Spinal operation navigator and design method and device thereof

Abstract

The invention provides a spinal operation navigator and a design method and device thereof. The spinal operation navigator is characterized in that a guide plate is suitable for fitting with a corresponding vertebral body; and the identification plate is fixedly connected with the guide plate and is suitable for identifying the pose of the guide plate. According to the spinal operation navigator, by arranging the guide plate and the identification plate of the spinal operation navigator, the guide plate is attached to the position of the corresponding vertebral body, positioning of the guide plate and the vertebral body is achieved, the pose of the guide plate is identified externally through the identification plate, and therefore external equipment can determine positioning of the guide plate and the vertebral body; therefore, on one hand, positioning and guiding of screw placement of the vertebral body are achieved, and on the other hand, positioning and navigation of a surgical robot and the like are synchronously achieved.

Description

Technical Field

[0001] This application relates to the field of medical image recognition technology, and more specifically, to a spinal surgery navigator and its design method and apparatus. Background Technology

[0002] Spinal surgery often requires the use of pins to position vertebrae, but there is currently a lack of spinal surgical navigators that can perform this pinning procedure. Summary of the Invention

[0003] The problem addressed by this application is the current lack of spinal surgery navigation devices capable of positioning pins.

[0004] To address the aforementioned problems, the first aspect of this application provides a spinal surgery navigator, comprising:

[0005] Guide boards and signage boards

[0006] The guide plate is adapted to fit the corresponding vertebral body;

[0007] The marking plate is fixedly connected to the guide plate and is suitable for marking the position and posture of the guide plate.

[0008] A second aspect of this application provides a design method for a spinal surgery navigator, comprising:

[0009] Acquire spinal CT images and construct a 3D model of the spine;

[0010] Based on a three-dimensional model of the spine, the vertebrae to be treated and the surgical plan are determined.

[0011] Based on the vertebral body to be processed, determine the fitted portion of the vertebral body;

[0012] Based on the surgical planning and fitting components, the structural parameters of the spinal surgery navigator were determined.

[0013] A third aspect of this application provides a design device for a spinal surgery navigator, comprising:

[0014] The 3D construction module is used to acquire spinal CT images and build a 3D model of the spine.

[0015] The planning and determination module is used to determine the vertebrae to be treated and the surgical plan based on the three-dimensional model of the spine;

[0016] The vertebral body fitting module is used to determine the fitting portion of the vertebral body based on the vertebral body to be processed.

[0017] The navigator determination module is used to determine the structural parameters of the spinal surgery navigator based on the surgical planning and fitting components.

[0018] A fourth aspect of this application provides an electronic device comprising: a memory and a processor;

[0019] The memory is used to store programs;

[0020] The processor, coupled to the memory, is used to execute the program for:

[0021] Acquire spinal CT images and construct a 3D model of the spine;

[0022] Based on a three-dimensional model of the spine, the vertebrae to be treated and the surgical plan are determined.

[0023] Based on the vertebral body to be processed, determine the fitted portion of the vertebral body;

[0024] Based on the surgical planning and fitting components, the structural parameters of the spinal surgery navigator were determined.

[0025] The fifth 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 design method of the spinal surgery navigator described above.

[0026] In this application, by setting a guide plate and a marker plate for a spinal surgery navigator, the guide plate is aligned with the corresponding vertebral body position to achieve the positioning of the guide plate and the vertebral body. The marker plate marks the position and posture of the guide plate externally, so that external equipment can determine the positioning of the guide plate and the vertebral body (during the operation). In this way, on the one hand, the positioning and guidance of the vertebral body screw placement are realized, and on the other hand, the positioning and navigation of the surgical robot and other devices are realized simultaneously. Attached Figure Description

[0027] Figure 1 This is a structural diagram of a spinal surgery navigator according to an embodiment of this application;

[0028] Figure 2 This is a schematic diagram of the feature recognition area of ​​the vertebral body in a spinal surgery navigator according to an embodiment of this application;

[0029] Figure 3A This is a structural diagram of another embodiment of the spinal surgery navigator according to the embodiments of this application;

[0030] Figure 3B This is a perspective view of a guide plate according to another embodiment of the spinal surgery navigator based on the embodiments of this application;

[0031] Figure 3C This is a side view of a guide plate according to another embodiment of the spinal surgery navigator based on the present application;

[0032] Figure 4 This is a flowchart illustrating a design method for a spinal surgery navigator according to an embodiment of this application;

[0033] Figure 5A diagram illustrating the architecture of a segmentation and recognition network for a spinal surgery navigator design method according to embodiments of this application;

[0034] Figure 6 This is a structural block diagram of a spinal surgery navigator design device according to an embodiment of this application;

[0035] Figure 7 This is a structural block diagram of an electronic device according to an embodiment of this application.

