Hair extraction system and path planning method for hair follicle extraction

Abstract

The application provides a hair extraction system and a hair follicle extraction path planning method, and relates to the technical field of hair extraction. The system comprises an imaging device, a mechanical arm and a processor. The imaging device and the mechanical arm are respectively in communication connection with the processor. The imaging device is used for collecting a blood vessel distribution image of a surgical area and sending the blood vessel distribution image to the processor. The processor is used for determining a surgical forbidden area of the surgical area based on the blood vessel distribution image and controlling the mechanical arm to avoid the surgical forbidden area to perform hair extraction in the surgical area. The application determines the surgical forbidden area through the blood vessel distribution image, avoids the surgical forbidden area to perform hair extraction in the surgical area, reduces the frequent occurrence of blood vessel injury in the hair extraction process, and thus improves the surgical efficiency and accuracy.

Description

[0001] Priority Application

[0002] This application claims priority to Chinese Patent Application No. 2024109113780, filed on July 8, 2024, entitled “Path Planning Method for Hair Follicle Extraction, Device, Equipment, Medium and Program Product,” which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0003] The present application relates to the field of hair extraction technology, in particular, to a hair extraction system and a path planning method for hair follicle extraction. BACKGROUND

[0004] In recent years, autologous hair transplantation technology is the most mature and effective treatment for hair loss. The principle is to transplant healthy hair follicles from the back of the head to the balding area. After a period of growth, a natural and aesthetic result can be achieved. Hair transplantation robots have emerged, especially hair follicle extraction robot technology has developed rapidly. Although this technology has developed rapidly, there are frequent blood vessel injuries during the hair extraction process, which affects the efficiency and accuracy of the surgery. SUMMARY

[0005] The purpose of the embodiments of the present application is to provide a hair extraction system and a path planning method for hair follicle extraction to avoid the surgical restricted area for hair extraction, reduce the frequent blood vessel injuries during the hair extraction process, and improve the efficiency and accuracy of the surgery.

[0006] In a first aspect, the embodiments of the present application provide a hair extraction system, which includes an imaging device, a mechanical arm, and a processor. The imaging device and the mechanical arm are in communication with the processor. The imaging device is used to collect a blood vessel distribution image of a surgical area and send the blood vessel distribution image to the processor. The processor is used to determine a surgical restricted area of the surgical area based on the blood vessel distribution image and control the mechanical arm to avoid the surgical restricted area for hair extraction in the surgical area.

[0007] The embodiments of the present application collect a blood vessel distribution image of a surgical area by an imaging device and send the collected blood vessel distribution image to a processor. The processor determines a surgical restricted area based on the blood vessel distribution image and controls a mechanical arm to avoid the surgical restricted area for hair extraction in the surgical area, which reduces the frequent blood vessel injuries during the hair extraction process and improves the efficiency and accuracy of the surgery.

[0008] In some embodiments, the system further comprises a vision device configured to capture an image of the surgical region when the imaging device is turned on; the image of the surgical region comprises follicle distribution information; and the processor is further configured to generate a planned path of follicle extraction based on the follicle distribution information and the surgical exclusion zone, and control the robotic arm to extract follicles in the surgical region based on the planned path of follicle extraction.

[0009] The embodiment of the present application determines the follicle distribution information through the image of the surgical region captured by the vision device, so that the processor generates a planned path of follicle extraction in combination with the follicle distribution information and the surgical exclusion zone, and controls the robotic arm to extract follicles in the surgical region based on the planned path of follicle extraction, thereby reducing the situation of frequent blood vessel injury in the hair extraction process, and uniformly extracting follicles in the surgical region, improving the efficiency and accuracy of the operation.

[0010] In some embodiments, the system further comprises a display device in communication with the vision device, the display device being configured to receive and display the image of the surgical region sent by the vision device.

[0011] The embodiment of the present application facilitates the surgical personnel to observe the situation of the surgical region of the patient in real time through the display device, thereby improving the efficiency and accuracy of the operation.

[0012] In some embodiments, the imaging device comprises at least one of a near-infrared imaging device, an optical imaging device, an ultrasonic imaging device, a fluorescence imaging device, an optical coherence tomography device, a magnetic resonance imaging device, an electronic computed tomography device, a digital subtraction angiography device, a direct digital X-ray radiography device, and a computed radiography system.

[0013] The embodiment of the present application can determine the type of the imaging device according to the actual situation to match the situation of the operation, thereby improving the efficiency and accuracy of the operation.

[0014] In some embodiments, the imaging device is arranged on the robotic arm.

[0015] The embodiment of the present application arranges the imaging device on the robotic arm, which not only simplifies the structure of the hair extraction system, but also can obtain a more accurate blood vessel distribution image of the surgical region, thereby improving the efficiency and accuracy of the operation.

[0016] In some embodiments, the blood vessel distribution image comprises blood vessel distribution information; the processor is configured to determine a surgical exclusion zone of the surgical region based on the blood vessel distribution image, comprising: the processor determines the surgical exclusion zone based on the blood vessel distribution information; and the surgical exclusion zone is configured to represent a region where blood vessels are located in the surgical region.

[0017] In the embodiments of the present application, the blood vessel distribution information reflects the distribution of blood vessels in the operation region, therefore, the operation forbidden zone is determined based on the blood vessel distribution information in the blood vessel distribution image, the accuracy of the operation forbidden zone is improved, and thus the operation efficiency and accuracy are improved.

[0018] In some embodiments, the processor determines the operation forbidden zone based on the blood vessel distribution information, including: the processor parses the blood vessel distribution information to obtain position information of each blood vessel in the blood vessel distribution information; and the processor determines a blood vessel position based on the position information of each blood vessel, and takes a surrounding region at a ninth preset distance from the blood vessel position as the operation forbidden zone.

[0019] In the embodiments of the present application, the operation forbidden zone is set, so that the blood vessels and the surrounding region of the blood vessels are avoided as much as possible when the hair follicles are taken, the situation of frequently damaging the blood vessels is reduced, and the operation efficiency and accuracy are improved.

[0020] In some embodiments, the processor is further configured to generate a planned path for hair follicle extraction according to the hair follicle distribution information and the operation forbidden zone, including: the processor determines a path starting point of the planned path according to the hair follicle distribution information; and the processor traverses the hair follicle distribution information from the path starting point based on the operation forbidden zone to generate the planned path for hair follicle extraction.

[0021] In the embodiments of the present application, the path starting point of the planned path is determined based on the hair follicle distribution information, so that the traversal is started from the path starting point. In this process, the starting point of the traversal is combined with the specific situation of the hair follicle distribution, instead of being randomly selected, which not only realizes personalized path planning, but also reduces unnecessary repeated operations in the operation process, thereby improving the accuracy of path planning, reducing damage to blood vessels in the operation process, and improving the operation efficiency and accuracy.

[0022] In some embodiments, the path starting point includes a ninth starting point and a tenth starting point; the processor traverses the hair follicle distribution information from the path starting point based on the operation forbidden zone to generate the planned path for hair follicle extraction, including: the processor traverses the hair follicle distribution information from the ninth starting point to the direction of the tenth starting point based on the operation forbidden zone to generate a forward search path; the processor traverses the hair follicle distribution information from the tenth starting point to the direction of the ninth starting point based on the operation forbidden zone to generate a reverse search path; and the processor generates the planned path by using the forward search path and the reverse search path.

[0023] In the embodiments of the present application, the hair follicle distribution information of the operation region is traversed from the ninth starting point and the tenth starting point, which is equivalent to dividing the operation region image into two regions for traversal, thereby improving the traversal speed, and thus improving the generation speed of the planned path, and further improving the operation efficiency.

[0024] In some embodiments, the processor is further configured to: if there is an undesirable target point in the planned path, the undesirable target point is removed; the undesirable target point is used to represent a point where a hair follicle is not extracted during the hair follicle extraction surgery; or if there is an undesirable target point in the planned path, a midpoint between the undesirable target point and the next target point is determined, and at least one eighth adjacent node adjacent to the undesirable target point between the undesirable target point and the next target point; the eighth adjacent node with a distance less than a tenth preset distance from the midpoint is taken as a replacement point of the undesirable target point, so as to dynamically adjust the planned path according to the replacement point; the undesirable target point is used to represent a point where a hair follicle is not extracted during the hair follicle extraction surgery.

[0025] The embodiments of the present application consider that there may be an undesirable target point in the planned path in actual surgery, and in order to make the surgery proceed normally and reduce the influence of the operation on the blood vessels, the planned path needs to be dynamically adjusted, thereby improving the efficiency and accuracy of the surgery.

[0026] In a second aspect, the embodiments of the present application provide a path planning method for hair follicle extraction, which comprises: acquiring a surgical region image; the surgical region image comprises blood vessel distribution information and hair follicle distribution information; determining a surgical forbidden area based on the blood vessel distribution information; the surgical forbidden area is used to represent a region where the blood vessels are located in the surgical region; and generating a planned path for hair follicle extraction according to the hair follicle distribution information and the surgical forbidden area.

[0027] The embodiments of the present application determine the surgical forbidden area through the blood vessel distribution information, and generate the planned path for hair follicle extraction based on the surgical forbidden area and the hair follicle distribution information, which not only can reduce the frequent occurrence of blood vessel injury during the hair follicle extraction process, but also can more evenly extract the hair follicles, thereby improving the efficiency and accuracy of the surgery.

[0028] In some embodiments, the generating of the planned path for hair follicle extraction according to the hair follicle distribution information and the surgical forbidden area comprises: determining a path starting point of the planned path according to the hair follicle distribution information; and based on the surgical forbidden area, traversing the hair follicle distribution information from the path starting point to generate the planned path for hair follicle extraction.

[0029] The embodiments of the present application determine the path starting point of the path planning through the hair follicle distribution information before traversing the hair follicle distribution information based on the surgical forbidden area, so that the traversal starts from the path starting point. In this process, since the starting point of the traversal combines the specific conditions of the hair follicle distribution, rather than randomly selecting a path starting point to start the traversal, not only is the personalized path planning realized, but also a good path starting point can reduce unnecessary repeated operations during the surgery, thereby improving the accuracy of the path planning, reducing the damage to the blood vessels during the surgery, and improving the efficiency and accuracy of the surgery.

[0030] In some embodiments, the path starting point includes a first starting point and a second starting point; based on the surgical exclusion zone, the follicle distribution information is traversed from the path starting point to generate a planned path for follicle extraction, including: based on the surgical exclusion zone, the follicle distribution information is traversed from the first starting point to the direction of the second starting point to generate a forward search path; according to the surgical exclusion zone, the follicle distribution information is traversed from the second starting point to the direction of the first starting point to generate a reverse search path; and the planned path is generated through the forward search path and the reverse search path.

