Interventional real-time monitoring method and system based on intelligent sensing technology

Abstract

The application relates to the technical field of image processing, in particular to a blood vessel intervention real-time monitoring method and system based on intelligent sensing technology. The method comprises the following steps: collecting two-dimensional images of multiple angles in a target area within a preset time period, selecting a reference image, and obtaining blood vessel blood pressure; mapping the blood vessel blood pressure and the reference image to the same time coordinate axis, obtaining a dynamic cycle of the blood vessel blood pressure, and obtaining a blood vessel three-dimensional image and a three-dimensional feature at each relative position in the dynamic cycle based on the dynamic cycle and the reference image; obtaining a reference path of a catheter assembly reaching a preset position of a blood vessel through real-time monitoring of a real-time dynamic cycle of the blood vessel blood pressure and a first model; real-time monitoring a motion trail of a head of the catheter assembly, and obtaining a path error; inputting the path error, a blood vessel dynamic image at the preset position and a catheter assembly characteristic into a second model, and obtaining an intervention operation risk probability value. The application solves the problems of real-time monitoring and risk prediction of a blood vessel intervention operation, and improves the precision and safety of the operation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, in particular to a blood vessel intervention real-time monitoring method and system based on intelligent sensing technology. BACKGROUND

[0002] Vascular intervention surgery is a common minimally invasive treatment method and is widely used in the treatment of cardiovascular diseases, cerebrovascular diseases and peripheral vascular diseases. However, there are still many deficiencies in the existing technology in the vascular intervention surgery. There is a lack of real-time and accurate monitoring means during the operation, and doctors mainly rely on imaging devices for navigation, but these devices have radiation exposure risk and cannot provide real-time feedback of the subtle changes inside the blood vessel, and the precision, real-time performance and safety still need to be improved, which cannot meet the needs of complex operation scenarios. Similar prior art discloses a cardiovascular intervention robot control monitoring system in Chinese patent application No. CN117426874A, which includes a catheter system for conveying an interventional instrument for performing a vascular intervention surgery to a target region through a patient's blood vessel, an image navigation system for constructing a three-dimensional image of the blood vessel distribution in the patient's body, and a control system for controlling the catheter system to perform the vascular intervention surgery; the three-dimensional image accuracy is improved by combining image fusion three-dimensional navigation and electromagnetic tracking navigation, thereby improving the artificial intelligence assisted algorithm, more intelligently planning the path of the catheter in the blood vessel, and maximizing the risk of damage to the blood vessel wall during the intervention surgery, and optimizing the stress bearing of the catheter. In addition, similar prior art discloses a unmanned interventional operating room system in German patent No. DE112022000032T5, which includes a catheter room and a control room, an observation window is arranged between the catheter room and the control room; a robot, an interventional surgery robot, a master robot, a puncture robot and an exchange catheter guide wire robot are arranged in the catheter room; a DSA device and a contrast agent injection device are installed on the catheter bed; a monitoring device is arranged in the control room, and the monitoring device is in communication connection with the robot, the DSA device and the contrast agent injection device, provides information of each device and robot, and the information is synchronously and real-timely updated for display by the doctor; a controller is arranged in the control room for man-machine interaction between the doctor and the robot, realizes artificial monitoring, and through the combination with the robot, achieves the purpose of unmanned interventional surgery and reduces the influence of interventional surgery on the health of the doctor. The above two patent documents both realize the control or guidance of the operation by the monitoring data obtained during the interventional surgery, so as to reduce the risk of the operation, but the above two technical solutions do not consider the dynamic changes of the intervention blood vessel and the operation cooperation with the catheter, so as to further reduce the probability of the operation risk. SUMMARY

[0003] The application provides a blood vessel intervention real-time monitoring method based on sensing technology, aiming to solve the problem of lack of real-time and accurate monitoring means in existing blood vessel intervention surgery. Through the technology, the accuracy and safety of the surgery can be significantly improved, and the risk of the surgery can be reduced. The method comprises the following steps:

[0004] Step S1: In a preset time period, a plurality of two-dimensional images of each angle in a target area are collected by an image acquisition unit, a reference image is selected from a plurality of two-dimensional images, and a blood vessel blood pressure is acquired by a monitoring unit in a catheter assembly;

[0005] Step S2: The blood vessel blood pressure and a plurality of reference images are mapped to the same time coordinate axis according to the acquisition time, the dynamic cycle of the blood vessel blood pressure is acquired, the blood vessel three-dimensional image and three-dimensional feature at each relative position in the dynamic cycle are acquired based on the dynamic cycle and a plurality of reference images, and a first model is trained based on the dynamic cycle and the blood vessel three-dimensional image and three-dimensional feature corresponding to each relative position;

[0006] Step S3: The real-time dynamic cycle of the blood vessel blood pressure is monitored, the three-dimensional dynamic image of the blood vessel is acquired based on the real-time dynamic cycle and the first model, and the reference path of the catheter assembly reaching a preset position of the blood vessel is acquired based on the three-dimensional dynamic image;

[0007] Step S4: In the process that the catheter assembly reaches the preset position, the motion trail of the head of the catheter assembly is monitored in real time, and the path error is acquired based on the motion trail and the reference path;

[0008] Step S5: The path error, the characteristics of the catheter assembly and the three-dimensional image at the preset position are input into a second model to acquire an intervention surgery risk probability value, wherein the second model is an intervention surgery risk prediction model.

