CT image three-dimensional reconstruction method and related device based on morphological gradient and center feature extraction

Abstract

The present application discloses a 3D reconstruction method of CT images based on morphological gradient and central feature extraction and related devices. The method includes: obtaining a medical CT image of a target object; segmenting and extracting the medical CT image to obtain a medical CT segmented target object image; obtaining a multi-view section sequence from the medical CT segmented target object image, performing morphological gradient difference operation on the multi-view section sequence, obtaining target object feature point set data under different view sections, recorded as a multi-view feature point set; performing adaptive central point set extraction on the multi-view feature point set to obtain a multi-view central feature point set; generating 3D reconstruction data based on the multi-view central feature point set data, and then obtaining 3D reconstruction data of the entire target object; performing Poisson probability distribution on the 3D reconstruction data to obtain a vertex point set, and then reconstructing based on the vertex point set to obtain a 3D reconstruction model. The present invention effectively reduces reconstruction data and improves reconstruction speed.

Description

Technical Field

[0001] The present invention relates to the technical field of three-dimensional reconstruction of medical image data, and in particular to a three-dimensional reconstruction method of CT images based on morphological gradient and center feature extraction and a related device. Background Art

[0002] With the continuous advancement of computer technology, medical technology has also made significant breakthroughs. Although traditional 3D reconstruction methods, such as surface rendering technology and volume rendering technology, have been widely used, they still face challenges in rendering speed and real-time processing when processing complex medical images. Surface rendering technology displays the external contour of an object by extracting surface meshes, but when processing high-resolution medical images, the rendering speed is slow and the amount of calculation is large. Volume rendering technology displays the internal structure of an object, but the calculation complexity is high, the hardware requirements are large, and it is difficult to meet the needs of real-time applications. Although the existing optimization algorithms and hardware acceleration have been improved to a certain extent, the problems of slow speed and high resource consumption have not been solved. Summary of the invention

[0003] The present invention relates to a 3D reconstruction method of CT images based on morphological gradient and center feature extraction and related devices, which include but are not limited to 3D reconstruction equipment, electronic devices, computer-readable storage media and computer program products.

[0004] A first aspect provides a 3D reconstruction method for CT images based on morphological gradient and center feature extraction, the method comprising:

[0005] Acquire a medical CT image of a target object and a medical CT segmentation target object image; the medical CT image is obtained by performing a CT scan on the target object, and the medical CT segmentation target object image is obtained based on manual segmentation and extraction of the medical CT image of the target object by a doctor and is verified by the DICOM-RT standard;

[0006] Generate a multi-view section sequence with an interval of ≤ 1 mm from the medical CT segmented target object image, perform morphological grayscale gradient difference operation on the multi-view section sequence, and obtain target object feature point set data under different view sections, which is recorded as a multi-view feature point set;

[0007] For the multi-view feature point set, an adaptive center point set feature extraction based on bandwidth calculation is performed, specifically including: determining the bandwidth according to the multi-view feature point set, calculating the centroid of the target area according to the bandwidth, and moving the window center to the centroid position, repeatedly iterating to find multiple adaptive feature center points that meet the bandwidth, and then using the adaptive feature center point to represent the point set in the bandwidth area to obtain the multi-view center feature point set;

[0008] Based on the multi-view central feature point set data, three-dimensional reconstruction data is generated to obtain the three-dimensional reconstruction data of the entire target object. The three-dimensional reconstruction data is subjected to Poisson probability distribution to obtain the vertex point set, and then reconstructed according to the vertex point set to obtain the three-dimensional reconstruction model.

[0009] In combination with any embodiment of the present application, the morphological gradient difference operation using multi-view slices includes: performing morphological corrosion on the multi-view slices, and then performing a difference operation on the morphologically corroded slices and the original slices to obtain a grayscale gradient difference ΔG between the corroded slices and the original slices, retaining feature areas with ΔG ≥ 50HU, and obtaining feature point set data of target objects at different viewpoints.

