KR102296478B1 - Apparatus and Method to control guide wire delivering device - Google Patents

Abstract

In the method for controlling a guide wire moving device performed by a processor, the control method includes: determining a target patch area based on a tip position of the guide wire in an image; A blood vessel structure similar to the target patch area from a database about blood vessel data Searching for similar blood vessel data having may include the step of controlling

Description

Apparatus and Method to control guide wire delivering device}

Hereinafter, a technique for a method of controlling a guidewire moving device based on a database in which blood vessel data is stored is provided.

When treating cardiovascular, cerebrovascular, and peripheral blood vessels, an interventional procedure that inserts a stent using a catheter is widespread. A guide wire is a tool for setting a route for transporting a stent, etc. into a blood vessel through a catheter. In order to transport the guide wire to the end of a diseased blood vessel, visual information based on medical images such as angiography and fine hand Tactile information based on the senses of

Recently, remote robots have been developed to reduce the operator's physical burden, such as radiation exposure, and to precisely control surgical tools. Although the surgical robot has passed the FDA and is being commercialized, it is necessary to learn to adapt to a new tool in order to perform a simple procedure. Even if you do not directly perform the corresponding motion, such as moving the guide wire backwards or rotating it at a certain angle, a function that the robot takes over is being added, but the proportion of the operation is small.

Korean Patent Publication No. 10-20170049172 (published on May 10, 2017)

In the guide wire moving device control method performed by a processor according to an embodiment, determining a target patch area based on the tip position of the guide wire in an image, similar to the target patch area from a database about blood vessel data Searching for similar blood vessel data having a blood vessel structure, determining a control command of the guide wire moving device based on control command related data mapped to the searched similar blood vessel data, and the guide wire according to the determined control command controlling the mobile device.

In addition, the guide wire moving device control method includes the steps of determining whether the tip of the guide wire has reached the target point of the target patch area, and if it is determined that the tip of the guide wire has reached the target point, the image and determining the next patch area based on the tip position of the guidewire.

According to one side, the method further includes extracting a plurality of patch regions along a blood vessel path from the image, and determining the target patch region includes a patch region including a tip of the guide wire among the plurality of patch regions. and determining as the target patch area.

When it is determined that the tip of the guide wire has reached the target point of the target patch area, one of the patch areas other than the target patch area among a plurality of patch areas including the tip of the guide wire is determined as the next patch area It may include further steps.

The step of searching for the similar blood vessel data of the control method according to the embodiment may include at least one of a blood vessel diameter of the target patch region, a vessel direction, the number of branching vessels, a branching angle, a shape of a blood vessel stenosis, and a component of a vascular stenosis. and searching for the similar blood vessel data based on the .

The searching for the similar blood vessel data may include inputting a similarity determination model using at least one of a blood vessel diameter, a blood vessel direction, the number of branch blood vessels, a branch angle, a shape of a blood vessel stenosis, and a component of a blood vessel stenosis of the target patch region. generating data, outputting a degree of similarity to the target patch region for blood vessel data in the database by inputting the generated input data to the similarity determining model, and collecting blood vessel data having the highest similarity among the database It may include extracting the similar blood vessel data.

The searching for the similar vascular data may include a plurality of vascular stenosis in the database based on at least one of a vascular diameter of the target patch region, a vascular direction, the number of branching vessels, a branching angle, a type of vascular stenosis, and a component of vascular stenosis. The method may include sequentially comparing each of the vascular data with the target patch region, and as a result of the comparison, extracting vascular data having the highest similarity as the similar vascular data.

Determining the control command according to an embodiment may include determining a control command of the guidewire moving device based on a deep learning weight and a neural network model stored for the similar blood vessel data.

The determining of the control command may include setting a deep learning weight stored for the similar blood vessel data as a weight of a command determination neural network model, patch region image information of the target patch region, tip position of the guidewire, and the target. The method may include setting data about at least one of the points as an input value, and outputting a control command by inputting the input value into the command-determining neural network model to which the weight is applied.

