Path planning method and device, computer equipment and storage medium

Abstract

The invention relates to a path planning method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring an initial puncture path and a preset search range; the initial puncture path is a puncture path which is input by a user and aims at a target tissue in the medical image; determining a plurality of candidate puncture paths around the initial puncture path on the medical image according to a preset search range; the candidate puncture path is a puncture path meeting a blood vessel interference condition, the blood vessel interference condition comprises that the blood vessel distance is greater than or equal to a preset distance threshold, and the blood vessel distance is the minimum distance between the puncture path and a blood vessel; and determining a target puncture path according to the puncture risk quantized value corresponding to each candidate puncture path. According to the method, the user operation and the computer algorithm are combined, the planned target puncture path can be better matched with the position of the puncture path expected by the user, the puncture angle and other aspects, and the adaptability between the automatically planned target puncture path and the path expected by the user can be improved.

Description

Technical Field

[0001] The present application relates to the field of medical equipment technology, and in particular to a path planning method, device, computer equipment and storage medium. Background Art

[0002] With the development of medical puncture technology, the intelligence of puncture path planning is getting higher and higher. From manual planning of puncture paths by doctors to assisting doctors in manual puncture path planning based on path interference detection, and then to automatic planning of puncture paths based on parameters set by doctors.

[0003] Although the automatic puncture path planning method is more efficient and intelligent, the automatic puncture path planning method still has the problem of low compatibility between the planned path and the path expected by the doctor. Summary of the invention

[0004] Based on this, it is necessary to provide a path planning method, device, computer equipment, computer-readable storage medium and computer program product that can plan the path desired by the doctor, thereby improving the adaptability and accuracy of path planning, in order to address the above technical problems.

[0005] In a first aspect, the present application provides a path planning method, comprising:

[0006] Obtaining an initial puncture path and a preset search range; the initial puncture path is a puncture path input by a user for a target tissue in a medical image;

[0007] Determine multiple candidate puncture paths around the initial puncture path on the medical image according to a preset search range; the candidate puncture paths are puncture paths that meet a vascular interference condition, the vascular interference condition includes that the vascular distance is greater than or equal to a preset distance threshold, and the vascular distance is the minimum distance between the puncture path and the blood vessel;

[0008] The target puncture path is determined according to the puncture risk quantification value corresponding to each candidate puncture path.

[0009] In one embodiment, determining a target puncture path according to the puncture risk quantification value corresponding to each candidate puncture path includes:

[0010] According to the puncture risk quantification value corresponding to each candidate puncture path, the initial puncture path is adjusted to determine the target puncture path.

[0011] In one embodiment, determining a target puncture path according to the puncture risk quantification value corresponding to each candidate puncture path includes:

[0012] According to the puncture risk quantification value corresponding to each candidate puncture path, a target puncture path is determined from each candidate puncture path.

[0013] In one embodiment, adjusting the initial puncture path according to the puncture risk quantification value corresponding to each candidate puncture path to determine the target puncture path includes:

[0014] According to the puncture risk quantification value corresponding to each candidate puncture path, a puncture risk heat map corresponding to the target tissue is generated; the puncture risk heat map is used to characterize the puncture risk degree around the initial puncture path;

[0015] Based on the puncture risk heat map, the initial puncture path is adjusted to determine the target puncture path.

[0016] In one embodiment, based on the puncture risk heat map, the initial puncture path is adjusted to determine the target puncture path, including:

[0017] Display the puncture risk heat map;

[0018] The user's adjustment operation on the initial puncture path based on the puncture risk heat map is obtained, and the target puncture path is determined based on the adjustment operation.

[0019] In one embodiment, the method further comprises:

[0020] Generate a puncture path recommendation map corresponding to the target tissue according to the puncture risk quantification value corresponding to each candidate puncture path; the puncture path recommendation map includes at least one candidate puncture path whose puncture risk quantification value is greater than or equal to a preset risk threshold;

[0021] Accordingly, the puncture risk heat map is displayed, including:

[0022] The puncture risk heat map and the puncture path recommendation map are fused and displayed.

[0023] In one embodiment, the method further comprises:

[0024] Obtaining preset puncture risk parameters;

[0025] For each candidate puncture path, determining a parameter value corresponding to the puncture risk parameter of the candidate puncture path;

[0026] Based on the parameter values ​​of the candidate puncture paths, a puncture risk quantification value corresponding to the candidate puncture paths is determined.

[0027] In one embodiment, the puncture risk parameter includes at least one of a blood vessel distance, a puncture angle, and a puncture distance;

[0028] The puncture angle is the angle between the puncture path and the corresponding normal vector, and the normal vector is a vector perpendicular to the tangent plane at the intersection of the puncture path and the preset surface;

[0029] The puncture distance is the distance between the puncture point corresponding to the puncture path and the puncture point corresponding to the initial puncture path.

[0030] In one embodiment, determining multiple candidate puncture paths around the initial puncture path on the medical image according to a preset search range includes:

[0031] Determine multiple original puncture paths around the initial puncture path on the medical image according to a preset search range;

[0032] Screening out an original puncture path that meets a preset screening condition from a plurality of original puncture paths; the preset screening condition includes a vascular interference condition;

[0033] The original puncture paths that meet the preset screening conditions are used as candidate puncture paths.

[0034] In one embodiment, the preset screening condition also includes a puncture angle condition, where the puncture angle condition is that the angle between the puncture path and the corresponding normal vector is less than or equal to a preset angle threshold, and the normal vector is a vector perpendicular to the tangent plane at the intersection of the puncture path and the preset surface.

[0035] In a second aspect, the present application also provides a path planning device, comprising:

[0036] The first acquisition module is used to acquire an initial puncture path and a preset search range; the initial puncture path is a puncture path input by a user for a target tissue in a medical image;

[0037] A first determination module is used to determine multiple candidate puncture paths around the initial puncture path on the medical image according to a preset search range; the candidate puncture paths are puncture paths that meet a vascular interference condition, the vascular interference condition includes that the vascular distance is greater than or equal to a preset distance threshold, and the vascular distance is the minimum distance between the puncture path and the blood vessel;

[0038] The second determination module is used to determine the target puncture path according to the puncture risk quantification value corresponding to each candidate puncture path.

[0039] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the path planning method in the first aspect when executing the computer program.

[0040] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the path planning method in the first aspect are implemented.

[0041] In a fifth aspect, the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the path planning method in the first aspect above.

[0042] The above-mentioned path planning method, device, computer equipment, storage medium and computer program product, the computer equipment obtains an initial puncture path and a preset search range; wherein the initial puncture path is a puncture path for a target tissue in a medical image input by a user; then, multiple candidate puncture paths around the initial puncture path are determined on the medical image according to the preset search range; and the target puncture path is determined according to the puncture risk quantification value corresponding to each candidate puncture path; wherein the candidate puncture path is a puncture path that satisfies a vascular interference condition, and the vascular interference condition includes that the vascular distance is greater than or equal to a preset distance threshold, and the vascular distance is the minimum distance between the puncture path and the blood vessel. That is to say, the path planning method proposed in the embodiment of the present application, combining user operation and computer algorithm, can determine a target puncture path that meets the vascular interference condition around the initial puncture path input by the user, with the assistance of the intelligent path planning algorithm; the target puncture path will be more closely matched with the position, puncture angle and other aspects of the puncture path expected by the user, that is, the target puncture path obtained by this method is more compatible with the path expected by the user, which can not only adapt to the needs and habits of different users for path planning to the greatest extent, but also avoid additional path adjustment operations made by users when they are dissatisfied with the automatically planned path, thereby improving the accuracy and speed of path planning for different users. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0044] Figure 1 A diagram of an application environment of a path planning method in an embodiment;

[0045] Figure 2 A schematic diagram of a process flow of a path planning method in one embodiment;

[0046] Figure 3 is a flow chart of a path planning method in another embodiment;

[0047] FIG4( a ) is a schematic diagram of mapping sampling points to scalp entry points in one embodiment;