[0010] In combination with any implementation manner of the present application, the adaptive center point feature extraction method is characterized in that the bandwidth calculation adopts the formula:

[0011] ,

[0012] Where h is the bandwidth, σ is the standard deviation of the point set in the window, and n is the number of points in the current window point set.

[0013] In combination with any embodiment of the present application, the three-dimensional reconstruction data generation includes: estimating the essential matrix between the image pairs based on the multi-view central feature point pairs, and eliminating the erroneous central feature point pairs, decomposing the rotation matrix and translation vector from the essential matrix to obtain the camera parameters, and using the central feature point pairs and the camera parameters to calculate the initial three-dimensional reconstruction data through triangulation.

[0014] In combination with any embodiment of the present application, the method of performing Poisson probability distribution on the three-dimensional point cloud data to obtain a vertex point set includes: performing Poisson probability distribution on the three-dimensional reconstruction data to obtain a vertex point set in the three-dimensional reconstruction data, connecting the three nearest adjacent points in the vertex point set into a triangular facet with a side length variance ratio of ≤0.15, and thereby obtaining a three-dimensional reconstructed model of the entire target object.

[0015] In a second aspect, a device for three-dimensional reconstruction of medical image data is provided, the device comprising:

[0016] an acquisition unit, configured to acquire a medical CT image of a target object, wherein the medical CT image is obtained by performing a CT scan on the target object and includes position and structural information of the target object in a three-dimensional space;

[0017] The acquisition unit is further used to acquire a medical CT segmentation target object image, wherein the medical CT segmentation target object image is obtained based on a doctor's manual segmentation and extraction of the medical CT image of the target object and is verified by the DICOM-RT standard;

[0018] A processing unit is used to generate a multi-view section sequence with an interval of ≤ 1 mm from the medical CT segmented target object image, perform morphological grayscale gradient difference operation on the multi-view section sequence, and obtain target object feature point set data under different view sections, which is recorded as a multi-view feature point set;

[0019] The processing unit is further used to perform adaptive center point set feature extraction based on bandwidth calculation according to the multi-view feature point set, specifically including: determining the bandwidth according to the multi-view feature point set, calculating the centroid of the target area according to the bandwidth, and moving the window center to the centroid position, repeatedly iterating to find multiple adaptive feature center points that meet the bandwidth, and then using the adaptive feature center point to represent the point set in the bandwidth area, to obtain the multi-view center feature point set;

[0020] The modeling unit is used to generate three-dimensional reconstruction data based on the multi-view central feature point set data, thereby obtaining the three-dimensional reconstruction data of the entire target object, and then performing Poisson probability distribution on the three-dimensional reconstruction data to obtain a vertex point set, and then triangulating the vertex point set to obtain a three-dimensional reconstructed model.

[0021] In a third aspect, an electronic device is provided, comprising: a processor, a communication module, a sensor, a user interface, and a storage unit, wherein the storage unit is used to store computer program code, wherein the program code includes computer instructions. When the processor executes these instructions, the electronic device will execute the method described in the second aspect and any embodiment thereof.

[0022] In a fourth aspect, another electronic device is provided, comprising: a processor, a wireless communication module, a touch screen, a speaker, and a storage unit, wherein the storage unit is used to store computer program code, wherein the program code includes computer instructions. When the processor executes these instructions, the electronic device will execute the method described in the second aspect and any embodiment thereof.

[0023] In a fifth aspect, a computer-readable storage medium is provided, wherein a computer program is stored, wherein the program includes program instructions. When these instructions are executed by a processor, the processor will execute the method described in the second aspect and any embodiment thereof.

[0024] In a sixth aspect, a computer program product is provided, the computer program product comprising a computer program or instructions. When the computer program or instructions are run on a computer, the computer will execute according to the method described in the second aspect and any of its embodiments.

[0025] It should be understood that the above general description and the following detailed description are only used as examples and explanations and do not impose any limitations on the present application.

