Guide wire autonomous delivery system based on fuzzy logic

Abstract

A guide wire autonomous delivery system based on fuzzy logic is disclosed. The guide wire autonomous delivery system comprises: an image processing module configured to collect a blood vessel image and extract feature information including a relative pose of a guide wire distal end and a blood vessel from the blood vessel image; a fuzzy logic calculation module configured to: calculate a guidewire delivery control parameter including at least one of axial translation and radial rotation based on the feature information and fuzzy logic; and a delivery control module configured to perform a delivery operation of the guidewire based on the feature information and the guidewire delivery control parameter. According to the guide wire autonomous delivery system based on the fuzzy logic, due to the fact that the fuzzy logic method is used, training operation does not need to be executed, high generalization ability, high interpretability and high success rate are achieved, the number of times that a doctor controls a robot in an operation is reduced, and the operation threshold and the workload of the doctor are reduced.

Description

Technical Field

[0001] This invention relates to a guidewire autonomous delivery system, and more specifically, to a guidewire autonomous delivery system based on fuzzy logic. Background Technology

[0002] Interventional vascular surgery is a major clinical method for treating coronary artery disease. Using digital subtraction angiography (DSA), surgeons guide interventional devices to the lesion site via a flexible guidewire. The surgeon manipulates the guidewire externally, advancing the distal tip along the arterial system to the target location by pushing and rotating the proximal end. Compared to traditional surgery, the introduction of robotic interventional vascular surgery reduces radiation exposure and physical fatigue while improving the precision of guidewire manipulation.

[0003] However, firstly, current vascular interventional surgical robots still rely entirely on continuous control by the surgeon during the procedure, exhibiting a low level of intelligence. Because current vascular interventional surgical robots cannot directly interact with the guidewire, and given the significant non-linear relationship between guidewire delivery and distal movement, even experienced surgeons require extensive training to master them.

[0004] Secondly, the next target stage for the intelligentization of vascular interventional surgical robots is task-level autonomy, meaning that the robotic system can automatically complete surgical tasks with only limited adjustments and control by the surgeon. At this level of autonomy, vascular interventional robots can reduce the complexity of surgeries and the workload of surgeons, avoiding mental fatigue and decreased precision in manual operations caused by prolonged periods of intense concentration.

[0005] Third, the core challenge of autonomous guidewire delivery lies in the fact that model-based methods are difficult to implement due to the physical properties of flexible guidewires, their complex mechanical interaction with the vascular system, and the inability of DSA images to provide three-dimensional information. Furthermore, existing learning-based methods often lack interpretability and pose safety risks in clinical applications. In addition, these methods require extensive training and have limited generalization ability. Summary of the Invention

[0006] The purpose of this invention is to provide a fuzzy logic-based autonomous guidewire delivery system that requires no training operations, has high generalization ability, strong interpretability, high success rate, reduces the number of times doctors need to control the robot during surgery, and lowers the surgical threshold and doctors' workload.

[0007] According to one embodiment of the present invention, a guidewire autonomous delivery system based on fuzzy logic is provided. The guidewire autonomous delivery system includes: an image processing module configured to: acquire vascular images and extract feature information including the relative pose of the distal end of the guidewire and the vascular vessel from the vascular images; a fuzzy logic calculation module configured to: calculate guidewire delivery control parameters including at least one of axial translation and radial rotation based on the feature information and fuzzy logic; and a delivery control module configured to: perform guidewire delivery operation based on the feature information and the guidewire delivery control parameters.

[0008] Optionally, the image processing module is configured to: convert the vascular image into a grayscale image and segment the vascular region; and extract feature information from the vascular region, including the relative pose of the distal end of the guidewire and the vascular model.

[0009] Optionally, the fuzzy logic calculation module is configured to: obtain the values ​​of n input variables based on feature information, where n is a positive integer; determine at least one latent fuzzy value corresponding to the value of each input variable based on the membership function of each of the n input variables; determine m fuzzy rules associated with the m combinations of latent fuzzy values ​​in the fuzzy rule base, where the m combinations of latent fuzzy values ​​refer to all combinations consisting of a latent fuzzy value corresponding to the value of each of the n input variables, and m is a positive integer; determine the membership function of the aggregated output variable corresponding to the set of the m fuzzy rules; and determine the value of the output variable corresponding to the n input variables as a guidewire delivery control parameter using the centroid method based on the membership function of the aggregated output variable, where each fuzzy rule reflects the correspondence between a combination of latent fuzzy values ​​and a specific fuzzy value of the output variable.

[0010] Optionally, the number of combinations of the m potential fuzzy values ​​corresponds to the product of the number of potential fuzzy values ​​corresponding to the value of each input variable.

[0011] Optionally, the fuzzy logic calculation module is configured to: for each of the m fuzzy rules, determine the membership degree of each of the n input variables to a specific fuzzy value corresponding to the input variable indicated by the fuzzy rule; determine the minimum value among the membership degrees of each of the n input variables as the rule premise membership degree of the fuzzy rule; truncate the membership function of the output variable using the rule premise membership degree of the fuzzy rule to obtain the rule conclusion membership function of the fuzzy rule; determine the maximum value among the values ​​of the rule conclusion membership function of each of the m fuzzy rules, and use the rule conclusion membership function corresponding to the determined maximum value as the aggregate output variable membership function corresponding to the set of the m fuzzy rules.

[0012] Optionally, the fuzzy logic calculation module is configured to: determine the abscissa corresponding to the centroid position of the region enclosed by the membership function of the aggregated output variable and the abscissa axis as the value of the output variable corresponding to the values ​​of the n input variables, and use it as the guidewire delivery control parameter.