[0031] Embodiments of the present application traverse the follicle distribution information of the surgical area from the first starting point and the second starting point, which is equivalent to dividing the surgical area image into two regions for traversal, improving the traversal speed, thereby improving the generation speed of the planned path, and further improving the surgical efficiency.

[0032] In some embodiments, based on the operation forbidden area, the forward search path is generated by traversing the follicle distribution information from the first starting point to the second starting point, including: determining first adjacent nodes: determining at least one first adjacent node of the first starting point; determining first passability: calculating a first distance between the first starting point and each first adjacent node, and determining whether each first adjacent node is located in the operation forbidden area; if there is a second adjacent node with a first distance greater than a first preset distance in the first adjacent nodes, the second adjacent node is removed; if there is a third adjacent node located in the operation forbidden area in the first adjacent nodes, the third adjacent node is removed; the remaining nodes in the first adjacent nodes are used as first passable nodes; determining a first target node: calculating the path cost of each first passable node, and determining a first target node in the first passable nodes based on the path cost; the first target node is used as a third starting point, and the steps of determining the first adjacent nodes, determining the first passability, and determining the first target node are repeatedly executed until the forward search path is generated; or, according to the operation forbidden area, the reverse search path is generated by traversing the follicle distribution information from the second starting point to the first starting point, including: determining fourth adjacent nodes: determining at least one fourth adjacent node of the second starting point; determining second passability: calculating a second distance between the second starting point and each fourth adjacent node, and determining whether each fourth adjacent node is located in the operation forbidden area; if there is a fifth adjacent node with a second distance greater than a second preset distance in the fourth adjacent nodes, the fifth adjacent node is removed; if there is a sixth adjacent node located in the operation forbidden area in the fourth adjacent nodes, the sixth adjacent node is removed; the remaining nodes in the fourth adjacent nodes are used as second passable nodes; determining a second target node: calculating the path cost of each second passable node, and determining a second target node in the second passable nodes based on the path cost; the second target node is used as a fourth starting point, and the steps of determining the fourth adjacent nodes, determining the second passability, and determining the second target node are repeatedly executed until the reverse search path is generated.

[0033] In the traversal process, the first target node in the first passable nodes is determined based on the path cost in the embodiments of the present application, so as to select one first target node from a plurality of first adjacent nodes, and finally the first target node is used as the next node of the current node. This process selects one first target node from a plurality of first passable nodes based on the path cost, so as to find the path with the minimum cost, and further improves the efficiency and accuracy of the operation. In addition, one second target node is selected from a plurality of second passable nodes based on the path cost, so as to find the path with the minimum cost, and further improves the efficiency and accuracy of the operation.

[0034] In some embodiments, the planning path is generated by the forward search path and the reverse search path, including: if the forward search path and the reverse search path meet, the planning path is generated by the forward search path and the reverse search path; if the forward search path and the reverse search path do not meet, a new first starting point and a new second starting point are determined based on the forward search path and the reverse search path, and path planning is performed according to the new first starting point and the new second starting point to generate the planning path.

[0035] The embodiments of the present application consider that there may be meeting or non-meeting situations when path planning is performed on the surgical area. For the non-meeting situation, the starting point and the ending point need to be re-determined, and path planning is performed based on the re-determined starting point and ending point, thereby improving the robustness and flexibility of the overall path planning.

[0036] In some embodiments, the surgical forbidden area is determined based on the blood vessel distribution information, including: analyzing the blood vessel distribution information to obtain position information of each blood vessel in the blood vessel distribution information; determining a blood vessel position based on the position information of each blood vessel, and taking a surrounding area within a fifth preset distance from the blood vessel position as the surgical forbidden area.

[0037] The embodiments of the present application set the surgical forbidden area, so that the blood vessels and the surrounding area of the blood vessels are avoided as much as possible during path planning, thereby reducing the situation of frequently damaging blood vessels and improving the efficiency and accuracy of the surgery.

[0038] In some embodiments, the surgical area image is obtained, including: obtaining a first image collected by a near-infrared imager and a second image collected by a vision system; the first image and the second image are images collected when the near-infrared imager is turned on; fusing the first image and the second image to generate the surgical area image; or obtaining a third image collected by the vision system when the near-infrared imager is turned on as the surgical area image.

[0039] The embodiments of the present application fuse the first image and the second image to generate the surgical area image, so that the blood vessel position in the surgical area image is more accurate, and the difference between the blood vessels and the hair follicles is more obvious, thereby improving the efficiency and accuracy of the surgery. Or directly taking the third image collected by the vision system as the surgical area image, thereby improving the efficiency of obtaining the surgical area image and further improving the efficiency of the surgery.

[0040] In some embodiments, after the planning path of hair follicle extraction is generated according to the hair follicle distribution information and the operation forbidden area, the method further includes: if there is an undesirable target point in the planning path, the undesirable target point is removed; the undesirable target point is used to represent a point where a hair follicle that is not extracted during the hair follicle extraction operation is located; or if there is an undesirable target point in the planning path, a midpoint of the undesirable target point and a next target point is determined, and at least one seventh adjacent node adjacent to the undesirable target point between the undesirable target point and the next target point; a seventh adjacent node with a distance less than a sixth preset distance from the midpoint is taken as a replacement point of the undesirable target point, so as to dynamically adjust the planning path according to the replacement point; the undesirable target point is used to represent a point where a hair follicle that is not extracted during the hair follicle extraction operation is located.

[0041] The embodiments of the present application consider that there may be an undesirable target point in the planning path in actual operation, and in order to make the operation proceed normally and reduce the influence of the operation on blood vessels, it is necessary to dynamically adjust the planning path, thereby improving the efficiency and accuracy of the operation.

[0042] In a third aspect, the embodiments of the present application provide a hair extraction method, which includes: extracting hair according to the planning path of hair follicle extraction; the planning path of hair follicle extraction is obtained by any one of the embodiments of the second aspect.

[0043] The embodiments of the present application improve the efficiency and accuracy of hair extraction during the operation by planning the path.

[0044] In a fourth aspect, the embodiments of the present application provide a path planning device for hair follicle extraction, which includes: an acquisition module configured to acquire an operation region image; the operation region image includes blood vessel distribution information and hair follicle distribution information; a determination module configured to determine an operation forbidden area based on the blood vessel distribution information; the operation forbidden area is used to represent a region where a blood vessel is located in the operation region; and a generation module configured to generate a planning path of hair follicle extraction according to the hair follicle distribution information and the operation forbidden area.

[0045] In a fifth aspect, the embodiments of the present application provide an electronic device, which includes: a processor and a memory, the memory stores machine readable instructions executable by the processor, and the machine readable instructions are executed by the processor to perform the method steps of any one of the embodiments of the second aspect, the third aspect or both aspects.

[0046] In a sixth aspect, the embodiments of the present application provide a non-transitory computer readable storage medium, which includes: the computer readable storage medium stores computer instructions, and the computer instructions make the computer execute the method steps of any one of the embodiments of the second aspect, the third aspect or both aspects.

[0047] In a seventh aspect, an embodiment of the present application provides a computer program product, comprising: a computer program, when executed by a processor, performs the method steps of the second aspect, the third aspect, or any one of the embodiments of the two aspects.

[0048] Other features and advantages of the present application will be described in the following description, and in part will become apparent to those skilled in the art upon examination of the following description and figures, or can be learned by practice of the application as described in the following description. The objects and advantages of the application can be realized and attained by means of the instrumentalities and combinations particularly pointed out in the appended claims. BRIEF DESCRIPTION OF DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments of the present application. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation to the scope, and for those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0050] Figure 1 A flowchart of a path planning method for hair follicle extraction provided by an embodiment of the present application;

[0051] Figure 2 A schematic diagram of the positional relationship between a near-infrared imager and a vision system provided by an embodiment of the present application;

[0052] Figure 3 A schematic diagram of a surgical area provided by an embodiment of the present application;

[0053] Figure 4 A schematic diagram of path planning provided by an embodiment of the present application;

[0054] Figure 5 A structural schematic diagram of a path planning device for hair follicle extraction provided by an embodiment of the present application;

[0055] Figure 6 A structural schematic diagram of a hair extraction system provided by an embodiment of the present application;

[0056] Figure 7 A structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0057] The embodiments of the technical solutions of the present application will be described in detail below with reference to the drawings. The following embodiments are only used to more clearly illustrate the technical solutions of the present application, and therefore only serve as examples, and cannot limit the protection scope of the present application.

[0058] It should be noted that all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "include" and "have" in the specification and claims of the present application and the above description of the drawings are intended to cover non-exclusive inclusion.

[0059] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "a plurality of" is two or more, unless otherwise explicitly and specifically limited.

[0060] In recent years, autologous hair transplantation technology is the most mature and effective treatment method for hair loss at present, and its principle is to transplant healthy hair follicles in the occipital region to the hair loss site, and after a period of growth, the natural and aesthetic effect can be achieved. In recent years, hair transplantation robot, especially hair follicle extraction robot technology has developed rapidly.

[0061] Taking the hair extraction process as an example, the hair extraction process usually needs to use a surgical needle to select healthy hair follicles in the occipital region. Considering that the surface layer of the occipital region has blood vessel distribution (head vein), in the hair extraction process, these blood vessels need to be avoided to avoid unnecessary damage. In the process of manual extraction by doctors, the blood vessels can be avoided as much as possible by relying on the experience and feeling of doctors, but it is still impossible to completely avoid. And for the extraction process of the surgical robot, it is more necessary to consider how to avoid these blood vessels to avoid unnecessary damage.

[0062] The inventors have found through long-term research that if blood vessel damage frequently occurs during the operation, the following consequences may occur:

[0063] 1. Cause a large amount of bleeding, which will affect the operation effect. Especially for patients with low blood coagulation level, damage to blood vessels (especially thicker veins) will cause a large amount of bleeding in the occipital region. The usual treatment method is to need to frequently wipe the bleeding site so that the doctor can clearly see the position of the hair follicle, but this treatment method will cause the operation time to be prolonged, which will affect the operation effect.

[0064] 2. Increased risk of infection: Blood vessel damage can lead to local or systemic infection. If the needle puncture site is not properly disinfected, it can become a way for bacteria to invade.

[0065] 3. Thrombosis: Repeated blood vessel damage can cause damage to the inner wall of the blood vessel, increasing the risk of thrombosis. Thrombosis can cause blood flow to be blocked, and in severe cases it can even cause deep vein thrombosis.