[0009] As a preferred technical solution of the application, after the step S5, the following steps are further included:

[0010] When the intervention surgery risk probability value is greater than or equal to a set threshold, the control accuracy of the catheter assembly is improved, the steps S3 and S4 are repeated, the path error is reacquired, the intervention surgery risk probability value is reacquired based on the reacquired path error and the step S5, and the step is repeated until the intervention surgery risk probability value is less than the set threshold.

[0011] When the control accuracy of the catheter assembly cannot meet the condition that the interventional operation risk probability value is less than the set threshold, the steps S1-S2 are repeated to retrain the first model, and the steps S3-S5 are repeated to reacquire the interventional operation risk probability value based on the reacquired first model.

[0012] As a preferred technical solution of the present application, the blood vessel three-dimensional image and three-dimensional feature at each relative position in the dynamic period are acquired based on the dynamic period and the plurality of reference images, comprising:

[0013] The blood vessel blood pressure and the reference images are mapped to the same time axis according to the acquisition time, the change period of the numerical value of the blood vessel blood pressure with time is analyzed by the dynamic time warping algorithm, and the change period is taken as the dynamic period of the blood vessel blood pressure.

[0014] The plurality of reference images are divided into groups according to the dynamic period, wherein the reference images in each group correspond to the same time in the same dynamic period, and the blood vessel features are extracted from each reference image in the group, and the blood vessel three-dimensional features corresponding to each time in the dynamic period of each group are acquired by integrating all the blood vessel features corresponding to each group, the blood vessel features include the diameter of the blood vessel, the centerline position of the blood vessel and the shape of the blood vessel, and the blood vessel three-dimensional features include the three-dimensional information of the blood vessel.

[0015] As a preferred technical solution of the present application, the training of the first model comprises:

[0016] Based on the plurality of dynamic periods included in the preset time period and the blood vessel three-dimensional image and corresponding three-dimensional feature at each relative position in each dynamic period, and the three-dimensional image and three-dimensional feature interpolation is performed on the position of the blood vessel three-dimensional image discontinuous between adjacent relative positions, the blood vessel three-dimensional image continuous frame and corresponding three-dimensional feature are acquired, and the plurality of dynamic periods and the blood vessel three-dimensional image continuous frame and corresponding three-dimensional feature corresponding to each dynamic period are taken as training data to train the first model.

[0017] As a preferred technical solution of the present application, the reference path is acquired, comprising:

[0018] According to the real-time monitoring of the numerical change of the blood pressure of the blood vessel, the real-time dynamic cycle of the blood pressure of the blood vessel is obtained, and the real-time dynamic cycle is input into the first model to obtain a three-dimensional dynamic image of the blood vessel changing over time, the three-dimensional dynamic image is mapped to a three-dimensional coordinate system to obtain a dynamic distribution of the blood vessel in the three-dimensional coordinate system, and the dynamic distribution is used to calculate an overlapping distribution area of each relative position in the real-time dynamic cycle, and a first size of the overlapping distribution area is calculated. When the first size is greater than a second size of the head of the catheter assembly and the difference between the first size and the second size is greater than or equal to a set value, the center line of the overlapping distribution area is taken as the reference path of the catheter assembly to the preset position, otherwise, a dynamic center line of the blood vessel is obtained from the three-dimensional dynamic image, and the dynamic center line is taken as the reference path of the catheter assembly. In addition, the advancing speed of the catheter assembly is adjusted based on the change speed of the dynamic image center line.

[0019] As a preferred technical solution of the present application, the path error is obtained, comprising:

[0020] The image acquisition unit is used to track and obtain a real-time image at the position of the head of the catheter assembly in real time, and the motion trajectory of the head of the catheter assembly is extracted from the real-time image. The maximum distance between the motion trajectory and the reference path in the real-time dynamic cycle is obtained, and the maximum distance is taken as the path error.

[0021] As a preferred technical solution of the present application, in the step S5, the characteristics of the catheter assembly include the type of catheter, the rigidity of the corresponding guide wire, and the size and material of the catheter assembly and the guide wire.

[0022] As a preferred technical solution of the present application, the training of the second model comprises:

[0023] The historical operation data is obtained from the storage unit, the historical operation data includes historical data of a plurality of patients, and the historical data includes characteristics of a catheter assembly used in an operation, a plurality of two-dimensional images of a target blood vessel, a planned path of an operation, an actual path of an operation, and an operation result. The three-dimensional dynamic image corresponding to the target blood vessel is obtained based on the plurality of two-dimensional images of the target blood vessel through the steps S1-S3. The historical path error is obtained through the planned path and the actual path. The path error, the three-dimensional dynamic image of the target blood vessel, and the characteristics of the catheter assembly are used as training data to train the second model.

