Kidney stone body surface incidence point determination method, system and equipment and storage medium

Abstract

The invention discloses a kidney stone body surface incidence point determination method, system and device and a storage medium, and the method comprises the steps: carrying out the slicing of a three-dimensional CT image of a kidney stone patient, and obtaining a plurality of two-dimensional CT images; performing binarization processing on the plurality of two-dimensional CT images through an Ostu threshold algorithm, and determining skeleton point cloud data and lung gas point cloud data according to the plurality of binarized images; obtaining body surface contour point cloud data through a gradient edge detection sobel algorithm according to the plurality of two-dimensional CT images; and inputting the body surface contour point cloud data, the skeleton point cloud data, the lung gas point cloud data and the calculus point prediction coordinates into the calculus body surface incidence point prediction model to obtain the optimal body surface incidence point of the kidney calculus. Through the calculus body surface incidence point prediction model, the accuracy of kidney calculus body surface incidence point planning is greatly improved, the practical operation difficulty of in-vitro lithotripsy operation incidence point selection is reduced, and the lithotripsy operation efficiency is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical equipment, and in particular relates to a method, system, equipment and storage medium for determining a body surface entrance point of a kidney stone. Background Art

[0002] Kidney stones are a common disease, and one of the treatments is extracorporeal shock wave lithotripsy (ESWL), which has always been a difficult problem in technical research. The traditional method of selecting the entry point mainly relies on the doctor's experience and manual operation, which is not only time-consuming, but also the accuracy of the results is limited by the operator's technical level. In addition, due to the complexity of the patient's anatomical structure, the traditional method is difficult to fully consider all clinical criteria, which may lead to poor surgical results or cause additional harm to the patient.

[0003] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present invention is to provide a method, system, device and storage medium for determining the surface incident point of kidney stones, aiming to solve the technical problem of how to accurately and efficiently select the optimal shock wave incident point.

[0005] To achieve the above object, the present invention provides a method for determining the body surface incident point of a kidney stone, the method comprising: Acquire a three-dimensional CT image of a patient with kidney stones, and slice the three-dimensional CT image to obtain multiple two-dimensional CT images; Binarization is performed on multiple two-dimensional CT images respectively by using the Ostu threshold algorithm, and bone point cloud data and lung gas point cloud data are determined based on the multiple binary images; The body surface contour point cloud data is obtained by using the gradient edge detection sobel algorithm based on multiple two-dimensional CT images; Constructing a skeleton avoidance constraint function according to the skeleton point cloud data, constructing a lung gas avoidance constraint function according to the lung gas point cloud data, and constructing a stone surface incident point prediction model according to the shock wave focal length constraint function, the skeleton avoidance constraint function and the lung gas avoidance constraint function; The body surface contour point cloud data, the bone point cloud data, the lung gas point cloud data and the stone point prediction coordinates are input into the stone body surface incident point prediction model to obtain the optimal body surface incident point of kidney stones.

[0006] Optionally, the step of slicing the three-dimensional CT image to obtain a plurality of two-dimensional CT images includes: Parsing the DICOM file of the kidney stone patient to obtain DICOM metadata; Determining the number of CT slices according to the DICOM metadata; The three-dimensional CT image is sliced ​​based on the number of CT layers, and the format of the sliced ​​multiple CT images is converted to obtain multiple two-dimensional CT images.

[0007] Optionally, the step of performing binarization processing on the multiple two-dimensional CT images respectively by using the Ostu threshold algorithm includes: respectively determining the foreground pixel ratio, background pixel ratio, foreground average gray value and background average gray value corresponding to each two-dimensional CT image; Obtaining the segmentation pixel threshold corresponding to each two-dimensional CT image through the Ostu threshold algorithm according to the foreground pixel ratio, the background pixel ratio, the foreground average grayscale value and the background average grayscale value; Binarization processing is performed on multiple two-dimensional CT images based on the segmentation pixel threshold.

[0008] Optionally, the step of determining the bone point cloud data and the lung gas point cloud data according to the multiple binary images includes: extracting bone point coordinates and lung gas point coordinates from a plurality of binary images according to the segmentation pixel point threshold; Skeleton point cloud data is generated according to the skeleton point coordinates, and lung gas point cloud data is generated according to the lung gas point coordinates.

