A bone structure screw channel automatic planning method and system, electronic equipment and storage medium

Abstract

The application discloses a kind of bone structure screw channel automatic planning method, system, electronic equipment and storage medium, the method is extracted by the morphological characteristics of the subdivision substructure of single vertebral bone structure, and according to the morphological characteristics, determine that the subdivision substructure that screw channel is expected to need to pass, and according to the disease type, the default planning path of screw channel is automatically generated, compared with the screw channel planning of prior art manual, the automation planning of screw channel is realized, the dependence on the experience and subjective judgment of operator is reduced, and the planning quality and planning efficiency can be effectively guaranteed, can realize fast, reliable and stable initial planning, finally improve surgical efficiency.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, specifically to an automatic planning method, system, electronic device, and storage medium for bone structure screw channels. Background Technology

[0002] Currently, screw placement within the vertebral body is a crucial step in many spinal surgeries. Surgeons typically insert guide wires into the pedicles of the lumbar and coccygeal vertebrae to define a channel, and then insert screws into the widened channel. However, the spine is surrounded by many important nerves and organs, and spinal surgery is characterized by high precision requirements and a small margin for error. During the procedure, the surgeon's understanding of the spinal structure is crucial; improper screw placement can cause serious neurovascular damage, as well as early fixation failure or pseudoarthrosis.

[0003] Currently, image-guided stereotactic navigation robots are rapidly developing in surgical subspecialties such as orthopedics, neurosurgery, and dentistry, and are gradually being clinically deployed. In orthopedics, these navigation robots are mainly used for assisted positioning and orientation of bone tissue or bony passages, including key steps such as drilling, grinding, and cutting. For spinal surgery navigation robots that rely on intraoperative image guidance, accurate and efficient surgical planning is a crucial step. However, current surgical planning is usually performed manually by the surgeon, a cumbersome and time-consuming process that relies heavily on the surgeon's experience and subjective judgment, making it difficult to effectively guarantee the quality and efficiency of planning. Therefore, the development of automated planning is urgently needed.

[0004] To facilitate understanding of the technical solution provided by this invention, several medical technical terms in the prior art are explained below:

[0005] 1. Pedicle screw technique: The pedicle is the strongest part of the spine and an effective point for manipulation and immobilization. The pedicle screw technique involves inserting screws into the vertebral body through the pedicle. Pedicle screws combined with bone grafting and fusion are gradually becoming the gold standard for the treatment of related diseases.

[0006] 2. Cortical Bone Channel Screw Technique: In patients with osteoporosis, fixation strength is weakened, and the risk of screw loosening and pull-out postoperatively is higher. By altering the screw placement channel to maximize contact between the screw and the cortical bone within the channel, the fixation strength is improved. This new placement method is called the cortical bone channel screw technique. The cortical bone channel screw technique has achieved satisfactory therapeutic results in diseases such as lumbar spondylolisthesis and lumbar degenerative diseases.

[0007] 3. Translaminar facet screw technique: Translaminar facet screws are mainly used for degenerative lumbar spine diseases. Through facet joint fusion, they increase the spine's resistance to rotation, shear force, and tension, or to posterior column separation, achieving biomechanical requirements. Compared to pedicle screws, this technique is less invasive. The insertion point for the translaminar facet screw should be in the lower third of the joint between the spinous process and the laminae of the superior vertebra, passing through the contralateral laminae, the center of the facet joint, and to the lateral edge of the superior facet joint. Summary of the Invention

[0008] The purpose of this invention is to overcome the above-mentioned technical deficiencies and provide an automatic planning method, system, electronic device and storage medium for bone structure screw channels, so as to solve the technical problem that the planning quality and planning efficiency cannot be effectively guaranteed when screw channels are planned manually in related technologies.

[0009] To achieve the above-mentioned technical objectives, the present invention adopts the following technical solution:

[0010] According to a first aspect of the present invention, an automatic planning method for screw channels in bone structures is provided, wherein the bone structure includes multiple single vertebral bone structures, each single vertebral bone structure including multiple substructures, the method comprising:

[0011] For any single vertebral bone structure, extract the morphological features of the substructures of the single vertebral bone structure, and determine the substructures through which the screw channel is expected to pass based on the morphological features.

[0012] The substructure containing the screw channel entry point region is defined as the screw channel entry point substructure.

[0013] The substructure containing the screw channel stop point region is defined as the screw channel stop point substructure.

[0014] Apart from the screw channel inlet substructure and the screw channel outlet substructure, the other substructures that the screw channel is expected to pass through are defined as the screw channel midpoint structure.

[0015] Based on the type of symptom, determine the central axis of the screw channel inlet substructure or the central axis of the screw channel midpoint substructure, and the straight line containing it is the default planned path of the screw channel; the starting point of the default planned path is the intersection of the extension line of the central axis and the screw channel inlet substructure, and the ending point is the intersection of the extension line of the central axis and the screw channel end substructure.

[0016] Preferably, the method further includes:

[0017] Extract the curved mesh of the surface of the screw channel entry point area, and determine the intersection of the default planned path and the curved mesh as the starting point of the default planned path;

[0018] Calculate the angle between the default planned path and the surface mesh;

[0019] Based on the included angle, determine whether there is a risk of bone surface slippage in the screw channel entry point area. If so, adjust the starting point, regenerate the screw channel path, and determine the regenerated screw channel path as the default planned path; otherwise, maintain the current default planned path.

[0020] Preferably, the method further includes:

[0021] Based on the morphological features, the sub-structures that the screw channel is expected to avoid are determined, and the 3D edge points of the sub-structures that need to be avoided are extracted.

[0022] Determine whether the default planned path intersects with the 3D edge point. If so, adjust the starting point of the default planned path, regenerate the screw channel path, and determine the regenerated screw channel path as the default planned path; otherwise, keep the current default planned path.

[0023] Preferably, the method further includes:

[0024] Based on the morphological features, extract the 3D edge points of the screw channel stop substructure;

[0025] Based on the 3D edge points, determine whether the default planned path has reached the screw channel endpoint area. If so, maintain the current default planned path; otherwise, adjust the starting point of the default planned path, regenerate the screw channel path, and determine the regenerated screw channel path as the default planned path.

[0026] Preferably, adjusting the starting point of the default planned path and regenerating the screw channel path specifically involves:

[0027] The current default planned path is shifted to the adjusted starting position, and the shifted path is determined as the newly generated screw channel path.

[0028] Preferably, the method further includes:

[0029] Calculate the thickness of each substructure that the screw channel is expected to pass through;

[0030] Calculate the length of the default planned path;

[0031] The screw size is determined based on the minimum thickness and the length of the default planned path.