[0024] The present application also provides a blood vessel intervention real-time monitoring system based on intelligent sensing technology, which is used to realize the above-mentioned method, and the system comprises:

[0025] An image acquisition unit is configured to collect a plurality of two-dimensional images of different angles in a target region within a preset time period, and select a reference image from the plurality of two-dimensional images;

[0026] A monitoring unit is located in the catheter assembly and configured to acquire a blood pressure of the blood vessel;

[0027] A calculation unit is configured to map the blood pressure of the blood vessel and the plurality of reference images to a same time coordinate axis according to acquisition time, acquire a dynamic cycle of the blood pressure of the blood vessel, and acquire a three-dimensional image and a three-dimensional feature of the blood vessel at each relative position in the dynamic cycle based on the dynamic cycle and the plurality of reference images;

[0028] A model training unit is configured to train a first model based on the dynamic cycle and the three-dimensional image and the three-dimensional feature of the blood vessel at each relative position;

[0029] The calculation unit is further configured to acquire a three-dimensional dynamic image of the blood vessel based on a real-time dynamic cycle of the blood pressure of the blood vessel and the first model, acquire a reference path of the catheter assembly to a preset position of the blood vessel based on the three-dimensional dynamic image, acquire a path error based on a motion trail of a head of the catheter assembly and the reference path during a process in which the catheter assembly reaches the preset position, and input the path error, a characteristic of the catheter assembly, and a three-dimensional image at the preset position into a second model to acquire a risk probability value of an interventional surgery, wherein the second model is an interventional surgery risk prediction model.

[0030] The application further provides a computer readable storage medium, which stores instructions, and the instructions are executed by a processor to implement the method.

[0031] Effects

[0032] The application collects two-dimensional images of different angles in a target region within a preset time period, and acquires a blood pressure of a blood vessel by a monitoring unit in a catheter, so as to realize multi-dimensional data acquisition of a blood vessel interventional surgery process. The multi-modal data fusion method makes up for the deficiency of traditional imaging devices that cannot provide real-time feedback of internal subtle changes of a blood vessel, and provides more comprehensive information support for precise navigation of a surgery.

[0033] Secondly, the method of mapping a blood pressure of a blood vessel and a reference image to a same time coordinate axis can accurately acquire a dynamic cycle of the blood pressure of the blood vessel, and construct a three-dimensional image and a three-dimensional feature of the blood vessel based on the dynamic cycle, so as to not only consider a static structure of the blood vessel, but also pay attention to dynamic changes, so that a surgery path planning is more in line with an actual physiological state of the blood vessel, and thus the risk of damage of a catheter to a blood vessel wall is effectively reduced.

[0034] Furthermore, through the collaborative work of the first and second models, the system can monitor the catheter's trajectory in real time and calculate path errors, thereby predicting the risk probability of interventional surgery. This real-time risk assessment mechanism provides surgeons with crucial decision-making references, making the surgical process more controllable. When the risk probability exceeds a set threshold, the system can automatically adjust the catheter's control precision and even retrain the model to optimize the surgical path, further improving the safety and success rate of the surgery. It also achieves real-time monitoring and risk prediction of vascular interventional surgery through intelligent sensing technology and advanced image processing algorithms, significantly improving the precision and safety of the procedure. The widespread application of this technology is expected to drive the development of vascular interventional surgery towards greater intelligence, precision, and safety, providing strong technical support for minimally invasive treatment of cardiovascular, cerebrovascular, and peripheral vascular diseases. Attached Figure Description

[0035] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0036] Figure 1 This is a flowchart of the real-time monitoring method for vascular intervention based on smart sensor technology in the embodiments of this application;

[0037] Figure 2 This is a flowchart of the method for calculating the dynamic cycle of blood vessels, three-dimensional images of blood vessels, and three-dimensional features in the embodiments of this application;

[0038] Figure 3 This is a flowchart of the reference path calculation method in the embodiments of this application;

[0039] Figure 4 This is a structural diagram of the real-time monitoring system for vascular intervention based on intelligent sensor technology in the embodiments of this application. Detailed Implementation

[0040] The embodiment of the present application provides a blood vessel intervention real-time monitoring method and system based on intelligent sensor technology. The terms "first", "second", "third", "fourth" and the like (if any) in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" or "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0041] For ease of understanding, the specific process of the embodiment of the present application is described as follows, as shown in the figure, one embodiment of the blood vessel intervention real-time monitoring method based on intelligent sensor technology in the present application comprises: Figure 1

[0042] Step S1: In a preset time period, a plurality of two-dimensional images of each angle in a target region are collected by an image acquisition unit, a reference image is selected from the plurality of two-dimensional images, and a blood vessel blood pressure is acquired by a monitoring unit in a catheter;

[0043] Specifically, when performing a blood vessel intervention operation, first, a preset time period is set, for example, 10 minutes, in the time period, a plurality of two-dimensional images of each angle in a target blood vessel region are collected by an image acquisition unit (such as a multi-angle X-ray imaging device), it is assumed that one image is collected every 10° from 0° to 360°, a total of 36 two-dimensional images are collected, then a two-dimensional image with the highest clarity and the most obvious blood vessel features is selected as a reference image from the 36 two-dimensional images, at the same time, blood vessel blood pressure data is acquired by a monitoring unit (such as a pressure sensor) in a catheter, it is assumed that blood pressure data is collected every 0.1 second for 10 seconds, a total of 100 blood pressure data points are collected, wherein the monitoring unit can also monitor blood flow velocity, temperature and other parameters, through the above technical solution, a reference image with high quality and corresponding blood vessel blood pressure can be acquired, which lays a foundation for further acquiring a dynamic cycle and a blood vessel three-dimensional image.