[0026] In the present application, compared with the prior art, the present invention adopts morphological gradient to extract feature point sets of different viewpoint sections, then performs adaptive center point set feature extraction to obtain multi-view center feature point sets, and then uses motion recovery structure method to construct three-dimensional point cloud data, calculates the vertex point set of its Poisson probability distribution according to the three-dimensional point cloud data, and then generates a three-dimensional reconstruction model according to the three-planarization of the point set, which effectively reduces the three-dimensional reconstruction data, optimizes the three-dimensional reconstruction technology, improves the rendering speed, reduces the hardware dependence, reduces the resource consumption, and improves the running speed and processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the background technology, the drawings required for use in the embodiments of the present application or the background technology will be described below.

[0028] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present application and are used together with the specification to illustrate the technical solution of the present application.

[0029] Figure 1 A schematic diagram of a process of a 3D reconstruction method of a CT image based on morphological gradient and center feature extraction provided in an embodiment of the present application;

[0030] Figure 2 is a schematic diagram of a medical CT image under this implementation mode;

[0031] Figure 3 A schematic diagram of an image region for segmenting and extracting a target object from a medical CT image provided in an embodiment of the present application;

[0032] Figure 4 A schematic diagram of three-dimensional point cloud data of the target object provided in an embodiment of the present application;

[0033] Figure 5 A schematic diagram of a triangulated planarized 3D reconstruction model of the target object provided in an embodiment of the present application;

[0034] Figure 6 A schematic diagram of the structure of a device for three-dimensional reconstruction of medical image data provided in an embodiment of the present application;

[0035] Figure 7 A schematic diagram of the hardware architecture of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0036] In order to allow professionals in the technical field to more fully understand the technical solution of the present application, the technical solution of the present application will be explained in detail and clearly through the accompanying drawings. It should be particularly pointed out that the described embodiments are only some examples of the present application and do not represent all. Based on these embodiments, those skilled in the art can directly derive all other possible implementation schemes without creative thinking, which are also included in the protection scope of the present application.

[0037] In the specification, claims and related drawings of this application, the terms "first", "second" and the like are used only to distinguish different elements and do not imply any particular order. At the same time, the use of "including" and "having" and their variations indicates non-exclusive inclusion. This means that if a process, method, system, product or device includes a series of steps or components, it means that the process, method, system, product or device is not limited to the listed steps or components, and may also include other steps or components not listed, or other steps or units inherent thereto.

[0038] The "embodiment" mentioned in this article refers to any instance in which a particular feature, structure or characteristic is combined, and these instances may belong to at least one embodiment of the present application. The "embodiment" mentioned in the text does not necessarily refer to the same specific case, nor does it mean that they are independent or exclusive alternatives. It should be understood by those skilled in the art that the embodiments described in the text can be used together with other embodiments. It should be clear that in the present application, "at least one" includes one or more instances, "multiple" means two or more instances, and "at least two" refers to two or more instances.

[0039] It should be understood that the method embodiment of the present application can also be implemented by a processor executing computer program code. The embodiment of the present application is described below in conjunction with the drawings in the embodiment of the present application.

[0040] See also Figure 1 , Figure 1 A flowchart of a method for three-dimensional reconstruction of medical image data based on edge detection is provided in an embodiment of the present application.

[0041] 101. Obtain a medical CT image of a target object.

[0042] In the embodiment of the present application, the medical CT image is an image obtained by performing a CT scan on the target object. The medical CT image includes the target object, wherein the image area of ​​the target object includes a three-dimensionally reconstructed target object image.

[0043] In the embodiment of the present application, the reference object lies on the bed for CT scanning, which results in the inclusion of non-target objects in the medical CT image. Figure 2It is a schematic diagram of a medical CT image under this implementation mode, which includes a target object and a non-target object. The non-target object is a bed board, etc., and the image area of ​​the target object includes a liver object.

[0044] 102. Obtain a medical CT segmentation target object image.

[0045] In the embodiment of the present application, the medical CT segmentation target object image is obtained based on the doctor's manual segmentation and extraction of the medical CT image of the target object, and is verified by the DICOM-RT standard; when the medical CT image includes the target object and the non-target object, the image area of ​​the target object is segmented and extracted from the medical CT image to obtain the segmented target object image, and the segmented target object image does not contain the segmented image of the non-target object.