[0032] Preferably, the method further includes:

[0033] If the single vertebral structure is a lumbar vertebra, and the screw channel is a pedicle screw channel, the entry point area of ​​the screw channel is the posterior surface of the pedicle entry point area, and the exit point area of ​​the screw channel is the anterior part of the vertebral body near the cortex or the cortex; the central axis is the central axis of the pedicle.

[0034] If the single vertebral structure is a lumbar vertebra, and the screw channel is a cortical bone screw channel, the screw channel entry point area is the posterior surface region of the entry point area of ​​the isthmus of the vertebral laminae, and the screw channel termination point area is the lateral cortex of the vertebral body; the central axis is the line connecting the centroids of the pedicle regions.

[0035] If the single vertebral structure is a lumbar vertebra, and the screw channel is a lamina screw channel, the screw channel entry point area is the dorsal surface of the contralateral lamina, and the screw channel insertion point area is the surface of the cortical region lateral to the pedicle; the central axis is the lamina central axis;

[0036] If the single vertebral structure is a lumbar vertebra, and the screw channel is a translaminar articular process screw channel, the screw channel entry point area is the dorsal surface of the contralateral lamina, and the screw channel insertion point area is the surface of the cortical region lateral to the pedicle; the central axis is the line connecting the centroids of the superior and inferior articular processes.

[0037] If the single vertebral structure is a lumbar vertebra, and the screw channel is a transarticular screw, the screw channel entry point is the center of the inferior articular process surface or the ipsilateral articular process near the inferior articular process, and the screw channel termination point is the surface of the cortical region lateral to the pedicle; the central axis is the line connecting the centroids of the superior and inferior articular processes.

[0038] According to a second aspect of the present invention, an automatic planning system for screw channels in bone structures is provided, the bone structures comprising multiple single vertebral bone structures, each single vertebral bone structure comprising multiple substructures, the system comprising:

[0039] The first determining module is used to extract the morphological features of the substructures of any single vertebral bone structure, and determine the substructures that the screw channel is expected to pass through based on the morphological features.

[0040] It is also used to determine the substructure in which the screw channel entry point region is located as the screw channel entry point substructure;

[0041] The substructure containing the screw channel stop point region is defined as the screw channel stop point substructure.

[0042] Apart from the screw channel inlet substructure and the screw channel outlet substructure, the other substructures that the screw channel is expected to pass through are defined as the screw channel midpoint structure.

[0043] The second determining module is used to determine the central axis of the screw channel entry point substructure or the central axis of the screw channel midpoint structure according to the type of disease. The straight line where the central axis is located is the default planned path of the screw channel. The starting point of the default planned path is the intersection of the extension line of the central axis and the screw channel entry point substructure, and the ending point is the intersection of the extension line of the central axis and the screw channel ending point substructure.

[0044] According to a third aspect of the present invention, an electronic device is provided, comprising:

[0045] A processor, and a memory connected to the processor;

[0046] The memory is used to store computer programs;

[0047] The processor is used to call and execute the computer program in the memory to perform the above-described method.

[0048] According to a fourth aspect of the present invention, a non-transitory computer-readable storage medium is provided storing computer instructions for causing a computer to perform the methods described above.

[0049] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

[0050] By extracting the morphological features of the substructures of a single vertebral bone and determining the substructures through which the screw channel is expected to pass based on these morphological features, and automatically generating the default planned path for the screw channel according to the type of disease, this method achieves automated screw channel planning compared to the manual planning of screw channels in existing technologies. This reduces reliance on the surgeon's experience and subjective judgment, effectively ensuring planning quality and efficiency. It enables fast, reliable, and stable initial planning, ultimately improving surgical efficiency.

[0051] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0052] Figure 1 This is a flowchart illustrating an automatic planning method for bone structure screw channels according to an exemplary embodiment;

[0053] Figure 2 This is a schematic diagram of the subdivided substructure of the lumbar vertebra according to an exemplary embodiment;

[0054] Figures 3A-3B This is a schematic diagram illustrating the effect of automatic planning of pedicle screw channel path according to an exemplary embodiment;

[0055] Figure 4This is a schematic diagram illustrating the effect of automatic planning of cortical bone screw channel path according to an exemplary embodiment;

[0056] Figure 5 This is a schematic diagram illustrating the effect of automatic planning of the lamina screw channel path according to an exemplary embodiment;

[0057] Figure 6 This is a schematic diagram illustrating the effect of automatic path planning via articular screw channel according to an exemplary embodiment;

[0058] Figure 7 This is a schematic diagram illustrating the effect of automatic planning of translaminar articular screw channel path according to an exemplary embodiment;

[0059] Figure 8 This is a schematic block diagram illustrating an automatic planning system for bone structure screw channels according to an exemplary embodiment;

[0060] Figures 9A-9B This is a schematic diagram illustrating cutting using a curved surface component according to an exemplary embodiment;

[0061] Figures 10A to 10H This is a schematic diagram of the structure of each individual vertebra according to an exemplary embodiment;

[0062] Figures 11A to 11C This is a subdivision map obtained after secondary cutting, as shown in an exemplary embodiment;

[0063] Figure 12 This is a coarse segmentation image obtained after a first-level cut, as shown in an exemplary embodiment.

[0064] Figures 13A-13E This is a schematic diagram illustrating the morphological features of the lumbar spine structure according to an exemplary embodiment;

[0065] Figure 14 This is a schematic diagram of the structure of a 3D U-net network model according to an exemplary embodiment;

[0066] Figure 15 This is an output diagram of a 3D U-net network model illustrated according to an exemplary embodiment;

[0067] Figure 16 This is a flowchart illustrating an automatic lumbar spine segmentation method according to an exemplary embodiment. Detailed Implementation

[0068] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0069] As described in the background section, there are technical problems in the related technologies where manual screw channel planning cannot effectively guarantee planning quality and efficiency.

[0070] To effectively address the problems in related technologies, this invention provides an automatic planning method, system, electronic device, and storage medium for bone structure screw channels, which will be described in detail below.

[0071] Example 1

[0072] Figure 1 This is a flowchart illustrating an automatic planning method for screw channels in a bone structure according to an exemplary embodiment. The bone structure includes multiple individual vertebral bone structures, and each individual vertebral bone structure includes multiple substructures, such as... Figure 1 As shown, the method includes:

[0073] Step S11: For any single vertebral bone structure, extract the morphological features of the substructures of the single vertebral bone structure, and determine the substructures that the screw channel is expected to pass through based on the morphological features.

[0074] Step S12: Determine the substructure where the screw channel entry point region is located as the screw channel entry point substructure; determine the substructure where the screw channel exit point region is located as the screw channel exit point substructure; determine the other substructures that the screw channel is expected to pass through, excluding the screw channel entry point substructure and the screw channel exit point substructure, as the screw channel midpoint structure.