[0013] Optionally, the n input variables include the distance from the distal end of the guidewire to the current vascular branch point in the target direction and the distance from the distal end of the guidewire to the next vascular branch point in the target direction. The output variables include the guidewire translation distance. The fuzzy values ​​corresponding to the distance from the distal end of the guidewire to the current vascular branch point in the target direction include short, medium, and long. The fuzzy values ​​corresponding to the distance from the distal end of the guidewire to the next vascular branch point in the target direction include short, medium, and long. The fuzzy values ​​corresponding to the guidewire translation distance include short, medium, and long. And / or the n input variables include the number of times the current vascular branch is attempted and the consistency between the bending direction of the distal end of the guidewire and the deviation of the target vascular branch. The output variables include the guidewire rotation angle at the delivery end. The fuzzy values ​​corresponding to the number of times the current vascular branch is attempted include very large, large, medium, and small. The fuzzy values ​​corresponding to the consistency between the bending direction of the distal end of the guidewire and the deviation of the target vascular branch include same and different. The fuzzy values ​​corresponding to the guidewire rotation angle at the delivery end include very large, large, medium, small, and very small.

[0014] Optionally, the delivery control module is configured to: detect whether the distal end of the guidewire is in the correct interventional path based on feature information; when the distal end of the guidewire is in the correct interventional path, control the guidewire to perform a translational operation without performing a rotational operation based on the guidewire delivery control parameters; when the distal end of the guidewire is not in the correct interventional path, retract the guidewire once, and then control the guidewire to perform a rotation once and deliver it forward based on the guidewire delivery control parameters, wherein, when performing the rotational operation, the guidewire is initially controlled to rotate along a first direction, and when it is detected that the bending direction of the distal end of the guidewire is opposite to the direction of the target blood vessel branch, the guidewire is controlled to rotate along a second direction opposite to the first direction.

[0015] According to one embodiment of the present invention, a computer-readable storage medium is provided, wherein instructions stored in the computer-readable storage medium, when executed by at least one processor, cause the at least one processor to perform: acquiring a vascular image; extracting feature information from the vascular image including the relative pose of the distal end of a guidewire and the vascular vessel; calculating guidewire delivery control parameters including at least one of axial translation and radial rotation based on the feature information and fuzzy logic; and performing a guidewire delivery operation based on the feature information and the guidewire delivery control parameters.

[0016] According to one embodiment of the present invention, a computer program product is provided, the computer program product comprising computer instructions, which, when executed by at least one processor, cause the at least one processor to perform: acquiring a vascular image; extracting feature information from the vascular image including the relative pose of the distal end of a guidewire and the vascular vessel; calculating guidewire delivery control parameters including at least one of axial translation and radial rotation based on the feature information and fuzzy logic; and performing a guidewire delivery operation based on the feature information and the guidewire delivery control parameters.

[0017] Therefore, the fuzzy logic-based autonomous guidewire delivery system according to the embodiments of this disclosure, due to the use of fuzzy logic methods, does not require training operations, has high generalization ability, strong interpretability, and high success rate, reduces the number of times doctors need to control the robot during surgery, lowers the surgical threshold and reduces the workload of doctors. Attached Figure Description

[0018] The above and / or other aspects of the present invention will become clearer and more readily understood through the following detailed description taken in conjunction with the accompanying drawings.

[0019] Figure 1 This is a flowchart of a guidewire autonomous delivery method based on fuzzy logic, according to an embodiment of the present invention.

[0020] Figure 2 This is a flowchart of a method for calculating guidewire delivery control parameters according to an embodiment of the present invention.

[0021] Figure 3 This is a diagram illustrating the membership function according to an embodiment of the present invention.

[0022] Figure 4 This is a flowchart of a method for determining the membership function of aggregate output variables according to an embodiment of the present invention.

[0023] Figure 5 This is a block diagram of a guidewire autonomous delivery system based on fuzzy logic, according to an embodiment of the present invention.

[0024] Figure 6 This is a detailed diagram of a fuzzy logic-based autonomous guidewire delivery system according to an embodiment of the present invention.

[0025] Throughout the accompanying drawings and detailed embodiments, unless otherwise described or provided, the same reference numerals will be understood to denote the same elements, features, and structures. The drawings may not be to scale, and for clarity, illustration, and convenience, the relative dimensions, scale, and depiction of elements in the drawings may be exaggerated. Detailed Implementation

[0026] The following detailed embodiments are provided to aid the reader in gaining a comprehensive understanding of the methods, apparatus, and / or systems described herein. However, various changes, modifications, and equivalents of the methods, apparatus, and / or systems described herein will become apparent upon understanding this disclosure. For example, the order of operations described herein is merely illustrative and is not limited to those orders set forth herein, but may be changed as will become clear upon understanding this disclosure, except for operations that must occur in a specific order. Furthermore, for the sake of clarity and conciseness, descriptions of features known upon understanding this disclosure may be omitted.

[0027] The features described herein may be implemented in different forms and should not be construed as being limited to the examples described herein. Rather, the examples described herein are provided merely to illustrate some of the many feasible ways of implementing the methods, apparatus, and / or systems described herein that will be clear upon understanding the disclosure of this application.

[0028] Throughout this specification, when a component is described as "connected to" or "attached to" another component, that component may be directly "connected to" or "attached to" that other component, or there may be one or more other components in between. Conversely, when an element is described as "directly connected to" or "directly attached to" another element, there may be no other elements in between. Similarly, similar expressions (e.g., "between" and "immediately between," and "adjacent to" and "closely adjacent to") should be interpreted in the same manner. As used herein, the term "and / or" includes any one of the relevant listed items or any combination of any two or more of the relevant listed items.

[0029] Although terms such as “first,” “second,” and “third” may be used herein to describe various components, assemblies, regions, layers, or parts, these components, assemblies, regions, layers, or parts are not limited by these terms. Rather, these terms are used only to distinguish one component, assembly, region, layer, or part from another. Therefore, without departing from the teaching of the examples described herein, the first component, first assembly, first region, first layer, or first part referred to as the first component, first assembly, first region, first layer, or first part may also be referred to as the second component, second assembly, second region, second layer, or second part.

[0030] The terminology used herein is for the purpose of describing various examples only and is not intended to limit disclosure. Unless the context clearly indicates otherwise, the singular form is intended to include the plural form as well. The terms “comprising,” “including,” and “having” indicate the presence of the features, quantities, operations, components, elements, and / or combinations thereof stated therein, but do not preclude the presence or addition of one or more other features, quantities, operations, components, elements, and / or combinations thereof.