[0046] In one possible implementation, a deep neural network segmentation model is used to segment the target object to obtain a segmented target object image.

[0047] In another possible implementation method, a threshold is used to segment the target object image to obtain a segmented target object image.

[0048] In yet another possible implementation, multi-dimensional information is formed by extracting the HU value of the liver object and the spatial coordinate information of the liver object in the medical CT image, and machine learning is used to cluster the multi-dimensional information to obtain a segmented image of the liver object.

[0049] See also Figure 3 , Figure 3 A schematic diagram of an image region for segmenting and extracting a target object from a medical CT image provided in an embodiment of the present application. Figure 3 The target object image shown is obtained by scanning the upper part of the target organ to obtain a medical CT image, and then manually segmenting the target object image based on the doctor's manual segmentation.

[0050] 103. Acquire multi-view cut planes from the medical CT segmented target object image, perform morphological gradient difference calculation using the multi-view cut planes, and obtain target object feature point set data under different view cut planes.

[0051] In the embodiment of the present application, the image area of ​​the target object for medical CT segmentation is determined, that is, the specific position and range of the target object in the medical CT image are clarified. Next, a multi-view section sequence with an interval of ≤ 1 mm is generated from the medical CT segmentation target object image, and then morphological corrosion is performed according to the multi-view section sequence, and then the morphological corrosion section is subjected to a difference operation with the original section to obtain the gray gradient difference ΔG between the corrosion section and the original section, retain the feature area with ΔG ≥ 50HU, and obtain the target object feature point set data of different view angles, which is recorded as a multi-view feature point set.

[0052] 104. Perform adaptive center point set feature extraction based on bandwidth calculation on the multi-view feature point set to obtain a multi-view center feature point set.

[0053] In the embodiment of the present application, the feature point set data of the target object at different perspectives are processed, and a suitable bandwidth value is determined according to the distribution of the multi-perspective point set. The bandwidth value is used as a parameter to calculate the centroid of the target area, and the window center is moved to the centroid position. The above process is repeated until multiple adaptive feature center points that meet the bandwidth conditions are found. Finally, these adaptive feature center points are used to represent the point set within the bandwidth area to obtain the multi-perspective center feature point set data.

[0054] 105. Generate three-dimensional reconstruction data based on the multi-view central feature point set data, and then obtain the three-dimensional reconstruction data of the entire target object.

[0055] In an embodiment of the present application, feature point set data of the target object at different perspectives of the segmented target object is determined to obtain central feature point set data, the essential matrix between the image pairs is estimated based on the multi-perspective central feature point pairs, and the erroneous central feature point pairs are eliminated. The rotation matrix and translation vector are decomposed from the essential matrix to obtain camera parameters, and the initial three-dimensional reconstruction data is calculated through triangulation using the central feature point pairs and the camera parameters.

[0056] See also Figure 4 , Figure 4 A schematic diagram of three-dimensional reconstruction data of the target object provided in an embodiment of the present application. Figure 4 The three-dimensional reconstruction data shown is obtained by performing a structure-from-motion method on the three-dimensional reconstruction data of the segmented target object.

[0057] 106. The three-dimensional reconstruction data is subjected to Poisson probability distribution to obtain a vertex point set, and then the vertex point set is triangulated to obtain a three-dimensional reconstruction model.

[0058] In an embodiment of the present application, based on the three-dimensional reconstruction data, Poisson probability distribution is performed to obtain the vertex point set in the three-dimensional reconstruction data, and the three adjacent points in the vertex point set that are closest to each other are connected into a triangular facet with a side length variance ratio of ≤0.15, thereby obtaining a three-dimensional reconstructed model of the entire target object.

[0059] See also Figure 5 , Figure 5 A schematic diagram of a triangulated planarized three-dimensional reconstruction model of the target object provided in an embodiment of the present application. Figure 5The three-dimensional reconstruction model of the target object shown is generated by generating a three-dimensional reconstruction model from a vertex set of the three-dimensional reconstruction data of the segmented target object, and the three-dimensional reconstruction model is obtained by processing the vertex set of the three-dimensional reconstruction data based on triangulation planarization.