[0066] 4. Phlebitis: Phlebitis refers to inflammation of the vein wall, often accompanied by pain, redness, and heat. Long-term or improper intravenous injections can lead to phlebitis.

[0067] 5. Scarring and tissue damage: Frequent needle pricking can cause scarring and damage to the tissue surrounding the vein, sometimes even leading to vein occlusion.

[0068] 6. Varicose veins: Long-term vein damage can cause the vein wall to weaken and expand, forming varicose veins. This not only affects the appearance, but can also cause pain and discomfort.

[0069] 7. Impaired vein function: Repeated vein damage can lead to long-term impairment of vein function, affecting blood return.

[0070] 8. Arteriovenous fistula: If the blood vessels are damaged and grow abnormally, an arteriovenous fistula may develop, leading to other complications.

[0071] 9. Patients experience pain or itching during or after surgery.

[0072] 10. After nerve damage, patients may experience neuropathic pain, a complication that can last for months or even years.

[0073] To effectively solve the above problems, the embodiments of the present application provide a path planning method for hair follicle extraction, which is used to plan the extraction path of hair follicles during the hair follicle extraction surgery process, reduce the frequent occurrence of blood vessel damage during the hair follicle extraction process, and thereby improve the efficiency and accuracy of the surgery.

[0074] Optionally, Figure 1 The flowchart of the path planning method for hair follicle extraction provided by the embodiments of the present application is shown. It can be understood that the path planning method for hair follicle extraction provided by the embodiments of the present application can be applied to terminal devices (also referred to as electronic devices) and servers; the terminal device can be specifically a smart phone, a tablet computer, a computer, a personal digital assistant (Personal Digital Assistant, PDA), etc.; the server can be specifically an application server or a Web server. In order to facilitate understanding of the technical solutions provided by the embodiments of the present application, the application scenario of the path planning method for hair follicle extraction provided by the embodiments of the present application is introduced below with the server as an example.

[0075] Since the path planning method for hair follicle extraction provided in the embodiments of the present application is used to plan the path for hair follicle extraction in the hair follicle extraction surgery, before the method is executed, preoperative preparation for the hair follicle extraction surgery needs to be performed, including: shaving the surgical area of the patient and sterilizing the surgical area and its surgical consumables (such as a hair extraction needle). In addition, the surgical area of the patient is placed in a suitable position so that the surgical robot can operate the surgical area of the patient.

[0076] When the path planning is performed, as shown in Figure 1 the method includes the following steps.

[0077] In step S101, the server acquires a surgical area image; the surgical area image includes blood vessel distribution information and hair follicle distribution information.

[0078] Since it is necessary to avoid blood vessels in the surgical area as much as possible during the surgery, a specific imaging technology is needed to enhance the visual information of the blood vessels in the surgical area, so that the blood vessel distribution information in the obtained surgical area image is clear and visible.

[0079] Optionally, in the embodiments of the present application, the surgical area image is acquired by combining a near-infrared imager and a vision system.

[0080] The near-infrared imager emits near-infrared light to the surgical area. Since the absorption rate of hemoglobin in blood to red light is high, after the blood vessels are irradiated by the near-infrared light, the color of the blood vessel area is darker than that of other non-blood vessel areas. Thus, a color difference is generated between the blood vessel area and the non-blood vessel area, thereby dividing the blood vessel area and the non-blood vessel area.

[0081] The vision system is used to collect the image of the surgical area when the near-infrared imager is turned on, and an image processing technology is used to extract the blood vessel distribution information and the hair follicle distribution information therefrom.

[0082] The near-infrared imager refers to an instrument or device capable of emitting near-infrared light. The vision system can be a binocular camera / trinocular camera, a camera, or other types of devices with image acquisition functions.

[0083] After the server acquires the surgical area image, the blood vessel distribution information and the hair follicle distribution information in the surgical area image can be obtained. The blood vessel distribution information includes one or more of the position information of each blood vessel in the surgical area, the thickness information of the blood vessel, and the type information of the blood vessel, and the hair follicle distribution information includes one or more of the position information of each hair follicle in the surgical area, the attitude information, and the hair follicle distribution situation.

[0084] It should be noted that the vision system and the near-infrared imager can be an integrated device integrated on the surgical robot, can be a separate device respectively installed at a suitable position of the surgical robot and detachable, or can be a device respectively provided on other surgical equipment independent of the surgical robot, as long as the shooting range of the vision system and the near-infrared imager can cover the surgical area.

[0085] Optionally, Figure 2 A schematic diagram of a positional relationship between a near-infrared imager and a vision system provided in an embodiment of the present application is shown in FIG. 1. Figure 2 As shown in FIG. 1, the vision system and the near-infrared imager are respectively and independently provided above a surgical area to collect images of the surgical area. The surgical area includes blood vessels and a hair follicle to be taken.

[0086] In step S102, the server determines a surgical forbidden area based on the blood vessel distribution information. The surgical forbidden area is used to represent a region where the blood vessels are located in the surgical area.

[0087] Optionally, the blood vessel distribution information can be obtained through the surgical area image, but there are also accompanying nerves around the blood vessels.

[0088] Since the accompanying nerves are responsible for transmitting deep touch and proprioception, if damaged, one or more of the following situations may occur: sensory loss or abnormality in the surgical area, chronic pain or abnormal pain sensation, affecting the healing process of the surgical area, increasing the risk of infection, etc. The accompanying nerves have low absorption of near-infrared light, and the blood vessel distribution information can be determined through the surgical area image, but it is difficult to determine the position of the accompanying nerves around the blood vessels.

[0089] In addition, during the operation, a fault tolerance space should be given to further reduce the influence on the blood vessels and improve the efficiency and accuracy of the operation.

[0090] Therefore, in order to reduce the damage to the blood vessels and the accompanying nerves during the operation, it is necessary to determine the surgical forbidden area based on the blood vessel distribution information, and the surgical forbidden area is used to represent the region where the blood vessels are located in the surgical area, which includes the blood vessels and the region near the blood vessels.

[0091] Based on this, the surgical forbidden area is set to lay a foundation for improving the efficiency and accuracy of the operation.

[0092] Figure 3 A schematic diagram of a surgical area provided in an embodiment of the present application is shown in FIG. 2. Figure 3 As shown in FIG. 2, the surgical area includes blood vessels, a surgical path, a hair follicle to be taken, and a surgical forbidden area. The surgical path is a region where the hair follicle to be taken and the dashed arrow are connected, and the surgical forbidden area is a region including the blood vessels and the region around the blood vessels.

[0093] In step S103, the server generates a planned path for hair follicle extraction according to the hair follicle distribution information and the operation forbidden area.

[0094] Optionally, after obtaining the hair follicle distribution information and the operation forbidden area, the server can plan a path for hair follicle extraction in a hair follicle extraction operation based on the hair follicle distribution information and the operation forbidden area, so as to extract the hair follicles in the operation area through the planned path.

[0095] It should be noted that the planned path for hair follicle extraction generated based on the operation forbidden area and the hair follicle distribution information can not only reduce the blood vessel damage and the accompanying nerve damage in the operation process, but also more evenly extract the hair follicles, thereby improving the operation effect.

[0096] In some embodiments, generating the planned path for hair follicle extraction according to the hair follicle distribution information and the operation forbidden area includes: determining a path starting point of the planned path according to the hair follicle distribution information; and based on the operation forbidden area, traversing the hair follicle distribution information from the path starting point to generate the planned path for hair follicle extraction.

[0097] Optionally, the path starting point of the planned path is determined through the hair follicle distribution information in the operation area image.

[0098] It should be noted that the determined path starting point can be one or multiple.

[0099] When there is only one path starting point, the hair follicle distribution information is traversed from the path starting point based on the operation forbidden area, thereby generating the planned path for hair follicle extraction. When traversing, any one of A* algorithm, random generated tree, greedy algorithm, Dijkstra algorithm, depth-first search algorithm, breadth-first search algorithm, and self-defined search algorithm, or a combination of multiple algorithms can be used. The algorithm can be set according to actual needs. It should be understood that the traversal algorithm includes but is not limited to the above-mentioned algorithms.

[0100] When there are multiple path starting points, each path starting point in the multiple path starting points can be used as a path starting point of a single planned path, and the hair follicle distribution information is traversed from the path starting point based on the operation forbidden area, thereby generating multiple planned paths. Finally, the best path is selected from the multiple planned paths as the final planned path.

[0101] At this time, since the multiple planned paths generated are independent of each other, the essence of the traversal is the same as that when there is only one path starting point. Therefore, when traversing, any one of A* algorithm, random generated tree, greedy algorithm, Dijkstra algorithm, depth-first search algorithm, breadth-first search algorithm, and self-defined search algorithm, or a combination of multiple algorithms can be used. The algorithm can be set according to actual needs.

[0102] When there are multiple path starting points, any two of the multiple path starting points can be regarded as mutually associated path starting points.

[0103] For example, if the multiple path starting points are two path starting points, which are respectively a first starting point and a second starting point, when traversing, the server generates a forward search path by traversing the hair follicle distribution information from the first starting point to the direction of the second starting point based on the surgery forbidden area, generates a reverse search path by traversing the hair follicle distribution information from the second starting point to the direction of the first starting point based on the surgery forbidden area, and finally generates a planning path according to the forward search path and the reverse search path. For the specific process of generating the planning path in this way, please refer to the following embodiments, which will not be described here.

[0104] If the multiple path starting points are three path starting points, two of them can be regarded as mutually associated path starting points, and the other one can be regarded as a separate path starting point, and the traversal process is performed respectively.

[0105] If the multiple path starting points are four path starting points, they can be combined two by two to generate mutually associated path starting points, and the traversal process is performed respectively. The traversal process of other number of path starting points is similar.

[0106] It should be noted that since the two path starting points are mutually associated path starting points, when traversing, it is traversed in the same direction from the two path starting points. Therefore, the traversal process involves a bidirectional traversal algorithm, at this time, any one or more of bidirectional A* algorithm, bidirectional random spanning tree, bidirectional greedy algorithm, bidirectional Dijkstra algorithm, and self-defined bidirectional search algorithm, or a combination of multiple unidirectional traversal algorithms can be used to realize bidirectional traversal. The algorithm can be set according to actual needs.

[0107] For example, the combination of multiple unidirectional traversal algorithms to realize bidirectional traversal can be that A* algorithm is used when generating a forward search path, and Dijkstra algorithm is used when generating a reverse search path.