[0036] Reference numerals: 1-guide plate; 2-identifier plate; 3-fitting part; 4-bending part; 5-fitting surface; 6-semi-circular hole; 7-protrusion; 8-horizontal groove. Detailed Implementation

[0037] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the following description, in conjunction with the accompanying drawings, will illustrate the specific features of this application.

[0038] The specific embodiments are described in detail below. Although exemplary embodiments of this application are shown in the accompanying 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.

[0039] 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.

[0040] This application provides a spinal surgery navigation device, the specific solution of which is... Figures 1-3C As shown. Combined with Figure 1 , Figure 2 The spinal surgery navigator includes: a guide plate 1 and a marker plate 2.

[0041] The guide plate is adapted to fit the corresponding vertebral body;

[0042] The marking plate is fixedly connected to the guide plate and is suitable for marking the position and posture of the guide plate.

[0043] In this application, by setting a guide plate and a marker plate for a spinal surgery navigator, the guide plate is aligned with the corresponding vertebral body position to achieve the positioning of the guide plate and the vertebral body. The marker plate marks the position and posture of the guide plate externally, so that external equipment can determine the positioning of the guide plate and the vertebral body (during the operation). In this way, on the one hand, the positioning and guidance of the vertebral body screw placement are realized, and on the other hand, the positioning and navigation of the surgical robot and other devices are realized simultaneously.

[0044] In one embodiment, the guide plate has a fitting surface 5 (the edge pointed to by the arrow in the figure) on one side relative to the marking plate, which is suitable for fitting with the vertebral plate.

[0045] In this application, the guide plate includes a fitting part 3 and a bending part 4. The bottom surface of the fitting part is a fitting surface, which fits the fitting area of ​​the vertebral body. The bending part is used to connect the two fitting parts and avoids the spinous process of the spine.

[0046] In this application, as shown in the figure, the fitting part is a curved element with a certain thickness. The side facing the spine is the fitting surface, which is completely fitted to the fitting area of ​​the spine; the other side can be a smooth regular curved surface or any other curved surface structure.

[0047] In this application, the curved part has an inverted U-shaped structure, and the two sides of the opening are respectively connected to a fitting part.

[0048] In one embodiment, the thickness of the bent portion is 3mm-12mm; the thickness of the fitting portion is 2mm-8mm.

[0049] In this way, by setting a preset thickness, the space occupied by the spinal surgery navigator can be reduced while avoiding excessive deformation during use.

[0050] In this application, the fitting surface corresponds to the feature recognition area of ​​the vertebral body. The feature recognition area / fitting part of the vertebral body is defined as follows: the lateral edge extends 5 mm outward from the junction of the vertebral body and the transverse process; the medial edge extends 10 mm inward from the junction of the lamina and the transverse process; the upper and lower edges are the upper and lower edges of the lamina. For thoracic vertebrae, since the lamina is imbricate, the upper edge is 3 mm above and below the upper edge of the lamina, and the lower edge is the lower edge of the lamina.

[0051] In this application, by setting the feature recognition area, soft tissue is easily peeled off on the one hand, and the fitting area (guide plate) is unique on the other hand.

[0052] In this application, the definition of the characteristic recognition area / fitting portion of the vertebral body gives the guide plate mechanical feedback characteristics: when pressure is applied to the guide plate, there is mechanical feedback when it encounters resistance, which can limit the movement of the guide plate and maintain its stability. Since the guide plate extends outward from the junction of the vertebral body and the transverse process, there is a bottoming effect at the extension part. When the downward force is applied during the installation of the guide plate, there is force feedback, and the guide plate will not shift.