Determining whether the tip of the guide wire has reached the target point of the target patch area, if it is determined that the tip of the guide wire does not reach the target point of the target patch area, tracking the tip position of the guide wire and determining a control command of the guidewire moving device based on the tracked tip position of the guidewire.

Also, the determining of the control command may include determining a control command of the guidewire moving device based on a series of control commands mapped to the similar blood vessel data.

In addition, the step of determining whether the tip of the guide wire has reached the target point of the target patch area, when it is determined that the tip of the guide wire does not reach the target point of the target patch area, the position of the guide wire tracking, if the guidewire tip is not included in the target patch area, providing a return command to the guidewire moving device until the tip of the guidewire is included in the target patch area .

The control command according to an embodiment may include a command to move the guide wire forward or backward, or to rotate the guide wire in a direction and an angle determined based on the control command related data.

1 is a flowchart illustrating a method for controlling a guide wire moving device according to an embodiment.
2 is a diagram illustrating determination of a target patch area by extracting a plurality of patch areas according to an exemplary embodiment.
3 is a diagram illustrating determining a target patch area based on a tip position of a guide wire according to an embodiment.
FIG. 4 is a flowchart illustrating control of a guide wire moving device by extracting similar blood vessel data having a blood vessel structure similar to that of a target patch region, and determining a control command, according to an exemplary embodiment.
5 is a flowchart illustrating a method for controlling a guidewire moving device after determining whether a guidewire tip has reached a target point in a target patch area according to an embodiment.
6 is a diagram illustrating determining a next patch area according to an exemplary embodiment.
7 is a block diagram schematically illustrating the configuration of a device for controlling a guide wire moving device according to an embodiment.

Specific structural or functional descriptions of the embodiments are disclosed for purposes of illustration only, and may be changed and implemented in various forms. Accordingly, the embodiments are not limited to a specific disclosure form, and the scope of the present specification includes changes, equivalents, or substitutes included in the technical spirit.

Although terms such as first or second may be used to describe various components, these terms should be interpreted only for the purpose of distinguishing one component from another. For example, a first component may be termed a second component, and similarly, a second component may also be termed a first component.

When a component is referred to as being “connected to” another component, it may be directly connected or connected to the other component, but it should be understood that another component may exist in between.

The singular expression includes the plural expression unless the context clearly dictates otherwise. In this specification, terms such as "comprise" or "have" are intended to designate that the described feature, number, step, operation, component, part, or combination thereof exists, and includes one or more other features or numbers, It should be understood that the possibility of the presence or addition of steps, operations, components, parts or combinations thereof is not precluded in advance.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art. Terms such as those defined in a commonly used dictionary should be interpreted as having a meaning consistent with the meaning in the context of the related art, and should not be interpreted in an ideal or excessively formal meaning unless explicitly defined in the present specification. does not Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. Like reference numerals in each figure indicate like elements.

The guidewire may be formed of a steel wire inserted into the lumen of the angiographic catheter or the cardiac catheter to lead it to a target blood vessel. The guide wire is inserted into the radial or femoral artery of the recipient prior to insertion of the stent in order to move the stent to a target intravascular location, and may be moved to the end of the cardiovascular system to be exemplarily located. The tip of the guide wire is the distal end of the guide wire, and may be a portion divided by the boundary between the blood vessel passage and the guide wire in the blood vessel image. The guide wire moving device may be a device for moving the guide wire by remotely controlling the operator to reduce the operator's physical burden, such as radiation exposure, and for precise control of the surgical tool.

1 is a flowchart illustrating a method for controlling a guide wire moving device according to an embodiment.

In step 110, the processor for controlling the guide wire moving device may determine the target patch area based on the position of the tip of the guide wire in the image. The processor may determine the target patch area based on the blood vessel including the tip of the guide wire in the image. Illustratively, the processor may determine a rectangular area centered on the tip of the guide wire and having a blood vessel including the guide wire as an axis as the target patch area.