[0031] Unless otherwise defined, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which the inventive concept pertains, based on the disclosure of this application. Unless expressly defined herein, terms (such as those defined in a general dictionary) shall be interpreted as having the same meaning as they have in the context of the relevant field and in the disclosure of this application, and shall not be interpreted ideally or overly formally. The use of the term “may” herein with respect to examples or embodiments (e.g., regarding what an example or embodiment may include or implement) indicates the existence of at least one example or embodiment that includes or implements such a feature, while not all examples are limited thereto.

[0032] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0033] Figure 1 This is a flowchart of a guidewire autonomous delivery method based on fuzzy logic, according to an embodiment of the present invention.

[0034] Reference Figure 1 The guidewire autonomous delivery method based on fuzzy logic includes steps S100 to S400.

[0035] In step S100, blood vessel images are acquired.

[0036] In step S200, feature information including the relative pose of the distal guidewire and the blood vessel is extracted from the vascular image. In one example, the vascular image can be converted to a grayscale image and the vascular region can be segmented. Then, feature information including the relative pose of the distal guidewire and the vascular model can be extracted from the vascular region. Furthermore, after the human physician sets the target location, path planning can be automatically performed to set the shortest interventional path.

[0037] In step S300, based on feature information and fuzzy logic, guidewire delivery control parameters, including at least one of axial translation and radial rotation, are calculated. Fuzzy logic is an intelligent reasoning and control method based on fuzzy set theory. It maps continuous, uncertain, or fuzzy input information into logical rules through membership functions, thereby simulating human fuzzy reasoning and decision-making processes in complex systems where formal models are difficult to establish. In the following text, reference will be made to... Figure 2 and Figure 3 The steps of calculating the guidewire delivery control parameters are described in detail in step S300.

[0038] In step S400, the guidewire delivery operation is performed based on the feature information and guidewire delivery control parameters.

[0039] In one example, the presence of the distal guidewire in the correct interventional path can be detected based on feature information. For instance, when the distal guidewire is in the correct path, the guidewire can be translated without rotation based on guidewire delivery control parameters. Conversely, if the distal guidewire is not in the correct path, it can be retracted once, then rotated and forward-delivered based on the guidewire delivery control parameters. This process can be repeated until the distal guidewire reaches the predetermined target position.

[0040] In one example, guidewire delivery can also be based on historical operation information. For instance, when performing a rotation operation, the guidewire can initially (or by default) rotate in a first direction, and when it is detected that the distal bending direction of the guidewire is opposite to the target vessel branch, the guidewire can rotate in a second direction opposite to the first direction. As another example, when performing a rotation operation, the guidewire can be controlled to rotate in a random direction, and when it is detected that the distal bending direction of the guidewire is opposite to the target vessel branch, the guidewire can be controlled to rotate in a direction opposite to that random direction.

[0041] In one example, a human physician can supervise guidewire delivery based on visual feedback from the monitor. For instance, if multiple autonomous attempts at a particular vascular branch fail, the physician can intervene actively (e.g., switch from autonomous to manual mode) to regain control of the guidewire, manipulate it using a controller, and relinquish control after passing the current vascular branch (e.g., switch back from manual to autonomous mode). Furthermore, during guidewire delivery, the physician can adjust the interventional route by setting waypoints.

[0042] According to embodiments of this disclosure, steps S100 to S400 may be performed continuously (repeatedly).

[0043] Therefore, the guidewire autonomous delivery method based on fuzzy logic according to the embodiments of this disclosure, due to the use of fuzzy logic, does not require training operations, has high generalization ability, strong interpretability, and high success rate, reduces the number of times doctors need to control the robot during surgery, lowers the surgical threshold and reduces the workload of doctors.

[0044] Figure 2 This is a flowchart of a method for calculating guidewire delivery control parameters according to an embodiment of the present invention. Figure 3 This is a diagram illustrating the membership function according to an embodiment of the present invention.

[0045] Reference Figure 2The step S300, which calculates guidewire delivery control parameters including at least one of axial translation and radial rotation based on feature information and fuzzy logic, may include steps S310 to S350. The step of calculating the guidewire delivery control parameters may include three stages: a fuzzification stage, a fuzzy inference stage, and a defuzzification stage. The fuzzification stage maps precise input values ​​to a predefined fuzzy set using a membership function and may correspond to a combination of steps S310 and S320. The fuzzy inference stage generates an output fuzzy set based on a fuzzy rule base and the fuzzification result and may correspond to a combination of steps S330 and S340. The defuzzification stage converts the fuzzy set output obtained in the fuzzy inference stage into a sharp value and may correspond to step S350.

[0046] In step S310, the values ​​of n input variables can be obtained based on feature information, where n is a positive integer.

[0047] In one example, when the n input variables and output variables correspond to the input and output variables of a translation controller used to control the translation operation of the guidewire, the n input variables may include the distance from the distal end of the guidewire to the current vascular branch point in the target direction. The distance from the distal end of the guidewire to the next vascular branch point in the target direction The output variables can include the guide wire translation distance. This example corresponds to guidewire delivery control parameters, including axial translation, used for translation controllers.

[0048] In another example, when the n input variables and output variables correspond to the input and output variables of a rotation controller used to control the rotation of the guidewire, respectively, the n input variables may include the number of repetitions attempted by the current vascular branch. Consistency between the direction of the distal guidewire bend and the deviation of the target vessel branch. The output variables may include the guidewire rotation angle at the delivery end. This example corresponds to guidewire delivery control parameters that include radial rotation for a rotation controller.

[0049] In step S320, at least one potential fuzzy value corresponding to the value of each of the n input variables can be determined based on the membership function of each input variable.

[0050] According to embodiments of this disclosure, a membership function can represent a function of the probability distribution of a variable's value (e.g., a precise value or a specific value) belonging to a fuzzy value. In some cases, a value of a variable (e.g., a precise value or a specific value) can belong to different fuzzy values ​​(hereinafter also referred to as latent fuzzy values) with the same or different membership degrees. Therefore, the same variable can have multiple membership functions corresponding to multiple fuzzy values.