[0053] In this application, the inner side of the guide plate extends towards the vertebral lamina, and during installation, an inward pressure presses the guide plate against the spinous process, thus preventing displacement of the guide plate.

[0054] In another implementation, such as Figures 3A-3C As shown:

[0055] The part where the guide plate and the label plate are combined has a semi-circular hole 6, which is suitable for accommodating fingers to press.

[0056] During the procedure, when the spinal surgery navigator is attached to the surface of the corresponding vertebra, the surgeon can insert their fingers into the semi-circular hole to press the guide plate to prevent the spinal surgery navigator from dislodging. In addition, the semi-circular hole at this position can prevent the surgeon from blocking the upper marker plate when pressing the guide plate, thus achieving the functions of pressing and not blocking simultaneously.

[0057] In this application, it should be noted that the semi-circular cavity 6 is through the guide plate and the marking plate (not shown in the figure) to accommodate the pressing tool.

[0058] In one embodiment, the surface of the semi-circular cavity is provided with at least a pair of symmetrical protrusions 7, adapted to abut against the finger when pressed.

[0059] In this application, by setting symmetrical protrusions, when the finger presses the surface of the semi-circular cavity, the protrusions abut against the finger. At this time, the finger can determine whether the pressing direction is in the center by sensing the symmetrical protrusions on both sides of the finger, thereby avoiding instability or misalignment of the spinal surgery navigator caused by pressing deviation (if the tactile sensation of both protrusions is the same, it means that the pressing is in the center; if the tactile sensation of one side is larger, it means that the pressing direction has deviated).

[0060] In one embodiment, the portion where the guide plate and the label plate are joined is provided with a transverse groove 8, and the bottom of the label plate is engaged in the transverse groove.

[0061] In this application, a horizontal groove is provided to partially separate the guide plate and the label plate, so as to avoid the presence of the label plate preventing the semi-circular hole from deforming and to prevent the protrusion from failing to change the tactile guidance of the pressing direction.

[0062] In one embodiment, a vertical groove (not shown in the figure) is provided at one end of the horizontal groove, and the vertical groove passes through the horizontal groove; a vertical protrusion (not shown in the figure) is provided at the bottom of the label plate, and the vertical protrusion is adapted to be engaged in the vertical groove.

[0063] In this application, by setting a vertical groove, the relative position of the signboard and the guide plate is fixed (it will not shift along the horizontal groove), thus avoiding displacement of the signboard due to deformation of the semi-circular hole.

[0064] This application provides a method for designing a spinal surgery navigator, the specific solution of which is as follows: Figures 4-5 As shown, this method can be executed by a spinal surgery navigator and its design device, which can be integrated into electronic devices such as computers, servers, computer clusters, and data centers. Combined with... Figure 4 The diagram shown is a flowchart of a spinal surgery navigator and its design method according to an embodiment of this application; wherein, the spinal surgery navigator design method includes:

[0065] S101, acquire spinal CT images and construct a 3D model of the spine;

[0066] In this application, the spinal CT image is a medical CT image (Computed Tomography, CT) containing the spine, and an image of the spinal portion can be obtained based on this medical CT image.

[0067] S102, based on a three-dimensional model of the spine, determines the vertebrae to be treated and the surgical plan;

[0068] In this application, a three-dimensional model of the spine is used to diagnose and identify the spine in order to determine the vertebrae to be treated.

[0069] In this application, the vertebrae to be processed are determined based on a three-dimensional model. This can be done by using a GPT model for diagnosis and identification, by training a conventional depth recognition model, or by other methods. The specific identification methods will not be elaborated in this application.

[0070] In this application, a surgical plan for the spine is determined based on the identified vertebrae to be treated. This surgical plan may include screw placement information, lateral connection information, etc.

[0071] S103, Based on the vertebral body to be processed, determine the fitting part of the vertebral body;

[0072] In this application, based on the vertebral body to be processed and the pin placement information, combined with the characteristics of the vertebral body itself, the fitting part of the vertebral body that can contact the guide plate is determined, which is the aforementioned feature recognition area.

[0073] S104, based on the surgical planning and fitting section, determines the structural parameters of the spinal surgery navigator.