[0060] Those skilled in the art will appreciate that, in the above method of specific implementation, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0061] The method of the embodiment of the present application is described in detail above, and the device of the embodiment of the present application is provided below.

[0062] See also Figure 6 , Figure 6 A schematic diagram of the structure of a CT image three-dimensional reconstruction device based on morphological gradient and center feature extraction provided in an embodiment of the present application. The three-dimensional reconstruction device 1 includes: an acquisition unit 11, a processing unit 12, and a modeling unit 13. Specifically:

[0063] An acquisition unit 11 is used to acquire a medical CT image of a target object, wherein the medical CT image is obtained by performing a CT scan on the target object and includes the position and structural information of the target object in a three-dimensional space, and is also used to acquire a medical CT segmented target object image, wherein the medical CT segmented target object image is obtained based on manual segmentation and extraction of the medical CT image of the target object by a doctor and is verified by the DICOM-RT standard;

[0064] The processing unit 12 is used to generate a multi-view section sequence with an interval of ≤ 1 mm from the medical CT segmented target object image, perform morphological grayscale gradient difference operation on the multi-view section sequence to obtain target object feature point set data under different view sections, which is recorded as a multi-view feature point set, and is also used to perform adaptive center point set feature extraction based on bandwidth calculation according to the multi-view feature point set, specifically including: determining the bandwidth according to the multi-view feature point set, calculating the centroid of the target area according to the bandwidth, and moving the window center to the centroid position, repeatedly iterating to find multiple adaptive feature center points that meet the bandwidth, and then using the adaptive feature center point to represent the point set in the bandwidth area to obtain the multi-view center feature point set;

[0065] The modeling unit 13 is used to generate three-dimensional reconstruction data based on the multi-view central feature point set data, thereby obtaining the three-dimensional reconstruction data of the entire target object, and then performing Poisson probability distribution on the three-dimensional reconstruction data to obtain a vertex point set, and then triangulating the vertex point set to obtain a three-dimensional reconstructed model.

[0066] In some embodiments, the functions or modules included in the device provided in the embodiments of the present application can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments. For the sake of brevity, it will not be repeated here.

[0067] Figure 7 A schematic diagram of the hardware architecture of an electronic device described in an embodiment of the present application is shown. The electronic device 2 is mainly composed of a processor 21 and a memory 22. In addition, the device may also include an input device 23 and an output device 24. The processor 21, the memory 22, the input device 23 and the output device 24 are interconnected through connection components, and these connection components can be various interfaces, data lines or communication buses, etc., which are not specifically specified in the embodiments of the present application. It should be clear that in multiple embodiments of the present application, the so-called connection refers to the mutual connection achieved by a specific method, which can be a direct connection or an indirect connection through other devices, such as connecting through various interfaces, data lines, communication buses, etc.

[0068] The processor 21 may be one or more graphics processing units (GPUs). If the processor 21 is a GPU, the GPU may be single-core or multi-core. As an option, the processor 21 may also be a processor group consisting of multiple GPUs, which are interconnected via one or more buses. In addition, the processor may also be other types of processors, which are not specifically limited in the embodiments of the present application.

[0069] The memory 22 is designed to store computer program instructions and various program codes required to execute the solution of the present application. As an option, the memory may include but is not limited to a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM) or a compact disc read-only memory (CD-ROM), which are used to store relevant instructions and data.

[0070] The input device 23 is used to input data and / or signals, and the output device 24 is used to output data and / or signals. The input device 23 and the output device 24 can be independent devices or an integrated device.

[0071] It should be appreciated that in the embodiment of the present application, the memory 22 can store not only related instructions but also related data. The embodiment of the present application does not specifically specify the specific data content stored in the memory.

