A method and system for assisting the positioning of percutaneous renal puncture target

Abstract

The present invention relates to the field of ultrasonic image target positioning, and specifically to an auxiliary positioning method and system for percutaneous renal puncture target. The method first constructs a patient's kidney region model, plans a reference puncture angle in the kidney region model, and collects ultrasound images of different frames of the kidney region in real time, performs edge detection on each frame of the ultrasound image, and determines the optimal detection position in combination with the kidney region model; analyzes the angle difference of the broken line angle formed by each key point between the ultrasound image and the slice image of the kidney region model, obtains the degree of feature difference, and determines the optimal detection angle; based on the position change of the key points of the adjacent frames of ultrasound images, the degree of feature difference between each frame of the ultrasound image and the slice image under the reference puncture angle, and combined with the optimal detection position and the optimal detection angle, the percutaneous renal puncture target is positioned. The present invention can position the percutaneous renal puncture target under the premise of ensuring the safety of the patient.

Description

Technical Field

[0001] The present invention relates to the field of ultrasonic imaging target positioning, and in particular to an auxiliary positioning method and system for percutaneous renal puncture target. Background Art

[0002] Percutaneous renal puncture surgery is an efficient and minimally invasive operation method that avoids tissue damage, greatly reduces patient trauma, and shortens recovery time. Secondly, during percutaneous renal puncture, precise positioning of the target point can ensure that the puncture needle accurately enters the target area, improves the accuracy of the percutaneous renal puncture operation, and is of great significance to percutaneous renal puncture.

[0003] In related technologies, percutaneous renal puncture is usually combined with ultrasound imaging technology, and ultrasound imaging is used to guide the puncture needle to achieve auxiliary positioning of the percutaneous renal puncture target. However, due to the presence of other blood vessels and organs around the human kidney area, and the various tissues and organs around the human kidney area have a certain degree of dynamics, the existing methods cannot locate the percutaneous renal puncture target while ensuring safety, thereby reducing the effect of auxiliary positioning of the percutaneous renal puncture target. Summary of the invention

[0004] In order to solve the technical problem that the existing methods cannot locate the percutaneous renal puncture target under the premise of ensuring safety, and reduce the effect of auxiliary positioning of the percutaneous renal puncture target, the purpose of the present invention is to provide a method and system for auxiliary positioning of the percutaneous renal puncture target, and the technical scheme adopted is as follows:

[0005] The present invention proposes an auxiliary positioning method for percutaneous renal puncture target, the method comprising:

[0006] Acquire CT scan data of the patient's kidney area, and collect ultrasound images of different frames of the patient's kidney area in real time, build a kidney area model based on the CT scan data, and plan a reference puncture angle in the kidney area model;

[0007] Perform edge detection on each frame of ultrasound image, and combine with the kidney region model to obtain the best detection position of the ultrasound detector; at the best detection position, perform slice processing on the kidney region model at different slice angles to obtain slice images at different slice angles; take any frame of ultrasound image or any slice image as the target image, perform local feature extraction processing on the target image, and obtain multiple key points in the target image; according to the distance between each key point in the target image, obtain multiple broken lines in the target image and the angle of each broken line; take the slice image with the same number of key points as that in each frame of ultrasound image as the reference slice image of each frame of ultrasound image, and according to the angle difference of the angle of the broken line between each frame of ultrasound image and each reference slice image, obtain the degree of feature difference between each frame of ultrasound image and each reference slice image; based on the degree of feature difference, select the best detection angle of the ultrasound detector from the slice angles corresponding to all slice images;

[0008] Obtaining the puncture reliability of each frame of ultrasound image according to the position change of the key point between each frame of ultrasound image and the next adjacent frame of ultrasound image, and the degree of feature difference between each frame of ultrasound image and the slice image at the reference puncture angle;

[0009] Based on the puncture reliability, the optimal detection position and the optimal detection angle of each frame of ultrasound image, the percutaneous renal puncture target is positioned.

[0010] Furthermore, obtaining the optimal detection position of the ultrasonic detector includes:

[0011] Perform corrosion processing on each frame of the ultrasound image, perform edge detection on the corroded ultrasound image, obtain multiple edge contours, and input the ultrasound image into U-Net to obtain the organ type corresponding to each edge contour;

[0012] The triangulation method is used to obtain the distances between different types of organs in the ultrasound image and the probe of the ultrasound detector, and the optimal detection position of the ultrasound detector is determined in the kidney region model according to the distances between different types of organs and the probe of the ultrasound detector.