[0044] Step S2: Map the blood vessel blood pressure and the reference image to the same time coordinate axis according to the acquisition time, acquire a dynamic cycle of the blood vessel blood pressure, and acquire a blood vessel three-dimensional image and a three-dimensional feature at each relative position in the dynamic cycle based on the dynamic cycle and each reference image;

[0045] ​Specifically, by mapping the 100 blood vessel blood pressure data points and the reference images obtained in step S1 to the same time coordinate axis according to the acquisition time, the dynamic time warping algorithm is used to analyze the change cycle of the blood vessel blood pressure value over time, and it is assumed that the analysis obtains a dynamic cycle of 4 seconds, that is, one contraction and relaxation cycle of the heart. Then, the reference images are divided into groups according to the relative positions of the acquisition time in the corresponding dynamic cycle, for example, the reference images with acquisition time in 0-0.5 seconds are divided into a group, the reference images with acquisition time in 0.5-1 second are divided into another group, and so on. The blood vessel features such as the blood vessel diameter and the center line position are extracted from each group of reference images, and each group of reference images and the corresponding blood vessel features are integrated to obtain the blood vessel three-dimensional image and the three-dimensional feature at each relative position in the dynamic cycle. Through the above technical solution, the relationship between the dynamic cycle of the blood vessel and the above blood vessel three-dimensional dynamic image is laid as a foundation.

[0046] Step S3: training a first model based on the dynamic cycle and the blood vessel three-dimensional image and three-dimensional feature corresponding to each time, monitoring the real-time dynamic cycle of the blood vessel blood pressure, and obtaining a reference path of the catheter assembly reaching a preset position of the blood vessel based on the real-time dynamic cycle, the first model, and the size of the catheter assembly;

[0047] Specifically, based on the dynamic cycle and the blood vessel three-dimensional image and three-dimensional feature at each relative position obtained in step S2, the first model is trained. It is assumed that the first model is a neural network model based on deep learning. During the operation, the value change of the blood vessel blood pressure is monitored in real time, the real-time dynamic cycle is obtained, the real-time dynamic cycle is input into the trained first model, the model outputs the three-dimensional dynamic image of the blood vessel changing over time, the three-dimensional dynamic image is mapped to a three-dimensional coordinate system based on the three-dimensional dynamic image, the dynamic distribution of the blood vessel in the three-dimensional coordinate system is obtained, the overlapping distribution area and the first size of each relative position in the real-time dynamic cycle are calculated according to the dynamic distribution, and the reference path is obtained according to the relationship between the first size of the above overlapping distribution area and the second size of the above catheter assembly. Through the above technical solution, the reference path of the catheter assembly reaching the above preset position can be accurately obtained, and damage to the blood vessel can be avoided.

[0048] Step S4: during the process that the catheter assembly reaches the preset position, a path error is obtained based on the motion trail of the catheter head and the reference path by monitoring the motion trail of the catheter head in real time;

[0049] Specifically, in the process of the catheter reaching the preset position, a real-time image at the position where the catheter head is located is tracked in real time by the image acquisition unit, assuming that an image is collected every 0.05 seconds, the motion trajectory of the catheter head is extracted from the real-time image. Compare the motion trajectory with the reference path obtained in step S3, obtain the maximum distance between the motion trajectory and the reference path in the real-time dynamic period, assuming that the maximum distance is 0.2 millimeters, the maximum distance is taken as the path error, through the above technical solution, the path error of the above catheter assembly in the blood vessel can be accurately obtained, thereby laying a foundation for further obtaining the operation risk probability of the interventional surgery through the second model.

[0050] Step S5: input the path error, the blood vessel dynamic image at the preset position and the characteristics of the catheter into the second model to obtain an interventional surgery risk probability value, wherein the second model is an interventional surgery risk prediction model.

[0051] Specifically, the path error obtained in step S4, the blood vessel dynamic image at the preset position (including blood vessel diameter, center line position and other features) and the characteristics of the catheter (such as the catheter type is a certain type of blood vessel catheter, the guide wire rigidity is medium, the size and material of the catheter and the guide wire are 2 millimeters in diameter, 100 centimeters in length and medical polymer material in material) are input into the second model, assuming that the second model is a risk prediction model based on machine learning, after model calculation, the interventional surgery risk probability value is output, through the above technical solution, the above interventional surgery risk probability can be accurately obtained, the control accuracy of the above catheter assembly is adjusted in advance, thereby reducing the operation risk of the above interventional surgery.

[0052] Further, after the step S5, it further includes,

[0053] When the interventional surgery risk probability value is greater than or equal to a set threshold, the control accuracy of the catheter is improved, and the step S3 and the step S4 are repeated to reacquire the path error, and the interventional surgery risk probability value is reacquired based on the reacquired path error and the step S5, and the step is repeated until the interventional surgery risk probability value is less than the set threshold.

[0054] When the control accuracy of the catheter cannot meet the interventional surgery risk probability value less than the set threshold by improving the control accuracy of the catheter, the step S1-step S2 is repeated to retrain the first model, and the step S3-step S5 is repeated to reacquire the interventional surgery risk probability value based on the reacquired first model.

