Puncture guidance systems, devices, and methods

Abstract

The application relates to the technical field of puncture guidance based on position prediction, and provides a puncture guidance system, device and method, which can gradually constrain the guiding direction of a needle tip to be the direction of a puncture target point or the direction of a position near the puncture target point. According to the geometric features of a distribution region in a puncture target point position set corresponding to the puncture target point position set, an observed position of an initial puncture reference point is obtained; based on continuous detection of the position of the puncture target point, whenever the puncture target point position set is updated, an observed position of a current puncture reference point corresponding to the update is obtained, based on the difference between the observed position of the current puncture reference point and the predicted position of the current puncture reference point, a prediction result obtained according to the predicted position of the current puncture reference point is corrected, and a predicted position of a next puncture reference point is obtained to guide the needle tip.

Description

Technical Field

[0001] This application relates to the field of puncture guidance technology based on location prediction, and in particular to a puncture guidance system, puncture guidance device, puncture guidance method, storage medium, and computer program product. Background Technology

[0002] The puncture guidance technique can guide the tip of the puncture needle to the puncture target point of the puncture object; then, through the puncture needle, the tissue at the puncture target point can be taken out for diagnosis or drugs can be infused into the tissue at the puncture target point for treatment.

[0003] In current puncture guidance technology, before the needle tip is inserted into the body of the punctured object, a guiding direction is determined based on the observed location of the puncture target point, and the needle tip is guided to continue to penetrate deeper into the body of the punctured object according to the guiding direction.

[0004] However, if a significant change in the position of the puncture target is found when the needle tip is about to reach the previously observed puncture target location along the guiding direction, the guiding direction of the needle tip needs to be significantly adjusted. This process can cause significant damage to the tissue of the punctured object. Summary of the Invention

[0005] Therefore, it is necessary to provide a puncture guidance system, puncture guidance device, puncture guidance method, storage medium, and computer program product to address the above-mentioned technical problems.

[0006] This application provides a puncture guidance system, the system including a prediction device, the prediction device performing the following steps:

[0007] Obtain the set of puncture target locations obtained by collecting data on the location of the puncture target when the subject is in the breath-holding phase before the puncture is performed;

[0008] Based on the geometric characteristics of the concentrated distribution area of ​​the puncture target locations corresponding to the set of puncture target locations, the observation position of the initial puncture reference point is obtained;

[0009] Based on continuous detection of the puncture target point position, whenever the set of puncture target point positions is updated, the observed position of the current puncture reference point corresponding to the update is obtained. Based on the difference between the observed position of the current puncture reference point and the predicted position of the current puncture reference point, the prediction result obtained based on the predicted position of the current puncture reference point is corrected to obtain the predicted position of the next puncture reference point. When the update is the first update, the current puncture reference point is the initial puncture reference point. The predicted position of the next reference point is used to guide the needle tip.

[0010] This application provides a puncture guidance device, the device comprising:

[0011] The target location acquisition module is used to acquire the set of puncture target locations obtained by collecting the location of the puncture target when the punctured object is in the breath-holding phase before the puncture is performed.

[0012] The reference point determination module is used to obtain the observation position of the initial puncture reference point based on the geometric characteristics of the concentrated distribution area of ​​the puncture target points corresponding to the set of puncture target point positions.

[0013] The prediction module is used to continuously detect the position of the puncture target point. Whenever the set of puncture target point positions is updated, the module obtains the observed position of the current puncture reference point corresponding to the update. Based on the difference between the observed position and the predicted position of the current puncture reference point, the module corrects the prediction result obtained based on the predicted position of the current puncture reference point to obtain the predicted position of the next puncture reference point. When the update is the first update, the current puncture reference point is the initial puncture reference point. The predicted position of the next reference point is used to guide the needle tip.

[0014] This application provides a puncture-guided method, wherein the steps of the method are performed by a predictive device, and the method includes the following steps:

[0015] Obtain the set of puncture target locations obtained by collecting data on the location of the puncture target when the subject is in the breath-holding phase before the puncture is performed;

[0016] Based on the geometric characteristics of the concentrated distribution area of ​​the puncture target locations corresponding to the set of puncture target locations, the observation position of the initial puncture reference point is obtained;

[0017] Based on continuous detection of the puncture target point position, whenever the set of puncture target point positions is updated, the observed position of the current puncture reference point corresponding to the update is obtained. Based on the difference between the observed position of the current puncture reference point and the predicted position of the current puncture reference point, the prediction result obtained based on the predicted position of the current puncture reference point is corrected to obtain the predicted position of the next puncture reference point. When the update is the first update, the current puncture reference point is the initial puncture reference point. The predicted position of the next reference point is used to guide the needle tip.

[0018] This application provides a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor using the methods described above.

[0019] This application provides a computer program product having a computer program stored thereon, the computer program being executed by a processor using the above-described method.

[0020] In the aforementioned puncture guidance system, puncture guidance device, puncture guidance method, storage medium, and computer program products, whenever the set of puncture target locations is updated, the observed position of the current puncture reference point can be obtained based on the geometric characteristics of the concentrated distribution area of ​​the puncture target locations corresponding to the set of puncture target locations. Based on the difference between the observed position and the predicted position of the current puncture reference point, the prediction result obtained based on the predicted position of the current puncture reference point is corrected. The predicted position of the next puncture reference point obtained through this correction process can be used as the guiding direction of the needle tip. This correction process can gradually constrain the guiding direction of the needle tip to the direction towards the puncture target point or the direction near the puncture target point. Even if the position of the puncture target point changes significantly during the puncture process, the guiding direction of the needle tip does not need to be adjusted significantly, thus reducing the damage to the tissue. Attached Figure Description

[0021] Figure 1(a) is a schematic diagram of the architecture of a puncture guidance system in one embodiment;

[0022] Figure 1(b) is a flowchart of a puncture guidance method in one embodiment;

[0023] Figure 2 This is a schematic diagram of the prediction process in one embodiment;

[0024] Figure 3 This is a flowchart illustrating a puncture-guided method based on preoperative and intraoperative images in one embodiment.

