CN119970266B - Body surface incidence point determination method, system, equipment and storage medium for kidney stones - Google Patents
Body surface incidence point determination method, system, equipment and storage medium for kidney stonesInfo
- Publication number
- CN119970266B CN119970266B CN202510454614.5A CN202510454614A CN119970266B CN 119970266 B CN119970266 B CN 119970266B CN 202510454614 A CN202510454614 A CN 202510454614A CN 119970266 B CN119970266 B CN 119970266B
- Authority
- CN
- China
- Prior art keywords
- point
- body surface
- cloud data
- incidence
- point cloud
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Apparatus For Radiation Diagnosis (AREA)
Abstract
本发明公开了一种肾结石的体表入射点确定方法、系统、设备及存储介质，所述方法包括：对肾结石患者的三维CT图像进行切片处理，获得多张二维CT图像；通过Ostu阈值算法分别对多张二维CT图像进行二值化处理，并根据多张二值化图像确定骨骼点云数据和肺部气体点云数据；根据多张二维CT图像通过梯度边缘检测sobel算法获得体表轮廓点云数据；将体表轮廓点云数据、骨骼点云数据、肺部气体点云数据及结石点预测坐标输入至结石体表入射点预测模型中，以获得肾结石的最优体表入射点。本发明通过结石体表入射点预测模型，极大提高了肾结石体表入射点规划的准确度，降低了体外碎石手术入射点选取的实操难度，提高了碎石手术的效率。
The present invention discloses a method, system, device, and storage medium for determining the surface entry point of a kidney stone. The method comprises: slicing a three-dimensional CT image of a kidney stone patient to obtain multiple two-dimensional CT images; binarizing the multiple two-dimensional CT images using an Ostu threshold algorithm, and determining bone point cloud data and lung gas point cloud data based on the multiple binarized images; obtaining surface contour point cloud data based on the multiple two-dimensional CT images using a gradient edge detection Sobel algorithm; and inputting the surface contour point cloud data, bone point cloud data, lung gas point cloud data, and stone point prediction coordinates into a stone surface entry point prediction model to obtain the optimal surface entry point of the kidney stone. The present invention, through the stone surface entry point prediction model, greatly improves the accuracy of kidney stone surface entry point planning, reduces the practical difficulty of entry point selection in extracorporeal lithotripsy surgery, and improves the efficiency of lithotripsy surgery.
Description
Technical Field
The invention belongs to the technical field of medical equipment, and particularly relates to a body surface incidence point determining method, a body surface incidence point determining system, body surface incidence point determining equipment and a storage medium for kidney stones.
Background
Kidney stones are a common disease, and one of the treatment modes is the use of External Shock Wave Lithotripsy (ESWL), which is also a difficult problem in technical research. Conventional methods of point of incidence selection rely primarily on the experience of the physician and manual operation, which is not only time consuming, but also results with limited accuracy to the level of skill of the operator. Furthermore, due to the complexity of the patient anatomy, conventional approaches have difficulty adequately considering all clinical guidelines, which may result in poor surgical outcome or additional injury to the patient.
The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present invention and is not intended to represent an admission that the foregoing is prior art.
Disclosure of Invention
The invention mainly aims to provide a body surface incidence point determining method, a body surface incidence point determining system, body surface incidence point determining equipment and a storage medium for kidney stones, and aims to solve the technical problem of how to accurately and efficiently select an optimal shock wave incidence point.
In order to achieve the above object, the present invention provides a body surface incidence point determination method for kidney stones, the body surface incidence point determination method for kidney stones comprising:
Acquiring a three-dimensional CT image of a kidney stone patient, and performing slice processing on the three-dimensional CT image to obtain a plurality of two-dimensional CT images;
Respectively carrying out binarization processing on a plurality of two-dimensional CT images through an Ostu threshold algorithm, and determining bone point cloud data and lung gas point cloud data according to the plurality of binarized images;
acquiring body surface contour point cloud data through a gradient edge detection sobel algorithm according to a plurality of two-dimensional CT images;
constructing a bone avoidance constraint function according to the bone point cloud data, constructing a lung gas avoidance constraint function according to the lung gas point cloud data, and constructing a stone body surface incidence point prediction model according to the shock wave focal length constraint function, the bone avoidance constraint function and the lung gas avoidance constraint function;
And inputting the body surface contour point cloud data, the bone point cloud data, the lung gas point cloud data and the calculus point prediction coordinates into the calculus body surface incidence point prediction model so as to obtain an optimal body surface incidence point of kidney calculus.
Optionally, the step of performing slice processing on the three-dimensional CT image to obtain a plurality of two-dimensional CT images includes:
resolving the DICOM file of the kidney stone patient to obtain DICOM metadata;
determining CT layer number according to the DICOM metadata;
And carrying out slice processing on the three-dimensional CT image based on the CT layer number, and carrying out format conversion on a plurality of sliced CT images so as to obtain a plurality of two-dimensional CT images.
