Hard magnetic driven vascular intervention guidewire robot system and method

Abstract

The application provides a hard magnetic driven vascular intervention guide wire robot system and method, which comprises a hard magnetic flexible guide wire catheter, a flexible catheter is sleeved outside the hard magnetic flexible guide wire, the tip of the hard magnetic flexible guide wire has a hard magnetism, and the extension or retraction action is completed in the catheter; a guide wire catheter driving device, which clamps the hard magnetic flexible guide wire catheter and provides driving force for the forward and backward movement of the hard magnetic flexible guide wire catheter; a seventh degree of freedom magnetic navigation system, which is arranged above the guide wire catheter driving device and comprises a mechanical arm, a servo rotary motor and a cylindrical permanent magnet, the motion direction of the hard magnetic flexible guide wire is controlled by changing the relative position of the cylindrical permanent magnet and the tip of the hard magnetic flexible guide wire; and a visual recognition module, which is arranged between the guide wire catheter driving device and the seventh degree of freedom magnetic navigation system and comprises a support and an industrial camera, the position of the hard magnetic flexible guide wire in the blood vessel is returned through the industrial camera and is used for subsequent path analysis. The application has great application potential in minimally invasive vascular intervention surgery.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vascular intervention treatment, in particular to a hard magnetic driven vascular intervention guide wire robot system and method. BACKGROUND

[0002] At present, the morbidity and mortality of cardiovascular and cerebrovascular diseases are high, which has caused great burden to people's health and the world's medical system. For most cardiovascular and cerebrovascular diseases, vascular intervention surgery (VIS) is an important treatment method, which usually reaches the lesion through the blood vessels by using instruments such as guide wires and catheters with the help of medical imaging equipment. However, the traditional medical guide wire and catheter cannot realize autonomous propulsion and path selection function, but rely on the manual operation of the surgeon in the body. Therefore, VIS has high requirements for the relevant experience and technology of the doctor. On the other hand, the surgery must be performed under X-ray, and the longer the surgery time, the greater the damage to the health of the doctors and patients involved in the surgery.

[0003] In view of the above problems, researchers have begun to consider combining micro robots and their control technology to complete the directional delivery of guide wires, stents or drugs in the human body. However, most of the existing vascular intervention robots use master-slave control, still need the doctor to manually control the catheter or guide wire, and can only realize the simple guide wire and catheter propulsion and rotation action, and cannot realize autonomous steering, and still lack flexibility and controllability at the complex blood vessel bifurcation. In the medical field, especially in the field of in-vivo intervention treatment, the application potential of cordless driven micro robots is very huge, among which, magnetic driving has the characteristics of remote driving, precise control, miniaturization, biocompatibility and multi-modal control, and has become one of the preferred driving methods of medical robots. At present, scholars have developed magnetic driven micro robots that can be applied to intestinal targeted drug delivery, vascular targeted treatment and minimally invasive surgery, and have verified their feasibility.

[0004] The development of a vascular intervention robot system capable of autonomous propulsion and autonomous steering can assist the doctor in remote control, effectively reduce the radiation exposure of the doctor, and eliminate the physiological tremor caused by hand operation and fatigue to improve the accuracy of the operation. SUMMARY

[0005] In view of the defects in the prior art, the purpose of the present application is to provide a hard magnetic driven vascular intervention guide wire robot system and method.

[0006] According to the hard magnetic driven vascular intervention guide wire robot system provided by the present application, the hard magnetic driven vascular intervention guide wire robot system comprises:

[0007] The hard magnetic flexible guide wire catheter is that the flexible catheter is sleeved outside the hard magnetic flexible guide wire, and the tip of the hard magnetic flexible guide wire has a hard magnetic property, and the extension or retraction action is completed in the catheter.

[0008] The guide wire catheter driving device: clamps the hard magnetic flexible guide wire catheter, and provides driving force for the forward and backward movement of the hard magnetic flexible guide wire catheter.

[0009] The seventh degree of freedom magnetic navigation system: arranged above the guide wire catheter driving device, comprising a mechanical arm, a servo rotary motor and a cylindrical permanent magnet, the movement direction of the hard magnetic flexible guide wire is controlled by changing the relative position of the cylindrical permanent magnet and the hard magnetic flexible guide wire tip;

[0010] The visual recognition module: arranged between the guide wire catheter driving device and the seventh degree of freedom magnetic navigation system, comprising a bracket and an industrial camera, the position of the hard magnetic flexible guide wire in the blood vessel is returned through the industrial camera, which is used for subsequent path analysis.