[0025] Figure 4 This is a flowchart illustrating the process of determining a puncture reference point in one embodiment;

[0026] Figure 5 This is a flowchart illustrating a puncture-guided method based on intraoperative images in one embodiment;

[0027] Figure 6 This is a flowchart illustrating a puncture-guided method based on intraoperative images in another embodiment;

[0028] Figure 7 This is a flowchart illustrating the particle filter algorithm in one embodiment;

[0029] Figure 8 This is a structural block diagram of a puncture guide device in one embodiment;

[0030] Figure 9 This is a diagram of the internal structure of a predictive device in one embodiment. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0032] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application can be combined with other embodiments.

[0033] The puncture guidance system provided in this application can be applied to real-time puncture scenarios guided by CT in interventional surgery. The puncture guidance system may include a prediction device, which can obtain the predicted position of the next puncture reference point and use the predicted position of the next puncture reference point as the current guidance result, outputting it to the puncture needle operating end for reference. The puncture needle operating end thereby guides the needle tip to move to the next puncture reference point; the puncture needle operating end includes, but is not limited to, a robotic arm and a doctor.

[0034] In some scenarios, robotic arms can also be considered part of a puncture guidance system, as shown in Figure 1(a).

[0035] When the predictive device obtains the predicted location of the next puncture reference point, the steps shown in Figure 1(b) can be performed:

[0036] Step S101: The prediction device acquires the set of puncture target locations obtained by collecting data on the location of the puncture target when the punctured object is in the breath-holding phase before the puncture is performed.

[0037] In tumor biopsy scenarios, the predictive device can set the tumor centroid as the puncture target. In this embodiment, before the puncture, the predictive device can detect the respiratory amplitude of the puncture subject using devices such as respiratory gating, prompting the subject to hold their breath within a specified respiratory amplitude range. At this time, the predictive device can determine that the subject is in the breath-holding phase. While the subject is in the breath-holding phase, the predictive device can collect the location of the puncture target, obtaining several locations to form a set of puncture target location locations. Each location in the set of puncture target location locations is observed and belongs to the observation location.

[0038] Furthermore, the method by which the predictive device acquires the location of the puncture target may specifically include: before the puncture is performed, the predictive device scans the punctured object in the breath-holding phase to obtain multiple frames of pre-puncture scan images; the predictive device unifies the position of the puncture target on each frame of pre-puncture scan images into the same coordinate system to obtain a set of puncture target positions.

[0039] In this embodiment, before the puncture is performed, when the puncture target is in the breath-holding phase, the prediction device can scan the puncture target using scanning imaging equipment such as CT to obtain multiple frames of images, which can be called multiple frames of pre-puncture scan images; when the scan is aimed at the puncture target of the puncture target, each frame of pre-puncture scan image may include the puncture target.

[0040] After obtaining multiple frames of pre-puncture scan images, the prediction device can perform puncture target detection on each frame of the pre-puncture scan image to determine whether the pre-puncture scan image contains the puncture target; if it does, the prediction device can obtain the position of the puncture target on that frame of the pre-puncture scan image.

[0041] If each frame of a multi-frame pre-puncture scan contains a puncture target point, the prediction device can obtain the position of the puncture target point on the multi-frame pre-puncture scan images. The position of the puncture target point on the pre-puncture scan image is described based on the coordinate system corresponding to that pre-puncture scan image; therefore, the position of the puncture target point on each frame of the pre-puncture image is described based on different coordinate systems. After obtaining the position of the puncture target point on each frame of the pre-puncture image, the prediction device can unify the position of the puncture target point on each frame of the pre-puncture image into the same coordinate system, describing the position of the puncture target point on each frame of the pre-puncture image based on the same coordinate system, thereby obtaining a set of puncture target point positions.

[0042] The aforementioned pre-puncture images can be collected during the preoperative stage corresponding to the start of the puncture procedure, or during the intraoperative stage corresponding to the start of the puncture procedure and the start of the puncture procedure. Accordingly, pre-puncture images collected during the preoperative stage can be called preoperative pre-puncture images, and pre-puncture images collected during the intraoperative stage can be called intraoperative pre-puncture images.

[0043] In some embodiments, the pre-puncture images used in constructing the set of puncture target locations may include two types, namely, pre-operative pre-puncture images and intra-operative pre-puncture images. The process of unifying the positions of the puncture target points on the pre-operative pre-puncture images and intra-operative pre-puncture images to the same coordinate system to obtain the set of puncture target locations will be described later.

[0044] In other embodiments, the pre-puncture images used when constructing the set of puncture target locations may include a single category, such as including only preoperative pre-puncture images, or only intraoperative pre-puncture images.

[0045] Among these, the set of puncture target locations obtained from pre-operative intraoperative images is more consistent with the current situation and has a better prediction effect. In this case, the prediction device unifies the positions of the puncture target points on each frame of pre-operative intraoperative images to the same coordinate system to obtain the set of puncture target locations. This can be achieved by: using one frame of the pre-operative intraoperative scan image as a reference image, and registering other frames of the pre-operative intraoperative scan image to the reference image; through this registration, mapping the positions of the puncture target points on the other frames of the pre-operative intraoperative scan image to the coordinate system corresponding to the reference image, thus obtaining the set of puncture target locations.