[0108] Before traversing the hair follicle distribution information based on the surgery forbidden area, the path starting point of the path planning is determined by the hair follicle distribution information in the embodiment of the application, so that the traversal starts from the path starting point. In this process, since the starting point of the traversal combines the specific situation of the hair follicle distribution, rather than randomly selecting a path starting point to start the traversal, not only is the personalized path planning realized, but also a good path starting point can reduce unnecessary repeated operations in the surgery process, thereby improving the accuracy of the path planning, reducing the damage to blood vessels during the surgery process, and improving the efficiency and accuracy of the surgery.

[0109] In some embodiments, the path starting point includes a first starting point and a second starting point; based on the surgical forbidden area, the hair follicle distribution information is traversed from the path starting point to generate a planned path for hair follicle extraction, including: the server traverses the hair follicle distribution information from the first starting point in the direction of the second starting point based on the surgical forbidden area to generate a forward search path; the server traverses the hair follicle distribution information from the second starting point in the direction of the first starting point based on the surgical forbidden area to generate a reverse search path; the server generates a planned path through the forward search path and the reverse search path.

[0110] Optionally, in order to further quickly generate the planned path and perform the surgery as soon as possible, the first starting point and the second starting point of the planned path can be determined by the hair follicle distribution information in the surgical area image. In this case, the path starting point includes the first starting point and the second starting point.

[0111] Figure 4 A schematic diagram of a path planning provided in an embodiment of the present application is shown as follows: Figure 4 As shown, the point where the hair follicle is located in the upper left corner of the surgical area image is defined as the first starting point, and the point where the hair follicle is located in the lower right corner of the surgical area image is defined as the second starting point. The gray box area in the surgical area image is regarded as a surgical restricted area, and the black dots are regarded as other hair follicles except the first and second starting points. The black line between the first and second starting points represents the planned path, which is composed of various hair follicle points.

[0112] It should be understood that the positions of the first starting point and the second starting point can be set at other locations in the surgical area image according to actual circumstances. For example, the point where the hair follicles are located in the upper right corner of the surgical area image is defined as the first starting point, and the point where the hair follicles are located in the lower left corner of the surgical area image is defined as the second starting point. Alternatively, the point where the hair follicles are located in the upper left corner of the surgical area image is defined as the second starting point, and the point where the hair follicles are located in the lower right corner of the surgical area image is defined as the first starting point.

[0113] Exemplarily, the server traverses the hair follicle distribution information from the first starting point toward the second starting point based on the surgical restricted area to generate a forward search path; the server traverses the hair follicle distribution information from the second starting point toward the first starting point based on the surgical restricted area to generate a reverse search path.

[0114] The specific process of generating the forward search path and the reverse search path is described in the following embodiment and will not be repeated here.

[0115] It should be noted that the server can generate both forward and reverse search paths based on the surgical restricted area simultaneously. Alternatively, the server can start generating the forward search path first, then after a certain period of time, start generating the reverse search path. Alternatively, the server can start generating the reverse search path first, then after a certain period of time, start generating the forward search path. The specific steps can be implemented based on the actual algorithm settings.

[0116] After generating the forward search path and the reverse search path, the server generates a planned path through the forward search path and the reverse search path.

[0117] It should also be noted that if the collected surgical area image is a three-dimensional image, in order to facilitate traversal of the hair follicle distribution information in the surgical area and improve traversal efficiency, the three-dimensional image can be mapped into a two-dimensional image.

[0118] 3D point Projected point on a two-dimensional plane The mapping relationship is:

[0119]

[0120] in, Represents the horizontal coordinate of a three-dimensional point, represents the vertical coordinate of a three-dimensional point, Represents the vertical coordinate of a three-dimensional point, represents the horizontal coordinate of a two-dimensional point, represents the vertical coordinate of a two-dimensional point, Indicates the distance between the projection plane and the viewpoint.

[0121] The embodiment of the present application traverses the hair follicle distribution information of the surgical area from the first starting point and the second starting point, which is equivalent to dividing the surgical area image into two areas for traversal, thereby improving the traversal speed, thereby improving the speed of generating the planned path, and further improving the surgical efficiency.

[0122] In some embodiments, the server generates the forward search path based on the surgery forbidden area, starting from the first starting point, traversing the hair follicle distribution information in the direction of the second starting point, including: determining the first adjacent node: determining at least one first adjacent node of the first starting point; judging the first passability: calculating the first distance between the first starting point and each first adjacent node, and judging whether each first adjacent node is located in the surgery forbidden area; if there is a second adjacent node in the first adjacent node whose first distance is greater than the first preset distance, the second adjacent node is removed; if there is a third adjacent node in the first adjacent node located in the surgery forbidden area, the third adjacent node is removed; the remaining nodes in the first adjacent node are taken as the first passable node; determining the first target node: calculating the path cost of each first passable node, and determining the first target node in the first passable node based on the path cost; taking the first target node as the third starting point, repeating the steps of determining the first adjacent node, judging the first passability, and determining the first target node, until the forward search path is generated.

[0123] Optionally, the server generates the forward search path based on the surgery forbidden area, starting from the first starting point, traversing the hair follicle distribution information in the direction of the second starting point, including: determining the first adjacent node, judging the first passability, and determining the first target node.

[0124] Determining the first adjacent node: determining at least one first adjacent node of the current node. For example, the at least one first adjacent node can include 4 first adjacent nodes, which are the nodes in the up, down, left and right directions of the current node, can also include 8 first adjacent nodes, which are the nodes in the up, down, left, right and four diagonal directions of the current node, and can also include 6 first adjacent nodes limited in certain directions. In actual application, the number of first adjacent nodes of the current node is determined according to specific problems. It should be noted that the first starting point is taken as the current node at the beginning of traversal.

[0125] Checking the first passability: checking the passability of each first adjacent node. Since the first adjacent node of the current node can be located in the surgery forbidden area, or the distance between the current node and the first adjacent node can be too far, and these two types of nodes should not be taken as the candidate target adjacent node.

[0126] Therefore, for each first adjacent node of the current node, the first distance between the current node and each first adjacent node should be calculated, and whether each first adjacent node is located in the surgery forbidden area should be judged; if there is a second adjacent node in the first adjacent node whose first distance is greater than the first preset distance, the second adjacent node is removed; if there is a third adjacent node in the first adjacent node located in the surgery forbidden area, the third adjacent node is removed; the remaining nodes in the first adjacent node are taken as the first passable node.

[0127] wherein the first preset distance is a value preset in advance, and can be set according to actual conditions.

[0128] The determining the first target node comprises updating the g value, selecting the first target node and joining the forward queue:

[0129] The updating the g value: using a g value updating formula to calculate the g value from the current node to each first passable node, wherein the g value represents the actual path cost from the current node to the first passable node:

[0130]

[0131] wherein, represents that the traversal is from the first starting point to the second starting point, i.e. forward traversal. is the g value of the current node. is the actual path cost from the current node to the first passable node . represents the horizontal coordinate of the first passable node, represents the vertical coordinate of the first passable node, represents the horizontal coordinate of the current node, represents the vertical coordinate of the current node. If the path just starts, the first starting point and the current node are the same point.

[0132] The selecting the first target node: after calculating the g value of each first passable node, the first target node is selected according to the f value. The f value is the sum of the g value and the h value, and the h value represents the heuristic estimate value, i.e. the estimated path cost from the first passable node to the first terminal point. The f value represents the comprehensive estimated cost from the current node through the first passable node to the second starting point.

[0133] The formula of the h value is as follows:

[0134]

[0135] wherein, represents the estimated path cost from the first passable node to the second starting point, i.e. the estimated distance from the first passable node to the second starting point. represents the horizontal coordinate of the first passable node, represents the vertical coordinate of the first passable node, represents the horizontal coordinate of the second starting point, represents the vertical coordinate of the second starting point.

[0136] The formula of the f value is as follows:

[0137]

[0138] wherein, represents the comprehensive estimated cost from the current node to the second starting point through the first passable node.

[0139] Join the forward queue: after selecting the first target node through the f value, the first target node is added to the forward queue, and its updated g value and f value are attached, for subsequent processing.

[0140] It should be noted that the forward queue is a pre-initialized empty queue, which is used to store the first target node determined when traversing from the first starting point to the second starting point.

[0141] In the traversal process, the first target node in the first passable node is determined based on the path cost, so as to determine one first target node from multiple first adjacent nodes, and finally take the first target node as the next node of the current node. This process selects one first target node from multiple first passable nodes based on the path cost, so as to find the path with the minimum cost, and further improve the efficiency and accuracy of the operation.

[0142] In some embodiments, the server traverses the follicle distribution information from the second starting point to the first starting point based on the operation forbidden area to generate a reverse search path, including: determining a fourth adjacent node: determining at least one fourth adjacent node of the second starting point; judging the second passability: calculating the second distance between the second starting point and each fourth adjacent node, and judging whether each fourth adjacent node is located in the operation forbidden area; if there is a fifth adjacent node with a second distance greater than the second preset distance in the fourth adjacent node, the fifth adjacent node is removed; if there is a sixth adjacent node located in the operation forbidden area in the fourth adjacent node, the sixth adjacent node is removed; the remaining nodes in the fourth adjacent node are taken as second passable nodes; determining a second target node: calculating the path cost of each second passable node, and determining a second target node in the second passable node based on the path cost; taking the second target node as the fourth starting point, repeating the steps of determining the fourth adjacent node, judging the second passability, and determining the second target node, until the reverse search path is generated.

[0143] Optionally, the server traverses the follicle distribution information from the second starting point to the first starting point based on the operation forbidden area to generate a reverse search path, including: determining a fourth adjacent node, judging the second passability, and determining a second target node.

[0144] The second preset distance is a pre-set value, which can be set according to actual conditions. Considering that in one operation area, the area where the first starting point is located and the area where the second starting point is located also have differences in blood vessel distribution and follicle distribution, therefore, the second preset distance and the first preset distance can be the same or different.

[0145] In determining the second target node, including updating g value, selecting the second target node and joining the backward queue:

[0146] Updating g value: using g value update formula to calculate the g value from the current node to each second passable node, wherein g value represents the actual path cost from the current node to the second passable node:

[0147]

[0148] Wherein, Indicates that from the second starting point, the direction of the first starting point is traversed, that is, backward traversal. Is the g value of the current node. Is the actual path cost from the current node to the second passable node . Indicates the horizontal coordinate of the second passable node, Indicates the vertical coordinate of the second passable node, Indicates the horizontal coordinate of the current node, Indicates the vertical coordinate of the current node. If the path just starts, the second starting point and the current node are the same point.

[0149] Selecting the second target node: after calculating the g value of each second passable node, the second target node is selected according to the f value.