[0072] You should understand that Figure 7Only a simplified design of an electronic device is shown. In actual use, the electronic device may also include other necessary components, such as different numbers of input / output devices, processors, memories, etc. All electronic devices that can implement the embodiments of the present application belong to the protection scope of the present application.

[0073] Those skilled in the art should recognize that, according to the components and algorithm steps of each example described in the embodiments disclosed herein, these functions can be implemented by electronic hardware or by combining computer software and electronic hardware. Whether these functions are performed by hardware or software will be determined based on the specific application requirements and design limitations of the technical solution. Technicians can adopt different implementation methods according to the needs of each specific application, but such implementation methods should not be considered to exceed the scope of protection of this application.

[0074] Professionals should understand that, for the convenience of description and simplification, the specific operation process of the above-mentioned systems, devices and components can refer to the corresponding steps in the previous method embodiments, and will not be repeated here. At the same time, professionals should also understand that each embodiment in this application has its own focus. For the convenience of description and simplification, the same or similar content may not be repeated in different embodiments. Therefore, if a part is not mentioned or described in detail in a certain embodiment, it can refer to the relevant description of other embodiments.

[0075] In several embodiments provided in the present application, it should be recognized that the disclosed systems, devices and methods can also be implemented in other ways. For example, the described device embodiments are only exemplary, wherein the division of the units is only a division of logical functions, and there may be different division methods in actual implementation. For example, multiple units or components may be merged or integrated into another system, or certain features may be omitted, or certain steps may not be performed. In addition, the connections between each other shown or discussed, whether direct or indirect, whether coupled or communicatively connected, may be implemented in electrical, mechanical or other forms through interfaces, devices or units.

[0076] The units described as independent components may or may not actually be physically separated; the parts presented as units may or may not be physical entities, that is, they may be concentrated in one location or dispersed across multiple network nodes. Depending on actual needs, some or all of these units may be selected to achieve the objectives of this embodiment.

[0077] In addition, in various embodiments of the present application, each functional unit can be integrated into one processing unit, or can exist physically independently, or two or more units can be merged into one unit. In the aforementioned embodiments, the relevant functions can be fully or partially implemented by software, hardware, firmware, or any combination thereof. If software implementation is selected, it can be carried out in whole or in part in the form of a computer program product. This computer program product contains one or more computer instructions. When these instructions are loaded and executed on a computer, a process or function that fully or partially complies with the description of the embodiment of the present application will be generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. These computer instructions can be stored in a computer-readable storage medium or transmitted through these media. Computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired (e.g., coaxial cable, optical fiber, DSL) or wireless (e.g., infrared, wireless, microwave, etc.). Computer-readable storage media can be any computer-accessible available medium, or a data storage facility such as a server or data center that integrates one or more available media. These available media may include magnetic media (such as floppy disks, hard disks, tapes), optical media (such as DVDs), semiconductor media (such as SSDs), etc. Those skilled in the art should understand that all or part of the processes for implementing the above-mentioned embodiments can be completed by computer program instructions related to hardware, and these programs can be stored in computer-readable storage media. When these programs are executed, they will contain the processes of the above-mentioned method embodiments. The above-mentioned storage media include, but are not limited to, various media that can store program codes, such as read-only memory (ROM), random access memory (RAM), disk or optical disk.

Claims

1. A 3D reconstruction method for CT images based on morphological gradient and center feature extraction, characterized in that: The method comprises: Acquire a medical CT image of a target object and a medical CT segmentation target object image; the medical CT image is obtained by performing a CT scan on the target object, and the medical CT segmentation target object image is obtained based on manual segmentation and extraction of the medical CT image of the target object by a doctor and is verified by the DICOM-RT standard; Generate a multi-view section sequence with an interval of ≤ 1 mm from the medical CT segmented target object image, perform morphological grayscale gradient difference operation on the multi-view section sequence, and obtain target object feature point set data under different view sections, which is recorded as a multi-view feature point set; For the multi-view feature point set, an adaptive center point set feature extraction based on bandwidth calculation is performed, specifically including: determining the bandwidth according to the multi-view feature point set, calculating the centroid of the target area according to the bandwidth, and moving the window center to the centroid position, repeatedly iterating to find multiple adaptive feature center points that meet the bandwidth, and then using the adaptive feature center point to represent the point set in the bandwidth area to obtain the multi-view center feature point set; Based on the multi-view central feature point set data, three-dimensional reconstruction data is generated to obtain the three-dimensional reconstruction data of the entire target object. The three-dimensional reconstruction data is subjected to Poisson probability distribution to obtain the vertex point set, and then reconstructed according to the vertex point set to obtain the three-dimensional reconstruction model.