[0011] Preferably, in the hard magnetic flexible guide wire catheter:

[0012] The hard magnetic flexible guide wire is composed of a titanium alloy inner core and a braided structure inside, and is coated with polytetrafluoroethylene material outside; the guide wire tip sheath is filled with axially magnetized neodymium iron boron magnetic particles;

[0013] The flexible catheter is made of thermoplastic resin material and is sleeved outside the hard magnetic flexible guide wire.

[0014] Preferably, in the guide wire catheter driving device:

[0015] The driving module has two groups, respectively clamping the hard magnetic flexible guide wire and the flexible catheter, and driving the forward and backward movement of the hard magnetic flexible guide wire catheter in the blood vessel; each driving module is composed of a pair of friction wheels, a servo motor, a worm gear, a power supply and a controller; the servo motor shaft end is connected with the worm gear meshing with the worm gear, the worm gear is coaxially connected with the driving wheel of the friction wheel, the flexible catheter is clamped between the driving wheel and the driven wheel of the friction wheel, and the flexible catheter is driven to rotate by the servo motor, so as to drive the driving wheel and the friction wheel to rotate, the flexible guide wire is clamped in the wire feeding mechanism, and the flexible guide wire is driven to rotate by the servo motor, so as to drive the driving wheel and the friction wheel to rotate, the code is transmitted through the control panel, and then the forward and backward movement of the hard magnetic flexible guide wire or the flexible catheter is controlled respectively;

[0016] The positioning shell: the two groups of driving modules are embedded in the bottom of the positioning shell, and the controller and the power supply are fixed around the shell body of the positioning shell.

[0017] Preferably, in the seventh degree of freedom magnetic navigation system:

[0018] 6-DOF mechanical arm;

[0019] The servo motor is arranged at the end of the 6-DOF mechanical arm;

[0020] The upper connecting seat is arranged between the 6-DOF mechanical arm and the servo motor;

[0021] The lower connecting seat is arranged at the lower part of the upper connecting seat;

[0022] The special-shaped central shaft is arranged in the central hole of the lower connecting seat;

[0023] The top cover is arranged outside the special-shaped central shaft;

[0024] The connecting disc is arranged at the end of the special-shaped central shaft;

[0025] The cylindrical box is arranged below the connecting disc;

[0026] The cylindrical permanent magnet is arranged inside the cylindrical box.

[0027] Preferably, in the visual identification module:

[0028] The base is included;

[0029] The lower stand is arranged on the base;

[0030] The upper stand is arranged on the lower stand;

[0031] The positioning clamp is arranged outside the upper stand or the lower stand;

[0032] The industrial camera is arranged in the positioning clamp.

[0033] According to the hard magnetic drive vascular intervention guide wire robot method provided by the application, the hard magnetic drive vascular intervention guide wire robot system is adopted, and the method comprises the following steps:

[0034] Step S1: color mark the guide wire tip, and acquire a required original two-dimensional image for vascular intervention;

[0035] Step S2: convert the collected original image into an HSV color space, generate a binary mask of the image, extract a target color area contour, and extract the center coordinates of the minimum circumscribed rectangle;

[0036] Step S3: perform pose prediction on the occluded guide wire tip based on a convolutional neural network, and perform model construction;

[0037] Step S4: collect pictures containing characteristics of the hard magnetic flexible guide wire tip, and train according to the model.

[0038] Preferably, in the step S2:

[0039] The collected original image is converted from BGR color space to HSV color space, and specific HSV threshold values are set to separate different color ranges; the color mark set at the guidewire tip is taken as the target, and a binary mask of the image is generated according to the set domain value, wherein the white part of the mask represents the pixels meeting the condition, and the black part represents the pixels not meeting the condition; the mask is expanded into the same shape as the original image, and is applied to the original image channel by channel to extract the target color region contour, and the contour is fitted with a minimum bounding rectangle to extract the center coordinates of the minimum bounding rectangle.