[0074] The fitting region, also known as the feature recognition region, is used to determine the fitting region data of the spinal surgery navigator. Based on the screw placement information in the surgical plan, the parameters of some structures of the spinal surgery navigator (such as screw placement holes) are determined. Then, based on the setting limitations of the spinal surgery navigator and the setting limitations of the label plate, the structural parameters of the spinal surgery navigator are determined.

[0075] In this application, given the known fitting area data, the guide plate thickness is set; a reverse pin placement hole (the length of the pin placement hole is a preset length) is generated based on the pin placement direction and pin placement starting point in the pin placement information; and an identification plate is generated based on the setting of the identification plate; at this point, the spinal surgery navigator is generated.

[0076] In this application, a corresponding spinal surgery navigator is directly generated from spinal CT images, thereby maximizing the compatibility between the generated spinal surgery navigator and the patient, and greatly reducing preoperative and intraoperative preparation time.

[0077] In one implementation, constructing the three-dimensional model of the spine includes:

[0078] The spinal CT image is input into the segmentation and recognition network to obtain the segmentation and recognition results.

[0079] The segmentation results and recognition results are registered;

[0080] Based on the segmentation and recognition results after registration, a three-dimensional model of the spine is constructed.

[0081] In this application, the purpose of registration is to align the segmentation results and the recognition results to the same coordinate system, ensuring that the two are consistent in space.

[0082] It should be noted that the segmentation results may vary due to differences in CT scan angle or resolution, and the recognition results may be based on different reference frames, which need to be unified into the space of the segmentation results.

[0083] In this application, rigid registration is used to handle global alignment problems, and non-rigid registration is used to handle local deformation problems.

[0084] Preferably, key anatomical points (such as the center point of the vertebral body) are used as reference points for registration to improve accuracy.

[0085] In this application, the voxel mesh reconstruction involves converting the voxel data in the segmentation results into a three-dimensional mesh model; surface extraction uses algorithms (such as Marching Cubes) to extract the surface of the spine; and model annotation is performed by annotating the vertebral body number, lesion area, and other information in the three-dimensional model based on the recognition results.

[0086] Preferably, the extracted 3D surface is smoothed (e.g., Laplacian Smoothing) to reduce the impact of noise and ensure that the generated 3D model has the correct topological structure (e.g., closed surface).

[0087] In one implementation, such as Figure 5 As shown, the process of inputting spinal CT images into a segmentation and recognition network to obtain segmentation and recognition results includes:

[0088] The spinal CT images are encoded to obtain coded maps of multiple layers;

[0089] The lowest-level encoding graph is segmented and embedded to obtain the embedded features;

[0090] Multi-attention processing is applied to the embedded features to obtain attention features;

[0091] The attention features and the encoding graphs of multiple layers are segmented and decoded to obtain the segmentation result;

[0092] The attention features and the encoding graphs of multiple layers are recognized and decoded to obtain the recognition results.

[0093] In this application, the two decoders share a single encoder and combine transformer multi-attention processing and CNN encoding to leverage the semantic relationships between them, thereby simultaneously extracting high-quality features.

[0094] In this application, separate decoding paths are used for segmentation and recognition, and multi-attention processing is performed before decoding to capture different aspects of patch relationships in the sequence, helping the decoder learn different patterns and representations.

[0095] In this application, the lowest-level encoding map usually contains the highest resolution detail information, and the role of segmentation embedding is to map this detail information to a high-dimensional feature space for multi-attention processing.

[0096] In this application, the purpose of recognition and decoding is to extract global information from attention features and encoding maps for labeling the category or attribute of spinal structures.

[0097] In this application, the goal of the segmentation decoding stage is to progressively upsample the attention features and multi-layer coding maps to restore the original resolution and generate a segmentation mask. The segmentation result is a pixel-level classification output that identifies which anatomical structure each pixel belongs to.

[0098] In one implementation, the attention features are adaptively adjusted, and then the adaptively adjusted attention features are segmented, decoded, and recognized.

[0099] In this way, by adaptively adjusting, the randomness of the processing is improved, avoiding problems such as poor training results caused by deterministic results.