Optionally, the step of performing binarization processing on the plurality of two-dimensional CT images through an Ostu threshold algorithm includes:
respectively determining foreground pixel proportion, background pixel proportion, foreground average gray value and background average gray value corresponding to each two-dimensional CT image;
obtaining a segmentation pixel point threshold value corresponding to each two-dimensional CT image through an Ostu threshold algorithm according to the foreground pixel proportion, the background pixel proportion, the foreground average gray value and the background average gray value;
and respectively carrying out binarization processing on the plurality of two-dimensional CT images based on the segmentation pixel point threshold value.
Optionally, the step of determining bone point cloud data and lung gas point cloud data from the plurality of binarized images includes:
Extracting skeleton point coordinates and lung gas point coordinates from a plurality of binarized images according to the segmentation pixel point threshold;
and generating skeleton point cloud data according to the skeleton point coordinates, and generating lung gas point cloud data according to the lung gas point coordinates.
Optionally, the step of obtaining the body surface contour point cloud data according to the plurality of two-dimensional CT images through a gradient edge detection sobel algorithm includes:
Judging whether the plurality of two-dimensional CT images are gray-scale images or not;
if yes, determining all pixel points corresponding to each two-dimensional CT image, and respectively calculating the horizontal gradient and the vertical gradient of each pixel point;
Calculating the approximate total amplitude of the gradient of each pixel point through a 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 gradient approximate total amplitude;
and determining body surface contour point cloud data according to the edge point coordinates.
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 calculus point prediction coordinates into the calculus body surface incidence point prediction model to obtain an optimal body surface incidence point of kidney calculus includes:
inputting the body surface contour point cloud data, the bone point cloud data, the lung gas point cloud data and the calculus point prediction coordinates into the calculus body surface incidence point prediction model;
Selecting a plurality of alternative incidence points from the body surface contour point cloud data according to a calculus point prediction coordinate and a Euclidean distance formula based on the calculus body surface incidence point prediction model;
Selecting a plurality of candidate incidence points from a plurality of candidate incidence points through a shock wave focal length constraint function, the bone avoidance constraint function and the lung gas avoidance constraint function;
Calculating the incidence point risk value of each candidate incidence point through a risk evaluation formula;
Selecting a candidate incidence point with the lowest risk value from a plurality of candidate incidence points according to the incidence point risk value;
and outputting the candidate incidence points with the lowest risk values through the stone body surface incidence point prediction model so as to obtain the optimal body surface incidence points of the kidney stones.
In addition, in order to achieve the above object, the present invention also provides a body surface incidence point determination system for kidney stones, the body surface incidence point determination system for kidney stones comprising:
The processing module is used for acquiring a three-dimensional CT image of a kidney stone patient, and carrying out slice processing on the three-dimensional CT image to obtain a plurality of two-dimensional CT images;
The extraction module is used for respectively carrying out binarization processing on the two-dimensional CT images through an Ostu threshold algorithm and determining bone point cloud data and lung gas point cloud data according to the two-dimensional CT images;
The extraction module is also used for obtaining body surface contour point cloud data through a gradient edge detection sobel algorithm according to a plurality of two-dimensional CT images;
The construction module is used for constructing a bone avoidance constraint function according to the bone point cloud data, constructing a lung gas avoidance constraint function according to the lung gas point cloud data, and constructing a stone body surface incidence point prediction model according to the shock wave focal length constraint function, the bone avoidance constraint function and the lung gas avoidance constraint function;
The output module is used for inputting the body surface contour point cloud data, the bone point cloud data, the lung gas point cloud data and the calculus point prediction coordinates into the calculus body surface incidence point prediction model so as to obtain an optimal body surface incidence point of kidney calculus.
In addition, in order to achieve the aim, the invention also provides a body surface incidence point determining device of kidney stones, which comprises a memory, a processor and a body surface incidence point determining program of kidney stones, wherein the body surface incidence point determining program of kidney stones is stored on the memory and can run on the processor, and is configured to realize the steps of the body surface incidence point determining method of kidney stones.
In addition, in order to achieve the above object, the present invention also proposes a storage medium having stored thereon a body surface incidence point determination program of kidney stones, which when executed by a processor, implements the steps of the body surface incidence point determination method of kidney stones as described above.
According to the method, firstly, a three-dimensional CT image of a kidney stone patient is obtained, the three-dimensional CT image is subjected to slicing treatment to obtain a plurality of two-dimensional CT images, then the two-dimensional CT images are subjected to binarization treatment respectively through an Ostu threshold algorithm, bone point cloud data and lung gas point cloud data are determined according to the two-dimensional CT images, body surface contour point cloud data are obtained through a gradient edge detection sobel algorithm according to the two-dimensional CT images, 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, a stone body surface incidence point prediction model is constructed according to a shock wave focal length constraint function, the bone avoidance constraint function and the lung gas avoidance constraint function, and finally body surface contour point cloud data, the bone point cloud data, the lung gas point cloud data and stone point prediction coordinates are input into the stone body surface incidence point prediction model to obtain an optimal body surface incidence point of the kidney stone. According to the invention, through the stone body surface incidence point prediction model, the accuracy of planning the kidney stone body surface incidence points is greatly improved, the actual operation difficulty of selecting the incidence points of the external stone breaking operation is reduced, the optimal solution capable of avoiding the risk area can be calculated, and the efficiency of the stone breaking operation is improved.