[0009] Optionally, the step of obtaining body surface contour point cloud data by gradient edge detection Sobel algorithm according to multiple two-dimensional CT images includes: Determine whether multiple two-dimensional CT images are grayscale images; If yes, all the pixels corresponding to each 2D CT image are determined, and the horizontal gradient and vertical gradient of each pixel are calculated respectively; Calculate the approximate total amplitude of the gradient of each pixel point by using the gradient edge detection sobel algorithm according to the horizontal gradient and the vertical gradient; Extracting edge point coordinates from a plurality of two-dimensional CT images according to the total amplitude of the gradient approximation; The body surface contour point cloud data is determined according to the edge point coordinates.

[0010] Optionally, the step of inputting the body surface contour point cloud data, the bone point cloud data, the lung gas point cloud data and the stone point prediction coordinates into the stone body surface incident point prediction model to obtain the optimal body surface incident point of kidney stones includes: Inputting the body surface contour point cloud data, the bone point cloud data, the lung gas point cloud data and the stone point prediction coordinates into the stone body surface incident point prediction model; Based on the stone body surface incident point prediction model, multiple candidate incident points are selected from the body surface contour point cloud data by using the Euclidean distance formula according to the stone point prediction coordinates; Selecting a plurality of candidate incident points from a plurality of candidate incident points by using the shock wave focal length constraint function, the bone avoidance constraint function and the lung gas avoidance constraint function; The entry point risk value of each candidate entry point is calculated by the risk assessment formula; Selecting a candidate incident point with a lowest risk value from a plurality of candidate incident points according to the risk value of the incident point; The candidate entry point with the lowest risk value is output through the stone surface entry point prediction model to obtain the optimal surface entry point of kidney stones.

[0011] In addition, to achieve the above-mentioned purpose, the present invention also provides a system for determining the body surface entrance point of kidney stones, the system for determining the body surface entrance point of kidney stones comprising: A processing module, used for acquiring a three-dimensional CT image of a patient with kidney stones, and slicing the three-dimensional CT image to obtain a plurality of two-dimensional CT images; An extraction module, used for performing binarization processing on a plurality of two-dimensional CT images respectively by using an Ostu threshold algorithm, and determining bone point cloud data and lung gas point cloud data according to the plurality of binarized images; The extraction module is also used to obtain body surface contour point cloud data through gradient edge detection sobel algorithm according to multiple two-dimensional CT images; A construction module, used to construct a skeleton avoidance constraint function according to the skeleton point cloud data, to construct a lung gas avoidance constraint function according to the lung gas point cloud data, and to construct a stone surface incident point prediction model according to the shock wave focal length constraint function, the skeleton avoidance constraint function and the lung gas avoidance constraint function; The output module is used to input the body surface contour point cloud data, the bone point cloud data, the lung gas point cloud data and the stone point prediction coordinates into the stone body surface incident point prediction model to obtain the optimal body surface incident point of kidney stones.

[0012] In addition, to achieve the above-mentioned purpose, the present invention also proposes a device for determining the surface impact point of kidney stones, the device comprising: a memory, a processor, and a program for determining the surface impact point of kidney stones stored in the memory and executable on the processor, the program for determining the surface impact point of kidney stones being configured to implement the steps of the method for determining the surface impact point of kidney stones as described above.

[0013] In addition, to achieve the above-mentioned purpose, the present invention also proposes a storage medium, on which a program for determining the surface impact point of kidney stones is stored. When the program for determining the surface impact point of kidney stones is executed by a processor, the steps of the method for determining the surface impact point of kidney stones as described above are implemented.