[0046] The method by which the predictive device unifies the position of the puncture target point on each frame of the pre-puncture image during the procedure to the same coordinate system may also include: setting a coordinate system and mapping the position of the puncture target point on each frame of the pre-puncture scan image during the procedure to the set coordinate system.

[0047] The above method can be applied to unify the position of the puncture target point on each frame of pre-puncture images to the same coordinate system.

[0048] Step S102: The prediction device obtains the observation position of the initial puncture reference point based on the geometric characteristics of the concentrated distribution area of ​​the puncture target positions corresponding to the set of puncture target positions.

[0049] The area formed based on the puncture target locations in the set of puncture target locations can be called the puncture target location distribution area. Within the puncture target location distribution area, there are some areas where puncture target locations are concentrated, and these areas can be called the concentrated distribution area of ​​puncture target locations.

[0050] The concentrated distribution area of ​​the puncture target points can be a geometrically shaped region in three-dimensional space, specifically a cuboid. The prediction device can analyze the geometric features of this concentrated distribution area, which are related to the region's geometric shape, specifically the corner points, center point, and points near the center point. After analysis, the prediction device can use the positions corresponding to the corner points, center points, or points near the center point of the concentrated distribution area as the positions of the initial puncture reference points. If the puncture target point locations are based on observations, the position of this initial puncture reference point is also considered observed and can be called the observed position of the initial puncture reference point. The observed position of this initial puncture reference point is described using the aforementioned unified coordinate system.

[0051] Step S103: The prediction device continuously detects the position of the puncture target point. Whenever the set of puncture target point positions is updated, the observed position of the current puncture reference point corresponding to the update is obtained. Based on the difference between the observed position of the current puncture reference point and the predicted position of the current puncture reference point, the prediction result obtained based on the predicted position of the current puncture reference point is corrected to obtain the predicted position of the next puncture reference point. When the update is the first update, the current puncture reference point is the initial puncture reference point. The predicted position of the next puncture reference point is used to guide the needle tip.

[0052] During the puncture guidance process, the prediction device can monitor the distance between the needle tip and the puncture reference point used for guidance in real time; when the detected distance is less than a threshold, the prediction device can update the set of puncture target point positions based on the real-time position of the puncture target point.

[0053] If no prediction has been made, the location of the puncture reference point used for current guidance can be the observed location of the initial puncture reference point; if a prediction has been made, the location of the puncture reference point used for current guidance can be the predicted location of the next puncture reference point.

[0054] Specifically:

[0055] The observation position at which the initial puncture reference point is obtained (which can be denoted as...) Afterwards, the respiratory amplitude of the punctured subject can be detected by devices such as respiratory gating, prompting the subject to adjust the current respiratory amplitude so that it is consistent with the respiratory amplitude when the puncture target position was collected before the puncture was performed.

[0056] Next, the puncture is performed. At this point, no prediction has been made, so... Overlaying onto the real-time monitoring screen, the puncture needle operating end is pressed The needle tip is guided into the object being punctured and continues to penetrate deeper. During this process, the predictive device can monitor the needle tip in real time. The distance between them. When the predictive device detects the distance between the needle tip and... When the distance between them is greater than the threshold, the puncture needle operating end continues to press. Guide the needle tip; at a certain moment (denoted as t) m ) Detected needle tip and When the distance between the two points is less than or equal to a threshold, the first prediction is initiated to change the position of the guide needle tip from the observed position to the predicted position; this threshold can be determined empirically.

[0057] During the initial prediction, the predictive device can obtain the predicted location of the next puncture reference point through pre-set parameters, denoted as... Then from tm At the start of the procedure, press the button on the puncture needle operating end. Guide needle tip.

[0058] according to Refer to the process of guiding the needle tip Figure 2 Predictive devices can Overlaying onto the real-time monitoring screen, the puncture needle operating end is pressed Guide the needle tip; during this process, the predictive device monitors the needle tip in real time. The distance between them, when the predictive device detects the needle tip and When the distance between them is greater than the threshold, the puncture needle operating end continues to press Guide the needle tip; at a certain moment (denoted as t) n ) Detected needle tip and When the distance between the target points is less than or equal to a threshold, the prediction device begins non-initial predictions. The prediction device bases its predictions on the distance between the target points and the threshold. n The observed position at each moment is used to update the set of puncture target point positions, and based on this update, the predicted position of the next puncture reference point is obtained. Then from t n At the start of the procedure, press the button on the puncture needle operating end. Guide needle tip.

[0059] Specifically, in the non-first-time prediction process, the prediction device is based on the puncture target point at t n After updating the set of puncture target locations, the observation location at each moment can be obtained and updated as described in step S102, corresponding to the current puncture reference point's observation location (which can be denoted as...). Predictive equipment based on A prediction result can be obtained, which represents the possible location of the next puncture reference point; to improve accuracy, the prediction device can... and The magnitude of the difference between the two values ​​is used to correct the prediction result, and the corrected result is used as the predicted location of the next puncture reference point.

[0060] The predictive device can obtain the predicted position of the next puncture reference point in the manner described above, so that the puncture needle operating end can adjust the guiding direction of the needle tip. The termination condition of this guidance can be determined according to the actual situation.

[0061] In this application, whenever the set of puncture target locations is updated, the observed position of the current puncture reference point can be obtained based on the geometric features of the concentrated distribution area of ​​the puncture target locations corresponding to the set of puncture target locations. Based on the difference between the observed position and the predicted position of the current puncture reference point, the prediction result obtained based on the predicted position of the current puncture reference point is corrected. The predicted position of the next puncture reference point obtained through this correction process can be used as the guiding direction of the needle tip. This correction process can gradually constrain the guiding direction of the needle tip to the direction towards the puncture target point or the direction near the puncture target point. Even if the position of the puncture target point changes significantly during the puncture process, the guiding direction of the needle tip does not need to be adjusted significantly, thereby reducing the damage to the tissue.