[0040] Preferably, in the step S3:

[0041] Based on the convolutional neural network, the position of the occluded guidewire tip is predicted, and the model is constructed: including multiple convolutional layers, maximum pooling layers, activation layers and fully connected layers; the image features are extracted through the convolutional layers, the ReLU activation function is used for nonlinear transformation of the convolutional layer output, the maximum pooling layer is used to reduce the data dimension, the batch normalization is used for the picture data, the flattened layer is connected to the fully connected layer, the high-level feature map is mapped to the output space, and the final result is generated through the output layer.

[0042] Preferably, in the step S4:

[0043] Model training is performed: collect pictures containing hard magnetic flexible guidewire tip features, normalize and enhance the data to obtain a learning data set, identify the tip position of each picture to obtain the tip center coordinates as feature labels; extract 30% of the pictures in the data set, perform local color occlusion on the guidewire tip, and train the position recognition ability under the occlusion condition; divide the data set into a training set and a validation set, use the mean square error as the loss function, optimize the model parameters through the Adam optimizer, and the MSE loss function calculation formula is as follows:

[0044]

[0045] Wherein, y i is the actual coordinate, is the predicted coordinate, and N is the sample number.

[0046] Compared with the prior art, the present application has the following beneficial effects:

[0047] 1. The hard magnetic driving method without a rope is used to realize the directional movement of the guidewire catheter in the blood vessel, solve the problem that the movement direction of the traditional guidewire catheter in the blood vessel is difficult to control, and realize the feedback closed-loop automatic control.

[0048] 2. The manufacturing process is simple and easy to operate, and has great application potential in minimally invasive vascular interventional surgery. BRIEF DESCRIPTION OF DRAWINGS

[0049] Other features, objects, and advantages of the application will become more apparent from the following detailed description of non-limiting embodiments thereof, when read in conjunction with the accompanying drawings:

[0050] Figure 1 A top view of a hard magnetic driven vascular interventional guide wire robot system model in the present application;

[0051] Figure 2 A three-dimensional view of a hard magnetic driven vascular interventional guide wire robot system model in the present application;

[0052] Figure 3 A structural schematic diagram of a magnetic navigation device in the system of the present application;

[0053] Wherein: 1 is a medical catheter; 2 is a medical guide wire; 3 is a catheter feeding motor; 4 is a driving wheel; 5 is a driven wheel; 6 is a guide wire wheel; 7 is a wire limiting mechanism; 8 is a guide wire and catheter feeding mechanism control board; 9 is a driving assembly shell; 10 is a worm gear; 11 is a guide wire feeding motor; 12 is a camera fixing device; 13 is a base; 14 is an industrial camera; 15 is a blood vessel model; 16 is a magnetic navigation driving motor; 17 is a flange device; 18 is a mechanical arm; 19 is a cable; 20 is a cylindrical permanent magnet; 21 is an upper connecting seat; 22 is a lower connecting seat; 23 is a special-shaped central shaft; 24 is a top cover; 25 is a connecting disc; 26 is a lower stand column; 27 is an upper stand column; 28 is a positioning clamp; 29 is a cylindrical box. DETAILED DESCRIPTION

[0054] The present application will be described in detail below with specific embodiments. The following examples will help those skilled in the art to further understand the present application, but do not limit the present application in any form. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of changes and improvements can be made. These all belong to the protection scope of the present application.

[0055] Example 1:

[0056] The application provides a hard magnetic driven vascular intervention guide wire robot system, which comprises a hard magnetic flexible guide wire catheter for establishing a vascular access in a vascular intervention operation, two groups of guide wire catheter driving mechanisms for driving the guide wire catheter to move, a magnetic navigation mechanism for guiding the moving direction of the guide wire catheter, a vascular model for simulating a vascular environment, and a visual perception module for image recognition and feedback. The intervention catheter is sleeved outside the hard magnetic flexible guide wire, the guide wire is first pushed forward by the guide wire catheter driving mechanism, and the visual perception module returns a camera shooting picture in real time, the magnetic navigation is controlled to the corresponding position and posture according to the preset path and the actual position of the guide wire, so that the guide wire enters a specified vascular bend or branch, if the guide wire is detected to enter an incorrect section during the process, the system movement is stopped immediately, the guide wire is withdrawn and the movement path is corrected until the guide wire reaches the specified end position.