[0051] In one example, the fuzzy values corresponding to the distance from the distal end of the guide wire to the current blood vessel branch point in the target direction may include "short", "medium", and "long", and the fuzzy values corresponding to the distance from the distal end of the guide wire to the next blood vessel branch point in the target direction may include "short", "medium", and "long", and the fuzzy values corresponding to the translation distance of the guide wire may include "short", "medium", and "long". Accordingly, referring to Figure 3 , the membership functions of the distance from the distal end of the guide wire to the current blood vessel branch point in the target direction may include the membership function corresponding to the fuzzy value "short" of , the membership function corresponding to the fuzzy value "medium" of , and the membership function corresponding to the fuzzy value "long" of . The membership functions of the distance from the distal end of the guide wire to the next blood vessel branch point in the target direction may include the membership function corresponding to the fuzzy value "short" of , the membership function corresponding to the fuzzy value "medium" of , and the membership function corresponding to the fuzzy value "long" of . And the membership functions of the translation distance of the guide wire may include the membership function corresponding to the fuzzy value "short" of , the membership function corresponding to the fuzzy value "medium" of , and the membership function corresponding to the fuzzy value "long" of . Accordingly, the potential fuzzy values corresponding to the value (e.g., exact value or specific value) of the distance from the distal end of the guide wire to the current blood vessel branch point in the target direction may include at least one of "short", "medium", and "long", and the potential fuzzy values corresponding to the value (e.g., exact value or specific value) of the distance from the distal end of the guide wire to the next blood vessel branch point in the target direction may include at least one of "short", "medium", and "long".

[0052] In another example, the fuzzy values corresponding to the number of times of attempting the current blood vessel branch may include "very large", "large", "medium", and "small", the fuzzy values corresponding to the consistency between the bending direction of the distal end of the guide wire and the deviation of the target blood vessel branch may include "same" and "different", and the fuzzy values corresponding to the rotation angle of the guide wire at the delivery end may include "very large", "large", "medium", "small", and "very small". Accordingly, referring to Figure 3 ​​​ The membership function corresponding to the fuzzy value "very large" of the membership function corresponding to the fuzzy value "large" of the membership function corresponding to the fuzzy value "medium" of and the membership function corresponding to the fuzzy value "small" of The membership function of the consistency between the distal bending direction of the guide wire and the deviation of the target blood vessel branch may include the membership function corresponding to the fuzzy value "same" of and the membership function corresponding to the fuzzy value "different" of And the membership function of the rotation angle of the delivery end guide wire may include the membership function corresponding to the fuzzy value "very large" of the membership function corresponding to the fuzzy value "large" of the membership function corresponding to the fuzzy value "medium" of the membership function corresponding to the fuzzy value "small" of and the membership function corresponding to the fuzzy value "very small" of The potential fuzzy values corresponding to the value (e.g., exact value or specific value) of the current number of attempts of the blood vessel branch may include at least one of "very large", "large", "medium", and "small", and the consistency between the distal bending direction of the guide wire and the deviation of the target blood vessel branch The potential fuzzy values corresponding to the value (e.g., exact value or specific value) of may include at least one of "same" and "different".

[0053] In step S330, m fuzzy rules associated with m combinations of potential fuzzy values may be determined (or activated) in the fuzzy rule base, where m is a positive integer.

[0054] According to an embodiment of the present disclosure, the fuzzy rule base may include multiple fuzzy rules and may be constructed based on the experience of human doctors. Each fuzzy rule may be composed of rules in the form of "if... then...", and may be represented by the following formula 1, where , ,..., are input variables, , ,..., are respectively a potential fuzzy value of the input variable , ,..., , is an output variable, and is a fuzzy value of the output variable , is a positive integer and represents the number of input variables.

[0055]

Formula 1

[0056] For example, multiple fuzzy rules in a fuzzy rule base corresponding to wire delivery control parameters including axial translation for a translation controller can be shown in Table 1 below.

[0057]

Table 1

[0058] For example, multiple fuzzy rules in a fuzzy rule base corresponding to wire delivery control parameters including radial rotation for a rotation controller can be shown in Table 2 below.

[0059]

Table 2

[0060] According to an embodiment of the present disclosure, each fuzzy rule can reflect a correspondence between a potential fuzzy value combination and a specific fuzzy value of an output variable. For example, the fuzzy rule numbered 3 in Table 1 can reflect a correspondence between a potential fuzzy value combination (e.g., is "short" and is "long") and a specific fuzzy value of an output variable (e.g., is "medium").

[0061] According to an embodiment of the present disclosure, m potential fuzzy value combinations can refer to all combinations composed of a potential fuzzy value corresponding to the value of each of n input variables, and m can be a positive integer. Therefore, the number of m potential fuzzy value combinations can correspond to the product of the number of potential fuzzy values corresponding to the values of each input variable.

[0062] For example, referring to Figure 3 , when has a value of 10 and has a value of 30, since the membership function corresponding to the fuzzy value "short" of and the membership function corresponding to the fuzzy value "medium" of have a distribution at a value of 10 of , therefore, the potential fuzzy values of corresponding to " has a value of 10" can be "short" and "medium"; since the membership function corresponding to The membership function corresponding to the fuzzy value "short", and the membership function corresponding to the fuzzy value "medium", and the membership function corresponding to the fuzzy value "long" are distributed at a value of 30. Therefore, the potential fuzzy values corresponding to "a value of 30" can be "short", "medium", and "long". Thus, when a value is 10 and a value is 30, there can be 6 potential fuzzy value combinations, namely, is "short" and is "short", is "short" and is "medium", is "short" and is "long", is "medium" and is "short", is "medium" and is "medium", and is "medium", and is "medium" and is "long". Correspondingly, the above 6 potential fuzzy value combinations can be respectively associated with the 6 fuzzy rules in Table 1 above (i.e., the fuzzy rules numbered 1 to 6 in Table 1).

[0063] In step S340, the aggregated output variable membership function corresponding to the set of m fuzzy rules can be determined. Hereinafter, the details of step S340 will be described in detail with reference to Figure 4 the details of step S340 will be described in detail.