[0075] Step S13: Based on the type of symptom, determine the central axis of the screw channel entry point substructure or the central axis of the screw channel midpoint substructure. The straight line containing the central axis is the default planned path of the screw channel. The starting point of the default planned path is the intersection of the extension line of the central axis and the screw channel entry point substructure, and the ending point is the intersection of the extension line of the central axis and the screw channel ending point substructure.

[0076] It should be noted that, in practice, the technical solution provided in this embodiment runs in the controller of the medical device, or is loaded into an electronic device connected to the controller. The controller of the medical device executes the corresponding method by calling the program stored in the electronic device.

[0077] The central axis refers to the central axis of the bony channel that provides the best mechanical stability for the substructure when viewed from the screw insertion point. That is, assuming the substructure is cut into several thin slices towards the screw insertion point, the centroids of each slice may not be on the same straight line, but they will definitely be distributed within a bony channel of a predetermined width. The central axis of this bony channel is the central axis. Practice shows that selecting the default planning path of the screw channel based on the central axis ensures good stability of the inserted screw. The selection of the central axis follows the principles of: Principle 1: Minimize damage to normal bone; Principle 2: Minimize interference with neural structures.

[0078] To facilitate understanding of the screw channel inlet structure, screw channel center point structure, and screw channel stop point structure mentioned in this embodiment, the following examples are provided:

[0079] For example, in the planning of a transarticular screw channel for the lumbar spine, it is necessary to sequentially pass through the superior articular process of the upper lumbar vertebra, the inferior articular process of the lower lumbar vertebra, and the lower edge of the pedicle of the lower lumbar vertebra. The superior articular process of the upper lumbar vertebra is the "screw channel entry point structure" mentioned in this embodiment, the pedicle of the lower lumbar vertebra is the "screw channel exit point structure" mentioned in this embodiment, and the inferior articular process of the lower lumbar vertebra is the "screw channel midpoint structure" mentioned in this embodiment.

[0080] For example, in the planning of translaminar facet screw channels for the lumbar spine, the path needs to be sequentially traversed through the left lamina of the upper lumbar vertebra, the right lamina of the lower lumbar vertebra, the superior facet of the upper lumbar vertebra, the inferior facet of the lower lumbar vertebra, and the lower edge of the pedicle of the next lumbar vertebra. The left lamina of the upper lumbar vertebra is the "screw channel entry point structure" mentioned in this embodiment, the pedicle of the next lumbar vertebra is the "screw channel exit point structure" mentioned in this embodiment, and the right lamina of the lower lumbar vertebra, the superior facet of the upper lumbar vertebra, and the inferior facet of the lower lumbar vertebra are all the "screw channel midpoint structures" mentioned in this embodiment.

[0081] It is understood that the technical solution provided in this embodiment extracts the morphological features of the substructures of a single vertebral bone structure, determines the substructures through which the screw channel is expected to pass based on the morphological features, and automatically generates the default planning path of the screw channel according to the type of disease. Compared with the manual planning of screw channels in the prior art, this realizes the automated planning of screw channels, reduces the dependence on the surgeon's experience and subjective judgment, and effectively ensures the planning quality and efficiency. It can achieve fast, reliable and stable initial planning, and ultimately improve surgical efficiency.

[0082] Furthermore, the method may also include:

[0083] Extract the surface mesh of the screw channel inlet region (see...) Figure 3BAs shown in the figure, the intersection of the default planning path and the surface mesh is determined as the starting point of the default planning path;

[0084] Calculate the angle between the default planned path and the surface mesh;

[0085] Based on the included angle, determine whether there is a risk of bone surface slippage in the screw channel entry point area. If so, adjust the starting point, regenerate the screw channel path, and determine the regenerated screw channel path as the default planned path; otherwise, maintain the current default planned path.

[0086] It should be noted that, based on the included angle, determining whether there is a risk of bone surface slippage in the screw channel entry point area can, in practice, be as follows:

[0087] If the included angle is between 70 and 90 degrees, the current risk of slippage is determined to be low.

[0088] If the included angle is between 40 degrees and 70 degrees, the current risk of slippage is determined to be medium risk.

[0089] If the included angle is between 0 and 40 degrees, the current risk of slipping is determined to be high.

[0090] When the risk level is determined to be medium or high, the starting point is adjusted and the screw path is regenerated.

[0091] Understandably, determining whether there is a risk of bone slippage in the screw channel entry area, and adjusting the starting point and regenerating the screw channel path when a risk of bone slippage is determined, can ensure that the screw can be stably and reliably inserted into the bone structure in one go, thereby ensuring the success rate of clinical surgery and reducing patient suffering.

[0092] Furthermore, the method may also include:

[0093] Based on the morphological features, the sub-structures that the screw channel is expected to avoid are determined, and the 3D edge points of the sub-structures that need to be avoided are extracted.

[0094] Determine whether the default planned path intersects with the 3D edge point. If so, adjust the starting point of the default planned path, regenerate the screw channel path, and determine the regenerated screw channel path as the default planned path; otherwise, keep the current default planned path.

[0095] Understandably, because bone structures are surrounded by a rich network of nerves, when planning screw channels in certain bone structures, it is necessary to consider the sub-structures that the default planning path needs to avoid. If there are sub-structures that need to be avoided, the default planning path needs to be adjusted by determining whether it intersects with the 3D edge points of the sub-structures that need to be avoided, so that the final planned screw channel path better meets the needs of clinical surgery.

[0096] For example, in some degenerative bones, the superior or inferior articular processes are still intact, so the screw channel planning needs to bypass these processes. However, in some patients with fractures or bone hyperplasia, the superior and inferior articular processes in their bones are damaged or diseased. Therefore, for the patient's rehabilitation, the screw channel path can directly pass through these damaged or diseased superior and inferior articular processes.

[0097] Furthermore, the method may also include:

[0098] Based on the morphological features, extract the 3D edge points of the screw channel stop substructure;

[0099] Based on the 3D edge points, determine whether the default planned path has reached the screw channel endpoint area. If so, maintain the current default planned path; otherwise, adjust the starting point of the default planned path, regenerate the screw channel path, and determine the regenerated screw channel path as the default planned path.

[0100] For example, if the single vertebral structure is a lumbar vertebra, and the screw channel is a cortical bone screw channel, the screw channel entry point region is the posterior surface region of the isthmus entry point region, and the screw channel termination region is the lateral cortex of the vertebral body. In this screw channel rule, the screw channel termination substructure is the vertebral body, and the position of the lateral cortex of the vertebral body on the vertebral body is determined. After extracting the 3D edge points of the vertebral body, the region of the lateral cortex of the vertebral body can be delineated based on the coordinates of the 3D edge points. Then, it is determined whether the termination coordinates of the default path fall within the region of the lateral cortex of the vertebral body. If so, it is determined that the default planned path has reached the screw channel termination region, and the current default planned path is maintained; otherwise, the starting position is adjusted until the termination coordinates fall within the region of the lateral cortex of the vertebral body.