[0062] In one embodiment, when the predictive device detects that the distance is less than a threshold, and updates the set of puncture target locations based on the real-time location of the puncture target, the following steps can be performed: directly add the real-time location of the puncture target to the set of puncture target locations to complete the update process.

[0063] In one embodiment, when the predictive device detects that the distance is less than a threshold, and updates the set of puncture target locations based on the real-time location of the puncture target, the following steps may also be performed: when the distance is detected to be less than the threshold, the puncture target location is removed from the set of puncture target locations, and the real-time location of the puncture target is added to the set of puncture target locations; the puncture target location is determined according to the chronological order of the acquisition time corresponding to the puncture target location.

[0064] The set of puncture target locations includes multiple locations of the puncture target, which can be obtained by observing the puncture target at different times, with each location corresponding to a specific observation time. The prediction device can determine the target location of the puncture target according to the chronological order of the observation times corresponding to each location; specifically, it can use the earliest observation time as the target location of the puncture target. Then, the prediction device can remove the target locations of the puncture target from the set of puncture target locations.

[0065] With t n For example, the prediction device can obtain the puncture target point at time t based on CT scan. n The observation position at time t, after removing the puncture target position from the set of puncture target position positions, can be used to determine the puncture target position at time t. n The observation location at any given time is added to the set of puncture target locations.

[0066] In one embodiment, when the predictive device determines the concentrated distribution area of ​​puncture target locations, it may specifically perform the following steps: clustering the set of puncture target locations according to the distance between them; and determining the concentrated distribution area of ​​puncture target locations based on the clustering results.

[0067] This embodiment uses clustering to determine the concentrated distribution area of ​​puncture target locations. Clustering algorithms include, for example, k-means or hierarchical clustering, and other similar clustering algorithms.

[0068] In one embodiment, when the predictive device determines the concentrated distribution area of ​​puncture target locations, it may specifically perform the following steps: obtain a puncture target location matrix based on the set of puncture target locations; perform principal component analysis on the puncture target location matrix to determine multiple locations as principal components; and determine the concentrated distribution area of ​​puncture target locations based on the multiple locations.

[0069] In this embodiment, principal component analysis is used to determine the concentrated distribution area of ​​puncture target locations.

[0070] Specifically, each location of the puncture target can be represented by three-dimensional coordinates. Based on the three-dimensional coordinates of each location in the set of puncture target locations, a matrix can be constructed, which can be called the puncture target location matrix, denoted as M. The row vectors of the puncture target location matrix M can represent the three-dimensional coordinates of the puncture target. Principal component analysis is performed on the puncture target location matrix M, and k locations (k is less than the number of locations included in the set of puncture target locations) are selected as principal components. Based on these k locations, the concentrated distribution area of ​​the puncture target locations is determined.

[0071] In one embodiment, when the prediction device obtains the observation position of the initial puncture reference point based on the geometric features of the concentrated distribution area of ​​the puncture target positions corresponding to the set of puncture target positions, the following steps may be performed: obtaining the center point of the concentrated distribution area of ​​the puncture target positions corresponding to the set of puncture target positions; and obtaining the observation position of the initial puncture reference point based on the center point.

[0072] In this embodiment, the prediction device can use the center point of the concentrated distribution area of ​​puncture target points as the initial puncture reference point, and correspondingly, the position of the center point is the observation position of the initial puncture reference point. This processing method can be applied to the updated set of puncture target point positions. After updating the set of puncture target point positions based on the real-time positions of the puncture target points, the concentrated distribution area of ​​puncture target points can be determined again, and the center point of the concentrated distribution area of ​​puncture target points can be used as the current puncture reference point, and correspondingly, the position of the center point is the observation position of the current puncture reference point.

[0073] In one embodiment of this application, the process of unifying the positions of the puncture target points on preoperative and intraoperative preoperative images to the same coordinate system to obtain a set of puncture target point positions is described below. Figure 3 Before the puncture procedure, when the subject is at a specified respiratory amplitude (denoted as A), the prediction device can scan the subject to obtain multiple pre-puncture scan images and determine the position of the puncture target point on these images. During the puncture procedure, when the subject is at the specified respiratory amplitude A, the prediction device can scan the subject to obtain multiple intra-operative pre-puncture scan images and determine the position of the puncture target point on these images. Based on the registration process between the pre-puncture and intra-operative pre-puncture scan images, a deformation field is obtained. The prediction device can use this deformation field to map the position of the puncture target point on the pre-puncture scan images to the intra-operative pre-puncture scan images, thereby obtaining a set of puncture target point positions.

[0074] After the prediction device obtains the set of puncture target locations, it can be referenced. Figure 4 The clustering method is used to obtain clustered regions, which are then used as the concentrated distribution area of ​​puncture target points. The center point of the concentrated distribution area of ​​puncture target points is used as the puncture reference point. Before prediction, the observation position of the puncture reference point is overlaid on the real-time monitoring screen to guide the needle tip. After prediction, the predicted position of the puncture reference point is overlaid on the real-time monitoring screen to guide the needle tip at the puncture needle operation end.

[0075] During the process of guiding the needle tip at the puncture needle operating end, the prediction device can monitor the distance between the needle tip and the position of the puncture reference point used for guidance in real time, and determine whether the distance is less than or equal to a threshold. If the distance is greater than the threshold, the puncture needle operating end continues to guide the needle tip according to the position of the puncture reference point used for guidance. If the distance is less than or equal to the threshold, the prediction device updates the puncture target point position set based on the current position of the puncture target point, and predicts the next puncture reference point. The puncture needle operating end guides the needle tip according to the predicted position of the next puncture reference point.