According to an embodiment, the processor may extract a plurality of patch regions along a blood vessel path from the image, and may determine a patch region including the tip of the guide wire among the plurality of patch regions as the target patch region. An embodiment in which a target patch area is determined by extracting a plurality of patch areas will be described in detail later with reference to FIG. 2 .

According to another embodiment, the processor determines whether the tip of the guide wire has reached the target point of the target patch area, and when it is determined that the tip of the guide wire has reached the target point, the tip position of the guide wire in the image Based on this, the next patch area may be determined. An embodiment of determining the next patch area after determining whether the target point is reached will be described in detail later with reference to FIG. 3 .

In operation 120 , the processor for controlling the guidewire moving device may search for similar blood vessel data having a blood vessel structure similar to that of the target patch region from a database about blood vessel data. The database according to an embodiment may be included in a device for controlling the guide wire moving device, but is not limited thereto, and may be included in an external device. When the database is included in the external device, the control device may communicate with the external device to receive the blood vessel data of the database.

The similar vascular data may be information stored with an image of a vascular structure having the highest similarity to the vascular structure of the target patch region, and the vascular structure image may be an image of an image taken during a previous vascular intervention. An embodiment of searching for similar blood vessel data will be described in detail later with reference to FIG. 4 .

In operation 130, the processor may determine a control command of the guidewire moving device based on the control command related data mapped to the searched similar blood vessel data. The control command related data may include deep learning weights stored for blood vessel data to determine the control command, and the deep learning weights may be weights applied to the command decision neural network model. According to another embodiment, the control command related data may include a series of control commands. The series of control commands may be procedure information that has been performed during imaging of blood vessel data.

In step 140 , the processor may control the guidewire moving device according to the control command determined in step 130 . As the processor controls the guidewire moving device, the guidewire moving device may advance the guidewire along the path of the blood vessel to proceed.

According to an embodiment, the control command may be a command for the guide wire moving device to move forward or backward, or rotate the guide wire. The command to rotate may be a command for the guide wire moving device to rotate the guide wire in a direction and an angle determined based on control command data. Illustratively, the guidewire tip is positioned around the branch, so that the processor can determine which branch the guidewire will enter based on the control command data, and the direction and angle required to allow the guidewire to enter the determined branch. can be rotated with Rotating the guide wire moving device of the guide wire may be to control the tip of the guide wire in a required direction, for example, left or right, with respect to the longitudinal direction of the guide wire as an axis.

FIG. 2 is a diagram illustrating determination of a target patch area 221 by extracting a plurality of patch areas 220 , 221 , 222 , 223 and 224 according to an exemplary embodiment.

According to an embodiment, the processor may extract a plurality of patch regions 220 , 221 , 222 , 223 , and 224 from the image 200 along the blood vessel path 210 . The vascular path 210 may be a path through which the guide wire is navigated to reach the final target point. The plurality of patches may be rectangular patches extracted based on the blood vessel path 210 , and may be centered on an area recognized by the processor as a blood vessel. At this time, the plurality of patches may have overlapping portions, and when the guidewire tip is positioned at the overlapping portion, the processor may change the target patch area 221 .

The plurality of patches may be rectangular patches extracted based on the blood vessel path 210 , and sizes of the plurality of patches may be determined according to the thickness of the blood vessel. The processor may determine the patch size so that a ratio of blood vessels in the extracted patch is greater than or equal to a certain ratio. By varying the patch size according to the blood vessel size, compared to the case of determining the same patch size at once, the patch size can be set smaller for vessels with relatively thin vessels, and the patch size can be set for vessels with thick vessels. Since it can be set large, it is possible to efficiently determine the number of patches up to the final target point.