[0150] The formula of h value is as follows:

[0151]

[0152] Wherein, Indicates the estimated path cost from the second passable node to the first starting point, that is, the estimated distance from the second passable node to the first starting point. Indicates the horizontal coordinate of the second passable node, Indicates the vertical coordinate of the second passable node, Indicates the horizontal coordinate of the first starting point, Indicates the vertical coordinate of the first starting point.

[0153] The formula of f value is as follows:

[0154]

[0155] Wherein, Indicates the comprehensive estimated cost from the current node through the second passable node to the first starting point.

[0156] Adding the second target node to the backward queue after selecting the second target node through the f value, and attaching the updated g value and f value of the second target node to the backward queue for subsequent processing.

[0157] It should be noted that the backward queue is a pre-initialized empty queue, which is used to store the second target node determined when traversing from the second starting point to the first starting point.

[0158] For the rest of the process, please refer to the above embodiment, which will not be repeated here.

[0159] In the traversal process, the embodiment of the present application selects a second target node from a plurality of second passable nodes based on path cost to find the path with the minimum cost, thereby further improving the efficiency and accuracy of the operation.

[0160] In some embodiments, the server generates a planning path by forward searching a path and reverse searching a path, including: if the forward searched path and the reverse searched path meet, generating the planning path by the forward searched path and the reverse searched path; if the forward searched path and the reverse searched path do not meet, determining a new first starting point and a new second starting point based on the forward searched path and the reverse searched path, and generating the planning path according to the new first starting point and the new second starting point.

[0161] Optionally, the follicle distribution of the operation area is traversed from the first starting point and the second starting point. Moreover, the distribution of blood vessels in the operation area is complex, and the distribution of blood vessels and the distribution of follicles are different in different operation areas. Therefore, the forward searched path and the reverse searched path may meet or not meet during the traversal process.

[0162] If the forward searched path and the reverse searched path meet, it indicates that there is a passable path between the first starting point and the second starting point in the operation area, as shown in the content of Figure 4 The planning path has a meeting point.

[0163] At this time, the forward searched path and the reverse searched path are connected at the meeting point to generate the planning path by the forward searched path and the reverse searched path. That is, the forward queue and the backward queue are merged, and the values in the merged queue are used to generate the planning path.

[0164] If the forward search path and the reverse search path do not meet, it indicates that there is a blood vessel obstruction between the first starting point and the second starting point in the operation area, and connection cannot be made. At this time, the path planning algorithm records the area where the path is blocked, and takes the two points that were not successfully connected last time as the new starting points (defined as s0 and s1 points) of the two blocked areas, and defines the points farthest from the newly generated two starting points (s0 and s1) in the corresponding areas as the end points (defined as e0 and e1 points). After the feasible paths of the starting points and the end points are found, they are connected, and at this time, it is considered that the path planning of the s0e0 area and the s1e1 area is found.

[0165] That is, when the forward search path and the reverse search path do not meet, new first starting points and new second starting points need to be determined based on the forward search path and the reverse search path, and path planning is performed according to the new first starting points and the new second starting points to generate a planning path.

[0166] The steps of performing path planning according to the new first starting points and the new second starting points to generate a planning path are as follows:

[0167] Determine the first new starting point: take the last point in the forward search path as a fifth starting point, and take the last point in the reverse search path as a sixth starting point;

[0168] Determine the second new starting point: determine a seventh starting point of the fifth starting point, and determine an eighth starting point of the sixth starting point;

[0169] Traversal: based on the operation forbidden area, start from the fifth starting point and traverse the hair follicle distribution information in the direction of the seventh starting point to generate a first sub-planning path; and based on the operation forbidden area, start from the seventh starting point and traverse the hair follicle distribution information in the direction of the fifth starting point to generate a second sub-planning path;

[0170] In addition, based on the operation forbidden area, start from the sixth starting point and traverse the hair follicle distribution information in the direction of the eighth starting point to generate a third sub-planning path; and based on the operation forbidden area, start from the eighth starting point and traverse the hair follicle distribution information in the direction of the sixth starting point to generate a fourth sub-planning path;

[0171] If the first sub-planning path and the second sub-planning path do not meet, the steps of determining new starting points, determining new end points, and traversing are repeatedly performed until the newly generated first sub-planning path and the newly generated second sub-planning path meet;

[0172] If the third sub-planning path and the fourth sub-planning path do not meet, the steps of determining the first new starting point, determining the second new starting point, and traversing are repeatedly performed until the newly generated third sub-planning path and the newly generated fourth sub-planning path meet.

[0173] An initial planning path is generated based on the meeting sub-planning paths.

[0174] Therefore, in one surgical area, there can be multiple planning paths that are independent of each other. One planning path can be regarded as one hair taking process.

[0175] Embodiments of the present application consider that when planning a path for a surgical area, there can be a meeting or non-meeting situation. For the non-meeting situation, the starting point and the ending point need to be re-determined, and path planning is performed based on the re-determined starting point and ending point, thereby improving the robustness and flexibility of the overall path planning.

[0176] In some embodiments, considering that for different patients or different surgical areas of a patient, the image boundary is exactly the position of the blood vessel distribution, at this time, the blood vessel position should be avoided, therefore, when the server determines the path starting point of the planning path according to the hair follicle distribution information, the path starting point should be determined in the non-blood vessel area.

[0177] Therefore, when the server determines the path starting point of the planning path according to the hair follicle distribution information, first, the initial path starting point of the planning path is determined according to the hair follicle distribution information, if the initial path starting point is not in the surgical forbidden area, the initial path starting point is taken as the path starting point; if the initial path starting point is in the surgical forbidden area, the hair follicle distribution information is searched with the initial path starting point as the center and the eighth preset distance as the radius, and a point located in the search area, closest to the initial path starting point, and not in the surgical forbidden area is taken as the path starting point.

[0178] The eighth preset distance is a pre-set value. It can be set according to actual conditions.

[0179] Similarly, since the server can determine the first starting point and the second starting point of the planning path through the hair follicle distribution information in the surgical area image, the first starting point and the second point should also be determined in the non-blood vessel area.

[0180] At this time, when the server determines the first starting point and the second starting point of the planning path according to the hair follicle distribution information, first, the initial first starting point and the initial second starting point are determined according to the hair follicle distribution information. In order to find the longest continuous path in the surgical area to the greatest extent, the points corresponding to the two hair follicles farthest apart in the hair follicle distribution information are taken as the initial first starting point and the initial second starting point; if the initial first starting point and the initial second starting point are not in the surgical forbidden area, the initial first starting point is taken as the first starting point, and the initial second starting point is taken as the second starting point.

[0181] If the initial first starting point is located in the operation forbidden area, a search is performed on the hair follicle distribution information with the initial first starting point as the center and a third preset distance as the radius, and a point located in the search area, closest to the initial starting point, and not in the operation forbidden area is taken as the first starting point; if the initial second starting point is located in the operation forbidden area, a search is performed on the hair follicle distribution information with the initial second starting point as the center and a fourth preset distance as the radius, and a point located in the search area, closest to the initial terminal point, and not in the operation forbidden area is taken as the second starting point.

[0182] The third preset distance and the fourth preset distance are preset values, and the third preset distance and the fourth preset distance can be the same or different. For example, one fifth of the straight-line distance between the initial first starting point and the initial second starting point is taken as the third preset distance and the fourth preset distance.

[0183] In the embodiments of the present application, when the path starting point, the first starting point or the second starting point is determined, it is also necessary to determine whether the path starting point, the first starting point or the second starting point is in the operation forbidden area. If it is in the operation forbidden area, it is necessary to re-determine the path starting point, the first starting point or the second starting point near the path starting point, the first starting point or the second starting point, so that the path starting point, the first starting point and the second starting point are not in the operation forbidden area, thereby reducing the damage to blood vessels in the operation process and improving the operation efficiency and accuracy.

[0184] In some embodiments, the server determines the operation forbidden area based on the blood vessel distribution information, including: the server parses the blood vessel distribution information to obtain position information of each blood vessel in the blood vessel distribution information; and the server determines a blood vessel position based on the position information of each blood vessel, and takes a surrounding area at a fifth preset distance from the blood vessel position as the operation forbidden area.

[0185] Optionally, when the server determines the operation forbidden area based on the blood vessel distribution information, the server can obtain the position information of each blood vessel in the operation area based on the blood vessel distribution information, because the server parses the operation area image.

[0186] Please refer to the content shown in Figure 3 In the embodiments of the present application, the operation forbidden area is determined based on the position information of each blood vessel. For example, a surrounding area at a fifth preset distance from the position of a blood vessel is taken as the operation forbidden area.

[0187] The fifth preset distance is a preset distance, which can be flexibly set based on the specific situation of the operation area of the patient. For example, the operation forbidden area is set as the area within 3-5 millimeters around the position of a blood vessel.

[0188] The embodiment of the application sets the operation forbidden area, so that the blood vessels and the surrounding areas of the blood vessels are avoided as much as possible during path planning, so as to reduce the frequent damage to the blood vessels and improve the operation efficiency and accuracy.

[0189] In some embodiments, the server acquires the operation area image, including: the server acquires a first image collected by the near-infrared imager and a second image collected by the vision system; the first image and the second image are images collected when the near-infrared imager is turned on; the server fuses the first image and the second image to generate the operation area image.

[0190] Optionally, during the operation, the blood vessel position in the operation area needs to be avoided as much as possible, therefore, the acquired operation area image is an image collected when the near-infrared imager is turned on.

[0191] In addition, the near-infrared imager also has the imaging function. The optical sensor in the near-infrared imager captures the reflected near-infrared light and converts it into an electrical signal, and the digital image data can be obtained after analog-digital conversion.

[0192] Therefore, the server can acquire the image collected by the near-infrared imager as the first image, and the image collected by the vision system as the second image. The first image is a high-contrast image of the blood vessels, and the second image is a distribution image of the blood vessels and the hair follicles.

[0193] The first image and the second image are fused to generate the operation area image. For example, the first image and the second image are fused by using an image fusion method based on deep learning. The image fusion method based on deep learning includes a convolutional neural network (CNN), an automatic encoder, GANs or a transformer model, etc.

[0194] The first image and the second image can also be superimposed to realize fusion, so that the blood vessel distribution in the operation area image is clearer.

[0195] The first image and the second image are fused to generate the operation area image, so that the blood vessel position in the operation area image is more accurate, and the difference between the blood vessels and the hair follicles is more obvious, thereby improving the operation efficiency and accuracy.

[0196] Optionally, the third image collected by the vision system when the near-infrared imager is turned on can also be used as the operation area image.