[0076] Reference Figure 5 ,and Figure 4 The difference is, Figure 5 In the example shown, the set of puncture target points is formed based on the position of the puncture target points on the intraoperative pre-puncture scan image. Specifically, during the puncture procedure, before the puncture is performed, when the puncture target is in respiratory amplitude A, the prediction device scans the puncture target to obtain multiple frames of intraoperative pre-puncture scan images. Then, the first frame of intraoperative pre-puncture scan image is used as the reference image for registration, and the position of the puncture target point on the other frames of intraoperative pre-puncture scan images is mapped to the first frame of intraoperative pre-puncture scan image, thereby unifying the multiple positions of the puncture target point into the same coordinate system. Figure 5 For other processing steps, refer to the guidelines for... Figure 4 The details of the introduction are not repeated here.

[0077] Reference Figure 6 ,and Figure 5 The difference is, Figure 6 The example shown is not registered; the prediction device can directly unify the position of the puncture target point on each frame of the pre-puncture scan image in the procedure to a single coordinate system. Figure 6 For other processing steps, refer to the guidelines for... Figure 4 The details of the introduction are not repeated here.

[0078] In one embodiment, when the prediction device corrects the prediction result obtained based on the predicted position of the current puncture reference point based on the difference between the observed position and the predicted position of the current puncture reference point, and obtains the predicted position of the next puncture reference point, the specific steps include: obtaining the correction degree based on the difference between the observed position and the predicted position of the current puncture reference point; the larger the difference, the greater the correction degree; obtaining the prediction result using the predicted position of the current puncture reference point and the reference point position prediction algorithm; correcting the prediction result according to the correction degree to obtain the predicted position of the next puncture reference point.

[0079] For example, taking the observation position of the current puncture reference point as... For example:

[0080] Press the puncture needle operating end During the needle tip guidance process, the predictive device monitors the needle tip and... The distance between them, when the needle tip and When the distance between them is greater than the threshold, the puncture needle operating end continues to press. Guide the needle tip; at a certain moment (denoted as t) n ) Detected needle tip and When the distance between the points is less than or equal to a threshold, the prediction device bases its prediction on the distance between the puncture target points and the threshold. n The observation position at each moment is updated to update the set of puncture target point positions, thus obtaining the current observation position of the puncture reference point. Predictive devices can The reference point location prediction algorithm is input to obtain the prediction result; then, the prediction device... and The degree of correction is determined by the magnitude of the difference between the two; the larger the difference, the greater the degree of correction. The predictive device then adjusts the prediction based on this degree of correction. The obtained prediction results yield the predicted location of the next puncture reference point.

[0081] Furthermore, the predicted position of the current puncture reference point is obtained by weighting each particle in the current particle set, for example: Among them, {y 11 y 12 , ..., y 1N} is a set of particles, {w 11 ,w 12 ,...,w 1N} represents the weight assigned to each particle.

[0082] The reference point location prediction algorithm can be a particle filter algorithm, which includes a state transition equation, and a reference... Figure 7 The prediction device can input the predicted position of the current puncture reference point into the state transition equation to obtain the prediction result, and input the observed position of the current puncture reference point into the observation equation to update the weights; in addition, the prediction device can also perform particle resampling.

[0083] When the prediction device determines the degree of correction based on the difference between the observed position and the predicted position of the current puncture reference point, it can specifically perform the following steps: based on the distance between the observed position of the current puncture reference point and each particle in the current particle set, update the weights of each particle in the current particle set to obtain an updated weight set representing the degree of correction; wherein, the greater the distance, the smaller the corresponding weight after the update.

[0084] For example, at the observation position of the current puncture reference point. Afterwards, the prediction device can obtain With particle set {y 11 y 12 , ..., y 1N The distance between each particle in the}, and the distance between a certain particle and The greater the distance between them, the smaller the weight of the particle after the update, thus obtaining the updated weight set {w} that characterizes the degree of correction. 21 ,w 22 ,...,w 2N}

[0085] In addition, when the prediction device obtains the prediction result using the predicted position of the current puncture reference point and the reference point movement prediction algorithm, it can specifically perform the following steps: obtain the current particle set corresponding to the predicted position of the current puncture reference point; use the state transition equation of the reference point movement prediction algorithm to change the particle distribution state of the current particle set to obtain the next particle set representing the prediction result.

[0086] For example, {y 11 y 12 , ..., y 1NEach particle in the set is input into the state transition equation, and the output of the state transition equation is obtained, thus yielding the next particle set representing the prediction result: {y} 21 y 22 , ..., y 2N}

[0087] In addition, when the prediction device corrects the prediction result according to the correction degree to obtain the predicted position of the next puncture reference point, the following steps can be performed: using the updated weight set, weight each particle of the next particle set to obtain the predicted position of the next puncture reference point.

[0088] For example, the updated weight set {w 21 ,w 22 ,...,w 2N The weights in} are assigned to the particle set {y} accordingly. 21 y 22 , ..., y 2N The particles in the array are weighted to obtain the predicted position of the next puncture reference point.

[0089]

[0090] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0091] In one embodiment, such as Figure 8 As shown, a puncture guidance device is provided, comprising:

[0092] The target location acquisition module 801 is used to acquire the set of puncture target locations obtained by collecting the location of the puncture target when the punctured object is in the breath-holding phase before the puncture is performed.