[0064] In step S350, based on the aggregated output variable membership function, the centroid method can be used to determine the value of the output variable corresponding to the n input variables as the guide wire delivery control parameter.

[0065] In one example, the abscissa corresponding to the centroid position of the region enclosed by the aggregated output variable membership function and the horizontal axis can be determined as the value of the output variable corresponding to the n input variables, as the guide wire delivery control parameter. In one example, the value of the output variable corresponding to the n input variables can be determined by the following formula 2, where represents the aggregated output variable membership function, represents the value of the output variable (e.g., the exact value or a specific value), and the interval composed of is the support interval when is . For example, the x-axis coordinate corresponding to the centroid position of the total area region is the exact value (or the clear value) of the final output parameter.

[0066]

Formula 2

[0067] Therefore, due to the use of the fuzzy logic method, the fuzzy-logic-based autonomous guide wire delivery method according to an embodiment of the present disclosure does not need to perform a training operation, has high generalization ability, strong interpretability, high success rate, reduces the number of times a doctor controls a robot during surgery, and lowers the surgical threshold and the workload of the doctor.

[0068] Figure 4 is a flowchart of a method for determining a membership function of an aggregated output variable according to an embodiment of the inventive concept.

[0069] Referring to Figure 4 , the step S340 of determining the membership function of the aggregated output variable corresponding to the set of m fuzzy rules may include steps S341 to S344.

[0070] In step S341, for each of the m fuzzy rules, the membership degree to which the value of each of the n input variables belongs to a specific fuzzy value corresponding to the input variable indicated by the fuzzy rule may be determined.

[0071] For example, referring to Figure 3 , in the case of the above six fuzzy rules associated with “ has a value of 10 and has a value of 30” (i.e., the fuzzy rules numbered 1 to 6 in Table 1), for the fuzzy rule numbered 1 in Table 1 (i.e., if is “short” and is “short”, then is “short”), it may be determined that the membership degree of the input variable with a value of 10 to the specific fuzzy value “short” corresponding to the input variable indicated by the fuzzy rule numbered 1 is 0.33, and it may be determined that the membership degree of the input variable with a value of 30 to the specific fuzzy value “short” corresponding to the input variable indicated by the fuzzy rule numbered 1 is 0.57; for the fuzzy rule numbered 2 in Table 1 (i.e., if is “short” and is “medium”, then is “short”), the membership degree of the input variable with a value of 10 to the specific fuzzy value “short” corresponding to the input variable indicated by the fuzzy rule numbered 2 and the membership degree of the input variable The membership degree belonging to the specific fuzzy value "medium" corresponding to the input variable indicated by the fuzzy rule numbered 2; for the fuzzy rule numbered 3 in Table 1 (i.e., if is "short" and is "long", then is "medium"), the membership degree of the input variable with a value of 10 belonging to the specific fuzzy value "short" corresponding to the input variable indicated by the fuzzy rule numbered 3 can be determined similarly, and the membership degree of the input variable with a value of 30 belonging to the specific fuzzy value "long" corresponding to the input variable indicated by the fuzzy rule numbered 3; for the fuzzy rule numbered 4 in Table 1 (i.e., if is "medium" and is "short", then is "medium"), the membership degree of the input variable with a value of 10 belonging to the specific fuzzy value "medium" corresponding to the input variable indicated by the fuzzy rule numbered 4 can be determined, and the membership degree of the input variable with a value of 30 belonging to the specific fuzzy value "short" corresponding to the input variable indicated by the fuzzy rule numbered 4; for the fuzzy rule numbered 5 in Table 1 (i.e., if is "medium" and is "medium", then is "medium"), the membership degree of the input variable with a value of 10 belonging to the specific fuzzy value "medium" corresponding to the input variable indicated by the fuzzy rule numbered 5 can be determined similarly, and the membership degree of the input variable with a value of 30 belonging to the specific fuzzy value "medium" corresponding to the input variable indicated by the fuzzy rule numbered 5; for the fuzzy rule numbered 6 in Table 1 (i.e., if [[ID=|32]]is "medium" and is "long", then is "medium"), the membership degree of the input variable with a value of 10 belonging to the specific fuzzy value "medium" corresponding to the input variable indicated by the fuzzy rule numbered 6 can be determined similarly, and the membership degree of the input variable with a value of 30 belonging to the specific fuzzy value "long" corresponding to the input variable indicated by the fuzzy rule numbered 6; for the fuzzy rule numbered 6 in Table 1 (i.e., if is "medium" and is "long", then is "medium"), the membership degree of the input variable with a value of 10 belonging to the specific fuzzy value "medium" corresponding to the input variable indicated by the fuzzy rule numbered 6 can be determined similarly, and the membership degree of the input variable with a value of 30 belonging to the specific fuzzy value "long" corresponding to the input variable indicated by the fuzzy rule numbered 6; for the fuzzy rule numbered 6 in Table 1 (i.e., if is "medium" and is "long", then is "medium"), the membership degree of the input variable with a value of 10 belonging to the specific fuzzy value "medium" corresponding to the input variable indicated by the fuzzy rule numbered 6 can be determined similarly, and the membership degree of the input variable with a value of 30

[0072] In step S342, the minimum value among the membership degrees of each of the n input variables can be determined as the rule premise membership degree of this fuzzy rule, as shown in the following formula 3, where represents the rule premise membership degree of the th fuzzy rule, represents the membership degree function of the input variable belonging to the fuzzy value , is a positive integer less than or equal to n, and is a positive integer less than or equal to m.

