Intelligent scheduling method and system for neurosurgical robot

Abstract

The invention relates to the technical field of brain blood vessel recognition in neurosurgery, in particular to an intelligent scheduling method and system for a neurosurgery robot. Based on a brain blood vessel image, edge pixel points are extracted through edge detection, and a main blood vessel path is generated. After a reference pixel point is selected, an exploration value is calculated according to gradient and gray level distribution of non-edge pixels in a neighborhood of the reference pixel point, and target pixel points with non-zero exploration values are screened out. And marking the edge pixel with the target pixel in the neighborhood as a to-be-analyzed point, and generating an exploration path in combination with the target pixel distribution and the exploration value. And according to the exploration value of the target pixel in the path, screening out the brain fine blood vessel path. And finally integrating paths of the main blood vessel and the fine blood vessels, and guiding operation scheduling of the neurosurgical robot. The brain microvessels can be accurately identified, so that the efficiency of related personnel working by using the neurosurgical robot is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of brain blood vessel identification during neurosurgery, and in particular to an intelligent scheduling method and system for a neurosurgery robot. Background Art

[0002] The neurosurgery robot is a computer-assisted surgery platform that integrates artificial intelligence, precision machinery, and multimodal imaging technologies, specifically designed for high-precision brain and spinal surgery. Its core is to achieve submillimeter operational accuracy through the collaboration of a robotic arm, a visual system, and an intelligent control system, significantly improving surgical safety and efficiency. By effectively combining medical image processing assistance systems, robots, and surgeons, it enables preoperative simulation of the surgical environment, planning of surgical procedures, and automated, precise spatial positioning of surgical instruments during surgery. Innovative technologies such as 3D structured light enable rapid positioning and registration while enabling augmented reality projection, projecting lesions, important functional areas, and fiber bundles into real space.

[0003] When using neurosurgery robots to complete related work, relevant personnel first need to identify the brain's vascular area; however, the hidden nature of the brain's tiny blood vessels makes it impossible for conventional image segmentation algorithms to accurately identify them, which increases the difficulty and inefficiency of relevant personnel when using neurosurgery robots. Summary of the Invention

[0004] In order to solve the technical problem that the hidden nature of brain micro-vessels makes it difficult for conventional image segmentation algorithms to accurately identify them, thereby increasing the difficulty and inefficiency of relevant personnel when using neurosurgery robots, the purpose of the present invention is to provide a method and system for intelligent scheduling of neurosurgery robots. The technical solutions adopted are as follows:

[0005] A method for intelligent scheduling of a neurosurgery robot, comprising:

[0006] Obtain images of brain blood vessels;

[0007] Perform edge detection on the brain vascular image to obtain all edge pixels; obtain the main vascular path composed of all edge pixels; select any edge pixel as a reference pixel; obtain the exploration value of each non-edge pixel in the preset neighborhood of the reference pixel based on the gradient distribution characteristics and grayscale distribution characteristics of the non-edge pixels in the preset neighborhood of the reference pixel; use the non-edge pixel with a non-zero exploration value as the target pixel; use the edge pixel in the preset neighborhood where the target pixel exists as the pixel to be analyzed; obtain the exploration path of each pixel to be analyzed based on the distribution characteristics of the target pixels around each pixel to be analyzed and the exploration value of the target pixel; screen all exploration paths based on the exploration value of each target pixel in the exploration path to obtain the brain microvascular path;

[0008] The neurosurgery robot is assisted in scheduling according to the main blood vessel path and the brain microvascular path.

[0009] Furthermore, the method for obtaining the exploration value of the non-edge pixel point includes:

[0010] The exploration value is obtained according to the exploration value calculation formula, which is as follows:

[0011]

[0012] Where E represents the exploration value of each non-edge pixel in the preset neighborhood of the reference pixel; N represents the number of non-edge pixels in the preset neighborhood of the reference pixel; t represents the gradient value of each non-edge pixel in the preset neighborhood of the reference pixel; t n represents the gradient value of the nth non-edge pixel in the preset neighborhood of the reference pixel, excluding the calculated non-edge pixel; M represents the number of non-edge pixels in the brain vascular image; t m Represents the gradient value of the mth non-edge pixel in the brain blood vessel image; represents the gradient mean of all non-edge pixels in the brain vascular image; f represents the grayscale value of each non-edge pixel in the preset neighborhood of the reference pixel; [] represents Iverson brackets, where the value is 1 if the condition in the brackets is met, and 0 if the condition is not met;

[0013] When there are non-edge pixels with multiple exploration values ​​in the preset neighborhood of an edge pixel, the mean of all exploration values ​​is calculated as the exploration value of such non-edge pixel.