Drawings
FIG. 1 is a schematic diagram of a body surface incidence point determination device for kidney stones in a hardware operating environment according to an embodiment of the invention;
FIG. 2 is a flow chart of a first embodiment of a method for determining body surface entry points of kidney stones according to the invention;
fig. 3 is a schematic flow chart of an automatic planning method for external incidence points of kidney stones according to a first embodiment of the method for determining body surface incidence points of kidney stones of the invention;
Fig. 4 is a block diagram showing the construction of a first embodiment of the body surface incidence point determining system for kidney stones according to the invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, fig. 1 is a schematic diagram of a body surface incidence point determining device for kidney stones in a hardware operation environment according to an embodiment of the present invention.
As shown in fig. 1, the body surface incidence point determining device for kidney stones may include a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM) or a stable nonvolatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage system separate from the processor 1001 described above.
It will be appreciated by those skilled in the art that the structure shown in fig. 1 does not constitute a limitation of the body surface entry point determination device for kidney stones, and may include more or fewer components than shown, or certain components in combination, or a different arrangement of components.
As shown in fig. 1, a memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a body surface incidence point determination program for kidney stones.
In the apparatus for determining the body surface incidence point of the kidney stone shown in fig. 1, 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 a user, and the processor 1001 and the memory 1005 in the apparatus for determining the body surface incidence point of the kidney stone according to the present invention may be disposed in the apparatus for determining the body surface incidence point of the kidney stone, and the apparatus for determining the body surface incidence point of the kidney stone calls the program for determining the body surface incidence point of the kidney stone stored in the memory 1005 through the processor 1001, and executes the method for determining the body surface incidence point of the kidney stone according to the embodiment of the present invention.
The embodiment of the invention provides a body surface incidence point determining method for kidney stones, and referring to fig. 2, fig. 2 is a flow chart of a first embodiment of the body surface incidence point determining method for kidney stones.
In this embodiment, the method for determining the body surface incidence point of the kidney stone includes the following steps:
And step S10, acquiring a three-dimensional CT image of a kidney stone patient, and carrying out slice processing on the three-dimensional CT image to obtain a plurality of two-dimensional CT images.
It is to be understood that the execution subject of the present embodiment may be a body surface incidence point determining system of kidney stones with functions of data processing, network communication, program running, etc., or may be other computer devices with similar functions, etc., and the present embodiment is not limited thereto.
In this embodiment, a DICOM-format CT slice file (i.e., DICOM file) of a kidney stone patient needs to be acquired in advance, and then the DICOM-format CT slice file is analyzed by using the medical image processing software SIMPLEITK to obtain a three-dimensional CT image and DICOM metadata, where the DICOM metadata includes detailed information such as patient information, scan parameters, CT layer number, and the like. Specific parameters include resolution of the image, size of the scan area, and scan time.
In a specific implementation, the three-dimensional CT image needs to be resampled, and the resolution of the three-dimensional CT image is adjusted to adapt to the requirement of subsequent processing.
The resampling process adjusts all images to the same voxel size of 1mm to eliminate effects due to device differences. In addition, the image standardization processing is carried out, the gray value of the image is adjusted to be in a uniform range of 0 to 255, the contrast of the image is enhanced, and the visual effect is improved.
Further, it is necessary to perform a slice processing on the three-dimensional CT image based on the number of CT layers (i.e., the number of CT slices), and perform a format conversion on the plurality of CT images after slicing to obtain a plurality of two-dimensional CT images.
It should be noted that, since the plurality of CT images after slicing are still in DICOM format, the plurality of CT images need to be subjected to format conversion to obtain a plurality of two-dimensional CT images in PNG format.
Assuming that the number of CT slices is 256, 256 two-dimensional CT images in PNG format are generated.
And step 20, respectively carrying out binarization processing on the two-dimensional CT images through an Ostu threshold algorithm, and determining bone point cloud data and lung gas point cloud data according to the two-dimensional CT images.
Further, the foreground pixel proportion, the background pixel proportion, the foreground average gray value and the background average gray value corresponding to each two-dimensional CT image are respectively determined, the segmentation pixel point threshold value corresponding to each two-dimensional CT image is obtained through an Ostu threshold algorithm according to the foreground pixel proportion, the background pixel proportion, the foreground average gray value and the background average gray value, and the binarization processing is respectively carried out on the two-dimensional CT images based on the segmentation pixel point threshold value.
In this implementation, the split pixel point threshold is used to split the two-dimensional CT image into gray values for the foreground and background regions. The prospect is the target area (the area corresponding to the bone and lung gas) needing to be extracted.
After a plurality of two-dimensional CT images are acquired, the two-dimensional CT images are firstly ensured to be gray-scale images, and if the two-dimensional CT images are color images, the two-dimensional CT images are firstly converted into the gray-scale images. After the conversion is completed, a histogram of 256 gradations is calculated for the image. An Ostu algorithm is then applied to calculate an optimal threshold (i.e., the split pixel threshold) such that the inter-class variance between foreground and background is maximized. The inter-class variance refers to statistics that measure the difference between foreground and background. The larger the inter-class variance, the higher the degree of discrimination between foreground and background.