[0014] The present invention first obtains a three-dimensional CT image of a patient with kidney stones, and slices the three-dimensional CT image to obtain a plurality of two-dimensional CT images, then binarizes the plurality of two-dimensional CT images respectively through an Ostu threshold algorithm, and determines bone point cloud data and lung gas point cloud data according to the plurality of binarized images, obtains body surface contour point cloud data through a gradient edge detection sobel algorithm according to the plurality of two-dimensional CT images, then constructs a bone avoidance constraint function according to the bone point cloud data, constructs a lung gas avoidance constraint function according to the lung gas point cloud data, and constructs a stone body surface incident point prediction model according to a shock wave focal length constraint function, a bone avoidance constraint function and a lung gas avoidance constraint function, and finally inputs the body surface contour point cloud data, the bone point cloud data, the lung gas point cloud data and the stone point prediction coordinates into the stone body surface incident point prediction model to obtain the optimal body surface incident point of the kidney stone. The present invention greatly improves the accuracy of kidney stone surface entry point planning through a stone surface entry point prediction model, reduces the practical difficulty of entry point selection for extracorporeal lithotripsy, can calculate the optimal solution that can avoid risk areas, and improves the efficiency of lithotripsy. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic structural diagram of a device for determining the body surface entrance point of kidney stones in a hardware operating environment involved in an embodiment of the present invention; Figure 2 It is a schematic flow chart of a first embodiment of a method for determining a body surface entry point of a kidney stone according to the present invention; Figure 3 It is a schematic flow chart of a method for automatically planning the external entry point of a kidney stone according to the first embodiment of the method for determining the body surface entry point of a kidney stone of the present invention; Figure 4 This is a structural block diagram of the first embodiment of the system for determining the body surface entry point of kidney stones of the present invention.

[0016] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0017] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0018] Reference Figure 1 , Figure 1The present invention is a schematic diagram of the structure of a device for determining the surface entry point of kidney stones in the hardware operating environment involved in the embodiment of the present invention.

[0019] like Figure 1 As shown, the device for determining the surface entry point of kidney stones may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (RandomAccess Memory, RAM), or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk storage. The memory 1005 may also be a storage system independent of the aforementioned processor 1001.

[0020] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the device for determining the body surface entry point of kidney stones, and may include more or less components than those shown in the figure, or a combination of certain components, or a different arrangement of components.

[0021] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a program for determining the body surface entry point of kidney stones.

[0022] exist Figure 1 In the device for determining the surface impact point of kidney stones shown in the figure, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the device for determining the surface impact point of kidney stones of the present invention can be arranged in the device for determining the surface impact point of kidney stones, and the device for determining the surface impact point of kidney stones calls the program for determining the surface impact point of kidney stones stored in the memory 1005 through the processor 1001, and executes the method for determining the surface impact point of kidney stones provided in the embodiment of the present invention.

[0023] The embodiment of the present invention provides a method for determining the surface incident point of kidney stones, referring to Figure 2 , Figure 2Schematic diagram of the flow chart of the first embodiment of the method for determining the body surface entry point of kidney stones of the present invention.

[0024] In this embodiment, the method for determining the body surface entry point of kidney stones comprises the following steps: Step S10: Acquire a three-dimensional CT image of a patient with kidney stones, and slice the three-dimensional CT image to obtain a plurality of two-dimensional CT images.

[0025] It is easy to understand that the execution subject of this embodiment can be a kidney stone surface entry point determination system with functions such as data processing, network communication and program running, or other computer equipment with similar functions, etc., and this embodiment is not limited.

[0026] In this embodiment, it is necessary to obtain the DICOM format CT slice file (i.e., DICOM file) of the kidney stone patient in advance, and then use the medical image processing software SimpleITK to parse the DICOM format CT slice file to obtain a three-dimensional CT image and DICOM metadata, and its DICOM metadata includes detailed information such as patient information, scanning parameters, and CT layer number. Specific parameters include image resolution, scanning area size, and scanning time.

[0027] In a specific implementation, it is necessary to resample the three-dimensional CT image and adjust the resolution of the three-dimensional CT image to meet the needs of subsequent processing.

[0028] The resampling process adjusts all images to the same voxel size of 1mm×1mm×1mm to eliminate the impact of equipment differences. In addition, the image is standardized to adjust the grayscale value of the image to a uniform range of 0 to 255 to enhance the image contrast and improve the visualization effect.

[0029] Furthermore, it is necessary to slice the three-dimensional CT image based on the number of CT layers (ie, the number of CT slices), and convert the format of the sliced ​​multiple CT images to obtain multiple two-dimensional CT images.

[0030] It should also be noted that, since the multiple CT images after slicing are still in DICOM format, the multiple CT images need to be format converted to obtain multiple two-dimensional CT images in PNG format.