[0057] A hard magnetic driven vascular intervention guide wire robot method, which comprises the following steps:

[0058] Step S1: color marking is performed on a guide wire tip, and an original two-dimensional image required for vascular intervention is acquired;

[0059] Step S2: the collected original image is converted into an HSV color space, a binary mask of the image is generated, a target color region contour is extracted, and the center coordinates of a minimum circumscribed rectangle are extracted;

[0060] Specifically, in the step S2:

[0061] The collected original image is converted from a BGR color space into an HSV color space, specific HSV threshold values are set to separate different color ranges, the color mark of the guide wire tip is taken as a target, a binary mask of the image is generated according to the set domain values, the white part in the mask represents a pixel meeting the condition, and the black part represents a pixel not meeting the condition, the mask is expanded into the same shape as the original image, is applied to the original image channel by channel, the target color region contour is extracted, the contour is fitted with a minimum circumscribed rectangle, and the center coordinates of the minimum circumscribed rectangle are extracted.

[0062] Step S3: pose prediction is performed on the occluded guide wire tip based on a convolutional neural network, and a model is constructed;

[0063] Specifically, in the step S3:

[0064] Pose prediction is performed on the occluded guide wire tip based on a convolutional neural network, and the model construction comprises a plurality of convolutional layers, a maximum pooling layer, an activation layer and a fully connected layer; the image features are extracted through the convolutional layers, the ReLU activation function is used to perform nonlinear transformation on the convolutional layer output, the data dimension is reduced through the maximum pooling layer, the picture data is batch normalized, the flattened layer is connected to the fully connected layer, the high-level feature map is mapped to the output space, and the final result is generated through the output layer.

[0065] Step S4: Collecting pictures containing hard magnetic flexible guide wire tip features, training according to the model.

[0066] Specifically, in the step S4:

[0067] Model training: collect pictures containing hard magnetic flexible guide wire tip features, normalize and data enhance them to obtain a learning data set, identify the tip position of each picture to obtain its tip center coordinates as a feature label; extract 30% of the pictures in the data set, locally color the guide wire tip, and train the position recognition ability under the shielding condition; divide the data set into a training set and a validation set, use mean square error as the loss function, optimize the model parameters through the Adam optimizer, and the MSE loss function calculation formula is as follows:

[0068]

[0069] Wherein, y i is the actual coordinate, is the predicted coordinate, and N is the sample number.

[0070] Example 2:

[0071] Example 2 is a preferred example of Example 1, which more specifically illustrates the present application.

[0072] The present application also provides a hard magnetic driven vascular interventional guide wire robot system, which can be realized by executing the flow steps of the hard magnetic driven vascular interventional guide wire robot method, that is, the hard magnetic driven vascular interventional guide wire robot method can be understood by those skilled in the art as a preferred embodiment of the hard magnetic driven vascular interventional guide wire robot system.

[0073] According to the hard magnetic driven vascular interventional guide wire robot system provided by the present application, as shown in Figure 3 , comprising:

[0074] Hard magnetic flexible guide wire catheter: flexible catheter 1 is sleeved on the outside of hard magnetic flexible guide wire 2, the tip of hard magnetic flexible guide wire 2 has hard magnetism, and the extension or retraction action is completed in the catheter;

[0075] Preferably, in the hard magnetic flexible guide wire catheter:

[0076] The inside of hard magnetic flexible guide wire 2 is composed of titanium alloy inner core and braided structure, and the outside is coated with polytetrafluoroethylene material; the guide wire tip sheath is filled with axially magnetized neodymium iron boron magnetic particles;

[0077] Flexible catheter 1 is made of thermoplastic resin material and is sleeved on the outside of hard magnetic flexible guide wire.