[0013] Furthermore, obtaining a plurality of key points in the target image includes:

[0014] The SIFT algorithm is used to extract local features of the target image and obtain multiple key points in the target image.

[0015] Further, the step of obtaining a plurality of broken lines in the target image and the angle between each broken line comprises:

[0016] Take any key point in the target image as the target key point, and select another key point closest to the target key point from other key points except the target key point as the nearest key point to the target key point;

[0017] Connect each key point in the target image with its nearest key point to obtain multiple polylines in the target image, where the angle of each polyline is formed by any two adjacent line segments in the polyline, and the angle range is .

[0018] Furthermore, obtaining the characteristic difference between each frame of ultrasound image and each reference slice image includes:

[0019] Use non-zero natural numbers to number all the polylines in the target image in order from top to bottom and from left to right, and obtain the polyline sequence number of each polyline in the target image;

[0020] Using non-zero natural numbers, all angles of each broken line in the target image are numbered to obtain the angle sequence number of each angle of each broken line in the target image;

[0021] Based on the calculation formula of the characteristic difference degree, the characteristic difference degree between each frame of ultrasound image and each reference slice image is obtained, and the calculation formula of the characteristic difference degree is:

[0022]

[0023] in, Indicates Frame ultrasound image and its The degree of feature difference between the reference slice images; Indicates The broken line number in the frame ultrasound image is The angle number in the polyline is The angle of the included angle; Indicates The broken line numbers in the reference slice image are The angle number in the polyline is The angle of the included angle; Indicates The number of polylines in the frame ultrasound image; Indicates The broken line number in the frame ultrasound image is The number of angles in the polyline; Represents the normalization function.

[0024] Furthermore, the selecting of the optimal detection angle of the ultrasonic detector includes:

[0025] The slice angle corresponding to the slice image corresponding to the minimum value of the characteristic difference degree is used as the optimal detection angle of the ultrasonic detector.

[0026] Furthermore, obtaining the puncture reliability of each frame of ultrasound image includes:

[0027] Taking any frame of ultrasound image as the target ultrasound image, taking any key point in the target ultrasound image as the key point to be analyzed, selecting a key point closest to the key point to be analyzed in the next frame of ultrasound image adjacent to the target ultrasound image as the reference key point of the key point to be analyzed, and constructing a displacement vector of the key point to be analyzed with the key point to be analyzed as the starting point and the reference key point of the key point to be analyzed as the end point;

[0028] Taking the average of the angles of the displacement vectors of all key points in the target ultrasound image as the overall angle value of the target ultrasound image;

[0029] Taking the absolute value of the difference between the angle of the displacement vector of each key point in the target ultrasound image and the overall angle value as the angle deviation of the displacement vector of each key point in the target ultrasound image;

[0030] Taking the product of the angle deviation of the displacement vector of each key point in the target ultrasound image and the modulus of the displacement vector as the initial fluctuation parameter of each key point in the target ultrasound image;

[0031] Normalizing the average values ​​of the initial fluctuation parameters of all key points in the target ultrasound image to obtain the fluctuation degree of the target ultrasound image;

[0032] Based on a method for calculating the degree of feature difference between each frame of ultrasound image and each reference slice image, the degree of feature difference between the target ultrasound image and the slice image at the reference puncture angle is calculated;

[0033] The product value of the characteristic difference degree between the target ultrasound image and the slice image under the reference puncture angle and the fluctuation degree of the target ultrasound image is negatively correlated and normalized to obtain the puncture reliability of the target ultrasound image.

[0034] Furthermore, constructing a kidney region model based on CT scan data includes:

[0035] The CT scan data of the patient's kidney area was input into the Minics software to construct a model of the patient's kidney area.

[0036] The present invention also proposes an auxiliary positioning system for a percutaneous renal puncture target, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor implementing any one of the steps of an auxiliary positioning method for a percutaneous renal puncture target when executing the computer program.