[0048] FIG4( b ) is a schematic diagram of a safe scalp cranial entry point and a manual cranial entry point among scalp cranial entry points in one embodiment;

[0049] FIG4( c ) is a schematic diagram of a puncture risk heat map in one embodiment;

[0050] Figure 5 is a flow chart of a path planning method in another embodiment;

[0051] Figure 6 A schematic diagram of a puncture risk heat map in another embodiment;

[0052] Figure 7 A schematic diagram of a puncture risk heat map in another embodiment;

[0053] Figure 8 is a flow chart of a path planning method in another embodiment;

[0054] FIG9( a ) is a schematic diagram of path hierarchy with a cost function value greater than 0.7 in one embodiment;

[0055] FIG9( b ) is a schematic diagram of path hierarchy with a cost function value greater than 0.6 in one embodiment;

[0056] Fig.10 is a flow chart of a path planning method in another embodiment;

[0057] Fig.11 A schematic diagram of calculating the puncture angle in one embodiment;

[0058] Fig.12 is a flow chart of a path planning method in another embodiment;

[0059] FIG13( a ) is a schematic diagram of an initial puncture path manually planned in one embodiment;

[0060] FIG13( b ) is a schematic diagram of a planned path range around an initial puncture path in one embodiment;

[0061] FIG13( c ) is a schematic diagram of a planned starting point around an initial puncture path in one embodiment;

[0062] FIG13( d ) is a schematic diagram of an original puncture path around an initial puncture path in one embodiment;

[0063] Fig.14 A schematic diagram of a blood vessel reconstruction image around an initial puncture path in one embodiment;

[0064] Fig.15 A schematic diagram of an initial puncture path satisfying a blood vessel interference condition in an embodiment;

[0065] Fig.16 A schematic diagram of an initial puncture path satisfying a blood vessel interference condition and a puncture angle condition in an embodiment;

[0066] Fig.17 A schematic diagram of a workflow of path planning in one embodiment;

[0067] Fig.18 is a structural block diagram of a path planning device in one embodiment;

[0068] Fig.19 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0069] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0070] With the development of medical puncture technology, the intelligence of puncture path planning is getting higher and higher. For example, the existing neurosurgery planning software mainly relies on doctors to manually select the entry point and target point for path planning. Due to the large number of intracranial blood vessels and their dense distribution, it takes a lot of time to manually plan a path that does not interfere with the blood vessels. In order to improve the intelligence of path planning, some relatively advanced software has a path vessel interference detection function, which can assist doctors to a certain extent in determining whether the manually planned path has interference. If there is interference, the doctor needs to continue to manually find a new path until a suitable path is found.

[0071] Of course, there are some more intelligent studies that try to help doctors plan paths automatically. However, there are many factors to consider in order to plan a puncture path reasonably. In addition to blood vessels, functional areas, fiber bundles, etc. must also be considered, and each doctor has his or her own habitual path. The results of automatic planning cannot satisfy every doctor. Therefore, although the current automatic puncture path planning method is becoming more and more intelligent, there is still a problem of low compatibility between the planned path and the path expected by the doctor.

[0072] Based on this, the embodiment of the present application proposes a path planning method that can combine the doctor's experience and computer algorithms to provide doctors with a path planning workflow with high human-computer integration, accurate planning results, and in line with the doctor's habits.

[0073] The path planning method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown in the figure, the computer device 102 can be a terminal or a server; the terminal can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers and portable wearable devices, and the portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server can be implemented as an independent server or a server cluster composed of multiple servers.

[0074] In an exemplary embodiment, Figure 2 As shown, a path planning method is provided, which is applied to Figure 1 Taking the computer device in as an example, the method includes the following steps 202 to 206.

[0075] in:

[0076] Step 202, obtaining an initial puncture path and a preset search range; the initial puncture path is a puncture path input by a user for a target tissue in a medical image.

[0077] Exemplarily, the medical image can be a scanned image of the site to be punctured, such as an image of a patient's brain blood vessels; in addition, the medical image can be a computed tomography (CT) scan image, a magnetic resonance imaging (MRI) scan image, or a scan image of other modalities; the content and modality of the medical image are not specifically limited in the embodiments of the present application.

[0078] Exemplarily, after acquiring a medical image of the site to be punctured, the user may draw an initial puncture path on the medical image for the target tissue in the site to be punctured; wherein the target tissue may include the lesion tissue in the site to be punctured. Exemplarily, when drawing the initial puncture path, the user may not need to consider whether the initial puncture path has any collision or interference with any tissue in the site to be punctured.

[0079] In an optional implementation, the user can draw the starting point and the end point on the medical image, and then the computer device can draw the initial puncture path on the medical image based on the starting point and the end point; wherein the initial puncture path can be a straight line segment passing through the starting point and the end point; of course, in the case of drawing multiple points, the computer device can also draw a curved initial puncture path on the medical image based on the multiple points. In addition, it should be noted that the starting point can be a point on the skin surface, and the end point can be a point on the target tissue, such as the center point of the target tissue (i.e., the center point of the lesion tissue); of course, the starting point can be not only a point on the skin surface, but also a point outside the skin, or any point in the skin except the end point.

[0080] The preset search range may be a search area around the initial puncture path determined based on the preset search radius and the initial puncture path; wherein the preset search radius may be a default search radius pre-stored in the computer device, or a search radius input by a user, or a search radius after the user adjusts the parameters of the default search radius, etc. Based on the preset search radius and the initial puncture path, the computer device may determine a search area of ​​the puncture path around the initial puncture path, i.e., the preset search range, so as to generate a puncture path that meets certain conditions and is desired by the user within the search area.

[0081] Step 204 , determining a plurality of candidate puncture paths around the initial puncture path on the medical image according to a preset search range.

[0082] Among them, the candidate puncture path is a puncture path that meets the vascular interference condition, and the vascular interference condition may include that the vascular distance is greater than or equal to the preset distance threshold, and the vascular distance is the minimum distance between the puncture path and the blood vessel. Since the puncture path is a path from the outside of the skin to the inside of the skin directly reaching the lesion target, that is, the puncture path will pass through one or more tissues between the outside of the skin and the lesion, and there may be blood vessels in different tissues, in order to avoid the puncture path from affecting the blood vessels, it is necessary to ensure that a certain distance is maintained between the puncture path and the blood vessels; in addition, since the blood vessels are irregularly arranged, the vertical distance between the blood vessels at different positions and the puncture path is different; therefore, when performing vascular interference detection, as long as the minimum distance between the blood vessel and the puncture path is greater than or equal to the preset distance threshold, it can be ensured that the distance between the blood vessels at other positions and the puncture path is definitely greater than the preset distance threshold, that is, the puncture path will not interfere with the blood vessels at any position.

[0083] For example, in a neurosurgery robot puncture procedure, before the operation is performed, it is usually necessary to reasonably plan the surgical puncture path based on the surgical target area, brain blood vessels and other information in the preoperative images. The puncture path planned manually or by software must ensure that there is no interference between the surgical instrument and key tissues, such as blood vessels, otherwise it will cause the instrument to collide with key tissues during the operation, causing serious surgical complications.

[0084] Therefore, based on the preset search range, when the computer device generates candidate puncture paths around the initial puncture path input by the user, it is necessary to consider whether each candidate puncture path interferes with the key tissue in the puncture site; illustratively, the computer device can pre-configure tissue interference conditions, such as blood vessel interference conditions; wherein the blood vessel interference conditions may include a minimum distance between the puncture path and the blood vessel, which should be greater than or equal to a preset distance threshold; for the puncture path within the search area, if it satisfies the blood vessel interference condition, that is, the minimum distance between the puncture path and the blood vessel is greater than or equal to the preset distance threshold, it can be considered that the distance between the puncture path and the blood vessel is far, then, the puncture path will not interfere with the blood vessel to a large extent, that is, the puncture path can be considered safe; for a safe puncture path, it can be determined as a candidate puncture path around the initial puncture path.