[0101] It is understandable that screw channel planning includes two application scenarios: one is automatic screw channel planning for single vertebral structures, and the other is automatic screw channel planning for multiple vertebral structures. For automatic screw channel planning for multiple vertebral structures, in order to ensure that the screw can stably fix the upper and lower bone structures after insertion, after the default planning path is generated, it is also necessary to check whether the default planning path passes through the point structure in the screw channel and reaches the stop area of ​​the screw channel, so as to ensure that the screw is stably inserted into the bone.

[0102] It should be noted that the preceding examples are all automatic screw channel planning examples for single vertebral structures. Automatic screw channel planning for multi-vertebral structures is the same as for single-vertebral structures, the only difference being that the screw channel may pass through several screw channel midpoint structures. In this case, when generating a default planning path based on the central axis of the entry point structure, it is necessary to manually check whether the default planning path passes through the expected screw channel midpoint structures and reaches the expected planned screw channel termination area. If it does not, the starting point position is adjusted to ensure that the screw can be stably inserted into the bone according to the adjusted default planning path.

[0103] In practice, adjusting the starting point of the default planned path and regenerating the screw channel path specifically involves:

[0104] The current default planned path is shifted to the adjusted starting position, and the shifted path is determined as the newly generated screw channel path.

[0105] In practice, the method further includes:

[0106] Calculate the thickness of each substructure that the screw channel is expected to pass through;

[0107] Calculate the length of the default planned path;

[0108] The screw size is determined based on the minimum thickness and the length of the default planned path.

[0109] It should be noted that the dimensions of a screw include its diameter and length.

[0110] Understandably, the screw diameter must be smaller than the thickness of each substructure the screw channel is expected to traverse. This ensures the screw remains within each substructure, meeting surgical requirements. If the screw diameter is too large, it cannot be inserted into the thinner substructures, altering the screw channel path, leading to poor postoperative screw stability and a high revision rate. Similarly, the screw length must be equal to or slightly less than the length of the default planned path to guarantee screw stability after placement.

[0111] To facilitate understanding of the automatic planning method for bone structure screw channels provided in this embodiment, the pedicle screw path planning in the automatic planning of screw channels for a single vertebral bone structure is used as an example for explanation as follows:

[0112] See Figure 2 If the single vertebral structure is a lumbar vertebra, the substructures of the lumbar vertebra include: vertebral body 1, left pedicle 2, right pedicle 3, left pedicle entry point region 4, right pedicle entry point region 5, left transverse process 6, right transverse process 7, spinous process 14, left superior articular process 8, left inferior articular process 12, right superior articular process 9, right inferior articular process 13, left lamina 10, and right lamina 11.

[0113] A: If the single vertebral structure is a lumbar vertebra, and the screw channel is a pedicle screw channel, the entry point area of ​​the screw channel is the posterior surface of the pedicle entry point area, and the exit point area of ​​the screw channel is the anterior part of the vertebral body near the cortex or at the cortex; the central axis is the central axis of the pedicle. The effect diagram after pedicle screw channel path planning is shown below. Figure 3A As shown (pedicle entry point area → pedicle → vertebral body).

[0114] In the case of pedicle screw channels, the automatic screw channel planning method includes:

[0115] Step S21: Based on morphological characteristics, determine the sub-structures that the screw channel is expected to pass through: pedicle entry point area → pedicle → vertebral body;

[0116] Step S22: Determine the pedicle entry point region (the sub-substructure on the posterior surface of the pedicle entry point region) as the screw channel entry point substructure, determine the vertebral body (the sub-substructure on the anterior part of the vertebral body near the cortex or at the cortex) as the screw channel termination point substructure, and determine the pedicle as the screw channel midpoint structure.

[0117] Step S23: Determine the central axis of the pedicle, and the straight line therein is the default planned path of the screw channel; the starting point of the default planned path is the intersection of the extension line of the central axis and the pedicle entry point area, and the ending point is the intersection of the extension line of the central axis and the vertebral body.

[0118] B: If the single vertebral structure is a lumbar vertebra, and the screw channel is a cortical bone screw channel, the screw channel entry point area is the posterior surface region of the isthmus entry point area, and the screw channel insertion point area is the lateral cortex of the vertebral body; the midline is the midline of the pedicle. The effect diagram after cortical bone screw channel path planning is shown below. Figure 4 As shown (laminus → base of superior articular process → pedicle entry point area → pedicle → vertebral body).

[0119] In the case of cortical bone screw channels, the automatic screw channel planning method includes:

[0120] Step S31: Based on morphological characteristics, determine the substructures that the screw channel is expected to pass through: lamina → base of superior articular process → pedicle entry point area → pedicle.

[0121] Step S32: Determine the lamina (the subdivided substructure containing the posterior surface region of the isthmus of the lamina) as the screw channel entry point substructure, determine the vertebral body (the subdivided substructure containing the lateral cortex of the vertebral body) as the screw channel termination point substructure, and determine the base of the superior articular process, the pedicle entry point region, and the pedicle as the screw channel midpoint structure.

[0122] Step S33: Determine the central axis of the pedicle, and the straight line containing it is the default planned path of the screw channel; the starting point of the default planned path is the intersection of the extension line of the central axis and the lamina, and the ending point is the intersection of the extension line of the central axis and the vertebral body.

[0123] C: If the single vertebral structure is a lumbar vertebra, and the screw channel is a lamina screw channel, the screw channel entry point area is the dorsal surface of the contralateral lamina, and the screw channel insertion point area is the surface of the cortical region lateral to the pedicle; the central axis is the lamina central axis. The effect diagram after lamina screw channel path planning is shown below. Figure 5 As shown (right lamina → right pedicle entry point area).

[0124] In the case of right-sided lamina screw channel, the automatic screw channel planning method includes:

[0125] Step S41: Based on morphological characteristics, determine the sub-structures that the screw channel is expected to pass through: right lamina → right pedicle entry point area;

[0126] Step S42: Determine the right lamina (the sub-substructure on the dorsal surface of the left lamina) as the screw channel entry point substructure, and determine the right pedicle entry point region (the sub-substructure on the surface of the cortical region on the lateral side of the pedicle) as the screw channel termination point substructure.

[0127] Step S43: Determine the central axis of the right lamina, and the straight line therein is the default planned path of the screw channel; the starting point of the default planned path is the intersection of the extension of the central axis and the right lamina, and the ending point is the intersection of the extension of the central axis and the right pedicle entry point area.