[0078] The guide wire catheter driving device 9: clamps the hard magnetic flexible guide wire catheter, and provides driving force for the forward and backward movement of the hard magnetic flexible guide wire catheter;

[0079] Preferably, in the guide wire catheter driving device 9:

[0080] There are two groups of driving modules, respectively clamping the hard magnetic flexible guide wire 2 and the flexible catheter 1, and driving the forward and backward movement of the hard magnetic flexible guide wire catheter in the blood vessel; each driving module is composed of a pair of friction wheels, a servo motor 3, a worm and gear 10, a power supply and a controller 8; the servo motor 3 is connected at the end of the shaft with the worm, the worm is coaxially connected with the driving wheel of the friction wheel, the flexible catheter 1 is clamped between the driving wheel 4 and the driven wheel 5 of the friction wheel, the worm and gear 10 is driven to rotate by the servo motor, thereby driving the driving wheel 4 and the friction wheel 5 to rotate, the flexible guide wire 2 is clamped in the wire feeding mechanism 6, the worm and gear 10 is driven to rotate by the servo motor, thereby driving the driving wheel 4 and the friction wheel 5 to rotate, and the code is transmitted through the control board to control the forward and backward movement of the hard magnetic flexible guide wire 2 or the flexible catheter 1 respectively;

[0081] The positioning shell 9: the two groups of driving modules are embedded in the bottom of the positioning shell, and the controller and the power supply are fixed around the shell body of the positioning shell 9.

[0082] The seventh degree of freedom magnetic navigation system 17: arranged above the guide wire catheter driving device 9, including a mechanical arm 18, a servo rotary motor 16 and a cylindrical permanent magnet 20, by changing the relative position of the cylindrical permanent magnet 20 and the tip of the hard magnetic flexible guide wire 2, the movement direction of the hard magnetic flexible guide wire 2 is controlled;

[0083] Preferably, in the seventh degree of freedom magnetic navigation system 17:

[0084] 6 degree of freedom mechanical arm 18;

[0085] The servo motor 16 is arranged at the end of the 6 degree of freedom mechanical arm 18;

[0086] The cable 19 is arranged at the end of the servo motor 16;

[0087] The upper connecting seat 21 is arranged between the 6 degree of freedom mechanical arm 18 and the servo motor 16;

[0088] The lower connecting seat 22 is arranged at the lower part of the upper connecting seat 21;

[0089] The special-shaped central shaft 23 is arranged in the central hole of the lower connecting seat 22;

[0090] The top cover 24 is arranged outside the special-shaped central shaft 23;

[0091] The connecting disc 25 is arranged at the end of the special-shaped central shaft 23;

[0092] A cylindrical box 29 is arranged below the connecting plate 25.

[0093] A cylindrical permanent magnet 20 is arranged inside the cylindrical box 29.

[0094] A visual recognition module: arranged between the guide wire catheter driving device 9 and the seventh degree of freedom magnetic navigation system 17, including a bracket 12 and an industrial camera 14, returning the position of the hard magnetic flexible guide wire 2 in the blood vessel through the industrial camera, for subsequent path analysis.

[0095] Preferably, in the visual recognition module:

[0096] It includes: a base 13;

[0097] A lower stand 26 is arranged on the base 13;

[0098] An upper stand 27 is arranged on the lower stand 26;

[0099] A positioning clamp 28 is arranged outside the upper stand 27 or the lower stand 26;

[0100] The industrial camera 14 is arranged in the positioning clamp 28.

[0101] Embodiment 3:

[0102] Embodiment 3 is a preferred example of embodiment 1, to more specifically illustrate the present application.

[0103] The present application provides a hard magnetic driven vascular interventional guide wire robot system. The system controls the travel direction of the hard magnetic guide wire through a permanent magnet, observes and checks whether the guide wire is located in the expected path in real time and adjusts its attitude, realizes the automatic control of the guide wire catheter, and realizes the controllable movement of the guide wire catheter in the blood vessel. Based on the visual recognition result, the mechanical arm and the guide wire robot are cooperatively controlled to complete the closed-loop control of the system.

[0104] The hard magnetic driven vascular interventional guide wire robot system includes: a guide wire catheter driving device; a hard magnetic flexible guide wire catheter clamped in the guide wire catheter driving device; a seventh degree of freedom magnetic navigation system arranged above the guide wire catheter driving device; a visual recognition module arranged between the guide wire catheter driving device and the seventh degree of freedom magnetic navigation system; and a blood vessel model connected with the guide wire catheter driving device.