Inter-class varianceThe calculation formula is as follows:
Wherein, the AndThe proportions of pixels below and above the split pixel point threshold T, namely the proportion of background to total pixels (i.e. background pixel proportion) and the proportion of foreground pixels to total pixels (i.e. foreground pixel proportion) are represented respectively,AndThe average gray values of pixels below and above the split pixel point threshold T, namely the background average gray value and the foreground average gray value, are represented respectively.
The gray scale of the search was set to 200 HU to 1500 HU for bone. For pulmonary gases, the gray scale range of the search is set to-1000 HU to-500 HU.
After a threshold value for maximizing the inter-class variance is obtained through an Ostu algorithm, the threshold value (namely a segmentation pixel point threshold value) is used for respectively binarizing a plurality of two-dimensional CT images.
It should be noted that pixels above the threshold are considered as target regions (bone or lung gas), and pixels below the threshold are considered as background.
Further, the bone point cloud data and the lung gas point cloud data are determined according to the plurality of binarized images in a processing mode that bone point coordinates and lung gas point coordinates are extracted from the plurality of binarized images according to the segmentation pixel point threshold value, bone point cloud data are generated according to the bone point coordinates, and lung gas point cloud data are generated according to the lung gas point coordinates.
And step S30, obtaining body surface contour point cloud data through a gradient edge detection sobel algorithm according to a plurality of two-dimensional CT images.
Further, judging whether the two-dimensional CT images are gray level images or not, if yes, determining all pixel points corresponding to the two-dimensional CT images, respectively calculating horizontal gradients and vertical gradients of the pixel points, calculating gradient approximate total amplitude values of the pixel points according to the horizontal gradients and the vertical gradients through a gradient edge detection sobel algorithm, extracting edge point coordinates from the two-dimensional CT images according to the gradient approximate total amplitude values, and determining body surface contour point cloud data according to the edge point coordinates.
In this implementation, the gradient edge detection sobel algorithm is a method for image edge detection, and the edge portion in the image is identified by calculating the gradient magnitude of the image pixel point.
After confirming that the image is a gray level image, applying a Sobel algorithm to obtain 256 CT images (namely, a plurality of two-dimensional CT images) in png format, traversing all the two-dimensional CT images, processing each pixel point of the two-dimensional CT images, and calculating gradients in the horizontal and vertical directions by using the gradient edge detection Sobel algorithm. The approximate total magnitude of the gradient is calculated from the following formula:
Wherein, the Refers to a horizontal gradient of the gradient,Referring to vertical gradients, the calculation methods of the two gradients are respectively:
Where a is the 3x3 region around each pixel in the two-dimensional CT image.
After the gradient calculation is completed, the algorithm sets a gradient threshold value, and only when the gradient of the pixel point is larger than the threshold value, the pixel point is considered as an edge point. The gradient threshold may be set to 50. And based on the gradient data, extracting coordinates from all edge points, namely the body surface contour point cloud data.
And S40, constructing a bone avoidance constraint function according to the bone point cloud data, constructing a lung gas avoidance constraint function according to the lung gas point cloud data, and constructing a stone body surface incidence point prediction model according to the shock wave focal length constraint function, the bone avoidance constraint function and the lung gas avoidance constraint function.
It should be further noted that, the focal length of the shock wave is defined as a function of the focal length constraint of the shock wave, which is the specific distance at which the shock wave energy is focused and reaches the maximum effect. The ideal point of incidence should lie within this focal range to ensure therapeutic effect. Is provided withFor the focal length of the device,For the actual distance from the device to the alternative point of incidence i, the constraint can be expressed as:
Wherein the method comprises the steps of Refers to the maximum deviation allowed, indicating the range in which the incident distance can fluctuate compared to the focal length. Here, theSet to 2cm.
For safety, it is desirable to ensure that the point of incidence is sufficiently distant from the bone or lung gas to avoid potential injury or diminished effectiveness from propagation of the shock wave in these media. The distance is calculated by traversing the bone point cloud according to the bone point cloud data obtained above, and calculating the nearest distance from the candidate incidence point i to the bone point cloud.
Let P denote one point in a skeletal point cloud, i denote an alternative incident point, and the skeletal point cloud may be represented as a set of points. Wherein each pointIs the coordinates of (a). The incident point coordinates are. Alternative incident point i to a point in the skeletal point cloudThe distance d of (2) is calculated by the following formula:
thus, the closest distance of the incident point i to the skeletal point cloud Is obtained by traversing all points in the skeletal point cloud and calculating the minimum distance:
and traversing the lung point cloud according to the lung point cloud data obtained above, and calculating the nearest distance from the candidate incidence point i to the lung point cloud.
Let F denote one point in the pulmonary point cloud, i denote an alternative point of incidence, the pulmonary point cloud may be expressed as a set of points. Wherein each pointIs the coordinates of (a). The incident point coordinates are. Alternative incident point i to a point in the pulmonary point cloudThe distance d of (2) is calculated by the following formula:
closest distance of the point of incidence i to the pulmonary point cloud Is obtained by traversing all points in the pulmonary point cloud and calculating the minimum distance:
from the above calculation, it was found that, For an alternative incident point i to the nearest bone distance,For the distance to the nearest pulmonary gas, the bone avoidance constraint function and pulmonary gas avoidance constraint function can be expressed as:
Wherein, the And (3) withThe minimum safe distance to bone and lung gas, respectively. Here the number of the elements is the number,Is set to be 1cm in length,Set at 0.5cm.