[0128] D: If the single vertebral structure is a lumbar vertebra, and the screw channel is a translaminar facet screw channel, the screw channel entry point area is the dorsal surface of the contralateral lamina, and the screw channel insertion point area is the surface of the cortical region lateral to the pedicle; the central axis is the central axis of the superior and inferior facet processes. The effect diagram after planning the translaminar facet screw channel path is shown below. Figure 6 As shown (contralateral lamina → superior articular process of the upper lumbar vertebra → inferior articular process of the lower lumbar vertebra → lower edge of the pedicle of the lower lumbar vertebra).

[0129] In the case of a screw channel via the right laminae and articular process, the automatic screw channel planning method includes:

[0130] Step S51: Based on morphological characteristics, determine the substructures that the screw channel is expected to pass through: left lamina → superior articular process of the upper lumbar vertebra → inferior articular process of the lower lumbar vertebra → lower edge of the pedicle of the lower lumbar vertebra.

[0131] Step S52: Determine the left lamina (the sub-substructure on the dorsal surface of the left lamina) as the screw channel entry point substructure, and determine the pedicle (the sub-substructure on the surface of the cortical region on the lateral side of the pedicle) as the screw channel exit point substructure.

[0132] Step S53: Determine the central axis of the superior and inferior articular processes. The straight line containing the central axis is the default planned path of the screw channel. The starting point of the default planned path is the intersection of the extension of the central axis and the left lamina, and the ending point is the intersection of the extension of the central axis and the pedicle.

[0133] E: If the single vertebral structure is a lumbar vertebra, and the screw channel is a transarticular screw, the screw channel entry point is the center of the inferior articular process surface or the ipsilateral articular process near the inferior articular process, and the screw channel insertion point is the surface of the cortical region lateral to the pedicle; the central axis is the central axis of the superior and inferior articular processes. The effect diagram after translaminar articular screw path planning is shown below. Figure 7 As shown (inferior articular process of the upper lumbar vertebra → superior articular process of the lower lumbar vertebra → lower edge of the pedicle of the next lumbar vertebra).

[0134] In the case of articular screw channels, the automatic screw channel planning method includes:

[0135] Step S61: Based on morphological characteristics, determine the substructures that the screw channel is expected to pass through: inferior articular process of the upper lumbar vertebra → superior articular process of the lower lumbar vertebra → lower edge of the pedicle of the next lumbar vertebra.

[0136] Step S62: Determine the inferior articular process of the upper lumbar vertebra (the subdivided substructure where the center of the inferior articular process surface is located) as the screw channel entry point substructure, and determine the pedicle (the subdivided substructure where the surface of the cortical region on the lateral side of the pedicle is located) as the screw channel exit point substructure.

[0137] Step S63: Determine the central axis of the superior and inferior articular processes. The straight line containing the central axis is the default planned path of the screw channel. The starting point of the default planned path is the intersection of the extension of the central axis and the inferior articular process of the superior lumbar vertebra, and the ending point is the intersection of the extension of the central axis and the pedicle.

[0138] It should be noted that the above embodiments are all based on step S11, "For any single vertebral structure, extract the morphological features of the substructures of the single vertebral structure, and determine the substructures that the screw channel is expected to pass through based on the morphological features." However, step S11 can be implemented in various ways in practice, one of which may include:

[0139] Step S110: Obtain an original image containing a complete vertebral structure, and continuously cut the vertebral structure in the original image to obtain multiple original images of single vertebral structures.

[0140] Step S120: Subdivide the single vertebral structure in the original image of each single vertebral structure into substructures, and add a mask to the subdivided substructures to obtain a substructure mask image.

[0141] Step S130: For any single vertebral bone structure, input the original image and substructure mask of the single vertebral bone structure into a pre-trained single vertebral multi-level multi-task model group to obtain the subdivided substructures of the single vertebral bone structure.

[0142] In practice, step S110 involves continuously cutting the vertebral structures in the original image to obtain multiple original images of individual vertebral structures, specifically as follows:

[0143] Obtain a raw 3D image containing the complete vertebral structure;

[0144] The complete vertebral structure in the original 3D image is continuously cut using a surface component, and the area between two adjacent target surfaces is determined as a single vertebral structure.

[0145] See Figure 9A and Figure 9B When a curved surface component is initially placed at a location within the complete vertebral structure, it defaults to a flat surface. However, if the bone surface at that location has an irregular shape, it will be manually adjusted to suit the application. Figure 9B The curved surface shown offers more precise cutting, but is more time-consuming. Both planes and curved surfaces can be manually sized to achieve precise segmentation of bone structures. The curvature of curved surfaces can be set to better wrap around the structure.

[0146] See Figures 10A to 10HAfter continuously cutting the complete vertebral structure, original images of multiple individual vertebral structures were obtained, including: upper cervical vertebrae (C1), upper cervical vertebrae (C2), lower cervical vertebrae (C3-C7), upper thoracic vertebrae (T1-T4), middle thoracic vertebrae (T3-T8), lower thoracic vertebrae (T9-T12), lumbar vertebrae (L1-L5), and sacrum.

[0147] In step S120, a mask is added to the subdivided substructure. This can be done using existing automatic segmentation methods, or it can be done manually using automatic or semi-automatic methods.

[0148] For step S130, in specific practice, the single-spine multi-level multi-task model group includes:

[0149] A first-level cutting model is used to perform first-level cutting on the single vertebral bone structure in the original image based on the substructure mask map, to obtain a coarse-divided image containing the first-level single vertebral bone structure.

[0150] Multiple secondary cutting models are used to perform secondary cutting on the primary single vertebral bone structure in the coarse image to obtain a subdivided image containing the secondary single vertebral bone structure.

[0151] Each single vertebral bone structure corresponds to a primary cutting model, each primary cutting model corresponds to multiple secondary cutting models, and each secondary cutting model corresponds to a type of clinical indication and planning requirement.

[0152] Assuming the single vertebral structure to be segmented is the lumbar vertebra, see [link / reference]. Figures 11A to 11C A single lumbar vertebra, by traditional definition, is mainly composed of the vertebral body, pedicles, facet joints (including the superior and inferior articular processes), laminae, transverse processes, and spinous processes. According to pre-defined rules (which can be referenced in spinal development, spinal biomechanics, and clinical applications), see [link to relevant documentation]. Figure 12 The vertebral body can be classified as anterior structure 101, while the facet joints, lamina, transverse processes, and spinous processes can be classified as posterior structures 102.

[0153] It should be noted that since the area near the pedicle is frequently needed as the surgical entry point in subsequent navigation planning, this embodiment proposes the concept of a pedicle entry point area to better handle subsequent entry point planning. The pedicle entry point area can be understood as being composed of parts of the transverse process, superior articular process, and pedicle, and its location intersects with all three, hence it is defined as a boundary area. The advantage of this definition is that it better determines the entry point by identifying the pedicle screw entry area, thus reducing the chance of bone slippage.