[0037] The present invention has the following beneficial effects:

[0038] The present invention takes into account that the existing methods cannot locate the percutaneous renal puncture target under the premise of ensuring safety, and reduces the effect of auxiliary positioning of the percutaneous renal puncture target. First, a renal region model of the patient is constructed based on the CT scan data of the patient's renal region, and ultrasound images of different frames of the patient's renal region are collected in real time. The reference puncture angle is manually planned, and dynamic information of various tissues and organs in the renal region is provided through real-time ultrasound images. The position and angle of the ultrasound detector are adjusted in real time accordingly to obtain the optimal detection position and the optimal detection angle, ensuring that the actual puncture path is consistent with the preset path, and then by analyzing the slice images of the renal region model at different slice angles and the fluctuation of tissues and organs in the ultrasound images of continuous frames, the reliability of puncture at different time points can be evaluated, so as to select the best time for puncture, avoid excessive movement of tissues and organs during the puncture process, and cause damage to the tissues and organs, thereby achieving positioning of the percutaneous renal puncture target under the premise of ensuring the safety of the patient, and improving the effect of auxiliary positioning of the percutaneous renal puncture target. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 A flow chart of an auxiliary positioning method for percutaneous renal puncture target provided by an embodiment of the present invention;

[0041] Figure 2 A schematic diagram of multiple broken lines and the angle between each broken line in a target image provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the auxiliary positioning method and system of a percutaneous renal puncture target proposed by the present invention, its specific implementation method, structure, features and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0043] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0044] The specific scheme of the auxiliary positioning method and system for percutaneous renal puncture target provided by the present invention is described in detail below with reference to the accompanying drawings.

[0045] See also Figure 1 , which shows a flow chart of an auxiliary positioning method for percutaneous renal puncture target provided by an embodiment of the present invention, the method comprising:

[0046] Step S1: Acquire CT scan data of the patient's kidney region, and collect ultrasound images of different frames of the patient's kidney region in real time, build a kidney region model based on the CT scan data, and plan a reference puncture angle in the kidney region model.

[0047] Percutaneous renal puncture surgery can be used to treat a variety of kidney area diseases. Currently, the scenario of renal biopsy is analyzed. Renal biopsy is when kidney tissue samples need to be obtained for pathological examination. Percutaneous renal puncture can be used for renal biopsy. However, since renal puncture biopsy has a high risk, corresponding preparations are required before the operation.

[0048] First, we need to understand the patient's medical history, history of drug allergies, and recent medications in detail to prevent increased bleeding risks during the operation. Renal puncture biopsy needs to be performed under ultrasound guidance, so before the operation, the patient needs to undergo detailed ultrasound monitoring of both kidneys, and provide precise guidance and training on breathing control and breath-holding under real-time ultrasound observation.

[0049] In order to reduce the occurrence of complications during the puncture process, the embodiment of the present invention first uses a CT scanning device to scan the patient's kidney area, obtains CT scanning data of the patient's kidney area, and inputs the CT scanning data into the Minics software to construct the patient's kidney area model. The kidney area model can clearly display the distribution of various tissues, organs and blood vessels around the kidney. The kidney area model can be analyzed later to determine the best position and angle for puncture. At the same time, in the embodiment of the present invention, medical personnel also need to manually plan the puncture angle based on the patient's kidney area model and predetermine the puncture angle, that is, the reference puncture angle. When performing percutaneous renal puncture at the reference puncture angle, blood vessels and other tissues and organs can be avoided to avoid damage to the patient.

[0050] At the same time, the patient took a prone position with a sandbag placed on his abdomen, and an ultrasound detector was used to collect ultrasound images of different frames of the patient's kidney area in real time.

[0051] Step S2: perform edge detection on each frame of ultrasound image, and combine with the kidney region model to obtain the best detection position of the ultrasound detector; at the best detection position, perform slice processing on the kidney region model at different slice angles to obtain slice images at different slice angles; use any frame of ultrasound image or any slice image as the target image, perform local feature extraction processing on the target image, and obtain multiple key points in the target image; obtain multiple broken lines in the target image and the angle of each broken line according to the distance between each key point in the target image; use the slice image with the same number of key points as that in each frame of ultrasound image as the reference slice image of each frame of ultrasound image, and obtain the degree of feature difference between each frame of ultrasound image and each reference slice image according to the angle difference of the broken line between each frame of ultrasound image and each reference slice image; based on the degree of feature difference, select the best detection angle of the ultrasound detector from the slice angles corresponding to all slice images.

[0052] In the above process, a three-dimensional model of the corresponding kidney area is generated based on the CT scan data collected from the patient's kidney area. When performing a kidney puncture biopsy, the doctor needs to continuously perform ultrasound guidance on the kidney area and perform puncture according to the ultrasound image displayed by the guidance. In order to better assist in positioning the puncture area, it is first necessary to determine the current scanning angle and area position based on the kidney area and other tissue organs in the real-time ultrasound image of the kidney area. Therefore, the embodiment of the present invention first performs edge detection on each frame of the ultrasound image to identify the edge contours of different types of tissue organs in the ultrasound image, and combines the kidney area model to obtain the optimal detection position of the ultrasound detector. Percutaneous renal puncture can be performed at the optimal detection position subsequently, so that the percutaneous renal puncture target can be positioned while ensuring the safety of the patient.