[0085] Exemplarily, the computer device may first determine all the original puncture paths within the search area at a preset interval (or step length), where the end points used to plan the original puncture paths are all lesion targets, and for the starting points used to plan the original puncture paths, different starting points correspond to different points on the skin surface; then, based on the vascular interference condition, the original puncture paths that meet the vascular interference condition are screened out from all the original puncture paths as candidate puncture paths. Exemplarily, the computer device may also first divide a safe area from the search area based on the vascular interference condition; then, within the safe area, multiple puncture paths that are completely within the safe area are determined at a preset interval (or step length) as candidate puncture paths; wherein the puncture path is completely within the safe area, which means that the straight line segment (or curve segment) corresponding to the puncture path is completely within the safe area, and does not include the situation where some straight line segments (or curve segments) are outside the safe area.

[0086] Exemplarily, the computer device can also determine whether the initial puncture path is safe based on the vascular interference condition, and mark the initial puncture path based on the determination result; for example: if the initial puncture path is safe, the initial puncture path can be marked as green; conversely, the initial puncture path can be marked as red.

[0087] Step 206: determine the target puncture path according to the puncture risk quantification value corresponding to each candidate puncture path.

[0088] Among them, the puncture risk quantification value corresponding to the candidate puncture path can be a puncture risk value obtained after quantification processing based on at least one puncture risk parameter, which can be used to characterize the degree of puncture risk; illustratively, the puncture risk quantification value and the puncture risk degree can be positively correlated, that is, the larger the puncture risk quantification value, the greater the puncture risk degree and the lower the safety; of course, the puncture risk quantification value and the puncture risk degree can also be negatively correlated, that is, the larger the puncture risk quantification value, the smaller the puncture risk degree and the higher the safety.

[0089] Exemplarily, the puncture risk parameter may include but is not limited to at least one of a blood vessel distance, a puncture angle and a puncture distance; wherein the blood vessel distance is the minimum distance between the puncture path and the blood vessel; the puncture angle is the angle between the puncture path and the corresponding normal vector, the normal vector is a vector perpendicular to the tangent plane at the intersection of the puncture path and a preset surface, the preset surface may include the skin surface corresponding to the target tissue, or the surface of other tissues passed by the puncture path, such as the skull surface, and any one of user-defined surfaces, etc.; the puncture distance is the distance between the puncture point corresponding to the puncture path and the puncture point corresponding to the initial puncture path, the puncture point corresponding to the puncture path may be the intersection between the puncture path and the preset surface, such as the intersection between the puncture path and the skin surface corresponding to the target tissue, or the intersection between the puncture path and other surfaces, etc.

[0090] Exemplarily, when there is one puncture risk parameter, for each candidate puncture path, the parameter value corresponding to the puncture risk parameter of the candidate puncture path can be normalized to determine the puncture risk quantification value corresponding to the candidate puncture path. When there are multiple puncture risk parameters, for each candidate puncture path, the parameter value corresponding to each puncture risk parameter of the candidate puncture path can be weighted summed to determine the puncture risk quantification value corresponding to the candidate puncture path.

[0091] Furthermore, when the quantified puncture risk values ​​corresponding to each candidate puncture path are determined, the computer device may determine the target puncture path based on the quantified puncture risk values ​​corresponding to each candidate puncture path.

[0092] Exemplarily, the computer device may adjust the initial puncture path according to the puncture risk quantification value corresponding to each candidate puncture path to determine the target puncture path. For example, the computer device may generate a puncture risk heat map around the initial puncture path according to the puncture risk quantification value corresponding to each candidate puncture path; then, the computer device may adjust the initial puncture path based on the puncture risk heat map and preset adjustment rules to determine the target puncture path while ensuring the minimum adjustment range.

[0093] Exemplarily, the computer device may also determine the target puncture path from each candidate puncture path according to the puncture risk quantification value corresponding to each candidate puncture path. For example, the computer device may determine any candidate puncture path from each candidate puncture path as the target puncture path; the computer device may also determine the candidate puncture path from each candidate puncture path that is closest to the initial puncture path as the target puncture path.

[0094] Exemplarily, when the computer device determines the target puncture path based on the initial puncture path input by the user, it can also determine whether the initial puncture path is safe based on the vascular interference condition; if it is determined that the initial puncture path is safe, the initial puncture path can also be directly determined as the target puncture path. Exemplarily, the computer device can also calculate the puncture risk quantification value corresponding to the initial puncture path; when the puncture risk quantification value is negatively correlated with the puncture risk degree, and the puncture risk quantification value corresponding to the initial puncture path is greater than or equal to the preset risk threshold, the initial puncture path can also be directly determined as the target puncture path; or, when the puncture risk quantification value is positively correlated with the puncture risk degree, and the puncture risk quantification value corresponding to the initial puncture path is less than or equal to the preset risk threshold, the initial puncture path can also be directly determined as the target puncture path.

[0095] In the above path planning method, the computer device obtains an initial puncture path and a preset search range; wherein the initial puncture path is a puncture path for a target tissue in a medical image input by a user; then, multiple candidate puncture paths around the initial puncture path are determined on the medical image according to the preset search range; and the target puncture path is determined according to the puncture risk quantification value corresponding to each candidate puncture path; wherein the candidate puncture path is a puncture path that satisfies a vascular interference condition, and the vascular interference condition includes that the vascular distance is greater than or equal to a preset distance threshold, and the vascular distance is the minimum distance between the puncture path and the blood vessel. That is to say, the path planning method proposed in the embodiment of the present application, combining user operation and computer algorithm, can determine a target puncture path that meets the vascular interference condition around the initial puncture path input by the user, with the assistance of the intelligent path planning algorithm; the target puncture path will be more closely matched with the position, puncture angle and other aspects of the puncture path expected by the user, that is, the target puncture path obtained by this method is more compatible with the path expected by the user, which can not only adapt to the needs and habits of different users for path planning to the greatest extent, but also avoid additional path adjustment operations made by users when they are dissatisfied with the automatically planned path, thereby improving the accuracy and speed of path planning for different users.

[0096] In an exemplary embodiment, Figure 3As shown, the above step 206 may also include steps 302 to 304. Among them:

[0097] Step 302: Generate a puncture risk heat map corresponding to the target tissue according to the puncture risk quantification value corresponding to each candidate puncture path.

[0098] The puncture risk heat map is used to characterize the puncture risk degree around the initial puncture path. Based on the puncture risk heat map, the computer device can fine-tune the initial puncture path, or, based on the puncture risk heat map, can also guide the user to fine-tune the initial puncture path.

[0099] For example, when generating a puncture risk heat map, the puncture risk quantification value corresponding to each candidate puncture path can be determined based on the two puncture risk parameters of the puncture path, namely, the puncture risk quantification value corresponding to the candidate puncture path can be determined by weighted summation based on the two-dimensional features of the puncture path, namely, the puncture risk quantification value corresponding to the candidate puncture path. Of course, the puncture risk quantification value corresponding to each candidate puncture path can also be determined based on the three puncture risk parameters of the puncture path, namely, the puncture angle and the puncture distance.

[0100] Exemplarily, the puncture risk heat map corresponding to the target tissue may be a risk heat map generated with the skin surface corresponding to the target tissue as the background, or may be a risk heat map generated with other types of preset curved surfaces as the background, etc.

[0101] Exemplarily, taking brain tissue as an example, the entire scalp can be used as the background, that is, the pixel value of the scalp is 0, the intersection points of each candidate puncture path and the scalp are determined, and the puncture risk quantification value corresponding to each candidate puncture path is used as the puncture risk quantification value corresponding to the intersection point of each candidate puncture path and the scalp; then, the puncture risk quantification value of each intersection point is smoothed to generate a puncture risk heat map with the scalp as the background.