[0031] Assuming that the number of CT slices is 256, 256 two-dimensional CT images in PNG format are generated.

[0032] Step S20: binarizing the plurality of two-dimensional CT images respectively by using the Ostu threshold algorithm, and determining the bone point cloud data and the lung gas point cloud data according to the plurality of binarized images.

[0033] Furthermore, the foreground pixel ratio, background pixel ratio, foreground average gray value and background average gray value corresponding to each two-dimensional CT image are determined respectively; the segmentation pixel point threshold corresponding to each two-dimensional CT image is obtained by using the Ostu threshold algorithm according to the foreground pixel ratio, background pixel ratio, foreground average gray value and background average gray value; and the multiple two-dimensional CT images are binarized respectively based on the segmentation pixel point threshold.

[0034] In this implementation, the segmentation pixel threshold is used to segment the two-dimensional CT image into grayscale values ​​of foreground and background regions, wherein the foreground is the target region to be extracted (the region corresponding to the bones and lung gas).

[0035] After acquiring multiple two-dimensional CT images, first ensure that the multiple two-dimensional CT images are grayscale images. If they are color images, first convert them into grayscale images. After the conversion is completed, calculate the 256-level grayscale histogram for the image. Then apply the Ostu algorithm to calculate an optimal threshold (i.e., the segmentation pixel threshold) so that the inter-class variance between the foreground and the background is maximized. The inter-class variance refers to a statistic that measures the difference between the foreground and the background. The larger the inter-class variance, the higher the distinction between the foreground and the background.

[0036] Between-class variance The calculation formula is:

[0037] in, and They represent the ratio of pixels below and above the segmentation pixel threshold T, that is, the ratio of background pixels to total pixels (i.e., background pixel ratio) and the ratio of foreground pixels to total pixels (i.e., foreground pixel ratio). and They represent the average gray values ​​of pixels below and above the segmentation pixel threshold T, namely the background average gray value and the foreground average gray value.

[0038] For bones, set the grayscale range to search from 200 HU to 1500 HU. For lung gas, set the grayscale range to search from -1000 HU to -500 HU.

[0039] After the Ostu algorithm is used to obtain the threshold that maximizes the inter-class variance, the threshold (i.e., the segmentation pixel threshold) is used to binarize multiple two-dimensional CT images.

[0040] It should also be noted that pixels above the threshold are considered as the target area (bone or lung gas), and those below the threshold are considered as the background.

[0041] Furthermore, the processing method for determining the bone point cloud data and the lung gas point cloud data based on multiple binary images is to extract the bone point coordinates and the lung gas point coordinates from the multiple binary images according to the segmentation pixel point threshold; generate the bone point cloud data according to the bone point coordinates, and generate the lung gas point cloud data according to the lung gas point coordinates.

[0042] Step S30: obtaining body surface contour point cloud data through gradient edge detection Sobel algorithm according to multiple two-dimensional CT images.

[0043] Furthermore, it is determined whether the multiple two-dimensional CT images are grayscale images; if so, all pixel points corresponding to each two-dimensional CT image are determined, and the horizontal gradient and vertical gradient of each pixel point are calculated respectively; the approximate total amplitude of the gradient of each pixel point is calculated by the gradient edge detection sobel algorithm according to the horizontal gradient and the vertical gradient; the edge point coordinates are extracted from the multiple two-dimensional CT images according to the approximate total amplitude of the gradient; and the body surface contour point cloud data is determined according to the edge point coordinates.

[0044] In this implementation, the gradient edge detection Sobel algorithm is a method for image edge detection, which identifies the edge portion in the image by calculating the gradient size of the image pixel points.

[0045] After confirming that the image is a grayscale image, the Sobel algorithm is applied to obtain 256 CT images in PNG format (i.e., multiple two-dimensional CT images). All two-dimensional CT images are traversed, and each pixel of the two-dimensional CT image is processed. The gradient edge detection Sobel algorithm is used to calculate the gradient in the horizontal and vertical directions. The approximate total amplitude of the gradient is calculated by the following formula:

[0046] in, Refers to the horizontal gradient, Refers to the vertical gradient. The calculation methods of these two gradients are:

[0047]

[0048] Where A is the 3x3 region around each pixel in the 2D CT image.