[0053] Preferably, in one embodiment of the present invention, the method for obtaining the optimal detection position of the ultrasonic detector specifically includes:

[0054] First, it is necessary to determine the scanning position based on the distance between tissues and organs in the ultrasound image obtained by the current real-time scanning. Since there may be a variety of tissues and organs other than the kidney in the ultrasound image of the kidney area, the relative position and distance of these internal structures and external organs can help us infer the approximate angle and area of ​​the ultrasound detector probe, thereby laying the foundation for subsequent fine adjustments. Therefore, the embodiment of the present invention first corrodes each frame of the ultrasound image to eliminate noise in the image and refine the boundaries of the object, performs edge detection on the corroded ultrasound image to obtain multiple edge contours, and inputs the ultrasound image into U-Net to obtain the organ type corresponding to each edge contour. Among them, the embodiment of the present invention can select the existing Canny edge detection algorithm or other edge detection algorithms for edge detection, which is not limited or elaborated here. Among them, U-Net is a technical means well known to those skilled in the art and is not elaborated here.

[0055] Then, the triangulation method is used to obtain the distances between different types of organs in the ultrasound image and the probe of the ultrasound detector, and the optimal detection position of the ultrasound detector is determined in the kidney area model according to the distances between different types of organs and the probe of the ultrasound detector. The triangulation method is a technical means well known to those skilled in the art and will not be elaborated here.

[0056] The above process obtains the optimal detection position of the ultrasound detector, and then the detection angle of the ultrasound detector can be analyzed. In the process of analysis, it is necessary to first slice the kidney region model at different slice angles at the optimal detection position to obtain slice images at different slice angles. Subsequently, ultrasound images of different frames and slice images at different slice angles can be analyzed to determine the optimal detection angle. Among them, the slice processing of the kidney region model is a technical means well known to technicians in this field and is not limited here. Subsequently, the matching degree of slice images at different slice angles with each frame of ultrasound image can be analyzed to screen the optimal detection angle, for different acquisition angles and different recognition degrees. The angles formed between the key matching points in the kidney area are relatively stable or have small differences. Therefore, any frame of ultrasound image or any slice image can be used as the target image, and local feature extraction processing can be performed on the target image to obtain multiple key points in the target image. According to the distances between the key points in the target image, multiple broken lines in the target image and the angles of each broken line can be obtained. Subsequently, the difference in the angles of the broken lines between the ultrasound image and the slice image can be analyzed to determine the optimal detection angle of the ultrasound detector. Subsequently, the optimal detection position and the optimal detection angle can be combined to perform more effective auxiliary positioning of the patient's percutaneous renal puncture target to avoid damage to the patient.

[0057] Preferably, in one embodiment of the present invention, a SIFT algorithm may be used to extract local features of a target image to obtain a plurality of key points in the target image, wherein the SIFT algorithm is a technical means well known to those skilled in the art and will not be described in detail herein.

[0058] Preferably, in one embodiment of the present invention, the method for acquiring the multiple broken lines in the target image and the angle between each broken line specifically includes:

[0059] Take any key point in the target image as the target key point, select another key point closest to the target key point from other key points except the target key point as the nearest key point of the target key point, and then connect each key point in the target image with the nearest key point of the key point to obtain multiple polylines in the target image, where the angle of each polyline is composed of any two adjacent line segments in the polyline, and the angle range of the angle is Each polyline may have one or more angles. Please refer to Figure 2 , which shows a schematic diagram of multiple broken lines in a target image and the angle of each broken line provided by an embodiment of the present invention, wherein L represents a broken line in the target image, A1, A2 and A3 represent three key points on the broken line L, and B represents an angle of the broken line L.

[0060] The same method as above can be used to obtain multiple broken lines and the angle of each broken line in each frame of ultrasound image and each slice image. The closer the key points in the ultrasound image and the slice image are, the more similar the key features between the two are. Therefore, the slice image with the same number of key points as in each frame of ultrasound image can be used as the reference slice image for each frame of ultrasound image to improve the accuracy of subsequent analysis of the best detection angle. From the above analysis, it can be seen that the smaller the angle difference between the angle formed by each key point in the ultrasound image and the angle formed by each key point in the reference slice image at a corresponding slice angle, the more similar the features between the slice image and the ultrasound image at the slice angle are, and further, the greater the possibility that the slice angle is the best detection angle. Therefore, the degree of feature difference between each frame of ultrasound image and each reference slice image can be obtained first according to the angle difference between the angle of the broken line between each frame of ultrasound image and each reference slice image, and the best detection angle of the ultrasound detector can be determined based on the degree of feature difference.