[0154] Therefore, considering the importance of the entry point area in robot-assisted pedicle screw fixation, this embodiment, based on the traditional classification method, will... Figure 11AIn the left pedicle 2, left transverse process 6, and left superior articular process 8, the junction area of ​​these three is defined as the left pedicle entry point region 4; the junction area of ​​the right pedicle 3, right transverse process 7, and right superior articular process 9 is defined as the right pedicle entry point region 5. In the first-level cutting model, Figure 11A The left pedicle entry point region 4 and the right pedicle entry point region 5 are defined as follows: Figure 5 The rear structure 102 in the middle.

[0155] See Figure 12 Assuming the single vertebral bone structure to be segmented is the lumbar vertebra, the substructures after the first-order segmentation of the lumbar vertebra include: vertebral body 101, posterior structure 102, and pedicle 103.

[0156] See Figure 16 The lumbar spine corresponds to one primary cutting model and multiple secondary cutting models. The purpose of the primary cutting model is to obtain... Figure 12 The coarse-segmented image shown, the purpose of the two-stage cutting model is to obtain Figures 11A to 11C The image shown is a detailed breakdown. Each secondary cutting model is trained to suit different clinical indications and planning needs. Therefore, for the lumbar spine, there can be multiple secondary cutting models, each designed to perform a different task.

[0157] See Figure 11A The substructures after secondary lumbar vertebral resection include: vertebral body 1, left pedicle 2, right pedicle 3, left pedicle entry point region 4, right pedicle entry point region 5, left transverse process 6, right transverse process 7, spinous process 14, left superior articular process 8, left inferior articular process 12, right superior articular process 9, right inferior articular process 13, left lamina 10, and right lamina 11, totaling 14 secondary substructures, of which 12 are symmetrical structures and 2 are independent structures (including vertebral body 1 and spinous process 14).

[0158] In summary, taking the lumbar spine as an example, the substructures after primary resection mainly include: vertebral body, pedicle, and posterior structures; the substructures after secondary resection are mainly a subdivision of the posterior structures, including: transverse process, pedicle entry point area, superior articular process, inferior articular process, lamina, and spinous process.

[0159] It is understood that the technical solution provided in this embodiment, targeting clinical indications and planning needs, adopts a multi-level, multi-task fine segmentation model group strategy. This decomposes the complex task of fine spinal segmentation into multiple sub-models to fulfill indication-based planning requirements, reducing the complexity of each model and improving its responsiveness. Users can select different secondary segmentation models according to different tasks, making it widely applicable and highly scalable.

[0160] In practice, the method also includes:

[0161] For the disconnected regions of the coarse segmented image, a connected component analysis algorithm is used to connect them with the surrounding connected regions, and the connected coarse segmented image is then input into the secondary segmentation model.

[0162] For the disconnected regions of the subdivided image, a connected component analysis algorithm is used to connect them with the surrounding connected regions, and the connected subdivided image is used as the output result.

[0163] In practice, the method also includes:

[0164] Extract the morphological features of secondary single vertebral bone structures from the subdivided images;

[0165] Based on the morphological characteristics, multiple single vertebral bone structures are fused to generate a bony channel formed between the multiple single vertebral bone structures; the bony channel includes at least the spinal canal, intervertebral foramen, and intervertebral disc region.

[0166] See Figures 13A-13E From a clinical application perspective, bony channels are of great significance. Therefore, after the sub-structures are further subdivided, bony channels need to be generated separately. Bony channels include, but are not limited to: the superior endplate of the vertebral body, the inferior endplate of the vertebral body, the spinal canal, the intervertebral foramen, the facet joints, and the lateral recesses.

[0167] For example, the spinal canal is a bony passage that naturally forms between multiple lumbar vertebrae when they are combined vertically.

[0168] To understand the specific location of the bony canals, please refer to [link / reference]. Figures 13A-13E , Figure 13A The diagram shows the superior endplate (the area within the upper dashed line in the diagram) and the inferior endplate (the area within the lower dashed line in the diagram) of the vertebral body. Figure 13B This indicates the spinal canal (the area within the dotted line in the diagram contains the spinal cord); Figure 13C This indicates the intervertebral foramen (within the area indicated by the dotted line in the diagram, where nerve roots enter and exit); Figure 13D This indicates the facet joints and articular surfaces (within the area indicated by the dashed lines in the diagram); Figure 13E This indicates the lateral recess (within the area indicated by the dashed line in the diagram).

[0169] It is understood that the technical solution provided in this embodiment takes into account the bony channels between multiple single vertebral bone structures after cutting. This provides a precise substructure segmentation map for subsequent clinical surgical planning, laying a solid foundation for achieving rapid, reliable and stable initial planning, and ultimately improving surgical efficiency, enhancing intraoperative decision support and safety reminders.

[0170] As mentioned above, the single-spine multi-level multi-task model group includes a first-level cutting model and multiple second-level cutting models, all of which are pre-trained.

[0171] Before model training, image preprocessing is required. This image preprocessing includes:

[0172] 1. Adjust the pixel spacing in the XYZ scanning directions of the original image of each single vertebral bone structure to be consistent, so as to obtain isotropic pixel volume and mask;

[0173] 2. Divide the image grayscale into different levels and perform grayscale processing on the original image;

[0174] 3. Construct three-dimensional samples based on single vertebral bone structures. The sample size should at least cover the complete image of the bone structure to be segmented, so that the 3D U-net network model can learn the overall structural morphological features.

[0175] In addition, during the image preprocessing stage, osteophytes need to be manually segmented from the vertebral structure using a mesh component (after the osteophytes are segmented, no mask is added to the segmented osteophytes, so the model training will not process the osteophyte image) to avoid the osteophytes affecting the model training results. Due to the varied morphology of osteophytes, their segmentation is not done automatically for the time being.

[0176] In addition, sample data augmentation during network model training can include adding random noise, rotation around the three axes XYZ within a certain angle range, scaling within a certain range, etc.

[0177] Understandably, image preprocessing can ensure that the data input into the subsequent first-level and second-level cutting models can be accurately identified and effectively processed, thereby improving the reliability and accuracy of model training.