[0049] After the gradient calculation is completed, the algorithm sets a gradient threshold. Only when the gradient of a pixel is greater than this threshold, it is considered an edge point. The gradient threshold can be set to 50. Based on the gradient data, the coordinates extracted from all edge points are the surface contour point cloud data.

[0050] Step S40: construct a skeleton avoidance constraint function according to the skeleton point cloud data, construct a lung gas avoidance constraint function according to the lung gas point cloud data, and construct a stone surface incident point prediction model according to the shock wave focal length constraint function, the skeleton avoidance constraint function and the lung gas avoidance constraint function.

[0051] It should also be noted that the focal length constraint function of the shock wave refers to the specific distance at which the shock wave energy is focused and achieves the maximum effect. The ideal injection point should be within this focal length range to ensure the treatment effect. is the focal length of the device, is the actual distance from the device to the candidate incident point i, then the constraint can be expressed as:

[0052] in Refers to the maximum allowable deviation, indicating the range in which the incident distance can fluctuate compared to the focal length. Set to 2cm.

[0053] For safety, it is necessary to ensure that the incident point is sufficiently far from the bones or lung gas to avoid potential damage or weakening of the effect caused by the propagation of the shock wave in these media. The distance is calculated by traversing the bone point cloud through the bone point cloud data obtained above and calculating the shortest distance from the candidate incident point i to the bone point cloud.

[0054] Let P represent a point in the skeleton point cloud, i represent the candidate incident point, and the skeleton point cloud can be represented as a set of points . Each point The coordinates of The coordinates of the incident point are . Alternative incident point i to a point in the bone point cloud The distance d is calculated by the following formula:

[0055] Therefore, the closest distance from the incident point i to the bone point cloud , is obtained by traversing all points in the skeleton point cloud and calculating the minimum distance:

[0056] Through the lung point cloud data obtained above, traverse the lung point cloud and calculate the shortest distance from the candidate incident point i to the lung point cloud.

[0057] Let F represent a point in the lung point cloud, i represent the candidate incident point, and the lung point cloud can be represented as a set of points . Each point The coordinates of The coordinates of the incident point are . Alternative incident point i to a point in the lung point cloud The distance d is calculated by the following formula:

[0058] The shortest distance from the incident point i to the lung point cloud , is obtained by traversing all points in the lung point cloud and calculating the minimum distance:

[0059] From the above calculation, is the distance from the candidate incident point i to the nearest bone, is the distance to the nearest lung gas, then the bone avoidance constraint function and the lung gas avoidance constraint function can be expressed as:

[0060] in, and are the minimum safe distances from bones and lung gas, respectively. Here, Set to 1cm, Set to 0.5cm.

[0061] The problem of selecting the extracorporeal entry point for kidney stones is formalized as a multiple knapsack problem. Taking into account the shock wave focal length constraint and the bone / lung gas avoidance constraint, a multiple knapsack model (i.e., the stone surface entry point prediction model) is constructed. Each constraint is regarded as a "knapsack", and each alternative entry point is regarded as an "item" with a specific "weight" (the weight here corresponds to the load of the constraint corresponding to the entry point) and "value" (the value here corresponds to the risk assessment of the entry point).

[0062] Define the following variables: : The total number of candidate incident points; : Decision variable, if the incident point i is selected then =1, otherwise =0.

[0063] : The distance from the incident point i to the stone target point.

[0064] : Device focal length.

[0065] : The distance from the incident point i to the nearest bone.

[0066] : The distance from the incident point i to the nearest lung gas.

[0067] : Risk assessment value of incident point i.

[0068] The goal is to select the entry point with the least risk while ensuring that all medical and anatomical constraints are met. The objective function is:

[0069] Constraints: ,

[0070] ,

[0071] ,

[0072] This means that the focal length can be effectively controlled only when the distance between the incident point i and the ideal focal length is within the maximum allowable deviation Δ, and the distance from the incident point to the nearest bone and lung gas is not less than S min and G min At the same time, ensure that the decision variable is binary, indicating that the incident point is selected or not:

[0073] Risks for entry points , the risk assessment formula is:

[0074] Among them, α, β, γ are weight factors, which are adjusted according to treatment priority and safety criteria. It is the maximum treatment distance considered, which refers to the longest distance that can be accepted in treatment. In practical applications, considering the flexibility of treatment and the changes in patient body shape, this distance can be appropriately increased. Set to focal length twice. Set to 0.3, Set to 0.3, Set to 0.4.