2. The method according to claim 1, characterized in that The morphological grayscale gradient difference operation is performed on the multi-view section sequence, including: performing morphological corrosion on the multi-view section sequence, and then performing a difference operation on the morphologically corroded section and the original section to obtain a grayscale gradient difference ΔG between the corroded section and the original section, retaining a feature area with ΔG ≥ 50HU, and obtaining feature point set data of the target object at different viewpoints.

3. The method according to claim 1, characterized in that The bandwidth is calculated using the formula: ， Where h is the bandwidth, σ is the standard deviation of the point set in the window, and n is the number of points in the current window point set.

4. The method according to claim 1, characterized in that: The three-dimensional reconstruction data generation includes: estimating the essential matrix between the image pairs based on the multi-view central feature point pairs, and eliminating the wrong central feature point pairs, decomposing the rotation matrix and translation vector from the essential matrix to obtain camera parameters, and using the central feature point pairs and the camera parameters to calculate the initial three-dimensional reconstruction data through triangulation.

5. The method according to claim 1, characterized in that The method of subjecting the three-dimensional reconstructed data to Poisson probability distribution to obtain a vertex point set includes: subjecting the three-dimensional reconstructed data to Poisson probability distribution to obtain a vertex point set in the three-dimensional reconstructed data, connecting the three nearest adjacent points in the vertex point set into a triangular facet with a side length variance ratio of ≤0.15, and then obtaining a three-dimensional reconstructed model of the entire target object.

6. A 3D reconstruction device for CT images based on morphological gradient and center feature extraction, characterized in that: The three-dimensional reconstruction device comprises: an acquisition unit, used to acquire a medical CT image of a target object, the medical CT image being obtained by performing a CT scan on the target object and including position and structural information of the target object in a three-dimensional space, and also used to acquire a medical CT segmented target object image, the medical CT segmented target object image being obtained based on manual segmentation and extraction of the medical CT image of the target object by a doctor and verified by the DICOM-RT standard; A processing unit is used to generate a multi-view section sequence with an interval of ≤ 1 mm from the medical CT segmented target object image, perform morphological grayscale gradient difference operation on the multi-view section sequence to obtain target object feature point set data under different view sections, recorded as a multi-view feature point set, and further used to perform adaptive center point set feature extraction based on bandwidth calculation according to the multi-view feature point set, specifically including: determining the bandwidth according to the multi-view feature point set, calculating the centroid of the target area according to the bandwidth, and moving the window center to the centroid position, repeatedly iterating to find multiple adaptive feature center points that meet the bandwidth, and then using the adaptive feature center point to represent the point set in the bandwidth area to obtain the multi-view center feature point set; The modeling unit is used to generate three-dimensional reconstruction data based on the multi-view central feature point set data, thereby obtaining the three-dimensional reconstruction data of the entire target object, and then performing Poisson probability distribution on the three-dimensional reconstruction data to obtain a vertex point set, and then triangulating the vertex point set to obtain a three-dimensional reconstructed model.

7. An electronic device, characterized in that: include: A processor and a storage unit, the storage unit is used to store computer program code, the code includes computer instructions, when the processor executes these instructions, the electronic device executes the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions. When the program instructions are executed by a processor, the processor is caused to execute the method according to any one of claims 1 to 5.

9. A computer program product, characterized in that The computer program product comprises a computer program or instructions, and when the computer program or instructions are run on a computer, the computer is caused to execute the method according to any one of claims 1 to 5.

Images