[0105] As Figure 1 And Figure 2As shown, the advancing system of the vascular interventional instrument in the present example includes a medical catheter 1, a guide wire 2, a catheter feeding motor 3, a driving wheel 4, a driven wheel 5, a guide wire wheel 6, a wire limiting mechanism 7, a guide wire and catheter feeding mechanism control board 8, a housing 9, a worm gear 10, and a guide wire feeding motor 11. The driving wheel 4 and the driven wheel 5 are clamped on both sides of the medical catheter 1, and the driving wheel 4 is connected to the worm gear 10. The worm gear 10 drives the driving wheel to rotate to advance or retreat the medical catheter 1. The advancement and retreat of the medical guide wire 2 are completed by the guide wire wheel 6 and the guide wire feeding motor 11. The driving assembly includes the catheter feeding motor 3, the guide wire and catheter feeding mechanism control board 8, and the guide wire feeding motor 11. The control board 8 can control the medical catheter 1 and the guide wire 2 to move linearly. The vascular model assembly includes a vascular model 15.

[0106] The motion strategy applied by the hard magnetic driven vascular interventional guide wire robot system provided by the present example is as follows: first, the intrinsic parameters of the camera 14 are calibrated, and the extrinsic parameters of the camera and the mechanical arm coordinate system are calibrated to obtain the conversion relationship between the camera coordinate system and the mechanical arm coordinate system. Subsequently, the position of the guide wire tip and the node position in the path are identified by the camera. In the process of maintaining uniform advancement of the guide wire 2, when the camera identifies that the guide wire approaches the turning node in the path, the mechanical arm is controlled to guide the direction of the guide wire tip, so that the guide wire advances according to the correct path specified in advance. After the guide wire passes through the node, the position of the guide wire tip is identified by the camera, and it can be judged whether the guide wire is advancing on the correct path. If it is found that the guide wire is not on the correct path, the guide wire is controlled to retreat to the front of the last node, and the node is passed through again.

[0107] Specifically, the present application provides a method for visual recognition and separation of vascular path, comprising: introducing the predictor module and model registry of SAM (Segment Anything with Memory): the SAM predictor module provides classes and functions for loading, configuring and using SAM models, and in the model registry, users can find and load corresponding pre-trained models according to specified model types or names; determining the target marker point, calling the predict method to predict the input image: using the loaded model to segment or other related tasks on the input image to obtain the required output result; the model selection obtains the mask with the highest score in the prediction result and its corresponding score and visualizes it. In order to realize accurate control, a path with a width of only one or a few pixels is provided for the system, and a skeletonization function skeletonize is introduced. The function can reduce the pixels of each object (such as blood vessels, text or other connected regions) in the original binary image to the center line by gradually refining the image, while maintaining the topological structure of the object. The final "skeleton" is a single-pixel-wide line network.

[0108] Specifically, the application also provides a method for visually identifying and predicting the position of a hard-magnetic flexible guide wire tip in a blood vessel, comprising: color marking the guide wire tip, obtaining an original two-dimensional image required for blood vessel intervention; converting the collected original image from a BGR color space to an HSV color space, extracting a target color region contour, fitting a minimum circumscribed rectangle to the contour, and extracting the center coordinates of the minimum circumscribed rectangle; establishing a machine learning model based on a convolutional neural network for pose prediction of the occluded guide wire tip, and performing model training, including: normalizing and data enhancing the pictures containing the features of the hard-magnetic flexible guide wire tip, and identifying the position of the tip to obtain the center coordinates of the tip as a feature label; training the position recognition ability under the occlusion condition; dividing the data set into a training set (85%) and a validation set (15%), using a mean squared error (MSE) as a loss function, and optimizing the model parameters through an Adam optimizer.