The kidney stone in vitro entry point selection problem is formed as a multiple knapsack problem, and a multiple knapsack model (namely a stone body surface entry point prediction model) is constructed by considering shock wave focal length constraint and bone/lung gas avoidance constraint, each constraint is regarded as a knapsack, and each alternative entry point is regarded as an article, and a specific weight (the weight corresponds to the load of the constraint corresponding to the entry point) and a value (the value corresponds to the risk assessment of the entry point) are carried out.
The following variables are defined:
Alternative incident point total number;
decision variables, if the point of incidence i is selected =1, Otherwise=0.
The distance from the incident point i to the stone target point.
Focal length of the device.
The distance of the incident point i to the nearest bone.
The distance of the point of incidence i to the nearest pulmonary gas.
Risk assessment value of incident point i.
The goal is to select the point of incidence with the least risk while ensuring that all medical and anatomical constraints are met. The objective function is:
constraint conditions:
,
,
,
Indicating that the point of incidence i can be selected only if it is within the allowed maximum deviation delta from the ideal focal length and the distance from the point of incidence to the nearest bone and lung gas is not less than S min and G min. At the same time, ensure decision variables Binary, indicating either the point of incidence selection or non-selection:
risk for incident point The risk assessment formula is:
where α, β, γ are weighting factors, adjusted according to treatment priority and safety criteria. The maximum treatment distance is the maximum distance that can be accepted in the treatment, and in practical applications, this distance can be appropriately increased in consideration of the flexibility of the treatment and the variation of the body type of the patient. Here, theSet to focal lengthIs 2 times as large as the above.The setting is made to be 0.3,The setting is made to be 0.3,Set to 0.4.
And S50, inputting the body surface contour point cloud data, the bone 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 an optimal body surface incidence point of kidney calculus.
The method comprises the steps of obtaining body surface contour point cloud data, bone point cloud data, lung gas point cloud data and stone point prediction coordinates, 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 a stone body surface incidence point prediction model, selecting a plurality of candidate incidence points from the body surface contour point cloud data according to the stone point prediction coordinates through a Euclidean distance formula based on the stone body surface incidence point prediction model, selecting a plurality of candidate incidence points from the plurality of candidate incidence points through a shock wave focal length constraint function, a bone avoidance constraint function and a lung gas avoidance constraint function, calculating incidence point risk values of the candidate incidence points through a risk evaluation formula, selecting a candidate incidence point with the lowest risk value from the plurality of candidate incidence points according to the incidence point risk values, and outputting the candidate incidence points with the lowest risk value through the stone body surface incidence point prediction model so as to obtain the optimal body surface incidence point of kidney stones.
It should be further noted that, traversing the body surface contour point cloud, calculating the Euclidean distance between the body surface contour point cloud and the calculus target point, and reserving all the calculated body surface contour points with the Euclidean distance less than or equal to 10cm as alternative incidence points.
The doctor selects a target two-dimensional CT image from a plurality of two-dimensional CT images, a calculus target point is selected based on the target two-dimensional CT image, xy coordinates are coordinates in the two-dimensional CT image, z coordinates are layers (positioned on the first layer) of the selected target two-dimensional CT image, and the three-dimensional coordinates (x, y, z) of the calculus target point are obtained.
In this embodiment, referring to fig. 3, fig. 3 is a schematic flow chart of an automatic planning method for external incidence points of kidney stones according to a first embodiment of the method for determining external incidence points of kidney stones according to the invention, and first, constraint condition inspection is performed on all candidate incidence points. Each constraint is considered a backpack, each backpack having a limited capacity, i.e. a maximum degree of violation that can be tolerated. The degree of constraint violation at each point of incidence is considered to be its consumption of backpack capacity. Backpack capacity for shock wave focal length constraintsSet to 2cm. Backpack capacity for skeletal and gas constraintsAnd (3) withSet to 1cm and 0.5cm, respectively.
For each incident point, calculate its capacity consumption for each backpack (i.e., constraint)。Defined as the degree to which the point of incidence i violates constraint j.
For shock wave focal length constraints:
Wherein the method comprises the steps of Refers to the distance from the point of incidence i to the point of the stone target. If the difference is greater than a predetermined valueThe backpack capacity of this constraint is considered to be over-consumed.
For bone avoidance constraints:
Wherein the method comprises the steps of Refers to the distance of the point of incidence i to the nearest bone.
For gas avoidance constraints:
Wherein the method comprises the steps of Refers to the distance of the point of incidence i to the nearest pulmonary gas. If the distance from the incident point to the bone or lung is less than the minimum safe distance, i.eAnd (3) withThe backpack capacity of this constraint is considered to be over-consumed.
If the volume of either backpack is exhausted, i.e., the point of incidence does not meet one or more constraints, the point of incidence will be excluded from subsequent treatment planning.
All the incidence points meeting the constraint conditions (namely a plurality of candidate incidence points) can be obtained through the method, and then risk values are carried out on the plurality of candidate incidence pointsIs a function of the evaluation of (3). And selecting an incidence point with the minimum comprehensive risk as an optimal solution of incidence, and outputting a result.