[0075] Step S50: inputting the body surface contour point cloud data, the bone point cloud data, the lung gas point cloud data and the stone point prediction coordinates into the stone body surface incident point prediction model to obtain the optimal body surface incident point of kidney stones.

[0076] Furthermore, the body surface contour point cloud data, bone point cloud data, lung gas point cloud data and stone point predicted coordinates are input into the stone body surface incident point prediction model; based on the stone body surface incident point prediction model, multiple alternative incident points are selected from the body surface contour point cloud data according to the stone point predicted coordinates through the Euclidean distance formula; multiple candidate incident points are selected from the multiple alternative incident points through the shock wave focal length constraint function, the bone avoidance constraint function and the lung gas avoidance constraint function; the incident point risk value of each candidate incident point is calculated respectively through the risk assessment formula; the candidate incident point with the lowest risk value is selected from the multiple candidate incident points according to the incident point risk value; the candidate incident point with the lowest risk value is output through the stone body surface incident point prediction model to obtain the optimal body surface incident point of kidney stones.

[0077] It should also be noted that the body surface contour point cloud is traversed, the Euclidean distance between the body surface contour point cloud and the stone target point is calculated, and all body surface contour points with a calculated Euclidean distance less than or equal to 10 cm are retained as candidate incident points.

[0078] The doctor selects a target two-dimensional CT image from multiple two-dimensional CT images and selects the target stone point based on the target two-dimensional CT image. The xy coordinates are the coordinates in the two-dimensional CT image, and the z coordinate is the layer number of the selected target two-dimensional CT image (the layer it is on). The result is the three-dimensional coordinates (x, y, z) of the stone target point.

[0079] In this embodiment, reference Figure 3 , Figure 3 This is a flow chart of the method for automatically planning the external entry point of kidney stones in the first embodiment of the method for determining the surface entry point of kidney stones of the present invention. For all candidate entry points, the constraint condition is first checked. Each constraint condition is regarded as a backpack, and each backpack has a limited capacity, that is, the maximum tolerable violation degree. The constraint violation degree of each entry point is regarded as its consumption of the backpack capacity. For the shock wave focal length constraint condition, the backpack capacity Set to 2cm. For the bone and gas constraints, the backpack capacity and Set to 1cm and 0.5cm respectively.

[0080] For each entry point, calculate its capacity consumption for each backpack (i.e. constraint condition) . It is defined as the degree to which the incident point i violates the constraint j.

[0081] For the shockwave focal length constraint:

[0082] in Refers to the distance from the incident point i to the stone target point. If the difference is greater than the preset , then the backpack capacity of this constraint is considered to be over-consumed.

[0083] For a bone avoidance constraint:

[0084] in Refers to the distance from the incident point i to the nearest bone.

[0085] For the gas avoidance constraint:

[0086] in Refers to the distance from the incident point i to the nearest lung gas. If the distance from the incident point to the bone or lung is less than the minimum safety distance, that is, and , then the backpack capacity of this constraint is considered to be over-consumed.

[0087] If the capacity of any knapsack is exhausted, that is, the entry point does not satisfy one or more constraints, the entry point will be excluded and not used for subsequent treatment planning.

[0088] Through the above, all the incident points that meet the constraints (i.e., multiple candidate incident points) can be obtained, and then the risk values ​​of multiple candidate incident points are calculated. The incident point with the smallest comprehensive risk is selected as the optimal solution for the incident and the result is output.