[0102] In an optional implementation, it is assumed that the initial puncture path and each candidate puncture path are generated based on the starting point and the end point, wherein the end point can be a target point in the target tissue, such as the target point T shown in FIG4(a); the starting point can be a point in the scalp, such as the sampling points E1, E2, and E3 shown in FIG4(a); and the sampling area can be a spherical area drawn with the starting point as the center according to a preset search radius. Then, by extending the initial puncture path and each candidate puncture path, the intersection point between the initial puncture path and the scalp, and the intersection point between each candidate puncture path and the scalp can be obtained, such as the scalp entry points M1, M2, and M3 shown in FIG4(a); at the same time, the sampling area is also mapped to the scalp along the TE path to obtain the corresponding scalp mapping area.

[0103] When generating a puncture risk heat map with the scalp as the background, the scalp entry point can be marked as the foreground color, and the other areas in the scalp mapping area except the scalp entry point can be marked as the background color; since each candidate puncture path is a pre-screened puncture path that meets the vascular interference condition, each candidate puncture path is a safe puncture path; then, the intersection between each candidate puncture path and the scalp, that is, the scalp entry point, will be a safe entry point and marked as the foreground color. Other scalp areas except the safe entry point can be used as dangerous areas and marked as the background color. As shown in Figure 4(b), each dark gray dot is a safe entry point, and the light gray circular mapping area is the scalp background area; in Figure 4(b), the intersection between the initial puncture path and the scalp, that is, the black rectangular point, is also marked, which can be marked as a manual entry point; it should be noted that the black rectangular point is also the center point of the light gray circular mapping area.

[0104] Based on the safe cranial entry points in Figure 4(b) and the puncture risk quantification values ​​corresponding to the safe cranial entry points, the safe cranial entry points can be clustered to obtain at least one safe area; and for each safe area, the safe area is gradient colored according to the puncture risk quantification values ​​corresponding to the safe cranial entry points in the safe area, thereby generating a puncture risk heat map, as shown in Figure 4(c). It should be noted that the safe area obtained by clustering can be any regular shape or irregular shape.

[0105] Step 304: Based on the puncture risk heat map, the initial puncture path is adjusted to determine the target puncture path.

[0106] Exemplarily, the computer device can adjust the initial puncture path based on the puncture risk heat map and the position of the initial puncture path on the puncture risk heat map to obtain the target puncture path; wherein, the position of the initial puncture path on the puncture risk heat map can be represented by the position of the intersection between the initial puncture path and the scalp (i.e., the manual cranial entry point) on the puncture risk heat map.

[0107] Exemplarily, since the puncture risk heat map can characterize the puncture risk level around the initial puncture path, the target cranial entry point that is closest to the manual cranial entry point and meets the preset puncture risk level threshold can be determined from the puncture risk heat map; then, the target puncture path can be determined based on the target cranial entry point and the target point, that is, the target puncture path can be a straight line segment passing through the target cranial entry point and the target point.

[0108] In this embodiment, the computer device can generate a puncture risk heat map corresponding to the target tissue according to the puncture risk quantification value corresponding to each candidate puncture path; the puncture risk heat map is used to characterize the puncture risk degree around the initial puncture path; then, based on the puncture risk heat map, the initial puncture path is adjusted to determine the target puncture path. That is, in this embodiment, the risk heat map is used to mark the area around the initial puncture path, and the puncture risk heat map around the initial puncture path is obtained; then, the initial puncture path is adjusted based on the puncture risk heat map, and the target puncture path is finally obtained; using this method, the area around the initial puncture path can be marked with different puncture risk degrees, thereby improving the marking accuracy of the target puncture path.

[0109] In an exemplary embodiment, Figure 5 As shown, the above step 304 may also include steps 502 to 504. Among them:

[0110] Step 502: Display the puncture risk heat map.

[0111] In this example, the computer device may output and display the generated puncture risk heat map to show the user the puncture risk situation around the initial puncture path drawn by the computer device. Figure 6 As shown, it includes the entire scalp area, the safe area and the danger area.

[0112] Step 504: obtaining the user's adjustment operation on the initial puncture path based on the puncture risk heat map, and determining the target puncture path based on the adjustment operation.

[0113] Exemplarily, the manual cranial entry point corresponding to the initial puncture path can be displayed on the puncture risk heat map, and the user can adjust the position of the manual cranial entry point corresponding to the initial puncture path based on the puncture risk heat map to move the manual cranial entry point corresponding to the initial puncture path into a safe area; then, when the user determines the moved cranial entry point, the computer device can generate a target puncture path based on the moved cranial entry point and the target point.

[0114] Exemplarily, the user may also randomly select a cranial entry point within a safe area based on the puncture risk heat map, and the computer device may generate a target puncture path based on the cranial entry point and target point marked by the user on the puncture risk heat map.

[0115] For example, reference Figure 7 As shown, in the puncture risk heat map, the initial puncture path (such as Figure 7 The manual path shown in FIG), the candidate puncture paths generated by the computer device around the initial puncture path (such as Figure 7The planned path shown in ), the target points and entry points corresponding to each puncture path, and the entry area, etc.; the entry area is Figure 6 The range surrounded by the danger zone shown is the scalp mapping area where the sampling area is mapped onto the scalp, such as the light grey circular mapping area shown in FIG. 4( b ) and FIG. 4( c ).

[0116] based on Figure 7 As shown in the puncture risk heat map, the user can adjust the initial puncture path based on the candidate puncture paths recommended by the computer device; for example, the user can select any candidate puncture path as the target puncture path from the candidate puncture paths displayed in the puncture risk heat map.

[0117] In this embodiment, the computer device outputs and displays the puncture risk heat map so that the user can manually adjust the initial puncture path based on the puncture risk heat map; the computer device obtains the user's adjustment operation on the initial puncture path based on the puncture risk heat map, and determines the target puncture path based on the adjustment operation. That is, the puncture path planning method in this embodiment can not only automatically determine a safe target puncture path that meets the vascular interference condition for the user based on the initial puncture path input by the user, but also provide the user with the function of manually adjusting the puncture path, so as to provide the user with a full range of diverse path planning methods, thereby meeting the habits and personalized needs of different users and improving the diversity and flexibility of path planning.

[0118] In an exemplary embodiment, Figure 8 As shown, the above method may further include step 802 and step 804. Wherein:

[0119] Step 802: Generate a puncture path recommendation map corresponding to the target tissue according to the puncture risk quantification value corresponding to each candidate puncture path.

[0120] Wherein, in the case where the puncture risk quantification value is negatively correlated with the puncture risk degree, the puncture path recommendation map may include at least one candidate puncture path whose puncture risk quantification value is greater than or equal to the preset risk threshold. Of course, in the case where the puncture risk quantification value is positively correlated with the puncture risk degree, the puncture path recommendation map may include at least one candidate puncture path whose puncture risk quantification value is less than or equal to the preset risk threshold.

[0121] Exemplarily, when the puncture risk quantification value is negatively correlated with the puncture risk degree, the computer device can screen out at least one candidate puncture path whose puncture risk quantification value is greater than or equal to the preset risk threshold from each candidate puncture path according to the puncture risk quantification value corresponding to each candidate puncture path and the preset risk threshold, as a recommended puncture path; and generate a puncture path recommendation map corresponding to the target tissue according to the screened recommended puncture path.

[0122] Exemplarily, the preset risk threshold may be a fixed value or a variable value; that is, the user may flexibly adjust the preset risk threshold so that the computer device may generate different puncture path recommendation diagrams based on different preset risk thresholds to meet different needs of users.

[0123] Exemplarily, when the puncture risk quantification value corresponding to the candidate puncture path is within the range of 0-1, the preset risk threshold can be any value greater than 0 and less than 1; it should be noted that, when the puncture risk quantification value is negatively correlated with the puncture risk level, the larger the puncture risk quantification value, the smaller the puncture risk level and the higher the safety level of the puncture path. Referring to FIG9(a), it shows the puncture path recommendation diagram corresponding to the preset risk threshold of 0.7. In FIG9(a), from left to right, schematic diagrams of recommended puncture paths in different coordinate systems are shown in order to facilitate users to view the recommended puncture paths from different viewing angles. Referring to FIG9(b), it shows the puncture path recommendation diagram corresponding to the preset risk threshold of 0.6.