[0061] Preferably, in one embodiment of the present invention, the method for acquiring the degree of feature difference between each frame of ultrasound image and each reference slice image specifically includes:

[0062] Use non-zero natural numbers to number all the polylines in the target image in order from top to bottom and from left to right to obtain the polyline sequence number of each polyline in the target image.

[0063] Again, non-zero natural numbers are used to label all the angles of each broken line in the target image, and the angle sequence number of each angle of each broken line in the target image is obtained.

[0064] Based on the calculation formula of the characteristic difference degree, the characteristic difference degree between each frame of ultrasound image and each reference slice image is obtained. The calculation formula of the characteristic difference degree is:

[0065]

[0066] in, Indicates Frame ultrasound image and its The degree of feature difference between the reference slice images; Indicates The broken line number in the frame ultrasound image is The angle number in the polyline is The angle of the included angle; Indicates The broken line numbers in the reference slice image are The angle number in the polyline is The angle of the included angle; Indicates The number of polylines in the frame ultrasound image; Indicates The broken line number in the frame ultrasound image is The number of angles in the polyline; Represents a normalization function, which is used to limit the calculation results to In one embodiment of the present invention, the normalization process may be specifically, for example, maximum and minimum value normalization process, and the normalization in subsequent steps may adopt maximum and minimum value normalization process. In other embodiments of the present invention, other normalization methods may be selected according to the specific range of numerical values, which will not be described in detail.

[0067] in, The smaller the difference, the greater the difference in the angle between the ultrasound image and the reference slice image. This indicates that the features between the ultrasound image and the reference slice image are more similar. The smaller it is, the more important it is to During the calculation of The polyline or polyline number is The broken line but no angle is The angle between That is, between the ultrasound image and the reference slice image, the angle difference between the angles with the same angle number in the broken lines with the same broken line number is calculated.

[0068] The smaller the degree of feature difference between a certain frame of ultrasound image and a slice image at a certain slice angle, the more similar the features between the slice image at the slice angle and the ultrasound image are, and thus the greater the possibility that the slice angle is the optimal detection angle. Therefore, based on the degree of feature difference, the optimal detection angle of the ultrasound detector can be selected from the slice angles corresponding to all slice images. Subsequently, based on the optimal detection angle and combined with the optimal detection position obtained above, the patient's percutaneous renal puncture target can be effectively assisted in positioning to avoid damage to the patient's tissues and organs during the puncture process.

[0069] Preferably, in one embodiment of the present invention, the method for acquiring the optimal detection angle of the ultrasonic detector specifically includes:

[0070] The minimum value is selected from all acquired feature difference degrees, and the slice angle corresponding to the slice image corresponding to the minimum value of the feature difference degree is used as the optimal detection angle of the ultrasonic detector.

[0071] At this point, the optimal detection position and optimal detection angle of the ultrasonic detector are obtained.

[0072] Step S3: The puncture reliability of each frame of ultrasound image is obtained according to the position change of key points between each frame of ultrasound image and the next adjacent frame of ultrasound image, and the degree of feature difference between each frame of ultrasound image and the slice image under the reference puncture angle.

[0073] In the actual detection process, the slight movement of various organs in the body caused by the patient's breathing will result in a low accuracy of the detection point judgment. During the puncture biopsy, the patient needs to hold his breath for a period of time to reduce the movement of various organs in the body and find the best time for puncture during the patient's breath holding.

[0074] The judgment of the puncture timing needs to consider the similarity between the features of the slice image at the reference puncture angle and each frame of ultrasound image, as well as the volatility of the kidney region organs in each frame of ultrasound image. The lower the degree of volatility of the kidney region organs in a certain frame of ultrasound image, and the more similar the features of the slice image at the reference puncture angle and the frame of ultrasound image, the more reliable the puncture operation is at the moment corresponding to the frame of ultrasound image. Therefore, the puncture reliability of each frame of ultrasound image can be obtained based on the position changes of key points between each frame of ultrasound image and the next adjacent frame of ultrasound image, and the degree of feature difference between each frame of ultrasound image and the slice image at the reference puncture angle. Subsequently, the best time for the puncture operation can be determined based on the puncture reliability, thereby improving the effect of auxiliary positioning of the patient's percutaneous renal puncture target and ensuring the safety of the patient.