[0109] Specifically, the application also provides a hard-magnetic flexible guide wire motion strategy based on nodes, including: the nodes are large curvature turns in the blood vessel, and the specific curvature threshold is determined according to the extracted blood vessel path quality. For each effective node, the actions required to be completed by each device are consistent, and a large loop is entered to traverse each effective node. In each loop, the system records the positions of the current effective node, the previous node and the next node. The vector formed from the current node to the guide wire tip position is A, the vector formed from the current node to the next node is B, and the vector formed from the current node to the previous node is C. These vectors can be used to determine whether the guide wire has reached the target node and whether it has entered the wrong path. After confirming the target position of the mechanical arm and the target deflection angle of the permanent magnet, the mechanical arm and the permanent magnet start moving towards the target position, and the guide wire starts advancing at the same time. In this process, the camera continuously acquires a photo stream, and when the length of vector A is less than the minimum reaching distance (flexibly set according to requirements, generally 1mm), it is considered that the guide wire has reached the target node. At this time, it is judged whether the mechanical arm has reached the target position, if not, the guide wire waits in place until the mechanical arm reaches the corresponding position. After the mechanical arm reaches the position, the guide wire continues to advance, and the camera continues to acquire a photo stream. When the length of vector A is greater than the minimum judgment distance (flexibly set according to requirements, generally 2mm), if the angle between vector A and vector B is less than the error allowed range (flexibly set according to requirements, generally 15°), it is considered that the guide wire has entered the correct path, otherwise it is considered that the guide wire has entered the wrong path, at which time the guide wire needs to be withdrawn until the length of vector A is less than the minimum reaching distance. After the computer analyzes the positional relationship between the wrong path and the correct path, the permanent magnet is deflected by one rotation unit (generally 1°) in the direction of the original wrong path, and the guide wire is controlled to advance again until the guide wire enters the correct path, completing a cycle. Until the guide wire reaches the end point, the program ends.

[0110] Those skilled in the art understand that, in addition to implementing the system provided by the present application and each device, module and unit thereof in the form of pure computer readable program code, the system provided by the present application and each device, module and unit thereof can also be implemented in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers and embedded microcontrollers, etc. by logically programming the method steps to achieve the same functions. Therefore, the system provided by the present application and each device, module and unit thereof can be considered as a hardware component, and the devices, modules and units included therein for implementing various functions can also be considered as structures within the hardware component; the devices, modules and units for implementing various functions can also be considered as both software modules implementing methods and structures within hardware components.

[0111] The specific embodiments of the present application are described above. It needs to be understood that the present application is not limited to the specific embodiments described above, and various changes or modifications can be made by those skilled in the art within the scope of the claims, which does not affect the essential content of the present application. The embodiments of the present application and the features in the embodiments can be combined with each other in any manner without conflict.

Claims

1. A hard-magnetic driven vascular intervention guidewire robot method, characterized by, The execution comprises: Step S1: color mark the guidewire tip, and acquire an original two-dimensional image required for blood vessel intervention; Step S2: convert the collected original image into an HSV color space, generate a binary mask of the image, extract the contour of the target color region, and extract the center coordinates of the minimum circumscribed rectangle; Step S3: perform pose prediction on the occluded guidewire tip based on a convolutional neural network, and perform model construction; Step S4: collect pictures containing characteristics of the hard-magnetic flexible guidewire tip, and perform training according to the model; In the step S2: The collected original image is converted from a BGR color space into an HSV color space, and specific HSV threshold values are set to separate different color ranges; the color mark of the guidewire tip is taken as a target, and a binary mask of the image is generated according to the set domain values; the white part of the mask represents pixels meeting the conditions, and the black part represents pixels not meeting the conditions; the mask is expanded into the same shape as the original image, and is applied to the original image channel by channel to extract the contour of the target color region; the contour is fitted with a minimum circumscribed rectangle, and the center coordinates of the minimum circumscribed rectangle are extracted; In the step S3: The pose of the occluded guidewire tip is predicted based on a convolutional neural network, and the model is constructed: comprising multiple convolutional layers, maximum pooling layers, activation layers, and fully connected layers; image features are extracted through the convolutional layers, the convolutional layer outputs are nonlinearly transformed using a ReLU activation function, the data dimension is reduced through the maximum pooling layers, the picture data is batch normalized, the flattened layer is connected to the fully connected layer to map high-level feature maps to an output space, and the final result is generated through the output layer; In the step S4: The model is trained: pictures containing characteristics of the hard-magnetic flexible guidewire tip are collected, normalized, and data-augmented to obtain a learning data set; the center coordinates of the tip of each picture are identified to obtain the tip center coordinates as feature labels; 30% of the pictures in the data set are extracted, the guidewire tip is locally color-occluded, and the position recognition ability under the occlusion condition is trained; the data set is divided into a training set and a validation set, the mean square error is used as a loss function, the model parameters are optimized through an Adam optimizer, and the MSE loss function calculation formula is as follows: wherein, is the actual coordinate, is the predicted coordinate, N is the number of samples.