[0124] Among them, the black area around the candidate recommended path in Figure 9(a) and Figure 9(b) may be the area where the blood vessel is located; that is, the computer device may reconstruct the blood vessel based on the medical image of the site to be punctured, thereby obtaining a blood vessel reconstructed image; based on this, the computer device may fuse the blood vessel reconstructed image with the recommended puncture path for display, thereby obtaining a puncture path recommendation map.

[0125] In an optional implementation, when generating a puncture path recommendation map, the puncture risk quantification value corresponding to each candidate puncture path used can be calculated by weighted summing up the three parameters of vascular distance, puncture angle and puncture distance; and when generating a puncture risk heat map, the puncture risk quantification value corresponding to each candidate puncture path used can be calculated by weighted summing up the two parameters of vascular distance and puncture angle.

[0126] Of course, the puncture risk quantification value corresponding to each candidate puncture path in the puncture path recommendation map can also be calculated by weighted summation based on the two parameters of blood vessel distance and puncture angle; the puncture risk quantification value corresponding to each candidate puncture path in the puncture risk heat map can also be calculated by weighted summation based on the three parameters of blood vessel distance, puncture angle and puncture distance. It should be noted that when generating the puncture path recommendation map and the puncture risk heat map, the number and / or types of preset risk parameters involved in calculating the puncture risk quantification value corresponding to the candidate puncture path can be the same or different; the embodiment of the present application does not specifically limit this.

[0127] Since the puncture risk heat map is used to guide path fine-tuning, there is no need to calculate the puncture distance, that is, there is no need to consider the distance between the puncture point corresponding to each candidate puncture path and the puncture point corresponding to the initial puncture path. When generating the puncture path recommendation map, the puncture path recommended for the user can be comprehensively considered from more dimensions.

[0128] Accordingly, the above step 502 may further include:

[0129] Step 804: The puncture risk heat map and the puncture path recommendation map are merged and displayed.

[0130] refer to Figure 7 As shown, for Figure 7 The planned path shown in , which can be not only the candidate puncture path in the above embodiments, but also the recommended puncture path determined based on step 802; that is, in an optional implementation, the above Figure 3 The puncture risk heat map generated in the embodiment shown is fused with the puncture path recommendation map generated in step 802 and displayed, so as to obtain the following: Figure 7 The fused image shown.

[0131] In this embodiment, when the puncture risk quantification value is negatively correlated with the puncture risk degree, the computer device can also screen out recommended puncture paths with puncture risk quantification values ​​greater than or equal to the preset risk threshold from each candidate puncture path according to the puncture risk quantification value corresponding to each candidate puncture path and the preset risk threshold, and generate a puncture path recommendation map based on the screened recommended puncture path; based on this, the computer device can also merge and display the above puncture risk heat map with the puncture path recommendation map. Using the method in this embodiment, the computer device can use a variety of different image display methods to generate different forms of images for display to the user, so that the user can intuitively view the puncture risk for the target tissue from different angles or different dimensions, thereby providing the user with a variety of path planning methods, thereby meeting the habits and personalized needs of different users, and improving the diversity and flexibility of path planning.

[0132] In an exemplary embodiment, Fig.10 As shown, the above method may further include steps 1002 to 1006. Among them:

[0133] Step 1002, obtaining preset puncture risk parameters.

[0134] Exemplarily, the computer device may obtain a default puncture risk parameter from a preset storage location, or may receive a puncture risk parameter input by a user, etc.; the method for obtaining the puncture risk parameter is not specifically limited in this embodiment.

[0135] Exemplarily, the puncture risk parameter may include at least one of a blood vessel distance, a puncture angle and a puncture distance; wherein the blood vessel distance is the minimum distance between the puncture path and the blood vessel; the puncture angle is the angle between the puncture path and the corresponding normal vector, the normal vector is a vector perpendicular to the tangent plane at the intersection of the puncture path and a preset surface, the preset surface may include a skin surface corresponding to the target tissue, or the surface of other tissues passed by the puncture path, such as a skull surface, and any one of user-defined surfaces, etc.; the puncture distance is the distance between the puncture point corresponding to the puncture path and the puncture point corresponding to the initial puncture path, the puncture point corresponding to the puncture path may be the intersection between the puncture path and the preset surface, such as the intersection between the puncture path and the skin surface corresponding to the target tissue, or the intersection between the puncture path and other surfaces, etc.

[0136] It should be noted that the puncture risk parameters may also include other parameters that can characterize the degree of puncture risk in addition to the blood vessel distance, puncture angle and puncture distance. When the puncture risk parameters include multiple ones, the computer device can evaluate the puncture risk degree of the puncture path according to any number of puncture risk parameters to obtain a quantified value of the puncture risk of the puncture path.

[0137] Step 1004: for each candidate puncture path, determine a parameter value corresponding to the puncture risk parameter of the candidate puncture path.

[0138] That is, for each candidate puncture path, the blood vessel distance value, puncture angle value, and puncture distance value of the candidate puncture path are determined.

[0139] Exemplarily, for the blood vessel distance parameter, the computer device may calculate the minimum distance between the candidate puncture path and the blood vessel based on the reconstructed blood vessel image, and obtain the blood vessel distance value of the candidate puncture path.

[0140] For example, for the puncture angle parameter, refer to Fig.11 As shown; the computer device can determine the direction vector n1 corresponding to the candidate puncture path according to the candidate puncture path; and based on the intersection point p between the candidate puncture path and the skin surface corresponding to the target tissue, determine the normal vector n2 perpendicular to the tangent plane at the intersection point p; then, calculate the angle β between the direction vector n1 and the corresponding normal vector n2 to obtain the puncture angle value of the candidate puncture path.

[0141] Exemplarily, for the puncture distance value, the computer device can calculate the distance between the two puncture points according to the puncture point corresponding to the candidate puncture path and the puncture point corresponding to the initial puncture path, as the puncture distance value of the candidate puncture path; wherein the puncture point corresponding to the puncture path can be the intersection between the puncture path and a preset surface, such as the intersection between the puncture path and the skin surface corresponding to the target tissue, or the intersection between the puncture path and other surfaces, etc.

[0142] Step 1006: Determine a puncture risk quantification value corresponding to the candidate puncture path based on the parameter value of the candidate puncture path.

[0143] Exemplarily, when the preset puncture risk parameters include multiple ones, the computer device may perform weighted summation on the parameter values ​​corresponding to the puncture risk parameters of the candidate puncture path to obtain the puncture risk quantification value corresponding to the candidate puncture path.

[0144] The following is an explanation using the preset puncture risk parameters including the blood vessel distance L, the puncture angle A and the puncture distance R as an example.

[0145] For example, assuming that the first set S A Each candidate puncture path P is stored in i (i=0,|i∈N), where N is the number of candidate puncture paths; in the first set S A Each candidate puncture path P can be stored in i The corresponding puncture point position coordinate information. It should be noted that the first set S A It can be the subsequent puncture path set S that satisfies both the vascular interference condition and the puncture angle condition. A .

[0146] For each candidate puncture path P i , the candidate puncture path P i The blood vessel distance L i 、Puncture angle A i and puncture distance R i , stored in the parameter set F pi Middle, that is, F pi ={L i ,A i ,R i}; Then, the computer device can i The corresponding parameter set F pi Add to the second set S n middle.

[0147] Exemplarily, the computer device may perform the second set S n Normalize the parameters in the set S nThe parameters are normalized according to categories, namely, vessel distance, puncture angle, and puncture distance, and the original parameters are replaced.

[0148] Assume that the parameter set of blood vessel distance can be recorded as V 1 , V 1 ={S ni (L),|i∈N}.

[0149] Assume that the parameter set of the puncture angle can be recorded as V 2 , V 2 ={S ni (A),|i∈N}.

[0150] Assume that the parameter set of the puncture distance can be recorded as V 3 , V 3 ={S ni (R),|i∈N}.