In this embodiment, firstly, a three-dimensional CT image of a kidney stone patient is acquired, the three-dimensional CT image is sliced to obtain a plurality of two-dimensional CT images, then, the two-dimensional CT images are respectively binarized by an Ostu threshold algorithm, bone point cloud data and lung gas point cloud data are determined according to the two-dimensional CT images, body surface contour point cloud data are obtained by a gradient edge detection sobel algorithm according to the 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, a stone body surface incidence point prediction model is constructed according to a shock wave focal length constraint function, the bone avoidance constraint function and the lung gas avoidance constraint function, and finally, the body surface contour point cloud data, the bone point cloud data, the lung gas point cloud data and stone point prediction coordinates are input into the stone body surface incidence point prediction model to obtain an optimal body surface incidence point of the kidney stone. According to the method, the accuracy of planning of the incidence points of the kidney stones body surface is greatly improved through the stone body surface incidence point prediction model, the practical operation difficulty of selecting the incidence points of the external stone breaking operation is reduced, the optimal solution capable of avoiding the risk area can be calculated, and the efficiency of the stone breaking operation is improved.
Referring to fig. 4, fig. 4 is a block diagram showing the structure of a first embodiment of the body surface incidence point determining system for kidney stones according to the invention.
As shown in fig. 4, a body surface incidence point determining system for kidney stones according to an embodiment of the invention includes:
The processing module 4001 is used for acquiring a three-dimensional CT image of a kidney stone patient, and carrying out slice processing on the three-dimensional CT image to obtain a plurality of two-dimensional CT images;
the extraction module 4002 is used for respectively carrying out binarization processing on the two-dimensional CT images through an Ostu threshold algorithm and determining bone point cloud data and lung gas point cloud data according to the two-dimensional CT images;
The extraction module 4002 is further configured to obtain body surface contour point cloud data according to a plurality of two-dimensional CT images through a gradient edge detection sobel algorithm;
The construction module 4003 is configured to construct a bone avoidance constraint function according to the bone point cloud data, construct a lung gas avoidance constraint function according to the lung gas point cloud data, and construct a stone body surface incidence point prediction model according to the shock wave focal length constraint function, the bone avoidance constraint function and the lung gas avoidance constraint function;
the output module 4004 is configured to input the body surface contour point cloud data, the bone point cloud data, the lung gas point cloud data, and the calculus point prediction coordinates into the calculus body surface incidence point prediction model, so as to obtain an optimal body surface incidence point of kidney calculus.
Other embodiments or specific implementations of the body surface incidence point determining system for kidney stones according to the present invention may refer to the above-mentioned method embodiments, and will not be described herein.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of embodiments, it will be clear to a person skilled in the art that the above embodiment method may be implemented by means of software plus a necessary general hardware platform, but may of course also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. read-only memory/random-access memory, magnetic disk, optical disk), comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (8)
1. The method for determining the body surface incidence point of the kidney stone is characterized by comprising the following steps of:
Acquiring a three-dimensional CT image of a kidney stone patient, and performing slice processing on the three-dimensional CT image to obtain a plurality of two-dimensional CT images;
Respectively carrying out binarization processing on a plurality of two-dimensional CT images through an Ostu threshold algorithm, and determining bone point cloud data and lung gas point cloud data according to the plurality of binarized images;
acquiring body surface contour point cloud data through a gradient edge detection sobel algorithm according to a plurality of two-dimensional CT images;
constructing a bone avoidance constraint function according to the bone point cloud data, constructing a lung gas avoidance constraint function according to the lung gas point cloud data, and constructing a stone body surface incidence point prediction model according to the shock wave focal length constraint function, the bone avoidance constraint function and the lung gas avoidance constraint function;
Inputting the body surface contour point cloud data, the bone point cloud data, the lung gas point cloud data and the calculus point prediction coordinates into the calculus body surface incidence point prediction model so as to obtain an optimal body surface incidence point of kidney calculus;
The step of inputting the body surface contour point cloud data, the bone 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 an optimal body surface incidence point of kidney calculus comprises the following steps:
inputting the body surface contour point cloud data, the bone point cloud data, the lung gas point cloud data and the calculus point prediction coordinates into the calculus body surface incidence point prediction model;
Selecting a plurality of alternative incidence points from the body surface contour point cloud data according to a calculus point prediction coordinate and a Euclidean distance formula based on the calculus body surface incidence point prediction model;
Selecting a plurality of candidate incidence points from a plurality of candidate incidence points through a shock wave focal length constraint function, the bone avoidance constraint function and the lung gas avoidance constraint function;
Calculating the incidence point risk value of each candidate incidence point through a risk evaluation formula;
The risk assessment formula:
In the formula, For the i-th point of incidence risk value,For the distance of the point of incidence i to the point of the stone target,Is the most considered treatment distance to be used,For the distance of the point of incidence i to the nearest bone,For the distance of the point of incidence i to the nearest pulmonary gas,Alpha, beta and gamma are weight factors for the focal length of the equipment;
Selecting a candidate incidence point with the lowest risk value from a plurality of candidate incidence points according to the incidence point risk value;
and outputting the candidate incidence points with the lowest risk values through the stone body surface incidence point prediction model so as to obtain the optimal body surface incidence points of the kidney stones.