[0089] In this embodiment, a three-dimensional CT image of a patient with kidney stones is first obtained, and the three-dimensional CT image is sliced ​​to obtain multiple two-dimensional CT images. Then, the multiple two-dimensional CT images are binarized by the Ostu threshold algorithm, and the bone point cloud data and the lung gas point cloud data are determined according to the multiple binarized images. The body surface contour point cloud data is obtained by the gradient edge detection sobel algorithm according to the multiple two-dimensional CT images. Then, a bone avoidance constraint function is constructed according to the bone point cloud data, a lung gas avoidance constraint function is constructed according to the lung gas point cloud data, and a stone surface incident point prediction model is constructed according to the shock wave focal length constraint function, the bone avoidance constraint function and the lung gas avoidance constraint function. Finally, the body surface contour point cloud data, the bone point cloud data, the lung gas point cloud data and the stone point prediction coordinates are input into the stone surface incident point prediction model to obtain the optimal body surface incident point of the kidney stone. This embodiment greatly improves the accuracy of kidney stone surface entry point planning through the stone surface entry point prediction model, reduces the practical difficulty of entry point selection for extracorporeal lithotripsy, can calculate the optimal solution that can avoid risk areas, and improves the efficiency of lithotripsy.

[0090] Reference Figure 4 , Figure 4This is a structural block diagram of the first embodiment of the system for determining the body surface entry point of kidney stones of the present invention.

[0091] like Figure 4 As shown, the system for determining the body surface entrance point of kidney stones proposed in the embodiment of the present invention includes: The processing module 4001 is used to obtain a three-dimensional CT image of a patient with kidney stones, and slice the three-dimensional CT image to obtain multiple two-dimensional CT images; An extraction module 4002 is used to perform binarization processing on the multiple two-dimensional CT images respectively by using an Ostu threshold algorithm, and determine the bone point cloud data and the lung gas point cloud data according to the multiple binary images; The extraction module 4002 is also used to obtain body surface contour point cloud data through gradient edge detection sobel algorithm according to multiple two-dimensional CT images; A construction module 4003 is used to construct a skeleton avoidance constraint function according to the skeleton point cloud data, to construct a lung gas avoidance constraint function according to the lung gas point cloud data, and to construct a stone surface incident point prediction model according to the shock wave focal length constraint function, the skeleton avoidance constraint function and the lung gas avoidance constraint function; The output module 4004 is used to input the body surface contour point cloud data, the bone point cloud data, the lung gas point cloud data and the stone point prediction coordinates into the stone body surface incident point prediction model to obtain the optimal body surface incident point of kidney stones.

[0092] Other embodiments or specific implementations of the system for determining the body surface entry point of kidney stones of the present invention can refer to the above-mentioned method embodiments, which will not be described in detail here.

[0093] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0094] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0095] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0096] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for determining the body surface entry point of kidney stones, characterized in that: The method for determining the body surface entry point of kidney stones comprises the following steps: Acquire a three-dimensional CT image of a patient with kidney stones, and slice the three-dimensional CT image to obtain multiple two-dimensional CT images; Binarization is performed on multiple two-dimensional CT images respectively by using the Ostu threshold algorithm, and bone point cloud data and lung gas point cloud data are determined according to the multiple binary images; The body surface contour point cloud data is obtained by using the gradient edge detection sobel algorithm based on multiple two-dimensional CT images; Constructing a skeleton avoidance constraint function according to the skeleton point cloud data, constructing a lung gas avoidance constraint function according to the lung gas point cloud data, and constructing a stone surface incident point prediction model according to the shock wave focal length constraint function, the skeleton avoidance constraint function and the lung gas avoidance constraint function; The body surface contour point cloud data, the bone point cloud data, the lung gas point cloud data and the stone point prediction coordinates are input into the stone body surface incident point prediction model to obtain the optimal body surface incident point of kidney stones.

2. The method according to claim 1, characterized in that The step of slicing the three-dimensional CT image to obtain a plurality of two-dimensional CT images comprises: Parsing the DICOM file of the kidney stone patient to obtain DICOM metadata; Determining the number of CT slices according to the DICOM metadata; The three-dimensional CT image is sliced ​​based on the number of CT layers, and the format of the sliced ​​multiple CT images is converted to obtain multiple two-dimensional CT images.