[0055] Specifically, when the intervention operation risk probability is greater than or equal to the set threshold, that is, when the intervention operation risk probability value is large, it is possible that the control accuracy of the catheter assembly is not high enough or the accuracy of the first model is not high enough, resulting in a large path error, thereby causing the intervention operation risk probability to be large. Since the control accuracy of the catheter assembly is easy to adjust, the control accuracy of the catheter assembly is first improved, that is, the first control frequency of the catheter assembly is increased to the second control frequency, so as to control the advancing speed and direction of the catheter assembly, and the steps S3 and S4 are repeated to reacquire the path error, and based on the reacquired path error and the intervention operation risk probability value acquired in the step S5, when the intervention operation risk probability value is still greater than or equal to the set threshold, the step is repeated, so that the speed and control accuracy of the catheter assembly can satisfy the condition that the intervention operation risk probability value is less than or equal to the set threshold, wherein the set threshold is 90%. When the accuracy of the catheter assembly cannot satisfy the condition by adjusting the accuracy of the catheter assembly, it is possible that the accuracy of the first model is not high enough, resulting in a large path error. Therefore, by repeating the steps S1-S5, the first model is retrained. Since the training data of the second model is processed by the first model, the second model also needs to be updated synchronously based on the retrained first model, and the intervention operation risk probability value is reacquired. Through the technical solution, the accuracy of the catheter assembly and the accuracy of the first model can be adjusted to accurately predict the operation risk of the intervention operation, that is, the intervention operation risk probability value.

[0056] Further, based on the dynamic period and the plurality of reference images, a three-dimensional image and a three-dimensional feature of a blood vessel at each relative position in the dynamic period are obtained, such as Figure 2 As shown, comprising:

[0057] The blood pressure of the blood vessel and the reference images are mapped to the same time axis according to the acquisition time, the change period of the value of the blood pressure of the blood vessel is analyzed by a dynamic time warping algorithm, and the change period is taken as the dynamic period of the blood pressure of the blood vessel;

[0058] The plurality of reference images are divided into groups according to the relative positions in the dynamic period according to the acquisition time, wherein the reference images in each group correspond to the same relative position in the dynamic period, and the blood vessel features are extracted from each reference image in the group. The three-dimensional image and the three-dimensional feature of the blood vessel at each relative position in the dynamic period corresponding to each group are obtained by integrating each reference image in each group and the corresponding blood vessel features.

[0059] Specifically, since the coronary artery also contracts and dilates with the contraction and dilation of the heart, in order to improve the operation accuracy of the interventional operation, the dynamic change of the blood vessel needs to be grasped, since the change of the blood vessel blood pressure corresponds to the dynamic change of the blood vessel, by mapping the blood vessel blood pressure and the reference image to the same time axis according to the acquisition time, and connecting the values of the blood vessel blood pressure, the blood pressure value curve can be obtained, and the change period of the blood vessel blood pressure with time is analyzed by the dynamic time warping algorithm, and the change period is taken as the dynamic period of the blood vessel blood pressure, since the dynamic period of the blood vessel blood pressure has synchronism with the dynamic change of the blood vessel, a plurality of the reference images are divided into groups according to the relative position in the corresponding dynamic period according to the acquisition time, and the relative positions of the reference images in each group are the same, wherein the calculation of the relative position includes obtaining the difference between the acquisition time of the corresponding reference image and the start time of the dynamic period, and taking the ratio of the difference to the corresponding dynamic period as the relative position of the reference image, since the reference images at the same relative position in the dynamic period correspond to the same dynamic characteristics of the blood vessel, and since different reference images in the same group correspond to different angles of the blood vessel, by extracting the blood vessel characteristics of each reference image in the group, and integrating the reference images of different angles to obtain the three-dimensional image of the blood vessel, and integrating the multi-angle blood vessel characteristics of the blood vessel in the reference image to obtain the three-dimensional characteristics of the blood vessel, wherein the three-dimensional characteristics include the diameter of the blood vessel, the center line position of the blood vessel and the shape of the blood vessel, by the technical solution, the three-dimensional image and three-dimensional characteristics of the blood vessel at each relative position in the corresponding dynamic period can be accurately obtained, which lays a foundation for accurate training of the first model.

[0060] Further, the training of the first model includes:

[0061] Based on the plurality of dynamic periods included in the preset time period, the three-dimensional image and the corresponding three-dimensional characteristics of the blood vessel at each relative position in each dynamic period, and the three-dimensional image and three-dimensional characteristics interpolation at the position between adjacent relative positions, the three-dimensional image continuous frame and the corresponding three-dimensional characteristics are obtained, and the plurality of dynamic periods and the corresponding three-dimensional image continuous frame and the corresponding three-dimensional characteristics of the blood vessel in each dynamic period are taken as training data to train the first model.