When a plurality of patches are extracted in the blood vessel image 200 , the processor may determine the target patch area 221 based on the position of the guide wire. The processor may determine a patch area including the tip of the guide wire among the plurality of patch areas 220 , 221 , 222 , 223 and 224 as the target patch area 221 . The target patch area 221 may be a patch area to be searched for blood vessel data having a similar blood vessel structure in a database including a plurality of blood vessel data.

After the guidewire moving device moves the guidewire, the processor controlling the guidewire moving device may track the position of the guidewire tip. When the processor determines that the tracked guidewire tip has reached the target point of the target patch area 221 , it may determine a next patch area and determine a control command for the next patch area. An embodiment of determining the next patch area will be described later in detail with reference to FIG. 6 .

When the target point is reached in the patch area, the processor may continuously determine the next patch area to control the guide wire moving device along the blood vessel path. The blood vessel path 210 may be navigated to the end of the blood vessel, and the last patch region 224 may include the end of the blood vessel as the final target point. When the tip of the guidewire reaches the final target point, the processor of the control method may end control of the guidewire moving device.

3 is a diagram illustrating determining the target patch area 321 based on the tip position of the guide wire according to an embodiment.

The control method according to an embodiment may determine the target patch region 321 based on the tip position of the guide wire without extracting a plurality of patch regions, unlike the embodiment described above in FIG. 2 . The processor may track the tip of the guidewire and determine the target patch area 321 based on the position of the tracked guidewire tip. The processor may determine a control command based on the database of blood vessel data to control the guide wire moving device, and then track the tip of the guide wire again. According to one embodiment, it is possible to determine the target patch area 321 again based on the tracked guide wire tip, but is not limited thereto, and when the tip of the guide wire reaches the target point, it is centered on the tip of the guide wire A target patch area 321 may be determined.

The entire vasculature may be hierarchically stored as data, and when a branch is included in the target patch region 321, the processor may reach the final target point with the shortest distance based on the hierarchical vasculature. You can select one of the branches to move the guidewire to the selected branch. For example, the entire blood vessel structure may be a data graph having a tree structure based on branches. When it is desired to move the guide wire to the leftmost blood vessel end in the blood vessel image 300 , the processor moves the guide wire to the left of the plurality of branches in the image to reach the shortest distance to the final target point of the leftmost blood vessel end. branch can be selected. The processor may generate a control command based on the selected branch.

4 is a flowchart illustrating control of the guide wire moving device 430 by extracting similar blood vessel data having a blood vessel structure similar to that of the target patch region 410 and determining a control command according to an exemplary embodiment.

According to an embodiment, the processor 420 may search for blood vessel data most similar to the blood vessel structure of the target patch region 410 from among the blood vessel data of the database. It may be information related to at least one of a blood vessel direction, the number of branching blood vessels, a branching angle, a form of a blood vessel stenosis, and a component of a vascular stenosis.

The processor 420 may search for similar blood vessel data similar to the target patch region 410 based on a neural network model. The similarity determination model may be a neural network model, a decision tree model, or a neural decision tree model. When the similarity determination model is a neural decision tree model, an input value of the similarity determination model may be a plurality of pieces of information described above regarding the vascular structure of the target patch region 410 . The similarity determination model of the processor 420 may output a value indicating a similarity to the target patch region 410, and the processor 420 determines that a value indicating a similarity among a plurality of blood vessel data in the database is the most High blood vessel data can be extracted as similar blood vessel data.

According to another exemplary embodiment, a plurality of blood vessel data in the database and the target patch region 410 may be compared one by one based on the above-described plurality of pieces of information regarding the blood vessel structure of the target patch region 410 . As a result of the comparison, blood vessel data having the highest similarity may be extracted as similar blood vessel data. The blood vessel data may be information in which numerical values, angles, directions, etc. about blood vessels extracted from blood vessel images are stored. Illustratively, in the blood vessel data, a blood vessel diameter, the number of branch blood vessels, and an angle at which branch blood vessels are branched may be stored as numerical values, and a type of blood vessel stenosis, stenosis components, and the like may be stored as text. The processor 420 may calculate the similarity by applying different weights to the information on the vascular structure of the target patch region 410 , and extract vascular data having the highest similarity among vascular data as similar vascular data. .