[0178] In practice, the first-level cutting model is trained based on a 3D U-net network model and includes:

[0179] Obtain training samples: Obtain the original image containing the complete vertebral structure; continuously segment the vertebral structure in the original image containing the complete vertebral structure to obtain the original image containing multiple single vertebral structures; select the original image of the single vertebral structure to be trained from the multiple segmented original images of single vertebral structures; add a mask to the first-level subdivision structure on the original image of the single vertebral structure to be trained to obtain the GT mask (Ground Truth, GT ground truth); use the original image of the single vertebral structure to be trained and the GT mask as training samples;

[0180] Model architecture construction: Define the network parameters of the 3D U-net network model, including the number of convolutional layers, the number of channels, the loss function, and the number of optimization iterations of the model; define two input channels, which are used to receive the original image of the single vertebral structure to be trained and the GT mask, respectively; define one output channel, which is used to output the coarse-segmented image;

[0181] Model training: Input the training samples into the constructed 3D U-net network model, perform iterative optimization, calculate the loss function between the first-level substructure segmentation mask predicted by the model and the GT mask, and adjust the network parameters according to the loss function until the number of optimization iterations reaches the preset number, and the value of the loss function is within the preset threshold range and tends to be stable. The model is then determined to have converged, and the model at this time is marked as a first-level segmentation model.

[0182] Model prediction: The newly acquired training samples are input into the first-level segmentation model to obtain a coarse-segmented image of the single vertebral bone structure to be trained.

[0183] Preferably, the training samples of the secondary cutting model are the coarse-segmented images output by the primary cutting model, and the coarse-segmented images carry mask information of the secondary single vertebral bone structures to be cut.

[0184] The network model structure and training method of the second-level cutting model are the same as those of the first-level cutting model, except that the network model parameters are different (the network model parameters include, but are not limited to: convolution type, number of convolution layers, weight distribution in the loss function, number of channels, and the number of optimization iterations of the model are slightly adjusted).

[0185] Taking the lumbar spine as an example, see Figure 14 The input to the 3D U-net network model is the original image of a single lumbar vertebra and its substructure mask. The output of the first-level segmentation model is a coarse-segmented image including the background, vertebral body, pedicle, and posterior structures. See the output image for reference. Figure 15 As shown.

[0186] The loss function can be various methods such as weighted cross-entropy or Dice loss function, or a combination thereof. In practice, given that there may be significant differences in volume between categories during substructure segmentation, this embodiment preferably uses weighted cross-entropy as the loss function. For example, the weights of [background, vertebral body, pedicle, posterior structure] are set to [1, 1, 6, 1] respectively, to reduce the problem of volume imbalance between categories and increase the weight of the smaller pedicle in the loss function.

[0187] It is understood that the technical solution provided in this embodiment can be applied to various application scenarios, including but not limited to processing the complex and varied substructure segmentation from the cervical spine to the thoracic and lumbar spine, and the substructure segmentation of any segment of the lumbar and thoracic spine, which only requires different classification methods to be used for sub-substructure subdivision.

[0188] In addition, this embodiment also proposes a multi-level, multi-task-based fine segmentation model group strategy. The segmentation substructure from coarse to fine can better improve the segmentation accuracy. At the same time, depending on the different clinical indications and planning needs, secondary segmentation models for different tasks are selectively trained, which reduces the complexity and mutual interference of the model's fine substructure segmentation and can improve the accuracy of subsequent planning.

[0189] Understandably, the introduction of multi-level models reduces the difficulty of training network models. For a network model, the more categories it needs to segment, the more complex the network structure itself may be, the larger the amount of training data required, and the easier it is for categories to be confused. This is especially true for delicate structures like the spine, where each substructure is relatively small, there are no obvious grayscale differences between substructures, and too many classifications make post-processing more difficult to distinguish. The technical solution provided in this implementation selectively trains secondary segmentation models to complete different tasks according to different clinical indications and planning needs, reducing the complexity and mutual interference of fine substructure segmentation in the model, and improving the accuracy of subsequent planning.

[0190] Example 2

[0191] Figure 8 This is a schematic block diagram illustrating an automatic planning system 100 for bone structure screw channels according to an exemplary embodiment. The bone structure includes multiple single vertebral bone structures, and each single vertebral bone structure includes multiple substructures, such as... Figure 8 As shown, the system 100 includes:

[0192] The first determining module 101 is used to extract the morphological features of the substructures of any single vertebral bone structure, and determine the substructures that the screw channel is expected to pass through based on the morphological features.

[0193] It is also used to determine the substructure in which the screw channel entry point region is located as the screw channel entry point substructure;

[0194] The substructure containing the screw channel stop point region is defined as the screw channel stop point substructure.

[0195] Apart from the screw channel inlet substructure and the screw channel outlet substructure, the other substructures that the screw channel is expected to pass through are defined as the screw channel midpoint structure.

[0196] The second determining module 102 is used to determine the central axis of the screw channel entry point substructure or the central axis of the screw channel midpoint structure according to the type of disease. The straight line where the central axis is located is the default planned path of the screw channel. The starting point of the default planned path is the intersection of the extension line of the central axis and the screw channel entry point substructure, and the ending point is the intersection of the extension line of the central axis and the screw channel ending point substructure.

[0197] It should be noted that, in practice, the technical solution provided in this embodiment runs in the controller of the medical device, or is loaded into an electronic device connected to the controller. The controller of the medical device executes the corresponding method by calling the program stored in the electronic device.

[0198] The implementation methods and beneficial effects of the above modules can be found in the description of the relevant steps in the above embodiments, and will not be repeated in this embodiment.

[0199] It is understood that the technical solution provided in this embodiment extracts the morphological features of the substructures of a single vertebral bone structure, determines the substructures through which the screw channel is expected to pass based on the morphological features, and automatically generates the default planning path of the screw channel according to the type of disease. Compared with the manual planning of screw channels in the prior art, this realizes the automated planning of screw channels, reduces the dependence on the surgeon's experience and subjective judgment, and effectively ensures the planning quality and efficiency. It can achieve fast, reliable and stable initial planning, and ultimately improve surgical efficiency.

[0200] Example 3

[0201] An electronic device according to an exemplary embodiment includes:

[0202] A processor, and a memory connected to the processor;

[0203] The memory is used to store computer programs;

[0204] The processor is used to call and execute the computer program in the memory to perform the above-described method.

[0205] It is understood that the technical solution provided in this embodiment extracts the morphological features of the substructures of a single vertebral bone structure, determines the substructures through which the screw channel is expected to pass based on the morphological features, and automatically generates the default planning path of the screw channel according to the type of disease. Compared with the manual planning of screw channels in the prior art, this realizes the automated planning of screw channels, reduces the dependence on the surgeon's experience and subjective judgment, and effectively ensures the planning quality and efficiency. It can achieve fast, reliable and stable initial planning, and ultimately improve surgical efficiency.

[0206] Example 4

[0207] An exemplary embodiment illustrates a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the methods described above.

[0208] It is understood that the technical solution provided in this embodiment extracts the morphological features of the substructures of a single vertebral bone structure, determines the substructures through which the screw channel is expected to pass based on the morphological features, and automatically generates the default planning path of the screw channel according to the type of disease. Compared with the manual planning of screw channels in the prior art, this realizes the automated planning of screw channels, reduces the dependence on the surgeon's experience and subjective judgment, and effectively ensures the planning quality and efficiency. It can achieve fast, reliable and stable initial planning, and ultimately improve surgical efficiency.

