissue, effusion and pancreas, and obtain the heat map of each layer of pancreatic necrotic tissue, effusion and pancreas;

[0082] The boundaries of each layer of pancreatic necrotic tissue, effusion, and the pancreas and its adjacent organs were determined based on the heat map of each layer of pancreatic necrotic tissue, effusion, and pancreas.

[0083] The threshold segmentation method can be used to extract the abdominal enhanced grayscale image data of each layer, and the pixels within the set threshold range can be extracted, so that the image pixels of the corresponding organ tissue can be obtained, and the region growing method is used to enhance the image pixels of each layer of pancreatic necrotic tissue, effusion and pancreas corresponding to the region type similar to each other, so that the image pixels of the pancreatic necrotic tissue, effusion and pancreas and the adjacent organs are more obviously distinguished. In this way, each layer of pancreatic necrotic tissue, effusion and pancreas can be easily separated from the boundaries of the adjacent organs, thereby facilitating the subsequent calculation to obtain the three-dimensional data information of the pancreatic necrotic tissue, effusion and the adjacent organs of the pancreas.

[0084] In one or more embodiments of the present invention, the delineation calculation module delineates the boundary contour of each layer of pancreatic necrotic tissue, effusion and pancreas respectively, and the specific implementation is:

[0085] The preset grayscale values ​​of normal tissues and organs were compared with the grayscale values ​​of each layer of pancreatic necrotic tissue, effusion and pancreas, and the boundary contours of pancreatic necrotic tissue, effusion and pancreas were outlined based on the comparison results.

[0086] By comparing the grayscale values ​​of the image pixels corresponding to each layer of pancreatic necrotic tissue, effusion and pancreas with the preset grayscale values ​​of normal tissue organs, the boundary contours of the pancreatic necrotic tissue and effusion can be determined. Combined with the boundaries of each layer of pancreatic necrotic tissue, effusion and pancreas obtained previously and their corresponding adjacent organs, the boundary contour of the pancreas can be obtained.

[0087] In one or more embodiments of the present invention, the three-dimensional model reconstruction and visualization system for pancreatic lesions also includes an optimization module, which is used to perform triangular facet optimization processing on the three-dimensional model of the pancreatic necrotic tissue, effusion, pancreas and its corresponding adjacent organs, remove surface nails, obtain an optimized three-dimensional model of the pancreatic necrotic tissue, effusion, pancreas and its corresponding adjacent organs, and export and save it.

[0088] By performing triangular facet optimization processing on the three-dimensional model of the pancreatic necrotic tissue, effusion, pancreas and its corresponding adjacent organs, nail-like objects on the surface can be removed and the smoothness of the model surface can be improved.

[0089] Compared with traditional two-dimensional ultrasound, CT or magnetic resonance imaging, the three-dimensional model reconstruction and visualization method and system for pancreatic lesions of the present invention can more objectively and stereoscopically display pancreatic lesions and their surrounding important anatomical structures in three-dimensional visualization images, thereby reducing the subjective errors of clinicians themselves. The three-dimensional visualization technology is applied to the surgical treatment of pancreatic necrotic tissue removal. Clinicians can accurately understand the detailed information of the lesion by zooming in and out of the three-dimensional department images and transparently operating them. Clinicians can simulate the surgical plan before surgery and select the best surgical method and surgical path, thereby achieving the best treatment effect of removing necrotic tissue, avoiding secondary surgery, reducing the incidence of postoperative related complications, and alleviating the economic and mental burden on patients.

[0090] The present invention also provides a three-dimensional model reconstruction and visualization device for pancreatic lesions, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method when executing the computer program.

[0091] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described are implemented.

[0092] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for three-dimensional model reconstruction and visualization of pancreatic lesions, characterized in that: The steps include: S1: collecting abdominal enhanced grayscale image data in layers from the CT data information of the target object according to the preset layer thickness; S2: using a fuzzy filtering algorithm to perform noise reduction, smoothing and optimization processing on each layer of the abdominal enhanced grayscale image data, so as to obtain the boundaries of each layer of pancreatic necrotic tissue, effusion and pancreas and its corresponding adjacent organs; S3: outlining the boundary contours of each layer of pancreatic necrotic tissue, effusion and pancreas respectively, and calculating the three-dimensional data information of the pancreatic necrotic tissue, effusion and pancreas according to the boundary contours of the pancreatic necrotic tissue, effusion and pancreas; S4: repeating S2 and S3 for the organs adjacent to the pancreatic necrotic tissue, effusion and the area where the pancreas is located, respectively, to obtain three-dimensional data information of the organs adjacent to the pancreatic necrotic tissue, effusion and the pancreas; S5: reconstructing a three-dimensional model of the pancreatic necrotic tissue, effusion and pancreas and their corresponding adjacent organs of the target object according to the three-dimensional data information of the pancreatic necrotic tissue, effusion and pancreas and their corresponding adjacent organs, and performing visual display; In S2, the fuzzy filtering algorithm is used to perform noise reduction, smoothing and optimization processing on each layer of the abdomen enhanced grayscale image data, which specifically includes the following steps: Creating a blank mask, extracting and processing each layer of the abdominal enhanced grayscale image data using a threshold segmentation method, and obtaining image pixels of organ tissues corresponding to different threshold ranges; The region growing method is used to enhance the image pixels with similar regional types corresponding to each layer of pancreatic necrotic tissue, effusion and pancreas, and obtain the heat map of each layer of pancreatic necrotic tissue, effusion and pancreas; The boundaries of each layer of pancreatic necrotic tissue, effusion and pancreas and their adjacent organs were determined based on the heat map of each layer of pancreatic necrotic tissue, effusion and pancreas.