The processor 420 may extract blood vessel data having a high degree of similarity to the target patch region 410 as similar blood vessel data, and may determine a control command based on control command related data mapped to the similar blood vessel data. The control command related data may include deep learning weights stored with respect to the blood vessel data to determine the control command, and the processor 420 may set the deep learning weights of the similar blood vessel data as the weights of the command determination neural network model. The processor 420 may input the data of the target patch region 410 to the command determination neural network model. For example, the data of the target patch region 410 may be patch region image information, a tip position of a guide wire, and a target point, and the patch region image information may be information about blood vessels adjacent to the tip of the guide wire. When a blood vessel branch is included in the target patch region 410 , the data of the target patch region 410 may include branch data selected for the guide wire to reach the final target point among the blood vessel branches. The processor 420 may output a control command by inputting the input value to the weighted command determination neural network model.

5 is a flowchart illustrating a method for controlling a guidewire moving device after determining whether a guidewire tip has reached a target point in a target patch area according to an embodiment.

In step 140 of FIG. 1, the processor performing the control method may control the guidewire moving device, and after controlling the guidewire moving device, in step 510, the processor determines that the guidewire tip is the target of the target patch area. It is possible to determine whether a point has been reached. The target point may be a final position at which the guide wire moves in the target patch area in order to move to the final target point that the guide wire wants to reach in the blood vessel. Exemplarily, the target point may be a contact point closer to the final target point among contact points where the blood vessel path and the target patch region meet in FIG. 2 . If the processor determines that the guidewire tip has reached the target point of the target patch area, it may proceed to step 550 , and if it is determined that the guidewire tip has not reached the target point of the target patch area, it may proceed to step 520 .

In step 520 , the processor may determine whether the guidewire tip is included in the target patch area. If it is determined that the guidewire tip is not included in the target patch area, the processor may proceed to step 540 , and if it is determined that the guidewire tip is still included in the target patch area, the processor may proceed to step 530 . have.

Step 530 may be a case in which the guidewire moves along the vascular path corresponding to the target patch area before the guidewire tip reaches the target point of the target patch area. In step 530, the processor determines that an additional control command is required until the guide wire reaches the target point, and provides a new control command including control command related data mapped to similar blood vessel data and the position of the guide wire tip. can decide

Step 540 is a case in which the guidewire tip has not yet reached the target point of the target patch area, but is not visible in the target patch area. Accordingly, in step 540, the processor may provide a return command to the guidewire moving device to return the guidewire moved along the wrong path back to the target patch area. The return command may be a command for the processor to provide control commands transmitted to the guidewire moving device to the guidewire moving device in a reverse order. Illustratively, when the processor transmits a control command to the guidewire moving device in the order of left rotation, forward, and forward, the processor may provide backward, backward, and right rotation return commands to the guidewire moving device.

In step 550, when the guidewire tip reaches the target point of the target patch area, the processor determines the next patch area so that the guidewire tip can reach the final target point, and then determines a control command. . In the same manner as the method for controlling the guide wire moving device in the target patch area described in FIG. 1 , the processor may control the guide wire moving device in the next patch area.

6 is a diagram illustrating determining a next patch area according to an exemplary embodiment.

The processor may determine the target patch area according to the position of the guide wire tip among the plurality of patch areas, and may determine the next patch area of the target patch area according to the movement direction of the guide wire. The guide wire of one embodiment of FIG. 6 proceeds from the upper end of the blood vessel to the lower end, and when the patch area 620 is the target patch area according to the guide wire movement direction, the patch area 630 may be the next patch area.