[0014] Furthermore, the method for obtaining the exploration path includes:

[0015] When there is no target pixel in the preset neighborhood of the pixel to be analyzed, it is considered that there is no exploration path in the preset neighborhood of the pixel to be analyzed;

[0016] When there is a target pixel point in the preset neighborhood of the pixel point to be analyzed, the target pixel points in the preset neighborhood of the pixel point to be analyzed are traversed according to the continuity characteristics of the target pixel points in the preset neighborhood of the pixel point to be analyzed to obtain a first exploration path of the pixel point to be analyzed;

[0017] When there are two or more target pixels in the preset neighborhood of the pixel to be analyzed, the target pixels in the preset neighborhood of the pixel to be analyzed are traversed according to the continuity characteristics around each target pixel to obtain a second exploration path for the pixel to be analyzed;

[0018] The first exploration path and the second exploration path are collectively referred to as the exploration path of the pixel point to be analyzed.

[0019] Furthermore, the method for obtaining the first exploration path includes:

[0020] When there is a target pixel point in the preset neighborhood of the pixel point to be analyzed, the number of target pixels in the preset neighborhood of the target pixel point is searched with the target pixel point as the center. If the number is 1, the above steps are repeated until there is no target pixel point in the preset neighborhood or there are two or more target pixels. The path composed of all the above target pixels is used as the first exploration path of the pixel point to be analyzed.

[0021] Furthermore, the method for obtaining the second exploration path includes:

[0022] When there are two or more target pixel points in the preset neighborhood of the pixel point to be analyzed, take each target pixel point as the pixel point to be traversed, and take each pixel point to be traversed as the center, and find the number of target pixel points in the preset neighborhood of the pixel point to be traversed. If the number is 1, repeat the above steps until there is no target pixel point in the preset neighborhood or there are two or more target pixel points, and stop. The path composed of the above target pixel points and the pixel points to be traversed is used as the corresponding second exploration path of each pixel point to be traversed in the preset neighborhood of the pixel point to be analyzed; traverse each pixel point to be traversed in the preset neighborhood of the pixel point to be analyzed to obtain all the second exploration paths of the pixel point to be analyzed.

[0023] Furthermore, the method for obtaining the path of brain micro-vasculars includes:

[0024] When there is a target pixel in the preset neighborhood of the pixel to be analyzed, the first exploration path of the pixel to be analyzed is used as the path of the brain microvascular;

[0025] When there are two or more target pixels in the preset neighborhood of the pixel to be analyzed, the exploration authenticity of each second exploration path is obtained according to the difference in exploration values ​​of the target pixels in each second exploration path of the pixel to be analyzed. The formula is as follows:

[0026]

[0027] Where, Ea j represents the exploration authenticity of the jth second exploration path of the pixel to be analyzed; e j represents the exploration value of the pixel points to be traversed in the j-th second exploration path; ∑E represents the sum of the exploration values ​​of the pixel points to be traversed in all second exploration paths; a represents the difference between the maximum number of target pixels in all second exploration paths and the number of target pixels in the j-th second exploration path; I represents the number of target pixels in the j-th second exploration path; E i represents the exploration value of the i-th target pixel point in the j-th second exploration path;

[0028] The second exploration path that explores the pixel point to be analyzed with the greatest degree of authenticity is used as the brain microvascular path.

[0029] A neurosurgical robot intelligent scheduling system, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of a neurosurgical robot intelligent scheduling method as claimed in any one of claims 1 to 6 when executing the computer program.

[0030] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned intelligent scheduling method for a neurosurgical robot.

[0031] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned intelligent scheduling method for a neurosurgical robot are implemented.