[0062] Specifically, since the three-dimensional image of the blood vessel at each relative position in the dynamic cycle is integrated from the reference image in the two-dimensional image acquired by the image acquisition unit, and since the two-dimensional image is acquired periodically, the three-dimensional image of the blood vessel in the dynamic cycle is discontinuous. In order to provide sufficient training data for the first model, the three-dimensional images of the blood vessel at adjacent relative positions in each dynamic cycle in the preset time period and the corresponding three-dimensional features are interpolated to obtain continuous frames of three-dimensional images of the blood vessel and corresponding three-dimensional features, which are used as training data to train the first model. The dynamic cycle is also input into the first model, and the projection of the acquired three-dimensional dynamic image of the blood vessel at multiple angles is obtained, and the projection is compared with the corresponding training data to determine the accuracy of the first model. When the accuracy of the first model is less than the set accuracy, the first model is retrained by repeating steps S1 and S2. Through the technical solution, a three-dimensional dynamic image prediction model of the blood vessel, i.e. the first model, with high accuracy can be obtained, which provides a basis for accurately obtaining the reference path of the catheter assembly, thereby improving the control accuracy of the interventional surgery and reducing the risk of surgery.

[0063] Further, the reference path is obtained, as shown in Figure 3 , comprising:

[0064] According to the real-time monitoring of the numerical change of the blood pressure of the blood vessel, the real-time dynamic cycle of the blood pressure of the blood vessel is obtained, and the real-time dynamic cycle is input into the first model to obtain a three-dimensional dynamic image of the blood vessel changing with time. Based on the three-dimensional dynamic image, a three-dimensional coordinate system is mapped and the dynamic distribution of the blood vessel in the three-dimensional coordinate system is obtained. According to the dynamic distribution, the overlapping distribution area of each relative position in the real-time dynamic cycle is calculated, and the first size of the overlapping distribution area is calculated. When the first size is greater than the second size of the head of the catheter assembly and the difference between the first size and the second size is greater than or equal to a set value, the center line of the overlapping distribution area is taken as the reference path of the catheter assembly to reach the preset position. Otherwise, the dynamic center line of the blood vessel is obtained from the three-dimensional dynamic image, and the dynamic center line is taken as the reference path of the catheter assembly. Further, the advancing speed of the catheter assembly is adjusted based on the change speed of the dynamic center line.

[0065] Specifically, by monitoring the change of the blood vessel blood pressure in real time, the real-time dynamic cycle is obtained by the method of dynamic cycle in step S2, and the real-time dynamic cycle is input into the first model, and the three-dimensional dynamic image output by the first model is obtained, wherein the three-dimensional dynamic image is labeled with corresponding three-dimensional features, and the three-dimensional dynamic image is mapped into the three-dimensional coordinate system, so as to quantify the dynamic distribution of the blood vessel in the three-dimensional dynamic image, and the overlapping distribution area of each relative position is obtained according to the dynamic distribution of the blood vessel in the real-time dynamic cycle, and the first size of the overlapping distribution area, that is, the cross-sectional size of the corresponding blood vessel, is calculated, and the first size is compared with the second size of the head of the catheter assembly, that is, the external size of the head of the catheter assembly. When the first size is greater than the second size and the difference between them is greater than the set value, at this time, the overlapping distribution area is used as the channel for the catheter assembly head to reach the preset position, which will not cause damage to the blood vessel, such as blood vessel perforation, and the center position of the overlapping distribution area, that is, the center line, is used as the reference path of the catheter assembly head. Otherwise, when the first size is less than or equal to the second size or the difference between them is less than the preset value, that is, the catheter assembly head cannot pass through the overlapping distribution area to reach the preset position, in order to guide the catheter assembly head to reach the preset position without causing damage to the blood vessel, the dynamic center line of the blood vessel is used as the reference path, wherein the preset position is the operation position, that is, the lesion position. Since the dynamic center line, that is, the blood vessel, changes with time, the advancing speed of the catheter assembly head is adjusted to make the motion trajectory of the catheter assembly head fit the dynamic center line as much as possible, wherein the advancing speed includes speed size and direction. Through the technical solution, the reference path of the catheter assembly is obtained, which lays a foundation for further reducing the operation risk of interventional surgery.

[0066] Further, the path error is obtained, comprising:

[0067] The image acquisition unit tracks the real-time image at the position of the head of the catheter assembly in real time, extracts the motion trajectory of the head of the catheter assembly from the real-time image, obtains the maximum distance between the motion trajectory and the reference path in the real-time dynamic cycle, and takes the maximum distance as the path error.

[0068] Specifically, since the head of the catheter assembly is made of a material that cannot be penetrated by X-rays, the position and movement trajectory of the head of the catheter assembly can be identified through the real-time image, the movement trajectory is compared with the reference path, the distance between each position of the movement trajectory and the corresponding reference path in the real-time dynamic cycle is obtained, and the maximum distance in the distance is the maximum distance as the path error, wherein the path error reflects the control accuracy of the catheter assembly and indirectly reflects the operation error during the operation, and through the technical solution, the path error of the head of the catheter assembly can be obtained in real time, which lays a foundation for accurately predicting the intervention operation risk probability through the path error.

[0069] Further, in the step S5, the catheter assembly characteristics include the catheter type, the rigidity of the corresponding guide wire, and the size and material of the catheter and the guide wire.