3. The method according to claim 1, characterized in that The step of performing binarization processing on the plurality of two-dimensional CT images respectively by using the Ostu threshold algorithm comprises: respectively determining the foreground pixel ratio, background pixel ratio, foreground average gray value and background average gray value corresponding to each two-dimensional CT image; Obtaining the segmentation pixel threshold corresponding to each two-dimensional CT image through the Ostu threshold algorithm according to the foreground pixel ratio, the background pixel ratio, the foreground average gray value and the background average gray value; Binarization processing is performed on multiple two-dimensional CT images based on the segmentation pixel threshold.

4. The method according to claim 3, characterized in that The step of determining the bone point cloud data and the lung gas point cloud data according to the multiple binary images comprises: extracting bone point coordinates and lung gas point coordinates from a plurality of binary images according to the segmentation pixel point threshold; Skeleton point cloud data is generated according to the skeleton point coordinates, and lung gas point cloud data is generated according to the lung gas point coordinates.

5. The method according to claim 1, characterized in that The step of obtaining body surface contour point cloud data by gradient edge detection Sobel algorithm according to multiple two-dimensional CT images includes: Determine whether multiple two-dimensional CT images are grayscale images; If yes, all the pixels corresponding to each 2D CT image are determined, and the horizontal gradient and vertical gradient of each pixel are calculated respectively; Calculate the approximate total amplitude of the gradient of each pixel point by using the gradient edge detection sobel algorithm according to the horizontal gradient and the vertical gradient; Extracting edge point coordinates from a plurality of two-dimensional CT images according to the total amplitude of the gradient approximation; The body surface contour point cloud data is determined according to the edge point coordinates.

6. The method according to any one of claims 1 to 5, characterized in that: The step of inputting the body surface contour point cloud data, the bone point cloud data, the lung gas point cloud data and the stone point prediction coordinates into the stone body surface incident point prediction model to obtain the optimal body surface incident point of kidney stones includes: Inputting the body surface contour point cloud data, the bone point cloud data, the lung gas point cloud data and the stone point prediction coordinates into the stone body surface incident point prediction model; Based on the stone body surface incident point prediction model, multiple candidate incident points are selected from the body surface contour point cloud data by using the Euclidean distance formula according to the stone point prediction coordinates; Selecting a plurality of candidate incident points from a plurality of candidate incident points by using the shock wave focal length constraint function, the bone avoidance constraint function and the lung gas avoidance constraint function; The entry point risk value of each candidate entry point is calculated by the risk assessment formula; Selecting a candidate incident point with a lowest risk value from a plurality of candidate incident points according to the risk value of the incident point; The candidate entry point with the lowest risk value is output through the stone surface entry point prediction model to obtain the optimal surface entry point of kidney stones.

7. A system for determining the body surface entry point of kidney stones, characterized in that: The body surface entry point determination system for kidney stones comprises: A processing module, used for acquiring a three-dimensional CT image of a patient with kidney stones, and slicing the three-dimensional CT image to obtain a plurality of two-dimensional CT images; An extraction module, used for performing binarization processing on a plurality of two-dimensional CT images respectively by using an Ostu threshold algorithm, and determining bone point cloud data and lung gas point cloud data according to the plurality of binarized images; The extraction module is also used to obtain body surface contour point cloud data through gradient edge detection sobel algorithm according to multiple two-dimensional CT images; A construction module, used to construct a skeleton avoidance constraint function according to the skeleton point cloud data, to construct a lung gas avoidance constraint function according to the lung gas point cloud data, and to construct a stone surface incident point prediction model according to the shock wave focal length constraint function, the skeleton avoidance constraint function and the lung gas avoidance constraint function; The output module is used to input the body surface contour point cloud data, the bone point cloud data, the lung gas point cloud data and the stone point prediction coordinates into the stone body surface incident point prediction model to obtain the optimal body surface incident point of kidney stones.

8. A device for determining the body surface entry point of kidney stones, characterized in that: The device includes: a memory, a processor, and a program for determining the surface entrance point of kidney stones stored in the memory and executable on the processor, wherein the program for determining the surface entrance point of kidney stones is configured to implement the steps of the method for determining the surface entrance point of kidney stones as described in any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium stores a program for determining the surface incident point of a kidney stone. When the program for determining the surface incident point of a kidney stone is executed by a processor, the steps of the method for determining the surface incident point of a kidney stone as described in any one of claims 1 to 6 are implemented.

Images