[0151] V 1 、V 2 、V 3 The elements in are normalized to the maximum and minimum values ​​(Min-Max) respectively, and the calculation formula is as follows:

[0152]

[0153] The normalized sets obtained are N 1 、N 2 、N 3 .

[0154] For the vascular distance value, the larger the vascular distance, the safer it is. However, for the puncture angle value and puncture distance value, the smaller the puncture angle value and the puncture distance value, the safer it is. Therefore, the features of the puncture angle and puncture distance need to be processed in reverse sequence, that is, N 2 = {1-N 2i ,|i∈N},N 3 = {1-N 3i ,|i∈N}.

[0155] For the second set S n Update the parameters in, use the normalized and deserialized parameters to replace the original parameters, and obtain the updated second set S n .

[0156] S n ={S ni (V 1i ,V 2i ,V 3i ),|i∈N}

[0157] Next, for each candidate puncture path, the puncture risk quantification value corresponding to the candidate puncture path is calculated. n In the above example, a candidate puncture path P is selected. i The corresponding parameter set F pi (V 1i ,V 2i ,V 3i ,|i∈N), and from the first set S A Take out the candidate puncture path P i Corresponding puncture point E i , E i ={(x,y,z),|i∈N}; and calculate the candidate puncture path P according to the following cost function: i The corresponding puncture risk quantification value.

[0158] Cost function:

[0159] f(P i )=W V *V 1i +W e *V 2i +W a *V 3i

[0160] Among them, W V is the weight corresponding to the vessel distance parameter, V 1i is the candidate puncture path P i Corresponding blood vessel distance value; W e is the weight corresponding to the puncture angle parameter, V 2i is the candidate puncture path P i Corresponding puncture angle value; W a is the weight corresponding to the puncture distance parameter, V 3i is the candidate puncture path P i The corresponding puncture distance value.

[0161] The calculated candidate puncture path P i The corresponding puncture risk quantification value and the candidate puncture path P i Corresponding puncture point E i Associate and store in the third set S P In the same way, the puncture risk quantification value corresponding to each candidate puncture path is calculated in turn, and finally a third set S including the puncture points and puncture risk quantification values ​​corresponding to each candidate puncture path is obtained. P , S P ={f(P i ), E i =(x,y,z)|i∈N}.

[0162] For example, the computer device can obtain different cost function values ​​by setting different weights corresponding to the three features of blood vessel distance, puncture angle, and puncture distance, and these values ​​are added to the third set S P In the third set S, according to the value of the cost function P By filtering and classifying the paths in , hierarchical display and recommendation of different paths can be completed; as shown in Figure 9(a) and Figure 9(b).

[0163] In this embodiment, the computer device can obtain preset puncture risk parameters, and for each candidate puncture path, determine the parameter value corresponding to at least one puncture risk parameter of the candidate puncture path; then, based on at least one parameter value of the candidate puncture path, determine the puncture risk quantification value corresponding to the candidate puncture path. Using this method, the computer device can quantify the puncture risk of the candidate puncture path from one or more dimensions, thereby obtaining a puncture risk quantification value that can be used to characterize the degree of puncture risk, providing data basis for subsequent path recommendation and path adjustment, and improving the reliability and accuracy of path planning.

[0164] In an exemplary embodiment, Fig.12 As shown, the above step 204 may also include steps 1202 to 1206. Among them:

[0165] Step 1202: determine multiple original puncture paths around the initial puncture path on the medical image according to a preset search range.

[0166] Exemplarily, referring to FIG. 13( a), the user can draw an initial puncture path on the medical image, and the initial puncture path can include a starting point (such as a manual starting point E) and an end point (such as a target point T) manually planned by the user; it should be noted that the manual starting point E can be a point inside the scalp, a point on the scalp, or a point outside the scalp; when the manual starting point E is a point inside the scalp, it can be a point on the surface of the target tissue inside the scalp, a point inside the target tissue, or a point outside the target tissue, etc.

[0167] For example, when the computer device obtains the initial puncture path, it can draw the intelligent planning path range with the manual starting point as the bottom center of the cone, the preset search radius as the bottom radius of the cone, and the end point as the vertex of the cone, as shown in the dotted line range of Figure 13 (b). The intelligent planning path range is used to instruct the computer device to determine the puncture path within the range, and to perform tissue interference detection on the puncture path within the range; that is, the intelligent planning path range here is the preset search range mentioned above.

[0168] Exemplarily, the computer device can determine the search sphere with the manual starting point E as the center of the sphere and the preset search radius as the radius of the sphere; and determine multiple planning starting points on the search sphere according to the preset step size, as shown in FIG13(c); since the sphere is a symmetrical structure, taking the manual starting point E on the outside of the scalp as an example, for the points on the hemispherical surface away from the scalp (such as the dark points in FIG13(c)) and the points on the hemispherical surface close to the scalp (such as the light points in FIG13(c)), when the two points are symmetrical with respect to the central curved surface, the line segments from the target point to the two points will overlap with each other; therefore, for the multiple planning starting points on the search sphere, the computer device can take the planning starting point on one side of the sphere, such as taking the planning starting point on the hemispherical surface away from the scalp, and connect them with the target point respectively, so as to obtain multiple original puncture paths around the initial puncture path, as shown in FIG13(d).

[0169] Step 1202: Filter out original puncture paths that meet preset filtering conditions from multiple original puncture paths.

[0170] The preset screening condition may include a blood vessel interference condition, and the blood vessel interference condition may include that the blood vessel distance is greater than or equal to a preset distance threshold, and the blood vessel distance is the minimum distance between the puncture path and the blood vessel.

[0171] For example, when multiple original puncture paths (which can be recorded as an original puncture path set) are obtained around the initial puncture path, the minimum distance between the original puncture path and the blood vessel can be determined for each original puncture path to obtain the blood vessel distance value L corresponding to the original puncture path. min Next, it can be determined whether the blood vessel distance value corresponding to the original puncture path is greater than or equal to the preset distance threshold D V ; If the blood vessel distance value corresponding to the original puncture path is greater than or equal to the preset distance threshold, that is, L min ≥D V , it can be determined that there is no blood vessel interference in the original puncture path, that is, the original puncture path is safe; if the blood vessel distance value corresponding to the original puncture path is less than the preset distance threshold, that is, L min <D V , it can be indicated that there is blood vessel interference in the original puncture path, and the original puncture path can be removed from the original puncture path set, and only the safe puncture path is retained.

[0172] Alternatively, the blood vessel distance value may be greater than a preset distance threshold, i.e., L min >D V The original puncture path is determined as a safe puncture path; the blood vessel distance value is less than or equal to the preset distance threshold, i.e., L min ≤D V The original puncture path is determined as the puncture path with blood vessel interference and is eliminated.

[0173] Exemplarily, the computer device can perform vascular reconstruction based on the medical image of the tissue to be punctured to obtain an initial vascular reconstruction image; then, the computer device can also determine the vascular reconstruction image within the intelligent planning path range from the initial vascular reconstruction image based on the intelligent planning path range shown in FIG. 13(b). Exemplarily, the computer device can also determine the vascular reconstruction image within the acquisition area from the initial vascular reconstruction image based on the acquisition area of ​​other vascular points; for example, the acquisition area of ​​the vascular point can include a cylindrical area drawn with the initial planning path as the central axis according to a preset search radius, and the obtained vascular reconstruction image within the cylindrical area can be as follows: Fig.14 shown.

[0174] Next, based on the reconstructed blood vessel image, the minimum distance between each original puncture path and the blood vessel can be calculated, and based on the minimum distance between each original puncture path and the blood vessel, the original puncture path that meets the blood vessel interference condition is screened out from multiple original puncture paths, such as Fig.15 As shown. For example, the original puncture path set without blood vessel interference path can be recorded as S V .