[0100] In one specific implementation, the adaptive adjustment of attention features includes:

[0101] Map attention features to layer data;

[0102] Divide the layer data into blocks to obtain independent blocks;

[0103] For each independent block, obtain the first and second neighboring blocks with different spacings;

[0104] A first feature block is generated based on the independent block and the first neighboring block;

[0105] A second feature block is generated based on the independent block and the second neighboring block.

[0106] The first and second feature blocks are compressed to obtain a compressed block.

[0107] Iterate through all the individual blocks and generate adjusted layer data based on the resulting compressed blocks;

[0108] Inversely map the layer data into attention features.

[0109] In this application, the layer data is divided into blocks, that is, the layer data is divided into corresponding image blocks by using a checkerboard pattern; wherein, the image block can be at the pixel level (that is, each pixel is an image block) or other levels, and the specific division depends on the actual processing situation.

[0110] In this application, a sliding window or a fixed step size is used to divide the image into blocks of the same size.

[0111] Preferably, in this application, each image block consists of 100-1000 pixels, thereby enabling more feature calculations between local regions while ensuring generation accuracy and reducing computational load.

[0112] In this application, an image block is selected as an independent block. The image blocks above, below, to the left, and to the right of this independent block are the first neighboring blocks; the image blocks one grid away from the top, bottom, left, and right of this independent block are the second neighboring blocks. The spacing between the first and second neighboring blocks and the independent block is different.

[0113] In this application, neighborhood information is extracted for each independent block to capture local structure.

[0114] In this application, generating the first feature block is to generate a local feature representation using an independent block and its first neighboring block. Specifically, this can be done by processing the independent block and the first neighboring block with convolutional layers and attention layers to obtain the first feature block.

[0115] In this application, the specific structure and parameters of the convolutional layer and attention layer can be obtained from the training data or determined according to the actual situation.

[0116] It should be noted that in this application, there are four first neighboring blocks and multiple first feature blocks.

[0117] In this application, the independent block and the first neighboring block are processed by convolutional layers and attention layers to obtain the first feature block. The specific process is as follows: the independent block and four neighboring blocks are concatenated together to form a multi-channel input, and the convolutional layer is used to extract features from the concatenated block; an important feature is enhanced by using a self-attention mechanism or a channel attention mechanism, the attention weight is calculated, and the output of the convolutional layer is weighted to enhance the important feature; the output of the attention layer is split into multiple feature blocks, and each feature block corresponds to the processing result of the independent block and at least one neighboring block.

[0118] In this application, a second feature block is generated to generate a broader local feature representation using the independent block and its second neighboring block. The specific generation process is the same as that of the first feature block, except that the parameters of the convolutional layer and the attention layer are different.

[0119] In this application, the generated feature blocks are compressed into a more compact representation to reduce computational cost while retaining key information. Feature compression is performed using pooling operations (such as max pooling or average pooling) or fully connected layers.

[0120] In this way, multiple first and second feature blocks are compressed into a single compressed block, which corresponds to the size and position of the individual blocks and is used to replace them. All image blocks are replaced by the compressed block, resulting in adjusted CT image data.

[0121] In this application, each image block of the layer data is traversed to obtain the corresponding compressed block.

[0122] In this application, for image blocks / independent blocks near the edge, their first and second neighboring blocks are incomplete. In this case, the incomplete blocks are completed by copying the first and second neighboring blocks in their relative positions. For example, if the first neighboring block above an independent block does not exist, the first neighboring block below it is copied and used as the block above it.

[0123] In this application, by completing the image blocks, the processing accuracy of adjacent image blocks is greatly improved.

[0124] In this application, the similarity relationship between local regions is captured by the adaptive adjustment module, thereby enhancing the feature representation. For images with rich texture or complex structure, high-quality image data can be generated, thus forming high-quality adjusted attention features.

[0125] In one implementation, S102, based on a three-dimensional model of the spine, determines the vertebra to be treated and the surgical plan, and may include:

[0126] Based on the three-dimensional model of the spine, the point cloud information of the vertebral body to be screwed is determined;

[0127] Obtain the statistical shape model and cortical bone screw planning information corresponding to the sequence number;

[0128] The statistical shape model is registered to the point cloud information, and the cortical bone screw planning of the vertebral body to be screwed is determined.