[0075] Preferably, in one embodiment of the present invention, the method for obtaining the puncture reliability of each frame of ultrasound image specifically includes:

[0076] First, any frame of ultrasound image is taken as the target ultrasound image, and any key point in the target ultrasound image is taken as the key point to be analyzed. In the adjacent next frame of ultrasound image of the target ultrasound image, a key point closest to the key point to be analyzed is selected as the reference key point of the key point to be analyzed, and the displacement vector of the key point to be analyzed is constructed with the key point to be analyzed as the starting point and the reference key point of the key point to be analyzed as the end point. Subsequently, the modulus and angle of the displacement vector of each key point in the target ultrasound image can be analyzed to reflect the movement of tissues and organs in the target ultrasound image. It should be noted that since the last frame of ultrasound image does not have an adjacent next frame of ultrasound image, the last frame of ultrasound image is not taken as the target ultrasound image for analysis.

[0077] The average value of the angles of the displacement vectors of all key points in the target ultrasound image is taken as the overall angle value of the target ultrasound image, and the absolute value of the difference between the angle of the displacement vector of each key point in the target ultrasound image and the overall angle value is taken as the angle deviation of the displacement vector of each key point in the target ultrasound image. The larger the angle deviation, the more the angle of the displacement vector of each key point deviates from the overall angle value, which further indicates that the degree of movement of tissues and organs in the target ultrasound image is greater.

[0078] The larger the modulus of the displacement vector of each key point in the target ultrasound image, the greater the degree of movement of the tissues and organs in the target ultrasound image. Therefore, the product of the angular deviation of the displacement vector of each key point in the target ultrasound image and the modulus of the displacement vector can be used as the initial fluctuation parameter of each key point in the target ultrasound image. The larger the initial fluctuation parameter, the more obvious the volatility or movement of the key point in the target ultrasound image. Then, the average value of the initial fluctuation parameters of all key points in the target ultrasound image can be normalized to obtain the degree of fluctuation of the target ultrasound image. The larger the degree of fluctuation, the greater the degree of movement of the tissues and organs in the target ultrasound image, and the more obvious the movement phenomenon.

[0079] As an example, in one embodiment of the present invention, the expression of the fluctuation degree of the target ultrasound image may be specifically, for example, as follows:

[0080]

[0081] in, Indicates the degree of fluctuation of the target ultrasound image; Indicates the target ultrasound image The displacement vector of each key point; Indicates the target ultrasound image The modulus of the displacement vector of each key point; Represents the modulo symbol; Indicates the target ultrasound image The angular deviation of the displacement vector of each key point; Indicates the target ultrasound image Initial fluctuation parameters of key points; Represents the number of key points in the target ultrasound image; Represents a normalization function, which is used to limit the calculation results to within the range.

[0082] Then, based on the calculation method of the feature difference degree between each frame of ultrasound image and each reference slice image, the feature difference degree between the target ultrasound image and the slice image at the reference puncture angle is calculated. The specific process is: using the same method as above, key points are extracted from the slice image of the kidney area model at the reference puncture angle, and multiple broken lines and the angle of each broken line in the slice image at the reference puncture angle are obtained and labeled. Finally, the feature difference degree calculation formula is used to calculate the feature difference degree between the target ultrasound image and the slice image at the reference puncture angle.

[0083] As an example, in one embodiment of the present invention, the expression for the degree of feature difference between the target ultrasound image and the slice image at the reference puncture angle may be specifically, for example, as follows:

[0084]

[0085] in, Indicates the degree of feature difference between the target ultrasound image and the slice image under the reference puncture angle; Indicates that the broken line number in the target ultrasound image is The angle number in the polyline is The angle of the included angle; The broken line number in the slice image under the reference puncture angle is The angle number in the polyline is The angle of the included angle; represents the number of broken lines in the target ultrasound image; Indicates that the broken line number in the target ultrasound image is The number of angles in the polyline; Represents a normalization function, which is used to limit the calculation results to within the range.

[0086] Finally, the more similar the features between the target ultrasound image and the slice image at the reference puncture angle, and the smaller the degree of movement of the tissue and organs in the target ultrasound image, the more reliable the puncture operation on the patient. Therefore, the product value of the degree of feature difference between the target ultrasound image and the slice image at the reference puncture angle and the degree of fluctuation of the target ultrasound image can be negatively correlated and normalized to obtain the puncture reliability of the target ultrasound image.