[0175] Exemplarily, the preset screening conditions may include other screening conditions in addition to the vascular interference condition, such as other tissue interference conditions, puncture angle conditions, etc.; wherein the puncture angle condition may be that the angle between the puncture path and the corresponding normal vector is less than or equal to a preset angle threshold, the normal vector is a vector perpendicular to the tangent plane at the intersection of the puncture path and the preset curved surface, and the preset curved surface may include a skin surface corresponding to the target tissue; for example Fig.11 The angle between the puncture path and the scalp normal vector is shown.

[0176] Exemplarily, in the case where the preset screening conditions include multiple ones, the computer device may screen out original puncture paths that simultaneously meet multiple screening conditions from multiple original puncture paths as candidate puncture paths.

[0177] For example, when the preset screening condition also includes the puncture angle condition, the computer device determines the original puncture path (i.e., the puncture path set S) that satisfies the vascular interference condition. V ), further, for the puncture path set S V The puncture angle values ​​β of the original puncture paths in the set S are determined respectively; then, from the puncture path set S V In the experiment, the puncture angle value β is less than or equal to the preset angle threshold D. a , that is, β≤D a The original puncture path is added to the new puncture path set SA In other words, we get a set of puncture paths S that satisfy both the vascular interference condition and the puncture angle condition. A . refer to Fig.16 As shown, it shows a puncture path that satisfies both the vascular interference condition and the puncture angle condition.

[0178] Step 1202: taking the original puncture paths that meet the preset screening conditions as candidate puncture paths.

[0179] Exemplarily, in the case where the preset screening conditions include multiple ones, the computer device may determine, from multiple original puncture paths around the initial puncture path, an original puncture path that simultaneously satisfies the multiple screening conditions as a candidate puncture path.

[0180] In this embodiment, the computer device determines multiple original puncture paths around the initial puncture path on the medical image according to a preset search radius; then, the original puncture paths that meet the preset screening conditions are screened out from the multiple original puncture paths, and the original puncture paths that meet the preset screening conditions are used as candidate puncture paths; wherein the preset screening conditions include vascular interference conditions; that is, in this embodiment, the computer device can screen the original puncture paths within the search area determined based on the preset search radius based on at least one screening condition including the vascular interference condition, and finally obtain the candidate puncture paths that meet the user's requirements; adopting this method, the accuracy of the candidate puncture paths can be improved, thereby obtaining a puncture path that is more adaptable to the user's requirements.

[0181] In an alternative embodiment, reference Fig.17 As shown, it shows a workflow diagram of path planning. Taking brain path planning as an example, it includes the following steps:

[0182] 1. Load complete brain vascular imaging data. If the brain vascular imaging data is MR data, then based on the brain vascular imaging data, a brain vascular reconstruction image and a brain scalp reconstruction image can be reconstructed; if the brain vascular imaging data is CT data, then based on the brain vascular imaging data, a brain vascular reconstruction image and a brain scalp reconstruction image (or a brain skull reconstruction image) can be reconstructed.

[0183] 2. The user selects a starting point (manual starting point) and an end point (target point) in the brain vascular imaging data to manually plan an initial puncture path, as shown in FIG13(a); in addition, the user can also set a preset search radius as the base radius of the cone, and use the manual starting point entered by the user as the base center point of the cone, and the end point entered by the user as the vertex of the cone to automatically draw the search area, as shown in FIG13(b).

[0184] 3. The computer device calls the automatic path fine-tuning algorithm to plan a safe path around the initial puncture path (i.e., within the search area), i.e., the above-mentioned candidate puncture path; and marks the surrounding plannable area; for the specific implementation process, please refer to the relevant content description shown in Figure 13 above.

[0185] 4. According to the set constraint information (such as the threshold of the above-mentioned cost function), the planned safe paths are recommended in layers, that is, paths with smaller risk values ​​(that is, larger cost function values) are recommended, as shown in Figures 9(a) and 9(b).

[0186] 5. According to the plannable area marked in step 3, the area around the manually planned initial puncture path is divided into a safe area and a risk area, a puncture risk heat map is generated, and the puncture risk heat map is displayed; Figure 6 and Figure 7 shown.

[0187] 6. Based on the guidance of the puncture risk heat map, the user can independently adjust the manually planned initial puncture path or the automatically planned recommended puncture path.

[0188] For example, taking brain tissue as an example, refer to Figure 7 As shown, the user can fix the target point and move the entry point (such as Figure 7 The manual cranial entry point shown in ) is adjusted to the risk heat map area (such as Figure 7 Then, according to the prompts of the puncture risk heat map, the entry point of the automatically planned path or the manual path can be adjusted to a safe area (such as Figure 6 in a safe area, or Figure 7 or, the user may select any point in the safe area as the cranial entry point according to the needs of different actual scenarios; after the adjusted cranial entry point is confirmed by the user, the computer device may generate a target puncture path according to the target point and the determined cranial entry point, and add the target puncture path to the path pool.

[0189] In this workflow, the user first roughly plans a path, and then the automatic adjustment algorithm automatically adjusts the path according to the user's planned path to ensure that the path changes as little as possible while avoiding critical intracranial tissues; further, the automatic adjustment algorithm will calculate all feasible path plannable areas near the user's planned path and display them to the user in the form of a 3D risk heat map, so that the user can intuitively and concisely adjust the entry point by dragging under the guidance of the 3D risk heat map, and make secondary fine-tuning. The whole process fully combines the efficient calculation of computers with human experience to achieve efficient and accurate puncture path planning.

[0190] This method combines image processing technology and sets path constraints, including the minimum distance between the puncture path and the blood vessel, the puncture angle, the path planning area, etc., to calculate a safe puncture path that meets the constraints, and stratifies the risks of the planned safe puncture path, and recommends different planned safe puncture paths according to different scenarios. In addition, a risk heat map is generated at the entry point of the manually planned path, and the nearby dangerous areas are displayed through visualization technology. Users can drag the entry point of the manually or automatically planned safe puncture path according to the risk heat map, and then adjust the path. It can not only make dynamic adjustments based on user experience, but also safely and effectively avoid key tissues such as blood vessels.

[0191] The puncture path rapid planning workflow in this embodiment includes three main steps: manual pre-planning, automatic path fine-tuning, and risk visualization guided fine-tuning. The entire planning process has a high degree of human-machine integration, an efficient process, and accurate results. In addition, the path automatic adjustment algorithm can plan a new path around the path manually planned by the user by setting constraints, and perform risk stratification on different paths to recommend a path with a lower risk value. The recommended path not only maintains the user's experience, but also quickly meets all hard constraints in path planning, including but not limited to vascular interference conditions and puncture angle conditions. Furthermore, the path planning algorithm uses visualization rendering technology and a path risk calculation algorithm to generate a risk heat map at the cranial entry point of the user's planned path, and attaches the risk heat map to the skin surface. The risk heat map can help users intuitively judge the safety of the path and assist in the rapid adjustment of the path entry point.

[0192] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0193] Based on the same inventive concept, the embodiment of the present application also provides a path planning device for implementing the path planning method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more path planning device embodiments provided below can refer to the limitations of the path planning method above, and will not be repeated here.

[0194] In an exemplary embodiment, Fig.18 As shown, a path planning device is provided, including: a first acquisition module 1802, a first determination module 1804 and a second determination module 1806, wherein:

[0195] The first acquisition module 1802 is used to acquire an initial puncture path and a preset search range; the initial puncture path is a puncture path input by a user for a target tissue in a medical image.

[0196] The first determination module 1804 is used to determine multiple candidate puncture paths around the initial puncture path on the medical image according to a preset search range; the candidate puncture paths are puncture paths that meet the vascular interference conditions, the vascular interference conditions include that the vascular distance is greater than or equal to a preset distance threshold, and the vascular distance is the minimum distance between the puncture path and the blood vessel.

[0197] The second determination module 1806 is used to determine the target puncture path according to the puncture risk quantification value corresponding to each candidate puncture path.

[0198] In one embodiment, the second determination module 1806 is specifically configured to adjust the initial puncture path according to the puncture risk quantification value corresponding to each candidate puncture path, and determine the target puncture path.