[0093] The reference point determination module 802 is used to obtain the observation position of the initial puncture reference point based on the geometric characteristics of the concentrated distribution area of ​​the puncture target points corresponding to the set of puncture target point positions.

[0094] The prediction module 803 is used to continuously detect the position of the puncture target point, and whenever the set of puncture target point positions is updated, obtain the observed position of the current puncture reference point corresponding to the update, and correct the prediction result obtained based on the predicted position of the current puncture reference point based on the difference between the observed position of the current puncture reference point and the predicted position of the current puncture reference point, so as to obtain the predicted position of the next puncture reference point; when the update is the first update, the current puncture reference point is the initial puncture reference point; the predicted position of the next puncture reference point is used to guide the needle tip.

[0095] In one embodiment, the target location acquisition module 801 is further configured to scan the punctured object in the breath-holding phase before puncture to obtain multiple frames of pre-puncture scan images; and to unify the positions of the puncture target points on each frame of pre-puncture scan images into the same coordinate system to obtain a set of puncture target point positions.

[0096] In one embodiment, the pre-puncture phase refers to the period between the start of the surgery and the pre-puncture phase, and the obtained pre-puncture scan image is the intraoperative pre-puncture scan image. The target location acquisition module 801 is further configured to use one of the intraoperative pre-puncture scan images as a reference image and register other intraoperative pre-puncture scan images to the reference image. Through the registration, the position of the puncture target on other intraoperative pre-puncture scan images is mapped to the reference coordinate system.

[0097] In one embodiment, the device further includes a clustering module for clustering the set of puncture target locations based on the distance between them; and for determining the concentrated distribution area of ​​the puncture target locations based on the clustering results.

[0098] In one embodiment, the device further includes a principal component analysis module, used to obtain a puncture target location matrix based on the set of puncture target locations; perform principal component analysis on the puncture target location matrix to determine multiple locations as principal components; and determine a concentrated distribution area of ​​puncture target locations based on the multiple locations.

[0099] In one embodiment, the reference point determination module 802 is used to obtain the center point of the concentrated distribution area of ​​the puncture target points corresponding to the set of puncture target point locations; and based on the center point, to obtain the observation position of the initial puncture reference point.

[0100] In one embodiment, the device further includes an update module for real-time monitoring of the distance between the needle tip and the position of the puncture reference point used for current guidance; when the detected distance is less than a threshold, updating the set of puncture target point positions based on the real-time position of the puncture target point.

[0101] In one embodiment, the device further includes an update processing module, which is further configured to remove the puncture target location from the puncture target location set and add the real-time location of the puncture target to the puncture target location set when the distance is detected to be less than a threshold; the puncture target location is determined according to the order of observation times corresponding to the puncture target locations.

[0102] In one embodiment, the prediction module is further configured to obtain a correction degree based on the difference between the observed position of the current puncture reference point and the predicted position of the current puncture reference point; the greater the difference, the greater the correction degree; obtain a prediction result using the predicted position of the current puncture reference point and the reference point position prediction algorithm; and correct the prediction result according to the correction degree to obtain the predicted position of the next puncture reference point.

[0103] In one embodiment, the predicted position of the current puncture reference point is obtained by weighting each particle in the current particle set, and the reference point position prediction algorithm includes a state transition equation.

[0104] The prediction module is further configured to update the weights of each particle in the current particle set based on the distance between the observed position of the current puncture reference point and the distance between each particle in the current particle set, thereby obtaining an updated weight set representing the degree of correction; wherein, the greater the distance, the smaller the corresponding weight after the update; obtain the current particle set corresponding to the predicted position of the current puncture reference point; change the particle distribution state of the current particle set using the state transition equation of the reference point movement prediction algorithm, thereby obtaining the next particle set representing the prediction result; and weight each particle in the next particle set using the updated weight set to obtain the predicted position of the next puncture reference point.

[0105] For specific limitations regarding the puncture guidance device, please refer to the limitations of the puncture guidance system above, which will not be repeated here. Each module in the aforementioned puncture guidance device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in hardware or independently of the processor in the puncture guidance system, or stored in software in the memory of the puncture guidance system, so that the processor can call and execute the corresponding operations of each module.

[0106] In one embodiment, a puncture-guided method is provided, the steps of which are performed by a predictive device. The internal structure of the predictive device can be shown in the diagram below. Figure 9As shown. The predictive device includes a processor, memory, and network interface connected via a system bus. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores puncture guidance data. The network interface communicates with external terminals via a network connection. The predictive device also includes input / output interfaces, which are connection circuits between the processor and external devices for exchanging information; they are connected to the processor via a bus and are referred to as I / O interfaces. When the computer program is executed by the processor, it implements a puncture guidance method.

[0107] Those skilled in the art will understand that Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the prediction device to which the present application is applied. A specific prediction device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0108] The method includes the following steps: obtaining a set of puncture target point locations collected when the puncture target is in the breath-holding phase before puncture; obtaining the observed position of an initial puncture reference point based on the geometric features of the concentrated distribution area of ​​the puncture target point locations corresponding to the set of puncture target point locations; continuously detecting the positions of the puncture target points, obtaining the observed position of the current puncture reference point corresponding to the update whenever the set of puncture target point locations is updated, and correcting the prediction result obtained based on the predicted position of the current puncture reference point based on the difference between the observed position of the current puncture reference point and the predicted position of the current puncture reference point, to obtain the predicted position of the next puncture reference point; when the update is the first update, the current puncture reference point is the initial puncture reference point; the predicted position of the next reference point is used to guide the needle tip.