[0073]

Formula 3

[0074] For example, as described above, in the case of the 6 fuzzy rules associated with "the value of is 10 and the value of is 30" (i.e., the fuzzy rules numbered from 1 to 6 in Table 1), for the fuzzy rule numbered 1 in Table 1 (i.e., if is "short" and is "short", then is "short"), the membership degree of the input variable with a value of 10 belonging to the specific fuzzy value "short" corresponding to this input variable indicated by the fuzzy rule numbered 1 (i.e., ), and the membership degree of the input variable with a value of 30 belonging to the specific fuzzy value "short" corresponding to this input variable indicated by the fuzzy rule numbered 1 (i.e., )) among the minimum values (i.e., ) can be determined as the rule premise membership degree of the fuzzy rule numbered 1 (i.e., ); for the fuzzy rule numbered 2 in Table 1 (i.e., if is "short" and is "medium", then is "short"), the minimum value among the membership degree of the input variable with a value of 10 belonging to the specific fuzzy value "short" corresponding to this input variable indicated by the fuzzy rule numbered 2 and the membership degree of the input variable with a value of 30 belonging to the specific fuzzy value "medium" corresponding to this input variable indicated by the fuzzy rule numbered 2 can be similarly determined as the rule premise membership degree of the fuzzy rule numbered 2; for the fuzzy rule numbered 3 in Table 1 (i.e., if is "short" and is "long", then is "medium"), the input variable with a value of 10 can be similarly subordinated to the membership degree of the specific fuzzy value "short" corresponding to this input variable indicated by the fuzzy rule numbered 3 and the input variable with a value of 30 subordinated to the membership degree of the specific fuzzy value "long" corresponding to this input variable indicated by the fuzzy rule numbered 3 among them, the minimum value is determined as the rule premise membership degree of the fuzzy rule numbered 3 ; for the fuzzy rule numbered 4 in Table 1 (i.e., if is "medium" and is "short", then is "medium"), the input variable with a value of 10 can be similarly subordinated to the membership degree of the specific fuzzy value "medium" corresponding to this input variable indicated by the fuzzy rule numbered 4 and the input variable with a value of 30 subordinated to the membership degree of the specific fuzzy value "short" corresponding to this input variable indicated by the fuzzy rule numbered 4 among them, the minimum value is determined as the rule premise membership degree of the fuzzy rule numbered 4 ; for the fuzzy rule numbered 5 in Table 1 (i.e., if is "medium" and is "medium", then is "medium"), the input variable with a value of 10 can be similarly subordinated to the membership degree of the specific fuzzy value "medium" corresponding to this input variable indicated by the fuzzy rule numbered 5 and the input variable with a value of 30 subordinated to the membership degree of the specific fuzzy value "medium" corresponding to this input variable indicated by the fuzzy rule numbered 5 among them, the minimum value is determined as the rule premise membership degree of the fuzzy rule numbered 5 ; for the fuzzy rule numbered 6 in Table 1 (i.e., if is "medium" and is "long", then ; for the fuzzy rule numbered 6 in Table 1 (i.e., if is "medium" and is "long", then is "medium"), the input variable with a value of 10 can be similarly subordinated to the membership degree of the specific fuzzy value "medium" corresponding to this input variable indicated by the fuzzy rule numbered 6 and the input variable with a value of 30 subordinated to the membership degree of the specific fuzzy value "medium" corresponding to this input variable indicated by the fuzzy rule numbered 6 and the input variable with a value of 30 subordinated to the membership degree of the specific fuzzy value "medium" corresponding to this input variable indicated by the fuzzy rule numbered 6 and the input variable with a value of 30 The minimum value among the membership degrees of the corresponding specific fuzzy value "length" is determined as the rule premise membership degree of the fuzzy rule numbered 6. .

[0075] In step S343, the membership function of the output variable can be truncated using the rule premise membership degree of the fuzzy rule to obtain the rule conclusion membership function of the fuzzy rule, as shown in Formula 4 below, where, The membership function representing the rule conclusion of a fuzzy rule. Indicates output variable Belonging to fuzzy values The membership function.

[0076] [Formula 4]

[0077] In step S344, the maximum value among the membership functions of the rule conclusions of each of the m fuzzy rules can be determined, and the membership function of the rule conclusions corresponding to the determined maximum value can be used as the membership function of the aggregated output variable corresponding to the set of m fuzzy rules, as shown in Formula 5 below, where, This represents the membership function of the aggregated output variable.

[0078] [Formula 5]

[0079] Therefore, the guidewire autonomous delivery method based on fuzzy logic according to the embodiments of this disclosure, due to the use of fuzzy logic, does not require training operations, has high generalization ability, strong interpretability, and high success rate, reduces the number of times doctors need to control the robot during surgery, lowers the surgical threshold and reduces the workload of doctors.

[0080] Figure 5 This is a block diagram of a guidewire autonomous delivery system based on fuzzy logic, according to an embodiment of the present invention.

[0081] Reference Figure 5 According to an embodiment of the present invention, the fuzzy logic-based autonomous guidewire delivery system 100 may include an image processing module 110, a fuzzy logic calculation module 120, and a delivery control module 130.

[0082] Image processing module 110 can be configured to: acquire vascular images and extract feature information from the vascular images, including the relative pose of the distal guidewire and the vascular vessel. In one example, image processing module 110 can be configured to: convert the vascular image into a grayscale image and segment the vascular region; and extract feature information from the vascular region, including the relative pose of the distal guidewire and the vascular model.

[0083] The fuzzy logic calculation module 120 can be configured to calculate guidewire delivery control parameters, including at least one of axial translation and radial rotation, based on feature information and fuzzy logic.

[0084] According to embodiments of this disclosure, the fuzzy logic calculation module 120 can be configured to: obtain the values ​​of n input variables based on feature information, where n is a positive integer; determine at least one latent fuzzy value corresponding to the value of each input variable based on the membership function of each of the n input variables; determine m fuzzy rules associated with m combinations of latent fuzzy values ​​in a fuzzy rule base, where the m combinations of latent fuzzy values ​​refer to all combinations consisting of a latent fuzzy value corresponding to the value of each of the n input variables, and m is a positive integer; determine the membership function of the aggregated output variable corresponding to the set of m fuzzy rules; and determine the value of the output variable corresponding to the n input variables as a guidewire delivery control parameter using the centroid method based on the membership function of the aggregated output variable, where each fuzzy rule reflects the correspondence between a latent fuzzy value combination and a specific fuzzy value of the output variable. According to embodiments of this disclosure, the number of m combinations of latent fuzzy values ​​corresponds to the product of the number of latent fuzzy values ​​corresponding to the value of each input variable.