[0199] In one embodiment, the second determination module 1806 is specifically configured to determine a target puncture path from among the candidate puncture paths according to the puncture risk quantification value corresponding to each candidate puncture path.

[0200] In one embodiment, the second determining module 1806 includes:

[0201] A generation submodule is used to generate a puncture risk heat map corresponding to the target tissue according to the puncture risk quantification value corresponding to each candidate puncture path; the puncture risk heat map is used to characterize the puncture risk degree around the initial puncture path;

[0202] The first determination submodule is used to adjust the initial puncture path based on the puncture risk heat map to determine the target puncture path.

[0203] In one embodiment, determining the submodule includes:

[0204] A display unit, used for displaying a puncture risk heat map;

[0205] The determination unit is used to obtain the user's adjustment operation on the initial puncture path based on the puncture risk heat map, and determine the target puncture path based on the adjustment operation.

[0206] In one embodiment, the device further comprises:

[0207] A generating module, configured to generate a puncture path recommendation map corresponding to the target tissue according to the puncture risk quantification value corresponding to each candidate puncture path; the puncture path recommendation map includes at least one candidate puncture path whose puncture risk quantification value is greater than or equal to a preset risk threshold;

[0208] Correspondingly, the display unit is specifically used to fuse and display the puncture risk heat map and the puncture path recommendation map.

[0209] In one embodiment, the device further comprises:

[0210] A second acquisition module is used to acquire preset puncture risk parameters;

[0211] A third determination module is used to determine, for each candidate puncture path, a parameter value corresponding to the puncture risk parameter of the candidate puncture path;

[0212] The fourth determination module is used to determine the puncture risk quantification value corresponding to the candidate puncture path based on the parameter value of the candidate puncture path.

[0213] In one embodiment, the puncture risk parameter includes at least one of a blood vessel distance, a puncture angle and a puncture distance; wherein the puncture angle is the angle between the puncture path and the corresponding normal vector, the normal vector is a vector perpendicular to the tangent plane at the intersection of the puncture path and a preset surface, and the preset surface may include a skin surface corresponding to the target tissue; the puncture distance is the distance between the puncture point corresponding to the puncture path and the puncture point corresponding to the initial puncture path.

[0214] In one embodiment, the first determining module 1804 includes:

[0215] A second determination submodule is used to determine a plurality of original puncture paths around the initial puncture path on the medical image according to a preset search range;

[0216] A screening submodule, used to screen out original puncture paths that meet preset screening conditions from multiple original puncture paths; the preset screening conditions include vascular interference conditions;

[0217] The third determination submodule is used to take the original puncture paths that meet the preset screening conditions as candidate puncture paths.

[0218] In one embodiment, the preset screening condition also includes a puncture angle condition, where the puncture angle condition is that the angle between the puncture path and the corresponding normal vector is less than or equal to a preset angle threshold, and the normal vector is a vector perpendicular to the tangent plane at the intersection of the puncture path and the preset surface, and the preset surface may include a skin surface corresponding to the target tissue.

[0219] Each module in the above-mentioned path planning device can be implemented in whole or in part by software, hardware or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0220] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Fig.19 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a path planning method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0221] Those skilled in the art will understand that Fig.19 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0222] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of the path planning method in any of the above embodiments are implemented.

[0223] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the path planning method in any of the above embodiments are implemented.

[0224] In one embodiment, a computer program product is provided, including a computer program, which implements the steps of the path planning method in any of the above embodiments when executed by a processor.

[0225] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0226] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0227] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0228] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A path planning method, It is characterized in that The method comprises: Acquire an initial puncture path and a preset search range; the initial puncture path is a puncture path input by a user for a target tissue in a medical image; Determine multiple candidate puncture paths around the initial puncture path on the medical image according to the preset search range; the candidate puncture paths are puncture paths that meet a vascular interference condition, the vascular interference condition includes that a vascular distance is greater than or equal to a preset distance threshold, and the vascular distance is a minimum distance between a puncture path and a blood vessel; A target puncture path is determined according to the puncture risk quantification value corresponding to each of the candidate puncture paths.

2. The method according to claim 1, It is characterized in that The step of determining a target puncture path according to the puncture risk quantification value corresponding to each candidate puncture path includes: According to the puncture risk quantification value corresponding to each of the candidate puncture paths, the initial puncture path is adjusted to determine the target puncture path.

3. The method according to claim 1, It is characterized in that The step of determining a target puncture path according to the puncture risk quantification value corresponding to each candidate puncture path includes: The target puncture path is determined from the candidate puncture paths according to the puncture risk quantification value corresponding to each of the candidate puncture paths.

4. The method according to claim 2, It is characterized in that The adjusting the initial puncture path according to the puncture risk quantification value corresponding to each candidate puncture path to determine the target puncture path includes: Generating a puncture risk heat map corresponding to the target tissue according to the puncture risk quantification value corresponding to each candidate puncture path; the puncture risk heat map is used to characterize the puncture risk degree around the initial puncture path; Based on the puncture risk heat map, the initial puncture path is adjusted to determine the target puncture path.

5. The method according to claim 4, It is characterized in that The adjusting the initial puncture path based on the puncture risk heat map to determine the target puncture path includes: Displaying the puncture risk heat map; An adjustment operation of the user on the initial puncture path based on the puncture risk heat map is obtained, and the target puncture path is determined based on the adjustment operation.

6. The method according to claim 5, It is characterized in that The method further comprises: Generate a puncture path recommendation map corresponding to the target tissue according to the puncture risk quantification value corresponding to each of the candidate puncture paths; the puncture path recommendation map includes at least one candidate puncture path whose puncture risk quantification value is greater than or equal to a preset risk threshold; Accordingly, displaying the puncture risk heat map includes: The puncture risk heat map and the puncture path recommendation map are fused and displayed.

7. The method according to claim 4, It is characterized in that The method further comprises: Obtaining preset puncture risk parameters; For each of the candidate puncture paths, determining a parameter value corresponding to the puncture risk parameter of the candidate puncture path; Based on the parameter value of the candidate puncture path, a puncture risk quantification value corresponding to the candidate puncture path is determined.

8. The method according to claim 7, It is characterized in that The puncture risk parameter includes at least one of the blood vessel distance, the puncture angle and the puncture distance; The puncture angle is the angle between the puncture path and the corresponding normal vector, and the normal vector is a vector perpendicular to the tangent plane at the intersection of the puncture path and the preset curved surface; The puncture distance is the distance between the puncture point corresponding to the puncture path and the puncture point corresponding to the initial puncture path.

9. The method according to claim 1, It is characterized in that The step of determining a plurality of candidate puncture paths around the initial puncture path on the medical image according to the preset search range includes: Determining a plurality of original puncture paths around the initial puncture path on the medical image according to the preset search range; Filtering out an original puncture path that meets a preset screening condition from the multiple original puncture paths; the preset screening condition includes the blood vessel interference condition; The original puncture path that meets the preset screening condition is used as the candidate puncture path.

10. The method according to claim 9, It is characterized in that The preset screening condition also includes a puncture angle condition, where the puncture angle condition is that the angle between the puncture path and the corresponding normal vector is less than or equal to a preset angle threshold, and the normal vector is a vector perpendicular to the tangent plane at the intersection of the puncture path and the preset surface.

11. A path planning device, It is characterized in that The device comprises: A first acquisition module is used to acquire an initial puncture path and a preset search range; the initial puncture path is a puncture path input by a user for a target tissue in a medical image; A first determination module is used to determine a plurality of candidate puncture paths around the initial puncture path on the medical image according to the preset search range; the candidate puncture paths are puncture paths that meet a vascular interference condition, the vascular interference condition includes that a vascular distance is greater than or equal to a preset distance threshold, and the vascular distance is a minimum distance between a puncture path and a blood vessel; The second determination module is used to determine the target puncture path according to the puncture risk quantification value corresponding to each of the candidate puncture paths.

12. A computer device comprising a memory and a processor, wherein the memory stores a computer program. It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 10 are implemented.

13. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.

Images