[0197] In some embodiments, after the server generates the planned path for the hair follicle extraction according to the hair follicle distribution information and the operation forbidden area, the method further comprises: if there is an undesirable target point in the planned path, the undesirable target point is removed; the undesirable target point is used to represent a point where a hair follicle is located and hair follicle extraction is not performed during the hair follicle extraction operation; or if there is an undesirable target point in the planned path, a midpoint between the undesirable target point and a next target point is determined, and at least one seventh adjacent node adjacent to the undesirable target point between the undesirable target point and the next target point; a seventh adjacent node with a distance less than a sixth preset distance from the midpoint is taken as a replacement point of the undesirable target point, so as to dynamically adjust the planned path according to the replacement point; the undesirable target point is used to represent a point where a hair follicle is located and hair follicle extraction is not performed during the hair follicle extraction operation.

[0198] Optionally, during the actual execution of the hair follicle extraction operation based on the planned path, the patient may move due to discomfort or anxiety, causing the position of the patient's head to change and the scalp to elastically deform; or the movement of the tissue during the hair follicle extraction process; or the environmental conditions in the operating room, such as light, temperature and humidity, may also change during the operation, resulting in a deviation between the pre-planned path and the actual hair follicle position.

[0199] Therefore, after the server generates the planned path for the hair follicle extraction according to the hair follicle distribution information and the operation forbidden area, there may be an undesirable target point during the actual operation. At this time, in order to make the operation proceed normally and reduce the impact of the operation on blood vessels, it is necessary to dynamically adjust the planned path, thereby improving the efficiency and accuracy of the operation. The undesirable target point is used to represent a point where a hair follicle is located and hair follicle extraction is not performed during the hair follicle extraction operation.

[0200] If there is an undesirable target point in the planned path, the undesirable target point is removed. By removing the undesirable target point in the planned path, the entire operation is still performed according to the planned path as a whole, improving the stability of the operation.

[0201] Alternatively, if there is an undesirable target point in the planned path, a midpoint between the undesirable target point and a next target point is determined, and at least one seventh adjacent node adjacent to the undesirable target point between the undesirable target point and the next target point; a seventh adjacent node with a distance less than a sixth preset distance from the midpoint is taken as a replacement point of the undesirable target point, so as to dynamically adjust the planned path according to the replacement point.

[0202] By taking the midpoint between the undesirable target point and the adjacent next target point as the reference point, the distance calculation can be simplified, thereby reducing the computational complexity. Moreover, the midpoint can be regarded as a balance point between the two points. By taking the midpoint as the reference point, the surgical robot can avoid large pose movement for taking points during hair follicle extraction to some extent.

[0203] The sixth preset distance is a preset value, which can be specifically set according to actual conditions.

[0204] Optionally, when the alternative point is selected, the adjacent point with a distance less than the seventh preset distance from the undesirable target point can also be selected as the alternative point.

[0205] Figure 5 A structure diagram of a path planning device for follicle extraction provided by an embodiment of the present application is shown in FIG. 1. The device includes an acquisition module 501, a determination module 502, and a generation module 503. Figure 5 The acquisition module 501 is configured to acquire a surgical region image. The surgical region image includes blood vessel distribution information and follicle distribution information.

[0206] The determination module 502 is configured to determine a surgical forbidden zone based on the blood vessel distribution information. The surgical forbidden zone is used to represent a region where blood vessels are located in the surgical region.

[0207] On the basis of the above embodiment, the generation module 503 is specifically configured to determine a path starting point of the planning path according to the follicle distribution information, and traverse the follicle distribution information from the path starting point based on the surgical forbidden zone to generate the planning path for follicle extraction.

[0208] On the basis of the above embodiment, the path starting point includes a first starting point and a second starting point. The generation module 503 is specifically configured to traverse the follicle distribution information from the first starting point to the direction of the second starting point based on the surgical forbidden zone to generate a forward search path, traverse the follicle distribution information from the second starting point to the direction of the first starting point based on the surgical forbidden zone to generate a reverse search path, and generate the planning path through the forward search path and the reverse search path.

[0209] On the basis of the above-mentioned embodiments, the generating module 503 is specifically configured to: determine the first adjacent node: determine at least one first adjacent node of the first starting point; determine the first passability: calculate the first distance between the first starting point and each first adjacent node, and determine whether each first adjacent node is located in the operation forbidden area; if there is a second adjacent node with a first distance greater than the first preset distance in the first adjacent node, the second adjacent node is removed; if there is a third adjacent node located in the operation forbidden area in the first adjacent node, the third adjacent node is removed; the remaining nodes in the first adjacent node are taken as the first passable node; determine the first target node: calculate the path cost of each first passable node, and determine the first target node in the first passable node based on the path cost; take the first target node as the third starting point, and repeatedly execute the steps of determining the first adjacent node, determining the first passability, and determining the first target node until the forward search path is generated.

[0210] On the basis of the above-mentioned embodiments, the generating module 503 is specifically configured to: determine the fourth adjacent node: determine at least one fourth adjacent node of the second starting point; determine the second passability: calculate the second distance between the second starting point and each fourth adjacent node, and determine whether each fourth adjacent node is located in the operation forbidden area; if there is a fifth adjacent node with a second distance greater than the second preset distance in the fourth adjacent node, the fifth adjacent node is removed; if there is a sixth adjacent node located in the operation forbidden area in the fourth adjacent node, the sixth adjacent node is removed; the remaining nodes in the fourth adjacent node are taken as the second passable node; determine the second target node: calculate the path cost of each second passable node, and determine the second target node in the second passable node based on the path cost; take the second target node as the fourth starting point, and repeatedly execute the steps of determining the fourth adjacent node, determining the second passability, and determining the second target node until the reverse search path is generated.

[0211] On the basis of the above-mentioned embodiments, the generating module 503 is specifically configured to: if the forward search path and the reverse search path meet, the planning path is generated through the forward search path and the reverse search path; if the forward search path and the reverse search path do not meet, the new first starting point and the new second starting point are determined based on the forward search path and the reverse search path, and the path planning is performed according to the new first starting point and the new second starting point to generate the planning path.

[0212] On the basis of the above-mentioned embodiments, the determining module 502 is specifically configured to: analyze the blood vessel distribution information to obtain the position information of each blood vessel in the blood vessel distribution information; determine the blood vessel position based on the position information of each blood vessel, and take the surrounding area with a distance of the fifth preset distance from the blood vessel position as the operation forbidden area.

[0213] On the basis of the above-mentioned embodiments, the acquisition module 501 is specifically configured to: acquire a first image collected by the near-infrared imager and a second image collected by the vision system; the first image and the second image are images collected when the near-infrared imager is turned on; the first image and the second image are fused to generate a surgical region image; or acquire a third image collected by the vision system when the near-infrared imager is turned on as the surgical region image.

[0214] On the basis of the above-mentioned embodiments, the device further comprises a path adjustment module configured to: if there is an undesirable target point in the planned path, the undesirable target point is removed; the undesirable target point is used to represent a point where a hair follicle located in the process of hair follicle extraction does not perform hair follicle extraction; or if there is an undesirable target point in the planned path, a midpoint of the undesirable target point and a next target point is determined, and at least one seventh adjacent node adjacent to the undesirable target point between the undesirable target point and the next target point; the seventh adjacent node with a distance less than a sixth preset distance from the midpoint is taken as a replacement point of the undesirable target point, so as to dynamically adjust the planned path according to the replacement point; the undesirable target point is used to represent a point where a hair follicle located in the process of hair follicle extraction does not perform hair follicle extraction.

[0215] It should be understood that the device corresponds to the above-mentioned hair follicle extraction path planning method embodiments, and can perform each step involved in the above-mentioned method embodiments. The specific functions of the device can be referred to the description in the above, and the detailed description is appropriately omitted here to avoid repetition. The device includes at least one software function module stored in the memory in the form of software or firmware or solidified in the operating system (OS) of the device.

[0216] Figure 6 A structure schematic diagram of a taking and extracting system provided by the embodiments of the present application is shown in FIG. 6, which includes an imaging device 61, a processor 62 and a mechanical arm 63; wherein the imaging device 61 and the mechanical arm 63 are in communication connection with the processor 62; the imaging device 61 is configured to collect a blood vessel distribution image of a surgical region and send the blood vessel distribution image to the processor 62; the processor 62 is configured to determine a surgical forbidden area of the surgical region based on the blood vessel distribution image and control the mechanical arm 63 to avoid the surgical forbidden area in the surgical region for taking and extracting. Figure 6

[0217] In the implementation process, the imaging device 61 includes at least one of a near-infrared imaging device, an optical imaging device, an ultrasonic imaging device, a fluorescence imaging device, an optical coherence tomography device, a magnetic resonance imaging device, an electronic computed tomography device, a digital subtraction angiography device, a direct digitization X-ray photography device and a computer X-ray imaging system. The imaging device can be specifically selected according to the actual situation, which is not limited in the present application.​

[0218] The imaging device 61 is arranged above the surgical area for imaging the blood vessel distribution of the surgical area to obtain a blood vessel distribution image. The above can be directly above or obliquely above, which can be set according to actual conditions, as long as the imaging device can image the surgical area at the arranged position.

[0219] The blood vessel distribution image refers to a visualized image of a blood vessel network obtained by a medical imaging technique. It includes at least one of the following information: blood vessel morphology, blood flow information, blood vessel density, abnormal features, tissue background, branch structure, etc.

[0220] The processor 62 is responsible for executing instructions of programs, data processing, controlling other hardware devices, etc. The processor 62 can be an integrated circuit chip with signal processing capability. The processor 62 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a ready-to-program gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. It can implement or execute various methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0221] The mechanical arm 63 is part of the surgical robot system. Through high-precision control of the mechanical arm, it can automatically operate according to the doctor's instructions or preset programs.

[0222] The communication connection can be wired or wireless, and the specific communication connection mode can be set according to actual conditions.

[0223] In an embodiment, the imaging device 61 and the processor 62 can be arranged on the mechanical arm 63. The integrated structure not only simplifies the structure of the hair taking system, but also can obtain more accurate blood vessel distribution image of the surgical area, so as to improve the surgical efficiency and accuracy.

[0224] Optionally, the imaging device 61 and the mechanical arm 63 are integrally arranged, and the processor 62 is part of the computer hardware system. By arranging the imaging device on the mechanical arm, the imaging device can adaptively image the surgical area with the movement of the mechanical arm, so as to obtain more accurate blood vessel distribution image of the surgical area, thereby improving the surgical efficiency and accuracy.