[0085] According to embodiments of this disclosure, the fuzzy logic calculation module 120 can be configured to: for each of m fuzzy rules, determine the membership degree of each of n input variables to a specific fuzzy value corresponding to the input variable indicated by the fuzzy rule; determine the minimum value among the membership degrees of each of the n input variables as the rule premise membership degree of the fuzzy rule; truncate the membership function of the output variable using the rule premise membership degree of the fuzzy rule to obtain the rule conclusion membership function of the fuzzy rule; determine the maximum value among the values ​​of the rule conclusion membership function of each of the m fuzzy rules, and use the rule conclusion membership function corresponding to the determined maximum value as the aggregate output variable membership function corresponding to the set of m fuzzy rules.

[0086] According to an embodiment of this disclosure, the fuzzy logic calculation module 120 can be configured to: determine the abscissa corresponding to the centroid position of the region enclosed by the membership function of the aggregated output variable and the abscissa axis as the value of the output variable corresponding to the values ​​of n input variables, and use it as the guide wire delivery control parameter.

[0087] The delivery control module 130 can be configured to perform guidewire delivery operations based on feature information and guidewire delivery control parameters.

[0088] According to embodiments of this disclosure, the delivery control module 130 can be configured to: detect whether the distal end of the guidewire is in the correct interventional path based on feature information; when the distal end of the guidewire is in the correct interventional path, control the guidewire to perform a translational operation without performing a rotational operation based on guidewire delivery control parameters; when the distal end of the guidewire is not in the correct interventional path, retract the guidewire once, and then control the guidewire to perform a rotation once and deliver it forward based on the guidewire delivery control parameters, wherein, when performing the rotational operation, the guidewire is initially controlled to rotate along a first direction, and when it is detected that the bending direction of the distal end of the guidewire is opposite to the direction of the target blood vessel branch, the guidewire is controlled to rotate along a second direction opposite to the first direction.

[0089] Therefore, the fuzzy logic-based autonomous guidewire delivery system according to the embodiments of this disclosure, due to the use of fuzzy logic methods, does not require training operations, has high generalization ability, strong interpretability, and high success rate, reduces the number of times doctors need to control the robot during surgery, lowers the surgical threshold and reduces the workload of doctors.

[0090] Figure 6 This is a detailed diagram of a fuzzy logic-based autonomous guidewire delivery system according to an embodiment of the present invention.

[0091] Reference Figure 6 The guidewire autonomous delivery system includes a vascular intervention scenario module (not shown), an image processing module 1100, a fuzzy logic calculation module 1200, a delivery control module 1300, and a human-machine collaboration module (not shown). Figure 6 The image processing module 1100, the fuzzy logic calculation module 1200, and the delivery control module 1300 can respectively correspond to Figure 5 The image processing module 110, fuzzy logic calculation module 120, and delivery control module 130 are included. Therefore, their repeated descriptions can be omitted to avoid redundancy.

[0092] The vascular interventional scenario module can consist of a vascular interventional surgical robot 1400, a catheter 1500, a guidewire 1600, a vascular model 1700, and a camera 1800. The vascular interventional surgical robot 1400 can manipulate the guidewire 1600 to deliver it within the vascular model 1700 and to a designated location via control commands from the delivery control module 1300 or the human-machine collaboration module. The vascular model 1700 can be made of resin material using 3D printing technology. The camera 1800 can be positioned directly above the vascular model 1700.

[0093] The image processing module 1100 can process the images acquired by the camera 1800 in real time, extract vascular structures, instrument poses and perform path planning, and send the extracted feature information to the fuzzy logic calculation module 1200 and the delivery control module 1300.

[0094] The fuzzy logic calculation module 1200 can calculate the specific control parameters for guidewire delivery during axial translation and radial rotation based on the guidewire and blood vessel pose information sent by the image processing module 1100, and send them to the delivery control module 1300.

[0095] The delivery control module 1300 can control the direction of guidewire translation and rotation and the delivery operation mode based on the feature information provided by the image processing module 1100, the specific control parameters provided by the fuzzy logic calculation module 1200 and its own recorded historical operation information, so that the guidewire can accurately reach the predetermined position.

[0096] The human-machine collaboration module may include a display 1910 and a controller 1920.

[0097] Therefore, the fuzzy logic-based autonomous guidewire delivery system according to the embodiments of this disclosure, due to the use of fuzzy logic methods, does not require training operations, has high generalization ability, strong interpretability, and high success rate, reduces the number of times doctors need to control the robot during surgery, lowers the surgical threshold and reduces the workload of doctors.

[0098] The fuzzy logic-based autonomous wire delivery method according to embodiments of the present invention can be programmed into a computer program and stored on a computer-readable storage medium. When executed by a processor, the computer program implements the fuzzy logic-based autonomous wire delivery method as described above. Examples of computer-readable storage media include: read-only memory (ROM), random access programmable read-only memory (PROM), electrically erasable programmable read-only memory (EEPROM), random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), flash memory, non-volatile memory, CD-ROM, CD-R, CD+R, CD-RW, CD+RW, DVD-ROM, DVD-R, DVD+R, DVD-RW, DVD+RW, DVD-RAM, BD-ROM, BD-R, BD-R LTH, BD-RE, Blu-ray or optical disc storage, hard disk drive (HDD), solid-state drive (SSD), card storage (such as multimedia cards, secure digital (SD) cards, or ultra-fast digital (XD) cards), magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid-state drive, and any other device configured to store a computer program and any associated data, data files, and data structures in a non-transitory manner and to provide the computer program and any associated data, data files, and data structures to a processor or computer so that the processor or computer can execute the computer program. In one example, the computer program and any associated data, data files, and data structures are distributed across a networked computer system, such that the computer program and any associated data, data files, and data structures are stored, accessed, and executed in a distributed manner through one or more processors or computers.

[0099] The fuzzy logic-based autonomous guidewire delivery system according to embodiments of this disclosure uses a fuzzy logic method, thus eliminating the need for training operations. It has high generalization ability, strong interpretability, and high success rate, reducing the number of times doctors need to control the robot during surgery, lowering the surgical threshold and reducing the workload of doctors.