2. The method for three-dimensional model reconstruction and visualization of pancreatic lesions according to claim 1, characterized in that: In S3, the step of respectively outlining the border contours of each layer of pancreatic necrotic tissue, effusion and pancreas specifically comprises the following steps: The preset grayscale values ​​of normal tissues and organs were compared with the grayscale values ​​of each layer of pancreatic necrotic tissue, effusion and pancreas, and the boundary contours of pancreatic necrotic tissue, effusion and pancreas were outlined based on the comparison results.

3. The method for three-dimensional model reconstruction and visualization of pancreatic lesions according to any one of claims 1 to 2, characterized in that: The following steps are also included: S6: performing triangular facet optimization processing on the three-dimensional model of the pancreatic necrotic tissue, effusion, pancreas and its corresponding adjacent organs, removing the nail-like objects on the surface, obtaining an optimized three-dimensional model of the pancreatic necrotic tissue, effusion, pancreas and its corresponding adjacent organs, and exporting and saving it.

4. A three-dimensional model reconstruction and visualization system for pancreatic lesions, characterized in that: It includes acquisition module, pre-processing module, delineation calculation module and reconstruction module; The acquisition module is used to acquire abdominal enhanced grayscale image data in layers from the CT data information of the target object according to a preset layer thickness; The preprocessing module is used to perform noise reduction, smoothing and optimization processing on each layer of the abdominal enhanced grayscale image data using a fuzzy filtering algorithm to obtain the boundaries of each layer of pancreatic necrotic tissue, effusion and pancreas and corresponding adjacent organs; The delineation calculation module is used to delineate the border contours of each layer of pancreatic necrotic tissue, effusion and pancreas respectively, and calculate the three-dimensional data information of the pancreatic necrotic tissue, effusion and pancreas according to the border contours of the pancreatic necrotic tissue, effusion and pancreas; The preprocessing module is further used to perform noise reduction, smoothing and optimization processing on each layer of the abdominal enhanced grayscale image data using a fuzzy filtering algorithm to obtain the boundaries of organs adjacent to the pancreatic necrotic tissue, effusion and the area where the pancreas is located; The delineation calculation module is further used to respectively delineate the boundary contours of each layer of organs adjacent to the pancreatic necrotic tissue, effusion and the region where the pancreas is located, and calculate the three-dimensional data information of the organs adjacent to the pancreatic necrotic tissue, effusion and the region where the pancreas is located based on the boundary contours of the organs adjacent to the pancreatic necrotic tissue, effusion and the region where the pancreas is located; The reconstruction module is used to reconstruct a three-dimensional model of the pancreatic necrotic tissue, effusion and pancreas and its corresponding adjacent organs of the target object according to the three-dimensional data information of the pancreatic necrotic tissue, effusion and pancreas and its corresponding adjacent organs, and to perform visual display; The specific implementation of the pre-processing module using the fuzzy filtering algorithm to perform noise reduction, smoothing and optimization processing on each layer of the abdominal enhanced grayscale image data is as follows: Creating a blank mask, extracting and processing each layer of the abdominal enhanced grayscale image data using a threshold segmentation method, and obtaining image pixels of organ tissues corresponding to different threshold ranges; The region growing method is used to enhance the image pixels with similar regional types corresponding to each layer of pancreatic necrotic tissue, effusion and pancreas, and obtain the heat map of each layer of pancreatic necrotic tissue, effusion and pancreas; The boundaries of each layer of pancreatic necrotic tissue, effusion, and the pancreas and its adjacent organs were determined based on the heat map of each layer of pancreatic necrotic tissue, effusion, and pancreas.

5. The three-dimensional model reconstruction and visualization system for pancreatic lesions according to claim 4, characterized in that: The delineation calculation module delineates the border contour of each layer of pancreatic necrotic tissue, effusion and pancreas respectively, and the specific implementation is as follows: The preset grayscale values ​​of normal tissues and organs were compared with the grayscale values ​​of each layer of pancreatic necrotic tissue, effusion and pancreas, and the boundary contours of pancreatic necrotic tissue, effusion and pancreas were outlined based on the comparison results.

6. The three-dimensional model reconstruction and visualization system for pancreatic lesions according to claim 4, characterized in that: It also includes an optimization module, which is used to perform triangular facet optimization processing on the three-dimensional model of the pancreatic necrotic tissue, effusion, pancreas and its corresponding adjacent organs, remove the nail-like objects on the surface, obtain the optimized three-dimensional model of the pancreatic necrotic tissue, effusion, pancreas and its corresponding adjacent organs, and export and save it.

7. A three-dimensional model reconstruction and visualization device for pancreatic lesions, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 3 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, 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 3 are implemented.

Images