[0087] As an example, in one embodiment of the present invention, the expression of the puncture reliability of the target ultrasound image may be specifically, for example, as follows:

[0088]

[0089] in, Indicates the puncture reliability of the target ultrasound image; Indicates the degree of fluctuation of the target ultrasound image; Indicates the degree of feature difference between the target ultrasound image and the slice image under the reference puncture angle; Represents a normalization function, which is used to limit the calculation results to within the scope; Indicates the preset adjustment parameter, which is used to prevent the denominator from being 0. The value range is In one embodiment of the present invention, Set to 0.01, The specific value of can also be set by the implementer according to the specific implementation scenario and is not limited here.

[0090] It should be noted that in other embodiments of the present invention, negative correlation mapping may be achieved through other basic mathematical operations, which will not be elaborated herein.

[0091] The puncture reliability of each frame of ultrasound image can be obtained by the same method as above.

[0092] Step S4: Positioning the percutaneous renal puncture target based on the puncture reliability, optimal detection position and optimal detection angle of each frame of ultrasound image.

[0093] The greater the puncture reliability of a certain frame of ultrasound image, the smaller the degree of movement of the tissues and organs in the patient's kidney area at the moment corresponding to the frame of ultrasound image, and the less obvious the movement phenomenon. In this case, performing percutaneous renal puncture at this moment can avoid damage to the patient's tissues and organs, which further indicates that this moment is the best time to perform percutaneous renal puncture. At the same time, performing percutaneous renal puncture at the optimal detection position and the optimal detection angle of the ultrasound detector can avoid damage to the patient's tissues and organs to the greatest extent. Therefore, based on the puncture reliability of each frame of ultrasound image and combined with the optimal detection position and the optimal detection angle of the ultrasound detector, percutaneous renal puncture can be performed on the patient, so that the auxiliary positioning effect of the patient's percutaneous renal puncture target is better, which is beneficial to ensuring the safety of the patient and improving the effect of auxiliary positioning of the percutaneous renal puncture target.

[0094] Preferably, in one embodiment of the present invention, the method of performing percutaneous renal puncture on a patient specifically comprises:

[0095] The moment corresponding to the ultrasound image where the puncture reliability is greater than the preset reliability threshold is taken as the optimal puncture moment, and at the optimal puncture moment, the patient is subjected to percutaneous renal puncture using the puncture needle at the optimal detection position and at the optimal detection angle, wherein the preset reliability threshold is set to 0.85, and the specific value of the preset reliability threshold can also be set by the implementer according to the specific implementation scenario, and is not limited here.

[0096] An embodiment of the present invention provides an auxiliary positioning system for a percutaneous renal puncture target, the system comprising a memory, a processor and a computer program, wherein the memory is used to store a corresponding computer program, the processor is used to run the corresponding computer program, and when the computer program runs in the processor, the method described in steps S1 to S4 can be implemented.

[0097] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0098] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for assisting the positioning of a target point for percutaneous renal puncture, characterized in that: The method comprises: Acquire CT scan data of the patient's kidney area, and collect ultrasound images of different frames of the patient's kidney area in real time, build a kidney area model based on the CT scan data, and plan a reference puncture angle in the kidney area model; Perform edge detection on each frame of ultrasound image, and combine with the kidney region model to obtain the best detection position of the ultrasound detector; at the best detection position, perform slice processing on the kidney region model at different slice angles to obtain slice images at different slice angles; use any frame of ultrasound image or any slice image as the target image, perform local feature extraction processing on the target image, and obtain multiple key points in the target image; obtain multiple broken lines in the target image and the angle of each broken line according to the distance between each key point in the target image; use the slice image with the same number of key points as that in each frame of ultrasound image as the reference slice image of each frame of ultrasound image, and obtain the degree of feature difference between each frame of ultrasound image and each reference slice image according to the angle difference of the broken line between each frame of ultrasound image and each reference slice image; based on the degree of feature difference, select the best detection angle of the ultrasound detector from the slice angles corresponding to all slice images; Obtaining the puncture reliability of each frame of ultrasound image according to the position change of the key point between each frame of ultrasound image and the next adjacent frame of ultrasound image, and the degree of feature difference between each frame of ultrasound image and the slice image at the reference puncture angle; Based on the puncture reliability, the optimal detection position and the optimal detection angle of each frame of ultrasound image, the percutaneous renal puncture target is positioned.