[0225] Optionally, the processor 62 and the mechanical arm 63 are integrated, and the imaging device 61 is separately arranged. By separately arranging the imaging device, the imaging of the surgical area is flexible, and the surgeon can perform the surgery.

[0226] Optionally, the imaging device 61, the processor 62, and the mechanical arm 63 are independently arranged. By independently arranging the devices, the flexibility and scalability of the hair extraction system are improved, and maintenance and upgrading are facilitated.

[0227] During the hair extraction process, it is necessary to avoid blood vessels in the surgical area as much as possible to reduce damage to the blood vessels. There are also accompanying nerves around the blood vessels. Due to the physiological characteristics of the accompanying nerves, if the accompanying nerves are damaged, the surgical effect will still be affected.

[0228] However, when the imaging device is used to image the surgical area, although the blood vessel distribution image can be obtained, the processor can obtain the blood vessel distribution information of the surgical area through the blood vessel distribution image, but it is difficult to determine the position of the accompanying nerves around the blood vessels. During the surgery, an error tolerance space should be given to further reduce the influence on the blood vessels and improve the efficiency and accuracy of the surgery.

[0229] Therefore, in order to reduce the damage to the blood vessels and the accompanying nerves during the surgery, it is necessary to determine the surgical forbidden zone based on the blood vessel distribution image. The surgical forbidden zone is used to represent the area where the blood vessels in the surgical area are located, which includes the blood vessels and the area near the blood vessels.

[0230] Illustratively, the imaging device is a near-infrared imaging device, i.e., a near-infrared imager. The imaging device, the processor, and the mechanical arm are integrated.

[0231] The near-infrared imager emits near-infrared light to the surgical area, and collects the blood vessel distribution image of the surgical area and sends it to the processor. The processor determines the surgical forbidden zone of the surgical area based on the blood vessel distribution image, and controls the mechanical arm to avoid the surgical forbidden zone in the surgical area for hair extraction.

[0232] The embodiments of the present application collect the blood vessel distribution image of the surgical area through the imaging device, and send the collected blood vessel distribution image to the processor, so that the processor determines the surgical forbidden zone through the blood vessel distribution image and controls the mechanical arm to avoid the surgical forbidden zone in the surgical area for hair extraction. This reduces the frequent occurrence of blood vessel damage during hair extraction, and improves the efficiency and accuracy of the surgery.

[0233] In some embodiments, the system further includes a vision device for collecting a surgical area image when the imaging device is turned on; the surgical area image includes hair follicle distribution information; the processor is further configured to generate a planned path for hair follicle extraction based on the hair follicle distribution information and the surgical forbidden zone, and control the mechanical arm to extract the hair follicles of the surgical area based on the planned path for hair follicle extraction.

[0234] The vision device is configured to capture an image of the surgical region when the imaging device is turned on, and send the captured image of the surgical region to the processor for processing.

[0235] The vision device can be a binocular camera / trinocular camera, a camera, or other types of devices with image capturing functions. The vision device can also be regarded as a vision system.

[0236] The vision device and the imaging device can be integrated devices on the surgical robot, or can be separate devices installed at appropriate positions of the surgical robot and detachable, or can be devices independent of the surgical robot and installed on other surgical devices. The specific arrangement can be determined according to actual conditions, as long as the shooting range of the vision device and the imaging device can cover the surgical region.

[0237] For example, based on the content shown in FIG. 1, the vision device and the near-infrared imager are independently arranged above the surgical region to capture images of the surgical region. The surgical region includes blood vessels and hair follicles to be extracted. Figure 2

[0238] The hair follicle distribution information includes one or more of the position information, the posture information, and the distribution of the hair follicles in the surgical region.

[0239] In the execution process, the processor generates a planned path for extracting the hair follicles according to the hair follicle distribution information and the surgical forbidden area, and controls the mechanical arm to extract the hair follicles in the surgical region based on the planned path for extracting the hair follicles. For details of the execution process, please refer to the above-mentioned embodiment of the path planning method for extracting the hair follicles, which will not be repeated here.

[0240] The embodiment of the present application determines the hair follicle distribution information based on the image of the surgical region captured by the vision device, so that the processor generates a planned path for extracting the hair follicles in combination with the hair follicle distribution information and the surgical forbidden area, and controls the mechanical arm to extract the hair follicles in the surgical region based on the planned path for extracting the hair follicles. On the basis of reducing the frequent occurrence of blood vessel injury in the hair extraction process, the hair follicles in the surgical region can also be uniformly extracted, thereby improving the surgical efficiency and accuracy.

[0241] In some embodiments, the system further includes a display device in communication with the vision device, and the display device is configured to receive and display the image of the surgical region sent by the vision device.

[0242] ​The display device is used to display information, images or videos. The display device can be any one or more of a liquid crystal display, a light emitting diode display, an organic light emitting diode display, a plasma display, a projector, a virtual reality head-mounted display, a curved display, a 3D display, etc. A suitable display can be selected according to actual conditions, which is not limited in the present application.

[0243] The display device and the visual device can be connected in a wired or wireless manner, which is selected according to actual conditions.

[0244] The display device can be used by the surgical staff to observe the situation of the patient's operation area in real time, thereby improving the operation efficiency and accuracy.

[0245] In some embodiments, based on the definition of the blood vessel distribution image and the information contained therein, the blood vessel distribution information can be determined according to the blood vessel distribution image. Therefore, the operation prohibited area of the operation area is determined by the processor based on the blood vessel distribution image, including: the operation prohibited area is determined by the processor based on the blood vessel distribution information; the operation prohibited area is used to represent the area where the blood vessels are located in the operation area.

[0246] The blood vessel distribution information includes one or more of the position information of each blood vessel in the operation area, the thickness information of the blood vessel, and the type information of the blood vessel.

[0247] In the embodiments of the present application, the blood vessel distribution information reflects the distribution of the blood vessels in the operation area, so that the operation prohibited area is determined based on the blood vessel distribution information in the blood vessel distribution image, thereby improving the accuracy of the operation prohibited area and improving the operation efficiency and accuracy.

[0248] In some embodiments, the processor determines the operation prohibited area based on the blood vessel distribution information, including: the processor analyzes the blood vessel distribution information to obtain the position information of each blood vessel in the blood vessel distribution information; and the processor determines the position of each blood vessel based on the position information of each blood vessel, and takes the surrounding area within the ninth preset distance from the position of the blood vessel as the operation prohibited area.

[0249] The specific execution process of the processor determining the operation prohibited area based on the blood vessel distribution information can refer to the above-mentioned embodiment of the server determining the operation prohibited area based on the blood vessel distribution information in the path planning method for extracting hair follicles, which will not be described here.

[0250] The embodiments of the present application set the operation prohibited area, so that the blood vessels and the surrounding area of the blood vessels can be avoided as much as possible when taking hair, thereby reducing the frequent damage to blood vessels and improving the operation efficiency and accuracy.

[0251] In some embodiments, the processor is further configured to generate the planned path for hair follicle extraction according to the hair follicle distribution information and the operation forbidden area, including: determining, by the processor, a path starting point of the planned path according to the hair follicle distribution information; and traversing, by the processor, the hair follicle distribution information from the path starting point based on the operation forbidden area to generate the planned path for hair follicle extraction.

[0252] The specific execution process of the processor generating the planned path for hair follicle extraction according to the hair follicle distribution information and the operation forbidden area can refer to the above-mentioned embodiments of the method for planning a path for hair follicle extraction, which will not be described here.

[0253] In the embodiments of the present application, the path starting point of the planned path is determined according to the hair follicle distribution information, so that the traversal is started from the path starting point. In this process, the starting point of the traversal is combined with the specific situation of the hair follicle distribution, rather than randomly selecting a path starting point to start the traversal, which not only realizes personalized path planning, but also reduces unnecessary repeated operations in the operation process, thereby improving the accuracy of path planning, reducing the damage to blood vessels in the operation process, and improving the operation efficiency and accuracy.

[0254] In some embodiments, the path starting point includes a ninth starting point and a tenth starting point; the processor traverses the hair follicle distribution information from the path starting point based on the operation forbidden area to generate the planned path for hair follicle extraction, including: the processor traverses the hair follicle distribution information from the ninth starting point to the direction of the tenth starting point based on the operation forbidden area to generate a forward search path; the processor traverses the hair follicle distribution information from the tenth starting point to the direction of the ninth starting point based on the operation forbidden area to generate a reverse search path; and the processor generates the planned path through the forward search path and the reverse search path.

[0255] The specific process of traversing the hair follicle distribution information from the path starting point by the processor to generate the planned path for hair follicle extraction can refer to the above-mentioned embodiments of the method for planning a path for hair follicle extraction, which will not be described here.

[0256] In the embodiments of the present application, the hair follicle distribution information of the operation area is traversed from the ninth starting point and the tenth starting point, which is equivalent to dividing the operation area image into two areas for traversal, thereby improving the traversal speed and the generation speed of the planned path, and further improving the operation efficiency.

[0257] In some embodiments, the processor is further used to: if there is an undesirable target point in the planned path, then eliminate the undesirable target point; the undesirable target point is used to represent the point where the hair follicles are not extracted during the hair follicle extraction surgery; or, if there is an undesirable target point in the planned path, determine the midpoint between the undesirable target point and the next target point, and at least one eighth adjacent node between the undesirable target point and the next target point that is adjacent to the undesirable target point; use the eighth adjacent node whose distance from the midpoint is less than the tenth preset distance as a replacement point for the undesirable target point, so as to dynamically adjust the planned path according to the replacement point; the undesirable target point is used to represent the point where the hair follicles are not extracted during the hair follicle extraction surgery.

[0258] The specific execution process of the planned path having an undesirable target point can be found in the embodiment of the path planning method for hair follicle extraction described above, which will not be repeated here.

[0259] The embodiments of the present application take into account that in actual surgery, there may be undesirable target points in the planned path. In order to ensure the normal operation of the operation and reduce the impact of the surgical operation on the blood vessels, the planned path needs to be dynamically adjusted to improve the efficiency and accuracy of the operation.

[0260] An embodiment of the present application provides a hair removal method, which includes: removing hair according to a planned path for hair follicle extraction; the planned path for hair follicle extraction is obtained by any embodiment of the above-mentioned path planning method for hair follicle extraction.

[0261] The specific process of how to generate the planning path for hair follicle extraction can be found in the above embodiment and will not be repeated here.

[0262] After determining the planned path for hair follicle extraction, the surgical robot extracts the hair follicles based on the planned path, thereby achieving hair removal.