[0109] In one embodiment, when the prediction device acquires the set of puncture target positions obtained by collecting the positions of the puncture target points when the puncture target is in the breath-holding phase before the puncture is performed, the specific steps include the following: before the puncture is performed, the puncture target is scanned in the breath-holding phase to obtain multiple frames of pre-puncture scan images; the positions of the puncture target points on each frame of pre-puncture scan images are unified into the same coordinate system to obtain the set of puncture target positions.

[0110] In one embodiment, the pre-puncture stage is the period between the start of the surgery and the pre-puncture stage, and the obtained pre-puncture scan image is the intraoperative pre-puncture scan image.

[0111] The prediction device unifies the positions of the puncture target points on each frame of pre-puncture scan images into the same coordinate system to obtain the set of puncture target point positions. Specifically, it includes the following steps: taking one frame of intraoperative pre-puncture scan image as a reference image, and registering other frames of intraoperative pre-puncture scan images to the reference image; through the registration, mapping the positions of the puncture target points on other frames of intraoperative pre-puncture scan images to the coordinate system corresponding to the reference image to obtain the set of puncture target point positions.

[0112] In one embodiment, before obtaining the observation position of the initial puncture reference point based on the geometric characteristics of the concentrated distribution area of ​​the puncture target positions corresponding to the set of puncture target positions, the prediction device further performs the following steps: clustering the set of puncture target positions according to the distance between the puncture target positions; and determining the concentrated distribution area of ​​the puncture target positions based on the clustering result.

[0113] In one embodiment, before obtaining the observation position of the initial puncture reference point based on the geometric characteristics of the concentrated distribution area of ​​the puncture target positions corresponding to the set of puncture target positions, the prediction device further performs the following steps: obtaining a puncture target position matrix based on the set of puncture target positions; performing principal component analysis on the puncture target position matrix to determine multiple positions as principal components; and determining the concentrated distribution area of ​​the puncture target positions based on the multiple positions.

[0114] In one embodiment, when the prediction device performs the calculation of the observation position of the initial puncture reference point based on the geometric features of the concentrated distribution area of ​​the puncture target locations corresponding to the set of puncture target locations, the specific steps include: obtaining the center point of the concentrated distribution area of ​​the puncture target locations corresponding to the set of puncture target locations; and obtaining the observation position of the initial puncture reference point based on the center point.

[0115] In one embodiment, the prediction device further performs the following steps: real-time monitoring of the distance between the needle tip and the location of the puncture reference point used for current guidance; when the distance is detected to be less than a threshold, updating the set of puncture target point locations based on the real-time location of the puncture target point.

[0116] In one embodiment, when the prediction device detects that the distance is less than a threshold, updating the set of puncture target locations based on the real-time location of the puncture target includes the following steps: when the distance is detected to be less than the threshold, removing the puncture target location from the set of puncture target locations and adding the real-time location of the puncture target to the set of puncture target locations; the puncture target location is determined according to the chronological order of the observation times corresponding to the puncture target locations.

[0117] In one embodiment, when the prediction device corrects the prediction result obtained based on the predicted position of the current puncture reference point based on the difference between the observed position and the predicted position of the current puncture reference point, and obtains the predicted position of the next puncture reference point, the specific steps include: obtaining a correction degree based on the difference between the observed position and the predicted position of the current puncture reference point; the larger the difference, the greater the correction degree; obtaining a prediction result using the predicted position of the current puncture reference point and a reference point position prediction algorithm; and correcting the prediction result according to the correction degree to obtain the predicted position of the next puncture reference point.

[0118] In one embodiment, the predicted position of the current puncture reference point is obtained by weighting each particle in the current particle set, and the reference point position prediction algorithm includes a state transition equation.

[0119] When the prediction device obtains the degree of correction based on the difference between the observed position of the current puncture reference point and the predicted position of the current puncture reference point, it specifically includes the following steps: based on the distance between the observed position of the current puncture reference point and each particle in the current particle set, the weights of each particle in the current particle set are updated to obtain an updated weight set representing the degree of correction; wherein, the larger the distance, the smaller the corresponding weight after the update.

[0120] When the prediction device obtains the prediction result using the predicted position of the current puncture reference point and the reference point movement prediction algorithm, it specifically includes the following steps: obtaining the current particle set corresponding to the predicted position of the current puncture reference point; using the state transition equation of the reference point movement prediction algorithm, changing the particle distribution state of the current particle set to obtain the next particle set representing the prediction result;

[0121] According to the degree of correction, the prediction result is corrected to obtain the predicted position of the next puncture reference point, including: using the updated weight set to weight each particle in the next particle set to obtain the predicted position of the next puncture reference point.

[0122] For specific limitations on puncture guidance methods, please refer to the limitations on puncture guidance systems mentioned above, which will not be repeated here.

[0123] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the various method embodiments described above.

[0124] In one embodiment, a computer program product is provided having a computer program stored thereon, the computer program being executed by a processor of the steps described in the various method embodiments above.

[0125] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0126] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0127] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0128] The above embodiments are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A puncture guidance system, characterized in that, The system includes a prediction device, which performs the following steps: Obtain the set of puncture target locations obtained by collecting data on the location of the puncture target when the subject is in the breath-holding phase before the puncture is performed; The set of puncture target locations is clustered based on the distance between them; Based on the clustering results, the concentrated distribution area of ​​the puncture target locations is determined; Based on the geometric characteristics of the concentrated distribution area of ​​the puncture target locations corresponding to the set of puncture target locations, the observation position of the initial puncture reference point is obtained; Based on continuous detection of the puncture target point position, whenever the set of puncture target point positions is updated, the observed position of the current puncture reference point corresponding to the update is obtained. Based on the difference between the observed position of the current puncture reference point and the predicted position of the current puncture reference point, the prediction result obtained based on the predicted position of the current puncture reference point is corrected to obtain the predicted position of the next puncture reference point. When the update is the first update, the current puncture reference point is the initial puncture reference point. The predicted position of the next puncture reference point is used to guide the needle tip.