[0070] Specifically, since the operation intervention risk probability value is the risk probability of successful operation, the path error reflects the operation accuracy of the catheter assembly, and the dynamic image of the blood vessel

[0071] Further, the training of the second model comprises:

[0072] The historical operation data is obtained from the storage unit, the historical operation data includes historical data of a plurality of patients, the historical data includes characteristics of a catheter assembly used in an operation, a plurality of two-dimensional images of a target blood vessel, a planned path of the operation, an actual path of the operation, and an operation result, a three-dimensional dynamic image corresponding to the target blood vessel is obtained based on the plurality of two-dimensional images of the target blood vessel through the steps S1-S3, and a historical path error is obtained through the planned path and the actual path, the path error, the three-dimensional dynamic image of the target blood vessel, the characteristics of the catheter assembly, and the operation result are used as training data to train the second model.

[0073] Specifically, a plurality of sets of training data are extracted from the historical operation data, wherein the path error reflects the control accuracy of the catheter assembly, and the three-dimensional dynamic image of the target blood vessel can reflect the difficulty of the operation at the preset position, i.e., the position of the patient, wherein the three-dimensional features of the target blood vessel are labeled on the three-dimensional dynamic image of the target blood vessel, the target blood vessel is the target position of the intervention operation, and the characteristics of the catheter assembly can reflect the accuracy of the operation, through the technical solution, a precise intervention operation risk probability prediction model can be obtained, thereby facilitating accurate prediction of the intervention operation risk.

[0074] The application also provides a blood vessel intervention real-time monitoring system based on intelligent sensing technology, which is used to realize the above method, such as Figure 4As shown, the system comprises:

[0075] an image acquisition unit, configured to collect a plurality of two-dimensional images of each angle in a target region within a preset time period, and select a reference image from the plurality of two-dimensional images;

[0076] a monitoring unit, located in the catheter assembly, configured to acquire a blood pressure of a blood vessel;

[0077] a calculation unit, configured to map the blood pressure of the blood vessel and the plurality of reference images to a same time coordinate axis according to acquisition time, acquire a dynamic cycle of the blood pressure of the blood vessel, and acquire a three-dimensional image and a three-dimensional feature of the blood vessel at each relative position in the dynamic cycle based on the dynamic cycle and the plurality of reference images;

[0078] a model training unit, configured to train a first model based on the dynamic cycle and the three-dimensional image and the three-dimensional feature of the blood vessel corresponding to each relative position;

[0079] the calculation unit is further configured to acquire a three-dimensional dynamic image of the blood vessel based on a real-time dynamic cycle of the blood pressure of the blood vessel and the first model, acquire a reference path of the catheter assembly to a preset position of the blood vessel based on the three-dimensional dynamic image, acquire a path error based on a motion trail of a head of the catheter assembly and the reference path during a process in which the catheter assembly reaches the preset position, and acquire a three-dimensional image of the preset position of the blood vessel based on the three-dimensional dynamic image.

[0080] a prediction unit, configured to input the path error, a characteristic of the catheter assembly, and the three-dimensional image of the preset position into a second model to acquire an intervention surgery risk probability value, wherein the second model is an intervention surgery risk prediction model.

[0081] The application further provides a computer readable storage medium, wherein the computer readable storage medium stores instructions, and the instructions are executed by a processor to implement the method.

[0082] In summary, the application realizes multi-dimensional data acquisition of the vascular interventional surgery process by collecting two-dimensional images of multiple angles in the target area within a preset time period and obtaining the blood pressure of the blood vessel in combination with the monitoring unit in the catheter. This multi-modal data fusion method makes up for the deficiency of traditional imaging devices that cannot provide real-time feedback of internal subtle changes of the blood vessel, and provides more comprehensive information support for precise navigation of the surgery. Secondly, the method of mapping the blood pressure of the blood vessel and the reference image to the same time coordinate axis can accurately obtain the dynamic cycle of the blood pressure of the blood vessel, and construct a three-dimensional image and three-dimensional features of the blood vessel based on this, not only considering the static structure of the blood vessel, but also focusing on the dynamic changes, so that the surgery path planning is more in line with the actual physiological state of the blood vessel, thereby effectively reducing the risk of damage to the blood vessel wall by the catheter. In addition, through the cooperative work of the first model and the second model, the system can monitor the motion trajectory of the catheter in real time, calculate the path error, and further predict the risk probability value of the interventional surgery. This real-time risk assessment mechanism provides an important decision reference for the surgeon, making the surgery process more controllable. When the risk probability value exceeds the set threshold value, the system can automatically adjust the control accuracy of the catheter, or even retrain the model to optimize the surgery path. Through the mutual cooperation of the above technical solutions, the accuracy and safety of the surgery can be significantly improved, and the risk of the surgery can be reduced.