[0032] The present invention has the following beneficial effects:

[0033] The present invention obtains a brain vascular image. Because the distribution of brain blood vessels, based on their physical shape, includes thick main vascular pathways and some fine vessels that are difficult to distinguish with the naked eye, and because the fine vessels have grayscale values ​​relatively close to the background, conventional image segmentation algorithms cannot identify the fine vessels. Therefore, the thick main vascular pathway is first confirmed, and then the gradient features and grayscale features around edge pixels are subsequently analyzed point by point to obtain the exploration value of each non-edge pixel within a preset neighborhood of the edge pixel. Because two fine vessels originating from a main vessel are separated by a distance, it is rare for two fine vessels to be separated by more than a few pixels. Therefore, if two or more non-edge pixels within the preset neighborhood of a non-edge pixel have exploration values ​​that are not zero, it indicates that such non-edge pixels are not true fine vessel pixels. Therefore, based on the distribution characteristics of target pixels around each pixel to be analyzed and the exploration value of the target pixel, an exploration path for each pixel to be analyzed is obtained. The exploration value differences of each exploration path are analyzed to obtain the brain fine vessel pathway. The main vascular pathway is combined with the main vascular pathway to assist in scheduling a neurosurgical robot. The present invention can accurately identify tiny blood vessels in the brain, thereby increasing the efficiency of relevant personnel when using a neurosurgery robot to perform work. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0035] Figure 1 A flowchart of an intelligent scheduling method for a neurosurgery robot provided by one embodiment of the present invention;

[0036] Figure 2 This is a block diagram of an intelligent scheduling system for a neurosurgery robot provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0037] To further illustrate the technical means and effectiveness of the present invention in achieving its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail the specific implementation, structure, features, and effectiveness of a method and system for intelligent scheduling of a neurosurgical surgical robot proposed in accordance with the present invention. In the following description, references to different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0038] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0039] The specific scheme of the intelligent scheduling method and system for a neurosurgical robot provided by the present invention is described in detail below with reference to the accompanying drawings.

[0040] See also Figure 1 , which shows a neurosurgery robot intelligent scheduling method provided by one embodiment of the present invention, the method comprising:

[0041] Step S1: Acquire a brain blood vessel image.

[0042] In order to facilitate the scheduling of a neurosurgery robot to operate on brain blood vessels, the embodiment of the present invention is mainly used in application scenarios where the brain blood vessel area is accurately identified, so a brain blood vessel image is first obtained.

[0043] In one embodiment of the present invention, DSA (digital subtraction angiography) is used to generate an initial brain vascular image, and noise reduction is performed on the initial brain vascular image to obtain a brain vascular image for subsequent operations. It should be noted that both DSA technology and noise reduction operations are well known to those skilled in the art and will not be described in detail here.

[0044] Step S2: Perform edge detection on the brain vascular image to obtain all edge pixels; obtain the main vascular path composed of all edge pixels; select any edge pixel as a reference pixel; obtain the exploration value of each non-edge pixel in the preset neighborhood of the reference pixel based on the gradient distribution characteristics and grayscale distribution characteristics of the non-edge pixels in the preset neighborhood of the reference pixel; use the non-edge pixel with a non-zero exploration value as the target pixel; use the edge pixel with the target pixel in the preset neighborhood as the pixel to be analyzed; obtain the exploration path of each pixel to be analyzed based on the distribution characteristics of the target pixels around each pixel to be analyzed and the exploration value of the target pixel; screen all exploration paths based on the exploration value of each target pixel in the exploration path to obtain the brain microvascular path.

[0045] As can be seen in practice, the distribution of brain blood vessels, based on their physical shape, includes thick main vascular pathways, as well as some tiny vessels that are difficult to distinguish visually. Because tiny vessels have relatively close grayscale values ​​to the background, conventional image segmentation algorithms cannot identify them. However, blood vessels are connected, and tiny vessels must be connected to thick vessels. Therefore, in the embodiments of the present invention, to locate tiny vessels, the location of thick main vessels must first be confirmed. Because the gradient and grayscale values ​​of the pixels of tiny vessels are relatively close to the background area, they cannot be reflected in the edge image. Therefore, edge detection is performed on the brain vascular image to obtain all edge pixels. These edge pixels form the main vascular pathway, and then the gradient and grayscale features around the edge pixels are subsequently analyzed point by point.