[0100] Although the invention has been specifically shown and described with reference to exemplary embodiments thereof, those skilled in the art will understand that various changes in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the claims.

Claims

1. A guidewire autonomous delivery system based on fuzzy logic, characterized in that, The autonomous guidewire delivery system includes: The image processing module is configured to: acquire vascular images and extract feature information from the vascular images, including the relative pose of the distal end of the guidewire and the vascular vessel; The fuzzy logic calculation module is configured to: calculate guidewire delivery control parameters, including at least one of axial translation and radial rotation, based on feature information and fuzzy logic; and The delivery control module is configured to perform guidewire delivery operations based on feature information and guidewire delivery control parameters.

2. The guidewire autonomous delivery system according to claim 1, characterized in that, The image processing module is configured as follows: Convert the blood vessel image to grayscale and segment the blood vessel region; and Feature information, including the relative pose of the distal guidewire and the vascular model, is extracted from the vascular region.

3. The guidewire autonomous delivery system according to claim 1, characterized in that, The fuzzy logic calculation module is configured as follows: The values ​​of n input variables are obtained based on feature information, where n is a positive integer; Based on the membership function of each of the n input variables, determine at least one potential fuzzy value corresponding to the value of each input variable; In the fuzzy rule base, determine m fuzzy rules associated with m potential fuzzy value combinations, where the m potential fuzzy value combinations refer to all combinations consisting of a potential fuzzy value corresponding to the value of each of the n input variables, and m is a positive integer; Determine the membership function of the aggregated output variable corresponding to the set of m fuzzy rules; Based on the membership function of the aggregated output variables, the centroid method is used to determine the values ​​of the output variables corresponding to the n input variables as guidewire delivery control parameters. Each fuzzy rule reflects the correspondence between a potential combination of fuzzy values ​​and a specific fuzzy value of the output variable.

4. The guidewire autonomous delivery system according to claim 3, characterized in that, The number of combinations of m potential fuzzy values ​​corresponds to the product of the number of potential fuzzy values ​​corresponding to the value of each input variable.

5. The guidewire autonomous delivery system according to claim 3, characterized in that, The fuzzy logic calculation module is configured as follows: For each of the m fuzzy rules, determine the degree of membership of the value of each of the n input variables to the specific fuzzy value corresponding to the input variable as indicated by the fuzzy rule; The minimum value among the membership degrees of each of the n input variables is determined as the rule premise membership degree of the fuzzy rule; By truncating the membership function of the output variable using the rule premise membership degree of the fuzzy rule, the rule conclusion membership function of the fuzzy rule can be obtained. Determine the maximum value among the membership functions of the rule conclusions of each of the m fuzzy rules, and use the membership function of the rule conclusions corresponding to the determined maximum value as the membership function of the aggregated output variable corresponding to the set of the m fuzzy rules.

6. The guidewire autonomous delivery system according to claim 3, characterized in that, The fuzzy logic calculation module is configured as follows: The x-coordinate corresponding to the centroid of the region enclosed by the membership function of the aggregated output variable and the x-axis is determined as the value of the output variable corresponding to the values ​​of the n input variables, and is used as the guidewire delivery control parameter.

7. The guidewire autonomous delivery system according to claim 3, characterized in that, The n input variables include the distance from the distal end of the guidewire to the current vascular branch point in the target direction and the distance from the distal end of the guidewire to the next vascular branch point in the target direction. The output variables include the guidewire translation distance. The fuzzy values ​​corresponding to the distance from the distal end of the guidewire to the current vascular branch point in the target direction include short, medium, and long. The fuzzy values ​​corresponding to the distance from the distal end of the guidewire to the next vascular branch point in the target direction also include short, medium, and long. Furthermore, the fuzzy values ​​corresponding to the guidewire translation distance include short, medium, and long. And / or The n input variables include the number of times the current vascular branch is attempted and the consistency between the guidewire distal bending direction and the target vascular branch deviation. The output variables include the guidewire rotation angle at the delivery end. The fuzzy values ​​corresponding to the number of times the current vascular branch is attempted include very large, large, medium, and small. The fuzzy values ​​corresponding to the consistency between the guidewire distal bending direction and the target vascular branch deviation include same and different. The fuzzy values ​​corresponding to the guidewire rotation angle at the delivery end include very large, large, medium, small, and very small.

8. The autonomous guidewire delivery system according to claim 1, characterized in that, The delivery control module is configured as follows: Based on feature information, it is detected whether the distal end of the guidewire is in the correct intervention path; When the distal end of the guidewire is in the correct intervention path, the guidewire is controlled to perform translational operations instead of rotational operations based on the guidewire delivery control parameters. If the distal end of the guidewire is not in the correct intervention path, the system controls a retraction of the guidewire, followed by a rotation and forward delivery of the guidewire based on the guidewire delivery control parameters. Specifically, when performing the rotation operation, the guidewire is initially rotated along a first direction, and when it is detected that the bending direction of the distal end of the guidewire is opposite to that of the target blood vessel branch, the guidewire rotates along a second direction opposite to the first direction.

9. A computer-readable storage medium, characterized in that, Instructions stored in the computer-readable storage medium, when run by at least one processor, cause the at least one processor to execute: Acquire vascular images; Feature information, including the relative pose of the distal guidewire and the blood vessel, is extracted from the vascular image. Based on feature information and fuzzy logic, guidewire delivery control parameters, including at least one of axial translation and radial rotation, are calculated; and Based on feature information and guidewire delivery control parameters, the guidewire delivery operation is performed.

10. A computer program product comprising computer instructions, characterized in that, The computer instructions, when run by at least one processor, cause the at least one processor to execute: Acquire vascular images; Feature information, including the relative pose of the distal guidewire and the blood vessel, is extracted from the vascular image. Based on feature information and fuzzy logic, guidewire delivery control parameters, including at least one of axial translation and radial rotation, are calculated; and Based on feature information and guidewire delivery control parameters, the guidewire delivery operation is performed.

Images