2. The method of claim 1, wherein the step of slicing the three-dimensional CT image to obtain a plurality of two-dimensional CT images comprises:
resolving the DICOM file of the kidney stone patient to obtain DICOM metadata;
determining CT layer number according to the DICOM metadata;
And carrying out slice processing on the three-dimensional CT image based on the CT layer number, and carrying out format conversion on a plurality of sliced CT images so as to obtain a plurality of two-dimensional CT images.
3. The method of claim 1, wherein the step of binarizing the plurality of two-dimensional CT images by an Ostu thresholding algorithm comprises:
respectively determining foreground pixel proportion, background pixel proportion, foreground average gray value and background average gray value corresponding to each two-dimensional CT image;
obtaining a segmentation pixel point threshold value corresponding to each two-dimensional CT image through an Ostu threshold algorithm according to the foreground pixel proportion, the background pixel proportion, the foreground average gray value and the background average gray value;
and respectively carrying out binarization processing on the plurality of two-dimensional CT images based on the segmentation pixel point threshold value.
4. The method of claim 3, wherein the step of determining bone point cloud data and lung gas point cloud data from the plurality of binarized images comprises:
Extracting skeleton point coordinates and lung gas point coordinates from a plurality of binarized images according to the segmentation pixel point threshold;
and generating skeleton point cloud data according to the skeleton point coordinates, and generating lung gas point cloud data according to the lung gas point coordinates.
5. The method of claim 1, wherein the step of obtaining body surface contour point cloud data from a plurality of two-dimensional CT images by a gradient edge detection sobel algorithm comprises:
Judging whether the plurality of two-dimensional CT images are gray-scale images or not;
if yes, determining all pixel points corresponding to each two-dimensional CT image, and respectively calculating the horizontal gradient and the vertical gradient of each pixel point;
Calculating the approximate total amplitude of the gradient of each pixel point through a 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 gradient approximate total amplitude;
and determining body surface contour point cloud data according to the edge point coordinates.
6. A body surface entry point determination system for kidney stones, the body surface entry point determination system comprising:
The processing module is used for acquiring a three-dimensional CT image of a kidney stone patient, and carrying out slice processing on the three-dimensional CT image to obtain a plurality of two-dimensional CT images;
The extraction module is used for respectively carrying out binarization processing on the two-dimensional CT images through an Ostu threshold algorithm and determining bone point cloud data and lung gas point cloud data according to the two-dimensional CT images;
The extraction module is also used for obtaining body surface contour point cloud data through a gradient edge detection sobel algorithm according to a plurality of two-dimensional CT images;
The construction module is used for constructing a bone avoidance constraint function according to the bone point cloud data, constructing a lung gas avoidance constraint function according to the lung gas point cloud data, and constructing a stone body surface incidence point prediction model according to the shock wave focal length constraint function, the bone avoidance constraint function and the lung gas avoidance constraint function;
The output module is used for inputting the body surface contour point cloud data, the bone point cloud data, the lung gas point cloud data and the calculus point prediction coordinates into the calculus body surface incidence point prediction model so as to obtain an optimal body surface incidence point of kidney calculus;
The output module is further used for inputting the body surface contour point cloud data, the bone point cloud data, the lung gas point cloud data and the calculus point prediction coordinates into the calculus body surface incidence point prediction model, selecting a plurality of candidate incidence points from the body surface contour point cloud data according to the calculus point prediction coordinates on the basis of the calculus body surface incidence point prediction model through a Euclidean distance formula, selecting a plurality of candidate incidence points from the plurality of candidate incidence points through a shock wave focal length constraint function, a bone avoidance constraint function and the lung gas avoidance constraint function, respectively calculating incidence point risk values of the candidate incidence points through a risk evaluation formula, selecting a candidate incidence point with a lowest risk value from the plurality of candidate incidence points according to the incidence point risk values, and outputting the candidate incidence point with the lowest risk value through the calculus body surface incidence point prediction model so as to obtain an optimal body surface incidence point of kidney calculus;
The risk assessment formula:
In the formula, For the i-th point of incidence risk value,For the distance of the point of incidence i to the point of the stone target,Is the most considered treatment distance to be used,For the distance of the point of incidence i to the nearest bone,For the distance of the point of incidence i to the nearest pulmonary gas,For the focal length of the device, α, β, γ are weighting factors.
7. A body surface entry point determination apparatus for kidney stones, characterized in that the apparatus comprises a memory, a processor and a body surface entry point determination program for kidney stones stored on the memory and executable on the processor, the body surface entry point determination program for kidney stones being configured to implement the steps of the body surface entry point determination method for kidney stones according to any one of claims 1 to 5.