[0046] It should be noted that, to reduce computational complexity and prevent the computer from misidentifying non-microvascular pixels, the present invention, when performing a point-by-point analysis of brain microvascular pixels, does not perform a global analysis of all edge pixels in the brain vascular image. Instead, the analysis focuses on selecting the starting point of the main vessel and then traversing the connected edge pixels from that point. Since the main vessel has a distinct starting point in the image, deep learning, through extensive training with extensive material, can easily identify the starting point of the main vessel. This starting point is then used as a reference pixel, and non-edge pixels within a preset neighborhood are analyzed starting from that reference pixel, traversing the main vessel pixels in sequence.

[0047] Although the grayscale values ​​of fine blood vessel pixels are similar to the background and their gradients are not obvious, their gradients and grayscale values ​​differ somewhat from those of normal, nonvascular background areas. In brain vascular images, after removing edge pixels, the grayscale and gradient values ​​of fine blood vessel pixels differ from those of other pixels. Therefore, in this embodiment of the present invention, an exploration value is obtained for each non-edge pixel within a preset neighborhood of a reference pixel based on the gradient and grayscale distribution characteristics of the non-edge pixels within the preset neighborhood of the reference pixel.

[0048] Preferably, in one embodiment of the present invention, the method for obtaining the exploration value of a non-edge pixel point includes:

[0049] The exploration value is obtained according to the exploration value calculation formula. The exploration value calculation formula is as follows:

[0050]

[0051] Where E represents the exploration value of each non-edge pixel in the preset neighborhood of the reference pixel; N represents the number of non-edge pixels in the preset neighborhood of the reference pixel; t represents the gradient value of each non-edge pixel in the preset neighborhood of the reference pixel; tn represents the gradient value of the nth non-edge pixel in the preset neighborhood of the reference pixel, excluding the calculated non-edge pixel; M represents the number of non-edge pixels in the brain vascular image; t m Represents the gradient value of the mth non-edge pixel in the brain blood vessel image; represents the gradient mean of all non-edge pixels in the brain vascular image; f represents the grayscale value of each non-edge pixel in the preset neighborhood of the reference pixel; [] represents Iverson brackets. If the condition in the brackets is met, the value is 1, and if the condition is not met, the value is 0.

[0052] In one embodiment of the present invention, the preset neighborhood is set to a 3×3 rectangular area centered at the reference pixel. It should be noted that the preset neighborhood can be set arbitrarily and is not limited here.

[0053] In the exploration value calculation formula, if the gradient value confusion between a pixel point other than the edge pixel points in the preset neighborhood and the rest of the pixels is The degree of chaos of the gradient value of the edge pixels removed from the entire image If the value is high, it means that the pixel is likely to be a tiny blood vessel pixel.

[0054] As a judgment condition, when the condition is met, it is considered that the edge pixel may be a fine blood vessel pixel, and then the non-edge pixel is analyzed subsequently; the gradient difference between the non-edge pixel and other non-edge pixels in the preset neighborhood is The larger the value is, the more likely the non-edge pixel is to be a microvascular pixel, that is, the larger the exploration value of the non-edge pixel is; the lower the grayscale value of the non-edge pixel in the preset neighborhood is, the more likely the non-edge pixel is to belong to the pixel of the vascular area, that is, the more likely the non-edge pixel is to be a microvascular pixel, the larger the exploration value of the non-edge pixel is. Since the maximum grayscale value is 255, the denominator is set to 255 to Perform normalization.

[0055] Since the distance between edge pixels is very small, when analyzing the preset neighborhood of adjacent edge pixels, it may be that a non-edge pixel has multiple exploration values. Therefore, when there are non-edge pixels with multiple exploration values ​​in the preset neighborhood of edge pixels, the mean of all exploration values ​​is calculated as the exploration value of such non-edge pixels.

[0056] In reality, two tiny blood vessels branching from a main blood vessel are separated by a distance, and it is rare for two tiny blood vessels to be separated by more than a few pixels. Therefore, if there are two or more non-edge pixels with exploration values ​​other than 0 within the preset neighborhood of a non-edge pixel, it means that such non-edge pixels are not true tiny blood vessel pixels. Therefore, in this embodiment of the present invention, the exploration path of each pixel to be analyzed is obtained based on the distribution characteristics of the target pixels around each pixel to be analyzed and the exploration value of the target pixel.