2. The method for assisting in positioning a target point for percutaneous renal puncture according to claim 1, characterized in that: The obtaining of the best detection position of the ultrasonic detector comprises: Perform corrosion processing on each frame of the ultrasound image, perform edge detection on the corroded ultrasound image, obtain multiple edge contours, and input the ultrasound image into U-Net to obtain the organ type corresponding to each edge contour; The triangulation method is used to obtain the distances between different types of organs in the ultrasound image and the probe of the ultrasound detector, and the optimal detection position of the ultrasound detector is determined in the kidney region model according to the distances between different types of organs and the probe of the ultrasound detector.

3. The method for assisting in positioning a target point for percutaneous renal puncture according to claim 1, characterized in that: The obtaining of a plurality of key points in the target image comprises: The SIFT algorithm is used to extract local features of the target image and obtain multiple key points in the target image.

4. The method for assisting in positioning a target point for percutaneous renal puncture according to claim 1, characterized in that: The step of obtaining a plurality of broken lines in the target image and the angle of each broken line comprises: Take any key point in the target image as the target key point, and select another key point closest to the target key point from other key points except the target key point as the nearest key point to the target key point; Connect each key point in the target image with its nearest key point to obtain multiple polylines in the target image, where the angle of each polyline is formed by any two adjacent line segments in the polyline, and the angle range is .

5. The method for assisting in positioning a target point for percutaneous renal puncture according to claim 1, characterized in that: The obtaining of the characteristic difference between each frame of ultrasound image and each reference slice image comprises: Use non-zero natural numbers to number all the polylines in the target image in order from top to bottom and from left to right, and obtain the polyline sequence number of each polyline in the target image; Using non-zero natural numbers, all angles of each broken line in the target image are numbered to obtain the angle sequence number of each angle of each broken line in the target image; Based on the calculation formula of the characteristic difference degree, the characteristic difference degree between each frame of ultrasound image and each reference slice image is obtained, and the calculation formula of the characteristic difference degree is: in, Indicates Frame ultrasound image and its The degree of feature difference between the reference slice images; Indicates The broken line number in the frame ultrasound image is The angle number in the polyline is The angle of the included angle; Indicates The broken line numbers in the reference slice image are The angle number in the polyline is The angle of the included angle; Indicates The number of polylines in the frame ultrasound image; Indicates The broken line number in the frame ultrasound image is The number of angles in the polyline; Represents the normalization function.

6. The method for assisting in positioning a target point for percutaneous renal puncture according to claim 1, characterized in that: The selecting of the best detection angle of the ultrasonic detector comprises: The slice angle corresponding to the slice image corresponding to the minimum value of the characteristic difference degree is used as the optimal detection angle of the ultrasonic detector.

7. The method for assisting in positioning the target point of percutaneous renal puncture according to claim 5, characterized in that: The puncture reliability of obtaining each frame of ultrasound image includes: Taking any frame of ultrasound image as the target ultrasound image, taking any key point in the target ultrasound image as the key point to be analyzed, selecting a key point closest to the key point to be analyzed in the next frame of ultrasound image adjacent to the target ultrasound image as the reference key point of the key point to be analyzed, and constructing a displacement vector of the key point to be analyzed with the key point to be analyzed as the starting point and the reference key point of the key point to be analyzed as the end point; Taking the average of the angles of the displacement vectors of all key points in the target ultrasound image as the overall angle value of the target ultrasound image; Taking the absolute value of the difference between the angle of the displacement vector of each key point in the target ultrasound image and the overall angle value as the angle deviation of the displacement vector of each key point in the target ultrasound image; Taking the product of the angle deviation of the displacement vector of each key point in the target ultrasound image and the modulus of the displacement vector as the initial fluctuation parameter of each key point in the target ultrasound image; Normalizing the average values ​​of the initial fluctuation parameters of all key points in the target ultrasound image to obtain the fluctuation degree of the target ultrasound image; Based on a method for calculating the degree of feature difference between each frame of ultrasound image and each reference slice image, the degree of feature difference between the target ultrasound image and the slice image at the reference puncture angle is calculated; The product value of the characteristic difference degree between the target ultrasound image and the slice image under the reference puncture angle and the fluctuation degree of the target ultrasound image is negatively correlated and normalized to obtain the puncture reliability of the target ultrasound image.

8. The method for assisting in positioning a target point for percutaneous renal puncture according to claim 1, characterized in that: The constructing of a kidney region model based on CT scan data comprises: The CT scan data of the patient's kidney area was input into the Minics software to construct a model of the patient's kidney area.

9. An auxiliary positioning system for percutaneous renal puncture target, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

Images