8. A storage medium having stored thereon a body surface entry point determination program of kidney stones, which when executed by a processor, implements the steps of the body surface entry point determination method of kidney stones according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510454614.5A CN119970266B (en) | 2025-04-11 | 2025-04-11 | Body surface incidence point determination method, system, equipment and storage medium for kidney stones |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510454614.5A CN119970266B (en) | 2025-04-11 | 2025-04-11 | Body surface incidence point determination method, system, equipment and storage medium for kidney stones |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119970266A CN119970266A (en) | 2025-05-13 |
| CN119970266B true CN119970266B (en) | 2025-09-16 |
Family
ID=95643474
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510454614.5A Active CN119970266B (en) | 2025-04-11 | 2025-04-11 | Body surface incidence point determination method, system, equipment and storage medium for kidney stones |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119970266B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114332343A (en) * | 2020-10-10 | 2022-04-12 | 腾讯科技（深圳）有限公司 | Image processing method, apparatus, computer equipment, and storage medium |
| CN115760934A (en) * | 2022-10-18 | 2023-03-07 | 中国人民解放军陆军军医大学 | An automatic calibration method for the eye-nose triangle |
| CN117765014A (en) * | 2023-11-22 | 2024-03-26 | 东方晶源微电子科技(北京)股份有限公司 | Image edge detection method, device, equipment and storage medium |
| CN118557256A (en) * | 2024-05-08 | 2024-08-30 | 华中科技大学同济医学院附属同济医院 | Method, device and equipment for processing shock wave incidence point of extracorporeal lithotripsy |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2560553B1 (en) * | 2010-04-22 | 2019-10-30 | University of Washington through its Center for Commercialization | Apparatus for stone clearance with ultrasound |
| US9282985B2 (en) * | 2013-11-11 | 2016-03-15 | Gyrus Acmi, Inc. | Aiming beam detection for safe laser lithotripsy |
| JP2019502477A (en) * | 2016-01-06 | 2019-01-31 | ボストン サイエンティフィック サイムド，インコーポレイテッドＢｏｓｔｏｎ Ｓｃｉｅｎｔｉｆｉｃ Ｓｃｉｍｅｄ，Ｉｎｃ． | System and method for creating a medical treatment plan |
| SG10201700386PA (en) * | 2017-01-17 | 2018-08-30 | Ndr Medical Tech Pte Ltd | A System And Method For Aligning An Elongated Tool To An Occluded Target |
| KR102682936B1 (en) * | 2022-10-27 | 2024-07-09 | 주식회사 아이도트 | Urinary tract location estimation system |
-
2025
- 2025-04-11 CN CN202510454614.5A patent/CN119970266B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114332343A (en) * | 2020-10-10 | 2022-04-12 | 腾讯科技（深圳）有限公司 | Image processing method, apparatus, computer equipment, and storage medium |
| CN115760934A (en) * | 2022-10-18 | 2023-03-07 | 中国人民解放军陆军军医大学 | An automatic calibration method for the eye-nose triangle |
| CN117765014A (en) * | 2023-11-22 | 2024-03-26 | 东方晶源微电子科技(北京)股份有限公司 | Image edge detection method, device, equipment and storage medium |
| CN118557256A (en) * | 2024-05-08 | 2024-08-30 | 华中科技大学同济医学院附属同济医院 | Method, device and equipment for processing shock wave incidence point of extracorporeal lithotripsy |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119970266A (en) | 2025-05-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107480677B (en) | Method and device for identifying interest region in three-dimensional CT image | |
| CN113920109B (en) | Medical image recognition model training method, recognition method, device and equipment | |
| US9801601B2 (en) | Method and system for performing multi-bone segmentation in imaging data | |
| US8761475B2 (en) | System and method for automatic recognition and labeling of anatomical structures and vessels in medical imaging scans | |
| US7643663B2 (en) | Volume measurement in 3D datasets | |
| US8958616B2 (en) | Image processing device and image processing method | |
| CN110570407B (en) | Image processing method, storage medium, and computer device | |
| CN110176010B (en) | Image detection method, device, equipment and storage medium | |
| JPWO2007013300A1 (en) | Abnormal shadow candidate detection method and abnormal shadow candidate detection apparatus | |
| JP3534009B2 (en) | Outline extraction method and apparatus | |
| CN105579847A (en) | Disease analysis device, control method and program | |
| CN111986139A (en) | Method and device for measuring intima-media thickness in carotid artery and storage medium | |
| CN113240661A (en) | Deep learning-based lumbar vertebra analysis method, device, equipment and storage medium | |
| JP6643821B2 (en) | Image processing device | |
| JP6458166B2 (en) | MEDICAL IMAGE PROCESSING METHOD, DEVICE, SYSTEM, AND PROGRAM | |
| CN118334437A (en) | A 3D multi-stage detection method for CT spine bone lesions based on multi-task deep learning | |
| CN115375787A (en) | Artifact correction method, computer device and readable storage medium | |
| CN115439423B (en) | CT image-based identification method, device, equipment and storage medium | |
| JPH1097624A (en) | Method and device for detecting abnormal shadow candidate | |
| JP2012143387A (en) | Apparatus and program for supporting osteoporosis diagnosis | |
| TW201726064A (en) | Medical image processing apparatus and breast image processing method thereof | |
| CN114742763B (en) | Bone image recognition optimization method, system, storage medium and electronic device | |
| WO2023021052A1 (en) | Object reconstruction in digital images | |
| CN119970266B (en) | Body surface incidence point determination method, system, equipment and storage medium for kidney stones | |
| CN113392895A (en) | Knee joint cartilage damage detection method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |