Precise navigation method and system for distal femur epiphyseal block

Abstract

The invention provides a precise navigation method and system for distal femoral epiphyseal block. The method comprises the following steps: acquiring a diagnosis result of femoral ectropion and ectropion and an intraoperative three-dimensional image of a knee joint; based on the diagnosis result and the intraoperative three-dimensional image, a bone three-dimensional model of the distal femur and planning information of epiphyseal block are generated; and tracking and displaying the poses of the screw placement tool, the guide equipment and the solid distal femur in real time so as to navigate the screw placement action of epiphyseal block. In the application, accurate screw placement of epiphyseal block is realized by planning the screw placement scheme of epiphyseal block, tracking the screw placement tool and the distal end of the solid femur in real time, so that accurate screw placement is realized without repeated perspective positioning, and radiation exposure and possible epiphyseal injury are avoided.

Description

Technical Field

[0001] This application relates to the field of medical image processing technology, and more specifically, to a precise navigation method and system for distal femoral epiphyseal block. Background Technology

[0002] Currently, distal femoral epiphyseal blockade for adjusting femoral varus or valgus is of great significance. Existing techniques mainly involve hemi-epiphysiodesis, a minimally invasive procedure that blocks the distal femoral epithelium on one side (medial or lateral) to achieve progressive correction of femoral varus or valgus.

[0003] This method involves minimal surgical trauma, rapid recovery, and a gradual correction process that can be adjusted as the bone grows. However, it requires multiple fluoroscopic positioning sessions during the procedure, increasing radiation exposure and potentially leading to epiphyseal damage. Summary of the Invention

[0004] To address the aforementioned problems, the first aspect of this application provides a precise navigation method for distal femoral epiphyseal block, comprising: Obtain diagnostic results for femoral varus / valgus and intraoperative three-dimensional images of the knee joint; Based on the diagnostic results and intraoperative 3D images, a 3D model of the distal femur is generated, along with planning information for epiphyseal block. The device tracks and displays the position of the pin placement tool, guiding device, and distal femur in real time to guide the pin placement process in epiphyseal block.

[0005] The second aspect of this application provides a manufacturing system for a precise navigation method for distal femoral epiphyseal arrest, comprising: The image acquisition unit is used to acquire the diagnostic results of femoral varus and valgus and intraoperative three-dimensional images of the knee joint. Intraoperative planning unit, which is used to generate a three-dimensional model of the distal femur based on diagnostic results and intraoperative three-dimensional images, and planning information for epiphyseal blockade; The intraoperative screw placement unit is used to track and display the position of the screw placement tool, guiding device, and distal femur in real time to guide the screw placement action in epiphyseal block.

[0006] A third aspect of this application provides an electronic device, including: a memory and a processor; the memory being configurable to store a program, and the processor being coupled to the memory for executing the program in the memory for: Obtain diagnostic results for femoral varus / valgus and intraoperative three-dimensional images of the knee joint; Based on the diagnostic results and intraoperative 3D images, a 3D model of the distal femur is generated, along with planning information for epiphyseal block. The device tracks and displays the position of the pin placement tool, guiding device, and distal femur in real time to guide the pin placement process in epiphyseal block.

[0007] The fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, the program being executed by a processor to implement the aforementioned precise navigation method for distal femoral epiphyseal block.

[0008] In this application, by planning the pin placement scheme for epiphyseal blockade and tracking the pin placement tool and the distal femur in real time, precise pin placement for epiphyseal blockade is achieved. This allows for precise pin placement without the need for multiple fluoroscopic positioning, avoiding radiation exposure and potential epiphyseal damage. Attached Figure Description

[0009] Figure 1 This is a flowchart of a precise navigation method for distal femoral epiphyseal block according to an embodiment of this application; Figure 2 This is an anteroposterior view of the epiphyseal blockade, a precise navigation method for distal femoral epiphyseal blockade according to an embodiment of this application. Figure 3 This is a lateral view of the epiphyseal blockade, a precise navigation method for distal femoral epiphyseal blockade according to an embodiment of this application. Figure 4 A diagram illustrating the architecture of a segmentation model for a precise navigation method for distal femoral epiphyseal block according to an embodiment of this application. Figure 5 This is an architectural diagram of a precision navigation system for distal femoral epiphyseal block according to an embodiment of this application; Figure 6 This is an architectural diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0010] To make the above-mentioned objects, features, and advantages of this application more apparent and understandable, specific embodiments of this application will be described in detail below with reference to the accompanying drawings. Although exemplary embodiments of this application are shown in the drawings, it should be understood that this application can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of this application and to fully convey the scope of this application to those skilled in the art.

[0011] It should be noted that, unless otherwise stated, the technical or scientific terms used in this application shall have the ordinary meaning as understood by one of ordinary skill in the art to which this application pertains.

[0012] This application provides a precise navigation method for distal femoral epiphyseal block as described above. The specific scheme of this method is as follows: Figures 1-4As shown, this method can be executed by a precise navigation system for distal femoral epiphyseal block, which can be integrated into electronic devices such as computers, servers, computer clusters, and data centers. Combined with... Figure 1 As shown, the precise navigation method for distal femoral epiphyseal block includes: S101, to obtain the diagnostic results of femoral varus and valgus and intraoperative three-dimensional images of the knee joint; The lateral varus or valgus of the femur is determined by measuring the femoral valgus angle or varus angle on a full-length lower limb radiograph. The valgus or valgus angle is unrelated to the internal or external rotation of the femoral head. The distal lateral angle of the femur (LDFA) is measured on a full-length lower limb radiograph to determine the varus or valgus of the knee, with the femoral side being the responsible side.

[0013] In cases of valgus deformity, a plate and locking screw are placed only on the medial side of the distal femur; in cases of varus deformity, a plate and locking screw are placed only on the lateral side of the distal femur.

[0014] S102, Based on the diagnostic results and intraoperative three-dimensional images, generate a three-dimensional model of the distal femur and planning information for epiphyseal arrest. S103 tracks and displays the position of the pin placement tool, guiding device, and distal femur in real time to guide the pin placement action in epiphyseal block.

[0015] In this application, by planning the pin placement scheme for epiphyseal blockade and tracking the pin placement tool and the distal femur in real time, precise pin placement for epiphyseal blockade is achieved. This allows for precise pin placement without the need for multiple fluoroscopic positioning, avoiding radiation exposure and potential epiphyseal damage.

[0016] Here, a detailed description of the background technology is necessary. It should be noted that this detailed description will raise several technical issues, which are extensions and should not be used as the basis for judging whether an independent solution lacks necessary features.

[0017] In existing techniques, a minimally invasive block is performed on one side (medial or lateral) of the distal femoral epiphysis to achieve gradual correction of femoral varus or valgus. The advantages of this method are: minimally invasive, minimal trauma; the ability to selectively block the medial or lateral side for precise adjustment of varus or valgus; and a gradual correction process that can be adjusted as the femur grows.

[0018] However, the drawbacks are also obvious: Positioning relies on fluoroscopy and experience: Intraoperative positioning requires multiple imaging confirmations, and the operation is highly dependent on the surgeon's experience. Insufficient precision and repeated adjustments may lead to epiphyseal damage and permanent premature epiphyseal closure.

[0019] High risk of radiation exposure: Repeated fluoroscopy is required during the operation, and both the child and the surgeon face additional radiation risks.

[0020] The effect of the blockade is not entirely controllable: insufficient blockade, excessive blockade, or misalignment may occur, resulting in an unsatisfactory corrective effect. Overcorrection or undercorrection may occur, or femoral sagittal plane deformity may occur, such as distal femoral flexion-extension deformity.

[0021] Implant-related complications include screw breakage, loosening, displacement, and even penetration into the joint cavity, requiring a second surgery.

[0022] In one embodiment, the planning information for epiphyseal block includes the placement information of the figure-eight plate and the placement information of at least two blocking screws.

[0023] In one embodiment, the pin placement information of the locking screw includes at least two of the following: pin placement position information, pin placement direction information, and pin placement depth information.

[0024] In one embodiment, the locking screw is positioned parallel to the epiphyseal line of the distal femur.

[0025] The insertion depth of the locking screw shall not exceed 1 / 3 of the epiphyseal plate.

[0026] The figure-eight plate is placed at the midpoint of the anteroposterior diameter of the femur.

[0027] There are two locking screws, which are set at both ends of the figure-eight steel plate.

[0028] In one implementation, S102, a three-dimensional model of the distal femur is generated based on the diagnostic results and intraoperative three-dimensional images, and epiphyseal arrest planning information, including: The intraoperative three-dimensional images of the knee joint are segmented and reconstructed into a three-dimensional skeletal model of the knee joint; the three-dimensional skeletal model of the knee joint includes a three-dimensional skeletal model of the distal femur. Based on the diagnostic results and a three-dimensional model of the knee joint skeleton, planning information for epiphyseal blockade is generated.

[0029] After obtaining a three-dimensional model of the knee joint skeleton, the algorithm can automatically identify the epiphysis and articular surfaces, calculate the optimal placement position of the figure-eight plate, and the screw placement angle and depth to achieve epiphyseal block planning.

[0030] The planning information is displayed on the screen in a graphical manner, including the placement position of the figure-eight steel plate, the screw placement point and placement angle, and the placement depth value.

[0031] Among them, the planning information for epiphyseal blockade generates a detailed PDF report, which includes basic patient information, image data, measurement angles and analysis conclusions, for clinicians to refer to.

[0032] In one embodiment, the intraoperative three-dimensional image is a CT medical image or a 3D fluoroscopic medical image.

[0033] Among them, CT medical image scanning and reconstruction: the patient lies supine on the CT scanning bed, and the knee joint is scanned according to the standard scanning protocol; the scan data is reconstructed in three dimensions using a special model to clearly display the bone structure around the knee joint.

[0034] Among them, 3D perspective medical images can be 3D C-arm images: using a rotatable C-arm X-ray system to acquire X-rays from multiple angles around the patient during surgery, and generating three-dimensional images through reconstruction algorithms.

[0035] In one embodiment, S103, which involves real-time tracking and display of the position and orientation of the pin placement tool, guiding device, and distal femur to guide the pin placement action in epiphyseal block, includes: Acquire and display the current pose of the guide device installed at the end of the robotic arm and the current pose of the distal femur. Plan the guide motion path from the current pose of the guide equipment to the ready position of the arresting screw; Control the robotic arm to move along the guide path to the nail placement preparation position; The relative position of the guide device to the distal femur is locked, and the current pose of the screw placement tool is displayed so that the surgeon can perform the screw placement action.

[0036] The positions of the pin placement tool, guiding device, and distal femur can be monitored in real time using an optical navigator and an optical positioning frame installed on the pin placement tool, guiding device, and distal femur.

[0037] During the specific surgical procedure, a local incision of about 1-2 cm can be made at the corresponding location on the distal femur to serve as the placement site for the plate and the locking screws. The screw placement process involves first placing the Kirschner wire, then placing the plate and ensuring its proper positioning (this step can be done manually or by a robotic arm), and finally placing the screws.

[0038] In the specific nail placement process, the steel plate can also be placed directly and its position confirmed to be good (this step can be done manually or by a robotic arm), and then the screws can be placed.

[0039] In one embodiment, S103, which involves real-time tracking and display of the position of the pin placement tool and the physical knee joint to guide the placement of the locking screw, further includes: Real-time monitoring of the spatial position and execution trajectory of the pin placement tool; Compare the execution trajectory with the insertion path of the locking screw to determine the path deviation; A warning message will be displayed if the path deviation exceeds the preset range.

[0040] In this way, by comparing in real time, the pin placement accuracy is ensured, greatly improving the precision of epiphyseal block.

[0041] Preferably, the navigation system can display the position, direction and depth of the epiphyseal plate in real time during the operation, so as to achieve precise positioning and avoid accidental damage to the joint surface or non-target areas.

[0042] Preferably, the navigation system presents a virtual trajectory on the screen, allowing the operator to perform operations with real-time feedback, thereby ensuring that the angle, depth, and symmetry of the epiphyseal plate penetration meet expectations and improving the controllability and consistency of the blocking effect.

[0043] Preferably, the navigation device can monitor the spatial position of surgical instruments in real time and compare it with the planned trajectory. When deviation occurs, the system can immediately issue a prompt or perform error correction, thereby reducing the need for repeated fluoroscopy, reducing radiation exposure, and improving operational accuracy and safety.

[0044] In this application, based on intraoperative navigation and image reconstruction, the three-dimensional position and orientation of the distal femoral epiphyseal plate can be clearly displayed, achieving individualized and precise positioning, and avoiding the limitations of traditional fluoroscopy that relies on experience.

[0045] In this application, by pre-setting the optimal drilling or screw insertion path and providing real-time trajectory guidance and deviation correction during operation, the high degree of controllability and consistency of the obstruction range, angle and depth are ensured.

[0046] In this application, the navigation technology significantly reduces the number of intraoperative fluoroscopy sessions, reduces radiation exposure for both the patient and the surgeon, and effectively avoids complications such as screws accidentally entering the joint surface, incomplete or excessive block, thereby greatly improving surgical safety and long-term corrective effects.

[0047] In one implementation, combined with Figure 4 As shown, the segmentation of the intraoperative three-dimensional image of the knee joint includes: The intraoperative 3D images are downsampled sequentially to obtain multiple levels of downsampled images; the downsampling process includes 3D convolution processing downsampling and parallel convolution processing downsampling. Upsampling is performed sequentially on downsampled images at multiple levels to obtain upsampled images at multiple levels; the upsampling process includes 3D convolution upsampling and parallel convolution upsampling. The highest-level upsampled image is processed to obtain the segmentation result.

[0048] Among them, combined Figure 4 As shown, the specific segmentation process is as follows: The intraoperative 3D images were sequentially processed by 3D convolution and downsampled to obtain the first downsampled image and the second downsampled image. The second downsampled image is subjected to parallel convolution and downsampling in sequence to obtain the third, fourth and fifth downsampled images in sequence; The fifth, fourth, and third downsampled images are sequentially concatenated, processed by parallel convolution, and upsampled to obtain the fourth and third upsampled images. The third downsampled image, the second downsampled image, and the first downsampled image are sequentially stitched together, processed by 3D convolution, and upsampled to obtain the second upsampled image and the segmentation result.

[0049] In one implementation, combined with Figure 4 As shown, the 3D convolution process includes: Perform 3D convolution on the input feature map to obtain a 3D feature map; The 3D feature map is normalized and activated to obtain the output feature map.

[0050] In one implementation, combined with Figure 4 As shown, the parallel convolution process includes: The input feature map is subjected to 3D convolution, normalization and activation processing to obtain the first 3D convolution map; The first 3D convolutional image is subjected to 3D convolution, normalization and activation processing to obtain the second 3D convolutional image; Multi-head attention and normalization are applied to the input feature map to obtain a multi-head convolutional map; After combining the multi-head convolutional map and the input feature map, multi-head attention, normalization and multi-layer perception processing are performed to generate the multi-layer perception map. The output feature map is obtained by combining the second 3D convolutional map and the multilayer perceptron map.

[0051] In this way, in parallel convolution processing, a parallel architecture of CNN and Transformer (CT Module) is used for feature extraction and feature fusion to fully explore image features.

[0052] In this application, a CNN+Transformer architecture is used for network design to minimize network parameters and greatly improve the efficiency of training and segmentation.

[0053] In another implementation, a novel method is used for intraoperative three-dimensional image segmentation, wherein the intraoperative three-dimensional image segmentation of the knee joint includes: The intraoperative three-dimensional images were downsampled sequentially to obtain downsampled images at multiple levels; Multi-scale processing is performed on the lowest-level downsampled image to obtain a multi-scale image; The downsampled graphs at multiple levels are subjected to gate fusion convolution processing based on gate sequences to obtain long connected graphs at multiple levels. The multi-scale graph and the long connected graph at multiple levels are upsampled sequentially to obtain upsampled graphs at multiple levels. The top-level upsampled image is convolved and activated to obtain the segmentation result.

[0054] In this application, multi-scale processing can be achieved by setting parallel convolution kernels to extract features at multiple scales, then using feature pyramid fusion to perform parallel processing of the multi-scale feature extraction, and finally using channel attention to fuse the features to obtain a multi-scale map.

[0055] The specific processes of downsampling and upsampling in this application will not be described in detail.

[0056] The process of performing gate fusion convolution based on gate sequences on downsampled graphs at multiple levels yields long connected graphs at multiple levels, including: Multiple convolutional branches are constructed, each input by at least two levels of downsampled images. After fusion, an output image of a preset level is obtained. The output image is then output after passing through a gate function, which is a function controlled by a gate sequence. Construct a gate sequence to control the output of the convolutional branch based on the gate function; if the number in the gate sequence is 1, the corresponding gate function allows the convolutional branch to output, and if the number in the gate sequence is 0, the corresponding gate function does not allow the convolutional branch to output. Merge the output graphs that are at the same preset level and are output together to form a long connected graph at that preset level.

[0057] In this application, the number of convolutional branches is greater than five times the number of layers to ensure the output of long connected graphs with multiple layers (if a long connected graph with 4 layers is to be output, the number of convolutional branches is set to at least 20).

[0058] In this application, the downsampled image size of the input in each convolution branch is different, and it can be unified to a preset layer size before processing.

[0059] In this application, the processing procedure for each convolutional branch includes: receiving multiple input downsampled images; performing size processing on the downsampled images to obtain multiple downsampled images of the corresponding size of the convolutional branch; performing fusion processing on multiple downsampled images of the same size to obtain an output image; obtaining the gate sequence number of the convolutional branch; if the number is 1, then the output image is used as the long connected graph output by the convolutional branch; if the number is 0, then no output is made, or an empty convolutional image is output.

[0060] In this application, the gate sequence is a sequence of digits 0 and 1. During the training phase of gate fusion convolution processing, the gate sequence can be randomly generated to improve the diversity of training, and the gate sequence is trained synchronously during the training phase; after training, the gate sequence with the best processing effect is taken as the final gate sequence.

[0061] In this application, by setting up gate fusion convolution processing and utilizing gate sequences and gate functions, downsampled images at multiple levels are randomly fused, thereby granting the downsampled images a similar fusion permission. This allows the downsampled images to be fused according to preferences during the training process (during training with a large amount of data, the combinations of downsampled fusion will be exhaustively explored, similar to the downsampled images having preferences), in order to achieve a more intelligent training effect.

[0062] In this application, multiple convolutional branches are constructed randomly, ensuring that different users construct different convolutional branches. Since the final training result includes gate sequences, only these gate sequences need to be retained to achieve confidentiality of the entire model, thus providing strong security. Furthermore, the gate sequences consume very little data and are easily saved and transmitted through various channels, greatly facilitating decryption and security.

[0063] In addition, random construction greatly enhances the diversity and randomness of gate fusion convolution processing, thereby approximately improving the level of intelligence.

[0064] Existing techniques primarily rely on the surgeon's experience to determine the epiphyseal plate position under fluoroscopy, which carries risks of inaccurate positioning and damage. This application, based on intraoperative navigation-based three-dimensional reconstruction and real-time positioning, can intuitively display the epiphyseal plate's anatomical structure, achieving individualized and precise positioning, and avoiding the instability of results caused by experience differences in traditional methods.

[0065] Traditional nerve block procedures require multiple fluoroscopy sessions to confirm the drilling or screw insertion path, increasing radiation exposure and operational difficulty. This application utilizes a navigation system to preset the optimal path and provide real-time dynamic guidance, ensuring accurate instrument insertion angle, depth, and symmetry, significantly reducing the number of fluoroscopy sessions and lowering radiological risks.

[0066] Existing methods often suffer from uncontrollable block range, insufficient or excessive block, and a high risk of implant complications. This application achieves precise control of the block range through real-time navigation feedback and error correction, effectively reducing complications such as screw breakage and articular surface damage, and significantly improving the safety and long-term effectiveness of the block.

[0067] In this application, tests were conducted on multiple patients who underwent navigation-guided distal femoral hemiechial block with figure-eight plate implantation. The measurement results of the method described in this application were compared with those of traditional measurement methods and the actual implantation angle during surgery. The results showed: Compared with the traditional freehand pin placement method under fluoroscopy, the angle error is reduced by more than 80%, and the deviation from the actual implantation angle during surgery is within ±1°.

[0068] In repeatable tests conducted by different personnel and at different time points, the consistency of the measurement results (ICC value) was greater than 0.98, demonstrating high stability and reliability.

[0069] This application provides a precise navigation system for distal femoral epiphyseal block, used to execute the precise navigation method for distal femoral epiphyseal block described above. The precise navigation system for distal femoral epiphyseal block is described in detail below.

[0070] like Figure 5 As shown, the precision navigation system for distal femoral epiphyseal block includes: The image acquisition unit 101 is used to acquire the diagnostic results of femoral varus and valgus and intraoperative three-dimensional images of the knee joint. Intraoperative planning unit 102 is used to generate a three-dimensional model of the distal femur based on diagnostic results and intraoperative three-dimensional images, and planning information for epiphyseal blockade. The intraoperative screw placement unit 103 is used to track and display the position of the screw placement tool, guide device, and distal femur in real time to guide the screw placement action of epiphyseal block.

[0071] In one embodiment, the planning information for epiphyseal block includes the placement information of the figure-eight plate and the placement information of at least two blocking screws.

[0072] In one embodiment, the pin placement information of the locking screw includes at least two of the following: pin placement position information, pin placement direction information, and pin placement depth information.

[0073] In one embodiment, the locking screw is positioned parallel to the epiphyseal line of the distal femur.

[0074] In one embodiment, the intraoperative planning unit 102 is further configured to: Intraoperative three-dimensional images of the knee joint are segmented and reconstructed into a three-dimensional skeletal model of the knee joint; the three-dimensional skeletal model of the knee joint includes a three-dimensional skeletal model of the distal femur; based on the diagnostic results and the three-dimensional skeletal model of the knee joint, planning information for epiphyseal block is generated.

[0075] In one embodiment, the intraoperative three-dimensional image is a CT medical image or a 3D fluoroscopic medical image.

[0076] In one embodiment, the intraoperative screw placement unit 103 is further used for: Acquire and display the current pose of the guide device installed at the end of the robotic arm and the current pose of the distal femur; plan the guide motion path from the current pose of the guide device to the screw placement preparation position; control the robotic arm to move along the guide motion path to the screw placement preparation position. The relative position of the guide device to the distal femur is locked, and the current pose of the screw placement tool is displayed so that the surgeon can perform the screw placement action.

[0077] In one embodiment, the intraoperative screw placement unit 103 is further used for: The system monitors the spatial position and execution trajectory of the pin-setting tool in real time; compares the execution trajectory with the insertion path of the retaining screw to determine the path deviation; and displays a warning message when the path deviation exceeds a preset range.

[0078] In one embodiment, the intraoperative planning unit 102 is further configured to: The intraoperative 3D images are downsampled sequentially to obtain multiple levels of downsampled images; the downsampling process includes 3D convolution downsampling and parallel convolution downsampling; the downsampled images at multiple levels are upsampled sequentially to obtain multiple levels of upsampled images; the upsampling process includes 3D convolution upsampling and parallel convolution upsampling; the highest level upsampled image is processed to obtain the segmentation result.

[0079] In one embodiment, the intraoperative planning unit 102 is further configured to: The input feature map is convolved with 3D to obtain a 3D feature map; the 3D feature map is then normalized and activated to obtain the output feature map.

[0080] In one embodiment, the intraoperative planning unit 102 is further configured to: The input feature map is subjected to 3D convolution, normalization, and activation processing to obtain a first 3D convolutional map; the first 3D convolutional map is subjected to 3D convolution, normalization, and activation processing to obtain a second 3D convolutional map; the input feature map is subjected to multi-head attention and normalization processing to obtain a multi-head convolutional map; the multi-head convolutional map and the input feature map are combined, and then multi-head attention, normalization, and multilayer perception processing are performed to obtain a multilayer perception map; the second 3D convolutional map and the multilayer perception map are combined to obtain an output feature map.

[0081] The precise navigation system for distal femoral epiphyseal block provided in the above embodiments of this application corresponds to the precise navigation method for distal femoral epiphyseal block provided in the embodiments of this application. Therefore, the specific content of the system corresponds to the precise navigation method for distal femoral epiphyseal block. The specific content can be referred to the records in the precise navigation method for distal femoral epiphyseal block, which will not be repeated in this application.

[0082] The precise navigation system for distal femoral epiphyseal block provided in the above embodiments of this application and the precise navigation method for distal femoral epiphyseal block provided in the embodiments of this application are based on the same inventive concept and have the same beneficial effects as the methods used, run or implemented by their stored applications.

[0083] The above describes the internal function and structure of a precision navigation system for distal femoral epiphyseal block, such as... Figure 6 As shown, in practice, the precise navigation system for distal femoral epiphyseal block can be implemented as an electronic device, including: a memory 301 and a processor 303.

[0084] Memory 301 can be configured to store a program.

[0085] Additionally, memory 301 can also be configured to store various other data to support operation on the electronic device. Examples of this data include instructions for any application or method used to operate on the electronic device, contact data, phonebook data, messages, pictures, videos, etc.

[0086] Memory 301 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. Processor 303, coupled to memory 301, is used to execute programs in memory 301 for: Obtain diagnostic results for femoral varus / valgus and intraoperative three-dimensional images of the knee joint; Based on the diagnostic results and intraoperative 3D images, a 3D model of the distal femur is generated, along with planning information for epiphyseal block. The device tracks and displays the position of the pin placement tool, guiding device, and distal femur in real time to guide the pin placement process in epiphyseal block.

[0087] In one embodiment, the planning information for epiphyseal block includes the placement information of the figure-eight plate and the placement information of at least two blocking screws.

[0088] In one embodiment, the pin placement information of the locking screw includes at least two of the following: pin placement position information, pin placement direction information, and pin placement depth information.

[0089] In one embodiment, the locking screw is positioned parallel to the epiphyseal line of the distal femur.

[0090] In one implementation, the processor 303 is further configured to: Intraoperative three-dimensional images of the knee joint are segmented and reconstructed into a three-dimensional skeletal model of the knee joint; the three-dimensional skeletal model of the knee joint includes a three-dimensional skeletal model of the distal femur; based on the diagnostic results and the three-dimensional skeletal model of the knee joint, planning information for epiphyseal block is generated.

[0091] In one embodiment, the intraoperative three-dimensional image is a CT medical image or a 3D fluoroscopic medical image.

[0092] In one implementation, the processor 303 is further configured to: Acquire and display the current pose of the guide device installed at the end of the robotic arm and the current pose of the distal femur; plan the guide motion path from the current pose of the guide device to the screw placement preparation position; control the robotic arm to move along the guide motion path to the screw placement preparation position. The relative position of the guide device to the distal femur is locked, and the current pose of the screw placement tool is displayed so that the surgeon can perform the screw placement action.

[0093] In one implementation, the processor 303 is further configured to: The system monitors the spatial position and execution trajectory of the pin-setting tool in real time; compares the execution trajectory with the insertion path of the retaining screw to determine the path deviation; and displays a warning message when the path deviation exceeds a preset range.

[0094] In one implementation, the processor 303 is further configured to: The intraoperative 3D images are downsampled sequentially to obtain multiple levels of downsampled images; the downsampling process includes 3D convolution downsampling and parallel convolution downsampling; the downsampled images at multiple levels are upsampled sequentially to obtain multiple levels of upsampled images; the upsampling process includes 3D convolution upsampling and parallel convolution upsampling; the highest level upsampled image is processed to obtain the segmentation result.

[0095] In one implementation, the processor 303 is further configured to: The input feature map is convolved with 3D to obtain a 3D feature map; the 3D feature map is then normalized and activated to obtain the output feature map.

[0096] In one implementation, the processor 303 is further configured to: The input feature map is subjected to 3D convolution, normalization, and activation processing to obtain a first 3D convolutional map; the first 3D convolutional map is subjected to 3D convolution, normalization, and activation processing to obtain a second 3D convolutional map; the input feature map is subjected to multi-head attention and normalization processing to obtain a multi-head convolutional map; the multi-head convolutional map and the input feature map are combined, and then multi-head attention, normalization, and multilayer perception processing are performed to obtain a multilayer perception map; the second 3D convolutional map and the multilayer perception map are combined to obtain an output feature map.

[0097] In this application, Figure 6 The diagram only shows some components and does not mean that the electronic device includes only these components. Figure 6 The components shown.

[0098] The electronic device provided in this embodiment is based on the same inventive concept as the precise navigation method for distal femoral epiphyseal block provided in this application embodiment, and has the same beneficial effects as the methods adopted, run or implemented by the application stored therein.

[0099] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-readable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0100] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A system that specifies functions within one or more boxes. These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including an instruction system implemented in a process. Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0101] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0102] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory. Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0103] This application also provides a computer-readable storage medium corresponding to the precise navigation method for distal femoral epiphyseal block provided in the foregoing embodiments, wherein a computer program (i.e., a program product) is stored thereon, and the computer program, when run by a processor, executes the precise navigation method for distal femoral epiphyseal block provided in any of the foregoing embodiments.

[0104] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, optical disc read-only memory (CDROM), digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0105] The computer-readable storage medium provided in the above embodiments of this application and the precise navigation method for distal femoral epiphyseal block provided in the embodiments of this application are based on the same inventive concept and have the same beneficial effects as the methods used, run or implemented by the application stored therein.

[0106] It should be noted that numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of this application may be practiced without these specific details. In some instances, well-known structures and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0107] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0108] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A precise navigation method for distal femoral epiphyseal block, characterized in that, include: Obtain diagnostic results for femoral varus / valgus and intraoperative three-dimensional images of the knee joint; Based on the diagnostic results and intraoperative 3D images, a 3D model of the distal femur is generated, along with planning information for epiphyseal block. The device tracks and displays the position of the pin placement tool, guiding device, and distal femur in real time to guide the pin placement process in epiphyseal block.

2. The precise navigation method for distal femoral epiphyseal block according to claim 1, characterized in that, The planning information for epiphyseal block includes the placement information of the figure-eight plate and the placement information of at least two blocking screws.

3. The precise navigation method for distal femoral epiphyseal block according to claim 1, characterized in that, The pin placement information of the locking screw includes at least two of the following: pin placement position information, pin placement direction information, and pin placement depth information.

4. The precise navigation method for distal femoral epiphyseal block according to claim 1, characterized in that, The locking screw is placed in a direction parallel to the epiphyseal line of the distal femur.

5. The precise navigation method for distal femoral epiphyseal block according to any one of claims 1-4, characterized in that, Based on the diagnostic results and intraoperative 3D images, a 3D model of the distal femur is generated, along with epiphyseal arrest planning information, including: The intraoperative three-dimensional images of the knee joint are segmented and reconstructed into a three-dimensional skeletal model of the knee joint; the three-dimensional skeletal model of the knee joint includes a three-dimensional skeletal model of the distal femur. Based on the diagnostic results and a three-dimensional model of the knee joint skeleton, planning information for epiphyseal blockade is generated.

6. The precise navigation method for distal femoral epiphyseal block according to any one of claims 1-4, characterized in that, The intraoperative three-dimensional images are CT medical images or 3D fluoroscopic medical images.

7. The precise navigation method for distal femoral epiphyseal block according to any one of claims 1-4, characterized in that, The real-time tracking and display of the position of the pin placement tool, guiding device, and distal femur to guide the pin placement action in epiphyseal block includes: Acquire and display the current pose of the guide device installed at the end of the robotic arm and the current pose of the distal femur. Plan the guide motion path from the current pose of the guide equipment to the ready position of the arresting screw; Control the robotic arm to move along the guide path to the nail placement preparation position; The relative position of the guide device to the distal femur is locked, and the current pose of the screw placement tool is displayed so that the surgeon can perform the screw placement action.

8. A precision navigation system for distal femoral epiphyseal block, characterized in that, include: The image acquisition unit is used to acquire the diagnostic results of femoral varus and valgus and intraoperative three-dimensional images of the knee joint. Intraoperative planning unit, which is used to generate a three-dimensional model of the distal femur based on diagnostic results and intraoperative three-dimensional images, and planning information for epiphyseal blockade; The intraoperative screw placement unit is used to track and display the position of the screw placement tool, guiding device, and distal femur in real time to guide the screw placement action in epiphyseal block.

9. An electronic device, characterized in that, include: Memory and processor; The memory is used to store programs; The processor, coupled to the memory, is used to execute the program for: Obtain diagnostic results for femoral varus / valgus and intraoperative three-dimensional images of the knee joint; Based on the diagnostic results and intraoperative 3D images, a 3D model of the distal femur is generated, along with planning information for epiphyseal block. The device tracks and displays the position of the pin placement tool, guiding device, and distal femur in real time to guide the pin placement process in epiphyseal block.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the precise navigation method for distal femoral epiphyseal block as described in any one of claims 1-7.

Images