[0057] Preferably, in one embodiment of the present invention, the method for obtaining the exploration path includes:

[0058] When there is no target pixel in the preset neighborhood of the pixel to be analyzed, the preset neighborhood does not have the grayscale features and gradient features of fine blood vessels, so it is considered that there is no exploration path in the preset neighborhood of the pixel to be analyzed.

[0059] When there is a target pixel point in the preset neighborhood of the pixel point to be analyzed, the number of target pixels in the preset neighborhood of the target pixel point is searched with the target pixel point as the center. If the number is 1, the above steps are repeated until there is no target pixel point in the preset neighborhood of the target pixel point that has not been traversed or there are two or more target pixels. The path composed of all the above target pixels is used as the first exploration path of the pixel point to be analyzed.

[0060] When there are two or more target pixel points in the preset neighborhood of the pixel point to be analyzed, take each target pixel point as the pixel point to be traversed, and take each pixel point to be traversed as the center to find the number of target pixel points in the preset neighborhood of the pixel point to be traversed. If the number is 1, repeat the above steps until there is no target pixel point in the preset neighborhood of the pixel point to be traversed that has not been traversed, or there are two or more target pixel points. Stop and use the path composed of the above target pixel points and the pixel points to be traversed as the corresponding second exploration path for each pixel point to be traversed in the preset neighborhood of the pixel point to be analyzed; traverse each pixel point to be traversed in the preset neighborhood of the pixel point to be traversed to obtain all the second exploration paths of the pixel point to be analyzed.

[0061] The first exploration path and the second exploration path are collectively referred to as the exploration path of the pixel to be analyzed.

[0062] Since not every path in the second exploration path of the pixel points to be analyzed is a path composed of microvascular pixels, the exploration value differences of each second exploration path are analyzed, and then the second exploration paths are screened, and finally together with the first exploration path, they form the brain microvascular path.

[0063] Preferably, in one embodiment of the present invention, the method for acquiring brain microvascular pathways includes:

[0064] When there is a target pixel point within the preset neighborhood of the pixel point to be analyzed, the first exploration path of the pixel point to be analyzed is used as the path of the brain microvascular.

[0065] When there are two or more target pixels in the preset neighborhood of the pixel to be analyzed, the exploration authenticity of each second exploration path is obtained according to the difference in exploration values ​​of the target pixels in each second exploration path of the pixel to be analyzed. The formula is as follows:

[0066]

[0067] Where, Ea j Indicates the exploration authenticity of the jth second exploration path of the pixel to be analyzed; E j represents the exploration value of the pixel points to be traversed in the j-th second exploration path; ∑E represents the sum of the exploration values ​​of the pixel points to be traversed in all second exploration paths; a represents the difference between the maximum number of target pixels in all second exploration paths and the number of target pixels in the j-th second exploration path; I represents the number of target pixels in the j-th second exploration path; E i Represents the exploration value of the i-th target pixel point in the j-th second exploration path.

[0068] In the formula for the degree of exploration truth, a represents the difference between the maximum number of target pixels in all second exploration paths and the number of target pixels in the jth second exploration path after the second exploration path is iterated, that is, the difference between the number of iterations of the path with the most iterations and the number of iterations of the second exploration path. Because it is difficult to grow two branch vessels on a blood vessel that is very close to each other, if multiple second exploration paths are generated, it means that the existence of a second exploration path may be a misjudgment caused by other reasons. The larger the exploration value of the pixels to be traversed in the second exploration path, the fewer the number of iterations. At this time, The smaller it is, the greater the possibility that it is not a microvessel; and as the average exploration value of the pixel points in another second exploration path becomes smaller, the total exploration value of the second exploration path decays more severely, and the exploration authenticity of the j-th second exploration path of the pixel point to be analyzed becomes smaller.

[0069] The second exploration path that explores the pixel point to be analyzed with the greatest degree of authenticity is used as the brain microvascular path.

[0070] Step S3: Assisting in scheduling the neurosurgery robot based on the main blood vessel pathways and the brain's microvascular pathways.

[0071] The main blood vessel pathways and all the brain's microvascular pathways are marked to obtain a vascular distribution image of the brain; the distribution image of the brain's microvascular pathways is input into the scheduling system of the neurosurgical robot, allowing the neurosurgical robot to perform deep learning on it, thereby completing the scheduling of the neurosurgical robot.

[0072] In summary, a brain vascular image is acquired; edge detection is performed on the brain vascular image to acquire all edge pixels; the main vascular path composed of all edge pixels is acquired; any edge pixel is selected as a reference pixel; the exploration value of each non-edge pixel in the preset neighborhood of the reference pixel is acquired based on the gradient distribution characteristics and grayscale distribution characteristics of the non-edge pixels in the preset neighborhood of the reference pixel; the non-edge pixel whose exploration value is not zero is used as the target pixel; the edge pixel with the target pixel in the preset neighborhood is used as the pixel to be analyzed; the exploration path of each pixel to be analyzed is acquired based on the distribution characteristics of the target pixels around each pixel to be analyzed and the exploration value of the target pixel; all exploration paths are screened based on the exploration value of each target pixel in the exploration path to acquire the brain fine vascular path; the neurosurgery robot is assisted in scheduling based on the main vascular path and the brain fine vascular path.

[0073] A second object of an embodiment of the present invention is to provide an intelligent scheduling system for a neurosurgical robot, the system comprising a memory, a processor, and a computer program, wherein the memory is used to store the corresponding computer program, and the processor is used to run the corresponding computer program. When the computer program is run in the processor, it can implement the method described in steps S1-S3, specifically including:

[0074] The image acquisition module 101 is used to acquire brain blood vessel images.

[0075] The vascular path acquisition module 102 is used to perform edge detection on the brain vascular image to obtain all edge pixels; obtain the main vascular path composed of all edge pixels; select any edge pixel as a reference pixel; obtain the exploration value of each non-edge pixel in the preset neighborhood of the reference pixel based on the gradient distribution characteristics and grayscale distribution characteristics of the non-edge pixels in the preset neighborhood of the reference pixel; use the non-edge pixel with a non-zero exploration value as the target pixel; use the edge pixel with the target pixel in the preset neighborhood as the pixel to be analyzed; obtain the exploration path of each pixel to be analyzed based on the distribution characteristics of the target pixels around each pixel to be analyzed and the exploration value of the target pixel; screen all exploration paths based on the exploration value of each target pixel in the exploration path to obtain the brain's fine vascular path.

[0076] The auxiliary scheduling module 103 is used to assist in scheduling the neurosurgery robot according to the main blood vessel pathways and the brain microvascular pathways.

[0077] The third object of an embodiment of the present invention is to provide a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the method described in steps S1-S3 is implemented when the processor executes the computer program.

[0078] A fourth object of an embodiment of the present invention is to provide a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in steps S1-S3 is implemented.

[0079] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0080] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. A neurosurgery robot intelligent scheduling method, characterized in that: The method includes: acquiring a brain vascular image; performing edge detection on the brain vascular image to acquire all edge pixels; acquiring a main vascular path composed of all edge pixels; selecting any edge pixel as a reference pixel; acquiring an exploration value of each non-edge pixel in a preset neighborhood of the reference pixel based on the gradient distribution characteristics and grayscale distribution characteristics of the non-edge pixels in the preset neighborhood of the reference pixel; using non-edge pixels with non-zero exploration values ​​as target pixels; using edge pixels with target pixels in the preset neighborhood as pixels to be analyzed; acquiring an exploration path for each pixel to be analyzed based on the distribution characteristics of the target pixels around each pixel to be analyzed and the exploration value of the target pixel; screening all exploration paths based on the exploration value of each target pixel in the exploration path to acquire a brain fine vascular path; and assisting in scheduling a neurosurgery robot based on the main vascular path and the brain fine vascular path.

2. The intelligent scheduling method for a neurosurgery robot according to claim 1, characterized in that: The method for obtaining the exploration value of the non-edge pixel point includes: obtaining the exploration value according to the exploration value calculation formula, and the exploration value calculation formula is as follows: Where E represents the exploration value of each non-edge pixel in the preset neighborhood of the reference pixel; N represents the number of non-edge pixels in the preset neighborhood of the reference pixel; t represents the gradient value of each non-edge pixel in the preset neighborhood of the reference pixel; t n represents the gradient value of the nth non-edge pixel in the preset neighborhood of the reference pixel, excluding the calculated non-edge pixel; M represents the number of non-edge pixels in the brain vascular image; t m Represents the gradient value of the mth non-edge pixel in the brain blood vessel image; represents the gradient mean of all non-edge pixels in the brain vascular image; f represents the grayscale value of each non-edge pixel in the preset neighborhood of the reference pixel; [] represents Iverson brackets, where the value is 1 if the condition in the brackets is met, and 0 if the condition is not met; when there are non-edge pixels with multiple exploration values ​​in the preset neighborhood of an edge pixel, the mean of all exploration values ​​is calculated as the exploration value of such non-edge pixels.