[0083] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, system and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0084] The integrated unit, if realized in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0085] The above-described embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for real-time monitoring of vascular intervention based on sensor technology, characterized in that, The method includes: Step S1: Within a preset time period, multiple two-dimensional images of various angles within the target area are collected by the image acquisition unit, a reference image is selected from the multiple two-dimensional images, and vascular blood pressure is also acquired by the monitoring unit within the catheter assembly. Step S2: Map the blood pressure of the blood vessels and the multiple reference images onto the same time coordinate axis according to the acquisition time to obtain the dynamic period of the blood pressure of the blood vessels. Based on the dynamic period and the multiple reference images, obtain the three-dimensional image and three-dimensional features of the blood vessels at each relative position within the dynamic period. Train the first model based on the dynamic period and the three-dimensional image and three-dimensional features of the blood vessels at each relative position. Step S3: Train a first model based on the dynamic cycle and the three-dimensional image and features of the blood vessel at each time point. By monitoring the real-time dynamic cycle of the blood vessel blood pressure, obtain a reference path for the catheter assembly to reach the preset position of the blood vessel based on the real-time dynamic cycle and the first model. Step S4: During the process of the catheter assembly reaching the preset position, the path error is obtained based on the movement trajectory of the catheter assembly head and the reference path by real-time monitoring; Step S5: Input the path error, the vascular dynamic image at the preset position, and the characteristics of the catheter assembly into the second model to obtain the interventional surgery risk probability value, wherein the second model is an interventional surgery risk prediction model; The acquisition of the reference path includes: acquiring the real-time dynamic cycle of the blood pressure based on real-time monitoring of the blood vessel blood pressure value, inputting the real-time dynamic cycle into the first model, acquiring a three-dimensional dynamic image of the blood vessel changing over time, mapping the three-dimensional dynamic image to a three-dimensional coordinate system and acquiring the dynamic distribution of the blood vessel in the three-dimensional coordinate system, calculating the overlapping distribution area of ​​each relative position within the real-time dynamic cycle based on the dynamic distribution, and calculating the first size of the overlapping distribution area. When the first size is greater than the second size of the catheter assembly head and the difference between the first size and the second size is greater than or equal to a set value, the center line of the overlapping distribution area is used as the reference path for the catheter assembly to reach the preset position. Otherwise, the dynamic center line of the blood vessel is acquired based on the three-dimensional dynamic image and used as the reference path for the catheter assembly. The forward speed of the catheter assembly is also adjusted based on the rate of change of the center line of the dynamic image. The training of the second model includes: acquiring historical surgical data from a storage unit, the historical surgical data including historical data of multiple patients, the historical data including the characteristics of the catheter assembly used in the surgery, multiple two-dimensional images of the target blood vessel, the planned surgical path, the actual surgical path, and the surgical result; acquiring a three-dimensional dynamic image of the target blood vessel based on the multiple two-dimensional images of the target blood vessel through steps S1-S3; acquiring historical path error through the planned path and the actual path; and using the path error, the three-dimensional dynamic image of the target blood vessel, and the characteristics of the catheter assembly as training data to train the second model.

2. The method according to claim 1, characterized in that, Following step S5, the method further includes: When the interventional surgery risk probability value is greater than or equal to a set threshold, the control precision of the catheter assembly is improved, and steps S3 and S4 are repeated to reacquire the path error. Based on the reacquired path error and step S5, the interventional surgery risk probability value is reacquired, and this step is repeated until the interventional surgery risk probability value is less than the set threshold. If improving the control precision of the catheter assembly fails to ensure that the interventional surgery risk probability value is less than the set threshold, repeat steps S1-S2 to retrain the first model, and repeat steps S3-S5 to re-acquire the interventional surgery risk probability value based on the re-acquired first model.

3. The method according to claim 1, characterized in that, Based on the dynamic period and multiple reference images, obtain three-dimensional images and three-dimensional features of blood vessels at each relative position within the dynamic period, including: The blood pressure and the reference image are mapped onto the same time axis according to the acquisition time. The change period of the blood pressure value over time is analyzed by the dynamic time warp algorithm, and the change period is taken as the dynamic period of the blood pressure. Multiple reference images are divided into groups according to their relative positions in the corresponding dynamic cycle based on the acquisition time. The reference images in each group have the same relative position in the dynamic cycle. Vascular features are extracted from each reference image in each group. Each reference image and its corresponding vascular features in each group are integrated to obtain a 3D image and 3D features of the blood vessels at each relative position in the dynamic cycle corresponding to the group.

4. The method according to claim 1, characterized in that, The training of the first model includes: Based on the multiple dynamic cycles included within the preset time period and the three-dimensional images of blood vessels and their corresponding three-dimensional features at each relative position within each dynamic cycle, and by interpolating the three-dimensional images and features at discontinuous positions of the three-dimensional images of blood vessels between adjacent relative positions, continuous frames of three-dimensional images of blood vessels and their corresponding three-dimensional features are obtained, and the multiple dynamic cycles and the continuous frames of three-dimensional images of blood vessels and their corresponding three-dimensional features corresponding to each dynamic cycle are used as training data to train the first model.

5. The method according to claim 1, characterized in that, The path error includes: The image acquisition unit tracks and acquires real-time images of the location of the catheter assembly head, extracts the motion trajectory of the catheter assembly head from the real-time images, obtains the maximum distance between the motion trajectory and the reference path within the real-time dynamic cycle, and uses the maximum distance as the path error.

6. The method according to claim 1, characterized in that, In step S5, the characteristics of the catheter assembly include the catheter type, the rigidity of the corresponding guidewire, and the size and material of the catheter and guidewire.

7. A real-time monitoring system for vascular intervention based on intelligent sensing technology, characterized in that, Used to implement the method as described in any one of claims 1-6.

8. A computer-readable storage medium storing instructions thereon, characterized in that, When the instructions are executed by the processor, they implement the method as described in any one of claims 1-6.

Images