[0263] The embodiment of the present application performs hair removal by planning a path, thereby improving the efficiency and accuracy of hair removal during surgery.

[0264] Figure 7 This is a schematic diagram of the electronic device structure provided in the embodiment of the present application, such as Figure 7 As shown, the electronic device includes a processor 701 (processor), a memory 702 (memory), and a bus 703; wherein the processor 701 and the memory 702 communicate with each other via the bus 703. The processor 701 is used to call program instructions in the memory 702 to execute the methods provided by the above-mentioned method embodiments.

[0265] The processor 701 can be an integrated circuit chip having a signal processing capability. The processor 701 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), and the like; or can be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The processor 701 can implement or execute the various methods, steps, and logical block diagrams disclosed in the embodiments of the present application. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0266] The memory 702 can include, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), and the like.

[0267] The embodiment discloses a computer program product, the computer program product includes a computer program stored on a non-transitory computer readable storage medium, the computer program includes program instructions, when the program instructions are executed by a computer, the computer can execute the method provided by each method embodiment.

[0268] The embodiment provides a non-transitory computer readable storage medium, the non-transitory computer readable storage medium stores computer instructions, and the computer instructions enable the computer to execute the method provided by each method embodiment.

[0269] In the embodiments provided by the present application, it should be understood that the disclosed device and method can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some communication interfaces, devices or units, and can be electrical, mechanical or other forms.

[0270] In addition, the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0271] Furthermore, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0272] The above is only an embodiment of the present application and is not used to limit the protection scope of the present application. For those skilled in the art, the present application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A hair removal system, characterized in that: The system includes: an imaging device, a robotic arm, and a processor; the imaging device and the robotic arm are respectively connected to the processor for communication; The imaging device is used to collect a blood vessel distribution image of the surgical area and send the blood vessel distribution image to the processor; The processor is configured to determine a surgical restricted area of ​​the surgical area based on the blood vessel distribution image, and control the robotic arm to avoid the surgical restricted area and perform hair removal in the surgical area; The system further includes a visual device configured to capture an image of the surgical area when the imaging device is turned on; the image of the surgical area includes hair follicle distribution information; the processor is further configured to generate a planned path for hair follicle extraction based on the hair follicle distribution information and the surgical restricted area, and control the robotic arm to extract hair follicles in the surgical area based on the planned path for hair follicle extraction; The processor is further configured to generate a planned path for hair follicle extraction based on the hair follicle distribution information and the surgical restricted area, including: The processor determines the starting point of the planned path according to the hair follicle distribution information; the path starting point includes a ninth starting point and a tenth starting point; The processor traverses the hair follicle distribution information from the ninth starting point toward the tenth starting point based on the surgical restricted area to generate a forward search path; The processor traverses the hair follicle distribution information from the tenth starting point toward the ninth starting point according to the surgical restricted area to generate a reverse search path; The processor generates the planned path through the forward search path and the reverse search path.

2. The system according to claim 1, wherein: The system further includes a display device, which is communicatively connected to the visual device and is configured to receive and display the surgical area image sent by the visual device.

3. The system according to claim 1, wherein: The imaging device includes at least one of a near-infrared imaging device, an optical imaging device, an ultrasonic imaging device, a fluorescence imaging device, an optical coherence tomography device, a magnetic resonance imaging device, an electronic computed tomography device, a digital subtraction angiography device, a direct digital X-ray device, and a computer X-ray camera system.

4. The system according to any one of claims 1 to 3, characterized in that: The imaging device is arranged on the robotic arm.

5. The system according to claim 1, wherein: The blood vessel distribution image includes blood vessel distribution information; The processor is configured to determine a surgical restricted area of ​​the surgical area based on the blood vessel distribution image, including: The processor determines a surgical restricted area based on the blood vessel distribution information; The surgical exclusion zone is used to represent the area in the surgical region where blood vessels are located.

6. The system according to claim 5, characterized in that The processor determines a surgical restricted area based on the blood vessel distribution information, including: The processor parses the blood vessel distribution information to obtain position information of each blood vessel in the blood vessel distribution information; The processor determines the position of each blood vessel based on the position information of each blood vessel, and uses the blood vessel position as the center and a surrounding area within a ninth preset distance from the blood vessel position as the surgical restricted area.

7. The system according to claim 1, wherein: The processor is further configured to: If there are undesirable target points in the planned path, the undesirable target points are removed; the undesirable target points are used to represent the points where the hair follicles are not to be extracted during the hair follicle extraction procedure; or If an undesirable target point exists in the planned path, the midpoint between the undesirable target point and the next target point, as well as at least one eighth adjacent node between the undesirable target point and the next target point, are determined; the eighth adjacent node whose distance from the midpoint is less than a tenth preset distance is used as a replacement point for the undesirable target point, so as to dynamically adjust the planned path based on the replacement point; the undesirable target point is used to represent the point at which the hair follicles are not to be extracted during the hair follicle extraction procedure.

8. A path planning method for hair follicle extraction, characterized in that: The method comprises: Acquire an image of the surgical area; the image of the surgical area includes blood vessel distribution information and hair follicle distribution information; Determining a surgical restricted area based on the blood vessel distribution information; the surgical restricted area is used to represent the area where the blood vessels are located in the surgical area; Determine a path starting point of the planned path according to the hair follicle distribution information; wherein the path starting point includes a first starting point and a second starting point; Based on the surgical forbidden area, traversing the hair follicle distribution information from the first starting point toward the second starting point to generate a forward search path; According to the surgical forbidden area, starting from the second starting point, traversing the hair follicle distribution information in the direction of the first starting point to generate a reverse search path; The planned path is generated by using the forward search path and the reverse search path; wherein the path points in the planned path are not in the surgical restricted area.

9. The method according to claim 8, characterized in that The step of traversing the hair follicle distribution information from the first starting point toward the second starting point based on the surgical restricted area to generate a forward search path includes: Determining a first adjacent node: determining at least one first adjacent node of the first starting point; Determining first traversability: calculating a first distance between the first starting point and each of the first adjacent nodes, and determining whether each of the first adjacent nodes is located in the surgical restricted area; if there is a second adjacent node among the first adjacent nodes whose first distance is greater than a first preset distance, eliminating the second adjacent node; if there is a third adjacent node among the first adjacent nodes that is located in the surgical restricted area, eliminating the third adjacent node; and using the remaining nodes among the first adjacent nodes as first traversable nodes; Determining a first target node: calculating a path cost of each of the first traversable nodes, and determining a first target node among the first traversable nodes based on the path cost; Taking the first target node as a third starting point, repeating the steps of determining the first adjacent node, determining the first accessibility, and determining the first target node until a forward search path is generated; or The step of traversing the hair follicle distribution information from the second starting point toward the first starting point according to the surgical restricted area to generate a reverse search path includes: Determining a fourth adjacent node: determining at least one fourth adjacent node of the second starting point; Determining the second traversability: calculating the second distance between the second starting point and each of the fourth adjacent nodes, and determining whether each of the fourth adjacent nodes is located in the surgical restricted area; if there is a fifth adjacent node among the fourth adjacent nodes whose second distance is greater than the second preset distance, eliminating the fifth adjacent node; if there is a sixth adjacent node among the fourth adjacent nodes that is located in the surgical restricted area, eliminating the sixth adjacent node; and using the remaining nodes among the fourth adjacent nodes as second traversable nodes; Determining a second target node: calculating a path cost of each of the second traversable nodes, and determining a second target node among the second traversable nodes based on the path cost; Taking the second target node as a fourth starting point, repeating the steps of determining the fourth adjacent node, determining the second accessibility, and determining the second target node until a reverse search path is generated; or Generating the planned path by using the forward search path and the reverse search path includes: If the forward search path and the reverse search path meet, generating the planned path through the forward search path and the reverse search path; If the forward search path and the reverse search path do not meet, a new first starting point and a new second starting point are determined based on the forward search path and the reverse search path, and path planning is performed according to the new first starting point and the new second starting point to generate a planned path.

10. The method according to claim 8, characterized in that Determining a surgical restricted area based on the blood vessel distribution information includes: parsing the blood vessel distribution information to obtain position information of each blood vessel in the blood vessel distribution information; The position of each blood vessel is determined based on the position information of each blood vessel, and the surrounding area within a fifth preset distance from the blood vessel position is used as the surgical restricted area with the blood vessel position as the center.

11. The method according to claim 8, characterized in that The step of acquiring an image of the surgical area includes: Acquire a first image captured by a near-infrared imager and a second image captured by a visual system; the first image and the second image are images captured when the near-infrared imager is turned on; fuse the first image and the second image to generate the surgical area image; or The third image captured by the visual system when the near-infrared imager is turned on is obtained as the surgical area image.

12. The method according to any one of claims 8 to 11, characterized in that: After generating a planned path for hair follicle extraction according to the hair follicle distribution information and the surgical restricted area, the method further includes: If there are undesirable target points in the planned path, the undesirable target points are removed; the undesirable target points are used to represent the points where the hair follicles are not to be extracted during the hair follicle extraction procedure; or If an undesirable target point exists in the planned path, a midpoint between the undesirable target point and the next target point, as well as at least one seventh adjacent node between the undesirable target point and the next target point and adjacent to the undesirable target point are determined; a seventh adjacent node whose distance from the midpoint is less than a sixth preset distance is used as a replacement point for the undesirable target point, so as to dynamically adjust the planned path based on the replacement point; the undesirable target point is used to represent the point at which a hair follicle is not to be extracted during the hair follicle extraction procedure.

13. A path planning device for hair follicle extraction, characterized in that: The device comprises: An acquisition module is used to acquire an image of the surgical area; the image of the surgical area includes blood vessel distribution information and hair follicle distribution information; A determination module, configured to determine a surgical restricted area based on the blood vessel distribution information; the surgical restricted area is used to represent an area within the surgical region where blood vessels are located; A generation module is configured to determine a starting point of a planned path based on hair follicle distribution information; the path starting point includes a first starting point and a second starting point; based on the surgical forbidden area, traversing the hair follicle distribution information from the first starting point in the direction of the second starting point to generate a forward search path; based on the surgical forbidden area, traversing the hair follicle distribution information from the second starting point in the direction of the first starting point to generate a reverse search path; generating the planned path through the forward search path and the reverse search path; wherein, path points in the planned path are not within the surgical forbidden area.

14. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and when the machine-readable instructions are executed by the processor, the method according to any one of claims 8 to 12 is performed.

15. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, executes the method according to any one of claims 8 to 12.

16. A computer program product, characterized in that include: A computer program, wherein when the computer program is executed by a processor, the method according to any one of claims 8 to 12 is executed.

Images