[0209] Of course, those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.). The program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The storage medium can be a memory, magnetic disk, optical disk, etc.

[0210] The specific embodiments of the present invention described above do not constitute a limitation on the scope of protection of the present invention. Any other corresponding changes and modifications made in accordance with the technical concept of the present invention should be included within the scope of protection of the claims of the present invention.

Claims

1. A method for automatic planning of a bone structure screw channel, characterized by, The bone structure comprises a plurality of single vertebrae structures, each single vertebrae structure comprises a plurality of sub-structures, and the method comprises: For any single vertebrae structure, extracting morphological features of the sub-structures of the single vertebrae structure, and determining sub-structures that the screw channel is expected to pass through according to the morphological features; Determining the sub-structure where the screw channel entry point region is located as the screw channel entry point sub-structure; Determining the sub-structure where the screw channel exit point region is located as the screw channel exit point sub-structure; Determining other sub-structures that the screw channel is expected to pass through except the screw channel entry point sub-structure and the screw channel exit point sub-structure as screw channel midpoint sub-structures; According to the type of the disease, determining the middle axis of the screw channel entry point sub-structure or the middle axis of the screw channel midpoint sub-structure, and the straight line where the middle axis is located is the default planning path of the screw channel; the starting point of the default planning path is the intersection of the extension line of the middle axis and the screw channel entry point sub-structure, and the ending point is the intersection of the extension line of the middle axis and the screw channel exit point sub-structure; The middle axis refers to the middle axis of the bone channel with the best mechanical stability of the sub-structure from the direction of the screw entry point.

2. The method of claim 1, wherein, Further comprising: extracting the curved surface grid of the surface of the screw channel entry point region, and determining the intersection of the default planning path and the curved surface grid as the starting point of the default planning path; calculating the included angle between the default planning path and the curved surface grid; According to the included angle, it is judged whether there is a risk of bone surface slipping at the screw channel entry point region, if yes, adjusting the starting point, regenerating the screw channel path, and determining the regenerated screw channel path as the default planning path; otherwise, keeping the current default planning path.

3. The method of claim 2, wherein, Further comprising: According to the morphological features, determining the sub-structures that the screw channel is expected to avoid, and extracting the 3D edge points of the sub-structures that need to be avoided; determining whether the default planning path intersects with the 3D edge points of the sub-structures that need to be avoided, if yes, adjusting the starting point of the default planning path, regenerating the screw channel path, and determining the regenerated screw channel path as the default planning path; otherwise, keeping the current default planning path.

4. The method of claim 3, wherein, Further comprising: According to the morphological features, extracting the 3D edge points of the screw channel exit point sub-structure; According to the 3D edge points of the screw channel exit point sub-structure, it is judged whether the default planning path reaches the screw channel exit point region, if yes, keeping the current default planning path; otherwise, adjusting the starting point of the default planning path, regenerating the screw channel path, and determining the regenerated screw channel path as the default planning path.

5. The method according to any one of claims 2 to 4, characterized in that, The adjustment of the starting point of the default planning path and the regeneration of the screw channel path are specifically: translating the current default planning path to the adjusted starting point position, and determining the translated path as the regenerated screw channel path.

6. The method of claim 5, wherein, Further comprising: calculating the thickness of each sub-structure that the screw channel is expected to pass through; calculating the length of the default planning path; Determine a size of the screw according to the minimum value of the thickness and a length of the default planned path.

7. The method of claim 5, wherein, Further comprising: If the single spinal bone structure is a lumbar vertebra, and the screw channel is a pedicle screw channel, the entry point area of the screw channel is a posterior surface of a posterior entry point area of the pedicle, and the end point area of the screw channel is a cortex near or at the anterior of the vertebral body; the central axis is a central axis of the pedicle; If the single spinal bone structure is a lumbar vertebra, and the screw channel is a cortical bone screw channel, the entry point area of the screw channel is a posterior surface of a posterior entry point area of the lamina isthmus, and the end point area of the screw channel is a lateral cortex of the vertebral body; the central axis is a central axis of the pedicle area; If the single spinal bone structure is a lumbar vertebra, and the screw channel is a lamina screw channel, the entry point area of the screw channel is a contralateral lamina dorsal surface, and the end point area of the screw channel is a lateral cortex area surface of the pedicle; the central axis is a central axis of the lamina; If the single spinal bone structure is a lumbar vertebra, and the screw channel is a transforaminal screw channel, the entry point area of the screw channel is a contralateral lamina dorsal surface, and the end point area of the screw channel is a lateral cortex area surface of the pedicle; the central axis is a central axis of the upper and lower articular processes; If the single spinal bone structure is a lumbar vertebra, and the screw channel is a transforaminal screw channel, the entry point area of the screw channel is a contralateral lamina dorsal surface, and the end point area of the screw channel is a lateral cortex area surface of the pedicle; the central axis is a central axis of the upper and lower articular processes.

8. An automatic bone structure screw channel planning system, characterized by, The bone structure comprises a plurality of single spinal bone structures, each single spinal bone structure comprises a plurality of sub-structures, and the system comprises: A first determining module configured to extract morphological features of the sub-structures of any single spinal bone structure, and determine a sub-structure expected to be passed through by a screw channel according to the morphological features; Further configured to determine a sub-structure where an entry point area of the screw channel is located as an entry point sub-structure of the screw channel; Determine a sub-structure where an end point area of the screw channel is located as an end point sub-structure of the screw channel; Determine other sub-structures except the entry point sub-structure and the end point sub-structure of the screw channel as midpoint sub-structures of the screw channel; A second determining module configured to determine a central axis of the entry point sub-structure of the screw channel or a central axis of the midpoint sub-structure of the screw channel according to a type of a disease, and determine a straight line where the central axis is located as a default planned path of the screw channel; a starting point of the default planned path is an intersection of an extension line of the central axis and the entry point sub-structure of the screw channel, and an end point is an intersection of the extension line of the central axis and the end point sub-structure of the screw channel, and the central axis refers to a central axis of a bone channel with the best mechanical stability of the sub-structure from the perspective of the entry point of the screw.

9. An electronic device, comprising: Comprise: A processor and a memory connected to the processor; The memory is configured to store a computer program; The processor is configured to call and execute the computer program in the memory to execute the method in any one of claims 1-7.

10. A non-transitory computer-readable storage medium having stored thereon computer instructions, wherein, The computer instructions are for causing a computer to perform the method of any one of claims 1-7. The computer instructions are for causing a computer to perform the method of any one of claims 1-7.

Images