According to an embodiment, when the guidewire tip reaches the target point 621 of the target patch area 620 , the processor may determine the next patch area 630 . The target point 621 of the target patch area 620 may be a point closest to the final target point among the intersections of the blood vessel path 610 and the target patch area 620 . When a plurality of patch areas are extracted in advance, the processor determines the patch area determined in the next order as the next patch area 630 , or overlaps the target patch area 620 at the target point 621 of the target patch area 620 . The patched area may be determined as the next patch area 630 .

According to another embodiment in which a plurality of patch areas are not extracted in advance, when the guidewire tip reaches the target point 621 of the target patch area 620, the processor processes the next patch area 630 around the guidewire tip. can be decided It is only one embodiment that the next patch area 630 is determined based on the guide wire tip, and the next patch area 630 is not limited thereto and may be generated according to a predetermined rule including the guide wire tip. Exemplarily, the processor may determine a patch area of a predetermined size as the next patch area 630 using the blood vessel path 610 in which the guidewire tip is located as a starting point.

In the next patch area 630 , the processor moves the guide wire moving device so that the guide wire tip is moved to the target point 631 of the next patch area 630 , and guides the guide wire moving device to the target point 631 of the next patch area 630 . When it is determined that the wire tip has arrived, it is possible to determine the patch area to which the guide wire is to be moved.

7 is a block diagram schematically illustrating the configuration of a device 700 for controlling the guide wire moving device 740 according to an embodiment.

Device 700 for controlling the guide wire moving device 740 may include a processor 710 and a memory 720 , an external database 730 , a guide wire moving device 740 , and an image capturing unit 750 . ) can transmit and receive data with at least one of the wireless/wired communication methods.

The processor 710 determines a target patch region based on the tip position of the guide wire in the image, searches for similar vascular data having a vascular structure similar to that of the target patch region from a database 730 about vascular data, and the A control command of the guidewire moving device 740 may be determined based on control command related data mapped to the searched similar blood vessel data, and the guidewire moving device 740 may be controlled according to the determined control command. Since the operation of the processor 710 has been described above with reference to FIGS. 1 to 6 , a detailed description thereof will be omitted.

The memory 720 may at least temporarily store data generated by the processor 710 and data received from an external device, and the data generated by the processor 710 may include a plurality of patch areas, a target patch area, It may include data about the patch area, and the like.

The embodiments described above may be implemented by a hardware component, a software component, and/or a combination of a hardware component and a software component. For example, the apparatus, methods and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate (FPGA) array), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For convenience of understanding, although one processing device is sometimes described as being used, one of ordinary skill in the art will recognize that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that can include For example, the processing device may include a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as parallel processors.

The software may comprise a computer program, code, instructions, or a combination of one or more thereof, which configures a processing device to operate as desired or is independently or collectively processed You can command the device. The software and/or data may be any kind of machine, component, physical device, virtual equipment, computer storage medium or device, to be interpreted by or to provide instructions or data to the processing device. , or may be permanently or temporarily embody in a transmitted signal wave. The software may be distributed over networked computer systems, and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and available to those skilled in the art of computer software. Examples of the computer readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floppy disks. - includes magneto-optical media, and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

As described above, although the embodiments have been described with reference to the limited drawings, those skilled in the art may apply various technical modifications and variations based on the above. For example, the described techniques are performed in a different order than the described method, and/or the described components of the system, structure, apparatus, circuit, etc. are combined or combined in a different form than the described method, or other components Or substituted or substituted by equivalents may achieve an appropriate result.

Claims (15)