3. The intelligent scheduling method for a neurosurgery robot according to claim 1, characterized in that: The method for obtaining the exploration path includes: when there is no target pixel point in the preset neighborhood of the pixel point to be analyzed, it is considered that there is no exploration path in the preset neighborhood of the pixel point to be analyzed; when there is a target pixel point in the preset neighborhood of the pixel point to be analyzed, the target pixel points in the preset neighborhood of the pixel point to be analyzed are traversed according to the continuation characteristics of the target pixel points in the preset neighborhood of the pixel point to be analyzed, and a first exploration path of the pixel point to be analyzed is obtained; when there are two or more target pixel points in the preset neighborhood of the pixel point to be analyzed, the target pixel points in the preset neighborhood of the pixel point to be analyzed are traversed according to the continuation characteristics around each target pixel point, and a second exploration path of the pixel point to be analyzed is obtained; the first exploration path and the second exploration path are collectively referred to as the exploration path of the pixel point to be analyzed.

4. The intelligent scheduling method for a neurosurgery robot according to claim 3, characterized in that: The method for obtaining the first exploration path includes: when there is a target pixel point within the preset neighborhood of the pixel point to be analyzed, with the target pixel point as the center, searching for the number of target pixels within the preset neighborhood of the target pixel point; if the number is 1, repeating the above steps until there is no target pixel point within the preset neighborhood or there are two or more target pixels; and stopping until the path composed of all the above target pixels is used as the first exploration path of the pixel point to be analyzed.

5. The intelligent scheduling method for a neurosurgery robot according to claim 3, characterized in that: The method for obtaining the second exploration path includes: when there are two or more target pixel points in the preset neighborhood of the pixel point to be analyzed, taking each target pixel point as the pixel point to be traversed, and taking each pixel point to be traversed as the center, searching for the number of target pixel points in the preset neighborhood of the pixel point to be traversed; if the number is 1, repeating the above steps until there is no target pixel point in the preset neighborhood or there are two or more target pixel points, and stopping; taking the path composed of the above target pixel points and the pixel points to be traversed as the corresponding second exploration path for each pixel point to be traversed in the preset neighborhood of the pixel point to be analyzed; traversing each pixel point to be traversed in the preset neighborhood of the pixel point to be analyzed to obtain all second exploration paths of the pixel point to be analyzed.

6. The intelligent scheduling method for a neurosurgery robot according to claim 5, characterized in that: The method for obtaining the path of brain microvasculars includes: when there is a target pixel point within a preset neighborhood of the pixel point to be analyzed, using the first exploration path of the pixel point to be analyzed as the path of the brain microvasculars; when there are two or more target pixels within the preset neighborhood of the pixel point to be analyzed, obtaining the exploration authenticity of each second exploration path based on the difference in exploration values ​​of the target pixels in each second exploration path of the pixel point to be analyzed, as shown in the following formula: Where, Ea j Indicates the exploration authenticity of the jth second exploration path of the pixel to be analyzed; E j represents the exploration value of the pixel points to be traversed in the j-th second exploration path; ∑E represents the sum of the exploration values ​​of the pixel points to be traversed in all second exploration paths; a represents the difference between the maximum number of target pixels in all second exploration paths and the number of target pixels in the j-th second exploration path; I represents the number of target pixels in the j-th second exploration path; E i represents the exploration value of the i-th target pixel point of the j-th second exploration path; the second exploration path of the pixel to be analyzed with the greatest exploration truth is taken as the brain microvascular path.

7. A neurosurgery robot intelligent scheduling system, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the intelligent scheduling method for a neurosurgical robot as described in any one of claims 1 to 6 are implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the intelligent scheduling method for a neurosurgical robot as claimed in any one of claims 1 to 6 are implemented.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the neurosurgical robot intelligent scheduling method as described in any one of claims 1 to 6 are implemented.

Images