2. A system for implementing the hard-magnetic driven vascular intervention guidewire robot method of claim 1, characterized in that, It comprises: A hard-magnetic flexible guidewire catheter: a flexible catheter (1) is sleeved outside a hard-magnetic flexible guidewire (2), and the tip of the hard-magnetic flexible guidewire (2) has a hard magnetism to complete the extension or retraction action in the catheter; A guidewire catheter driving device: clamping the hard-magnetic flexible guidewire catheter, providing driving force for the forward and backward movement of the hard-magnetic flexible guidewire catheter; A seventh-degree-of-freedom magnetic navigation system (17): arranged above the guidewire catheter driving device, comprising a mechanical arm (18), a servo rotary motor (16), and a cylindrical permanent magnet (20); by changing the relative position of the cylindrical permanent magnet (20) and the tip of the hard-magnetic flexible guidewire (2), the movement direction of the hard-magnetic flexible guidewire (2) is controlled. Visual recognition module: set between the guide wire catheter driving device and the seventh degree of freedom magnetic navigation system (17), including support (12) and industrial camera (14), returning the position of hard magnetic flexible guide wire (2) in blood vessels through industrial camera for subsequent path analysis.

3. The hard-magnetic driven vascular intervention guidewire robot system of claim 2, wherein, In the hard magnetic flexible guide wire catheter: The inside of the hard magnetic flexible guide wire (2) is composed of titanium alloy inner core and braided structure, and the outside is coated with polytetrafluoroethylene material; the guide wire tip sheath is filled with axially magnetized neodymium iron boron magnetic particles; The flexible catheter (1) is made of thermoplastic resin material, which is sleeved outside the hard magnetic flexible guide wire.

4. The hard-magnetic drive vascular intervention guidewire robot system of claim 2, wherein, In the guide wire catheter driving device: There are two groups of driving modules, which respectively clamp the hard magnetic flexible guide wire (2) and the flexible catheter (1), and drive the forward and backward movement of the hard magnetic flexible guide wire catheter in the blood vessels; each driving module is composed of a pair of friction wheels, a servo motor (3), a worm and gear (10), a power supply and a controller (8); the shaft end of the servo motor (3) is connected with the worm, the worm is coaxially connected with the driving wheel of the friction wheel, the flexible catheter (1) is clamped between the driving wheel (4) and the driven wheel (5) of the friction wheel, and the worm and gear (10) is driven to rotate by the servo motor, so as to drive the driving wheel (4) and the friction wheel to rotate, the flexible guide wire (2) is clamped in the guide wire feeding mechanism (6), the worm and gear (10) is driven to rotate by the servo motor, so as to drive the driving wheel (4) and the friction wheel to rotate, the code is transmitted through the control panel, and then the forward and backward movement of the hard magnetic flexible guide wire (2) or the flexible catheter (1) is controlled respectively; Driving assembly shell (9): two groups of driving modules are embedded in the bottom of the positioning shell, and the controller and the power supply are fixed around the shell of the driving assembly shell (9).

5. The hard-magnetic drive vascular intervention guidewire robot system of claim 2, wherein, In the seventh degree of freedom magnetic navigation system (17): 6 degree of freedom mechanical arm (18); Servo rotary motor (16) is arranged at the end of the 6 degree of freedom mechanical arm (18); Upper connecting seat (21) is arranged between the 6 degree of freedom mechanical arm (18) and the servo rotary motor (16); Lower connecting seat (22) is arranged at the lower part of the upper connecting seat (21); Special-shaped middle shaft (23) is arranged in the central hole of the lower connecting seat (22); Top cover (24) is arranged outside the special-shaped middle shaft (23); Connecting disc (25) is arranged at the end of the special-shaped middle shaft (23); Cylindrical box (29) is arranged below the connecting disc (25); Cylindrical permanent magnet (20) is arranged inside the cylindrical box (29).

6. The hard-magnetic drive vascular intervention guidewire robot system of claim 2, wherein, In the visual recognition module: It includes: base (13); Lower stand column (26) is arranged on the base (13); Upper stand column (27) is arranged on the lower stand column (26); Positioning clamp (28) is arranged outside the upper stand column (27) or the lower stand column (26); Industrial camera (14) is arranged in the positioning clamp (28).

Images