In the guide wire moving device control method performed by the processor,
extracting a plurality of patch regions along a blood vessel path from an image;
determining a patch area including a tip of the guide wire in the image among the plurality of patch areas as a target patch area;
retrieving similar vascular data having a vascular structure similar to the target patch region from a vascular data database;
determining a control command of the guidewire moving device based on the deep learning weight and neural network model stored for the searched similar blood vessel data;
controlling the guide wire moving device according to the determined control command;
determining whether the tip of the guide wire has reached a target point of the target patch area; and
When it is determined that the tip of the guide wire has reached the target point, determining the next patch area based on the position of the tip of the guide wire in the image
A guide wire moving device control method comprising a.
delete delete According to claim 1,
When it is determined that the tip of the guide wire has reached the target point of the target patch area, one of the patch areas other than the target patch area among a plurality of patch areas including the tip of the guide wire is determined as the next patch area step
Guide wire moving device control method further comprising a.
According to claim 1,
The step of retrieving the similar blood vessel data comprises:
retrieving the similar vascular data based on at least one of a vascular diameter, vascular direction, number of branching vessels, branching angle, type of vascular stenosis, and components of vascular stenosis of the target patch region;
A guide wire moving device control method comprising a.
6. The method of claim 5,
The step of retrieving the similar blood vessel data comprises:
generating input data of a similarity determination model using at least one of a blood vessel diameter, a blood vessel direction, the number of branching blood vessels, a branching angle, a shape of a blood vessel stenosis, and components of a blood vessel stenosis of the target patch region;
outputting a degree of similarity to the target patch region with respect to the blood vessel data of the database by inputting the generated input data into the similarity determination model; and
extracting blood vessel data having the highest similarity among the database as the similar blood vessel data;
A guide wire moving device control method comprising a.
6. The method of claim 5,
The step of retrieving the similar blood vessel data comprises:
Each of the plurality of vascular data of the database and the target patch region based on at least one of a vessel diameter, vessel direction, number of branch vessels, branch angle, type of vessel stenosis, and components of vessel stenosis of the target patch region sequentially comparing them;
As a result of comparison, extracting blood vessel data having the highest similarity as the similar blood vessel data
A guide wire moving device control method comprising a.
delete According to claim 1,
The step of determining the control command comprises:
setting a deep learning weight stored for the similar blood vessel data as a weight of a command decision neural network model;
setting data on at least one of the patch area image information of the target patch area, the tip position of the guide wire, and the target point as an input value; and
outputting a control command by inputting the input value into the command-determining neural network model to which the weight is applied.
A guide wire moving device control method comprising a.
10. The method of claim 9,
determining whether the tip of the guide wire has reached a target point of the target patch area;
tracking the position of the tip of the guide wire when it is determined that the tip of the guide wire has not reached the target point of the target patch area; and
Determining a control command of the guide wire moving device based on the tracked tip position of the guide wire
Guide wire moving device control method further comprising a.
According to claim 1,
The step of determining the control command comprises:
determining a control command of the guidewire moving device based on a series of control commands mapped to the similar blood vessel data
A guide wire moving device control method comprising a.
According to claim 1,
determining whether the tip of the guide wire has reached a target point of the target patch area;
tracking the position of the guide wire when it is determined that the tip of the guide wire has not reached the target point of the target patch area;
If the guide wire tip is not included in the target patch area, providing a return command to the guide wire moving device until the tip of the guide wire is included in the target patch area
A guide wire moving device control method comprising a.
According to claim 1,
The control command is
Command to move the guide wire forward or backward, or to rotate the guide wire in a direction and an angle determined based on the data related to the control command
A guide wire moving device control method comprising a.
A computer-readable recording medium storing one or more computer programs including instructions for performing the method of any one of claims 1, 4 to 7, and claim 9 to 13.
In the control device for controlling the guide wire moving device,
A plurality of patch regions are extracted from an image along a blood vessel path, a patch region including a tip of the guide wire in the image among the plurality of patch regions is determined as a target patch region, and the target patch region is retrieved from a database about blood vessel data. Searching for similar blood vessel data having a blood vessel structure similar to the patch region, determining a control command of the guidewire moving device based on the deep learning weight and neural network model stored for the searched similar blood vessel data, and responding to the determined control command Control the guide wire moving device accordingly, determine whether the tip of the guide wire has reached the target point of the target patch area, and when it is determined that the tip of the guide wire has reached the target point, within the image A processor that determines the next patch area based on the tip position of the guidewire.
A control device comprising a.

Images