2. The system according to claim 1, characterized in that, When the prediction device acquires the set of puncture target point locations obtained by collecting data on the locations of the puncture target points when the puncture target is in the breath-holding phase before the puncture is performed, the specific steps include the following: Before the puncture is performed, the subject being punctured during the breath-holding phase is scanned to obtain multiple pre-puncture scan images; The positions of the puncture target points on each frame of the pre-puncture scan image are unified into the same coordinate system to obtain the set of puncture target point positions.

3. The system according to claim 2, characterized in that, The period before puncture is the stage between the start of the surgery and the puncture, and the obtained pre-puncture scan image is the intraoperative pre-puncture scan image. When the prediction device unifies the positions of the puncture target points on each frame of pre-puncture scan image to the same coordinate system to obtain the set of puncture target point positions, it specifically includes the following steps: Use one frame of the intraoperative pre-puncture scan image as the reference image, and register the other frames of the intraoperative pre-puncture scan image to the reference image; The registration process maps the position of the puncture target point on the pre-puncture scan image in other frames to the coordinate system corresponding to the reference image, thus obtaining a set of puncture target point positions.

4. The system according to claim 1, characterized in that, Before obtaining the observation position of the initial puncture reference point based on the geometric features of the concentrated distribution area of ​​the puncture target points corresponding to the set of puncture target point positions, the prediction device also performs the following steps: Based on the set of puncture target locations, a puncture target location matrix is ​​obtained; Principal component analysis was performed on the puncture target location matrix to determine multiple locations that serve as principal components; Based on the aforementioned multiple locations, a concentrated distribution area of ​​puncture target locations is determined.

5. The system according to claim 1, characterized in that, When the prediction device obtains the observation position of the initial puncture reference point based on the geometric features of the concentrated distribution area of ​​the puncture target point positions corresponding to the set of puncture target point positions, the specific steps include the following: Obtain the center point of the concentrated distribution area of ​​the puncture target locations corresponding to the set of puncture target locations; Based on the center point, the observation position of the initial puncture reference point is obtained.

6. The system according to claim 1, characterized in that, The prediction device also performs the following steps: Real-time monitoring of the distance between the needle tip and the puncture reference point used for current guidance; When the distance is detected to be less than the threshold, the set of puncture target locations is updated based on the real-time location of the puncture target.

7. The system according to claim 6, characterized in that, When the prediction device detects that the distance is less than the threshold, and updates the set of puncture target locations based on the real-time location of the puncture target, the specific steps include the following: When the distance is detected to be less than the threshold, the puncture target location is removed from the puncture target location set, and the real-time location of the puncture target is added to the puncture target location set. The target location of the puncture point is determined according to the order of observation times corresponding to the puncture point location.

8. The system according to claim 1, characterized in that, When the prediction device corrects the prediction result obtained based on the predicted position of the current puncture reference point based on the difference between the observed position and the predicted position of the current puncture reference point, and obtains the predicted position of the next puncture reference point, the specific steps include the following: The degree of correction is determined based on the difference between the observed position and the predicted position of the current puncture reference point; the greater the difference, the greater the degree of correction. The prediction result is obtained by using the predicted position of the current puncture reference point and the reference point position prediction algorithm; The prediction result is corrected according to the degree of correction to obtain the predicted position of the next puncture reference point.

9. The system according to claim 8, characterized in that, The predicted position of the current puncture reference point is obtained by weighting each particle in the current particle set, and the reference point position prediction algorithm includes the state transition equation. When the prediction device determines the degree of correction based on the difference between the observed position of the current puncture reference point and the predicted position of the current puncture reference point, the specific steps include the following: Based on the observed position of the current puncture reference point and the distance between each particle in the current particle set, the weights of each particle in the current particle set are updated to obtain an updated weight set representing the degree of correction; wherein, the greater the distance, the smaller the corresponding weight after the update. When the prediction device obtains the prediction result using the predicted position of the current puncture reference point and the reference point movement prediction algorithm, it specifically includes the following steps: Obtain the current particle set corresponding to the predicted position of the current puncture reference point; By using the state transition equation of the reference point moving prediction algorithm, the particle distribution state of the current particle set is changed to obtain the next particle set that represents the prediction result. According to the aforementioned correction level, the prediction result is corrected to obtain the predicted location of the next puncture reference point, including: Using the updated weight set, the particles in the next particle set are weighted to obtain the predicted position of the next puncture reference point.

10. A puncture guiding device, characterized in that, The device includes: The target location acquisition module is used to acquire the set of puncture target locations obtained by collecting the location of the puncture target when the punctured object is in the breath-holding phase before the puncture is performed. The clustering module is used to cluster the set of puncture target locations based on the distance between them; and to determine the concentrated distribution area of ​​the puncture target locations based on the clustering results. The reference point determination module is used to obtain the observation position of the initial puncture reference point based on the geometric characteristics of the concentrated distribution area of ​​the puncture target points corresponding to the set of puncture target point positions. The prediction module is used to continuously detect the position of the puncture target point. Whenever the set of puncture target point positions is updated, the module obtains the observed position of the current puncture reference point corresponding to the update. Based on the difference between the observed position and the predicted position of the current puncture reference point, the module corrects the prediction result obtained based on the predicted position of the current puncture reference point to obtain the predicted position of the next puncture reference point. When the update is the first update, the current puncture reference point is the initial puncture reference point. The predicted position of the next puncture reference point is used to guide the needle tip.

Images