[0129] In one implementation, point cloud information of the vertebral body to be fitted with a screw is determined based on a three-dimensional model of the spine, including:

[0130] Based on the three-dimensional model of the spine, voxel data of the vertebral body to be screwed were obtained;

[0131] The voxel data of the vertebrae to be placed are converted into a triangular patch network;

[0132] The triangular patch network is converted into point cloud information.

[0133] In one implementation, obtaining the statistical shape model corresponding to the sequence number includes:

[0134] Acquire training CT data;

[0135] Based on the training CT data, voxel data of the corresponding sequenced vertebral bodies were segmented;

[0136] Convert voxel data into point cloud data of the cone body;

[0137] A statistical shape model of the vertebra is established based on the point cloud data of the vertebra.

[0138] In one specific embodiment, there are multiple statistical shape models; step S104, registering the statistical shape models to the point cloud information, includes:

[0139] Calculate the registration matrix between each statistical shape model and the point cloud information of the cone;

[0140] Obtain quantitative evaluation indicators;

[0141] Based on quantitative evaluation indicators, the closest statistical shape model is determined;

[0142] Based on the registration matrix, the closest statistical shape model is mapped to the point cloud information of the cone.

[0143] In this application, the quantitative evaluation index can be Hausdorff distance, surface coverage, root mean square error, etc. Through this index, the difference between different statistical shape models and the point cloud information of the cone is evaluated, so that the statistical shape model with the smallest difference is the closest.

[0144] In one specific embodiment, the step of determining the cortical bone screw planning for the vertebral body to be fitted includes:

[0145] Obtain the cortical bone screw planning information corresponding to the serial number;

[0146] Based on the registration matrix, the cortical bone screw planning information corresponding to the closest statistical shape model is mapped to the point cloud information of the vertebral body;

[0147] The mapped cortical bone screw planning information is converted into voxel data and fused with CT image data.

[0148] This application provides a spinal surgery navigator and its design device, which is used to execute the spinal surgery navigator and its design method described above. The spinal surgery navigator and its design device are described in detail below.

[0149] like Figure 6 As shown, the spinal surgery navigator and its design device include:

[0150] 3D construction module 101 is used to acquire spinal CT images and construct a 3D model of the spine.

[0151] The planning and determination module 102 is used to determine the vertebrae to be treated and the surgical plan based on the three-dimensional model of the spine;

[0152] Vertebral body fitting module 103 is used to determine the fitting part of the vertebral body based on the vertebral body to be processed;

[0153] The navigator determination module 104 is used to determine the structural parameters of the spinal surgery navigator based on the surgical planning and fitting section.

[0154] In one implementation, the three-dimensional building module 101 is further configured to:

[0155] The spinal CT image is input into the segmentation and recognition network to obtain the segmentation and recognition results; the segmentation and recognition results are registered; and a three-dimensional model of the spine is constructed based on the registered segmentation and recognition results.

[0156] In one implementation, the three-dimensional building module 101 is further configured to:

[0157] The spinal CT image is encoded to obtain a multi-layer encoded map; the lowest layer encoded map is segmented and embedded to obtain embedded features; the embedded features are processed by multi-attention to obtain attention features; the attention features and the multi-layer encoded map are segmented and decoded to obtain the segmentation result; the attention features and the multi-layer encoded map are recognized and decoded to obtain the recognition result.

[0158] The spinal surgery navigator and its design device provided in the above embodiments of this application are based on the same inventive concept as the spinal surgery navigator and its design method provided in the embodiments of this application, and have the same beneficial effects as the methods adopted, run or implemented by the application stored therein.

[0159] The above describes the internal functions and structure of a spinal surgery navigator and its design device, such as... Figure 7 As shown, in practice, the spinal surgery navigator and its design device can be implemented as an electronic device, including: a memory 301 and a processor 303.

[0160] Memory 301 can be configured to store a program.

[0161] Additionally, memory 301 can also be configured to store various other data to support operation on the electronic device. Examples of such data include instructions for any application or method used to operate on the electronic device, contact data, phonebook data, messages, pictures, videos, etc. 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.

[0162] Processor 303, coupled to memory 301, is used to execute programs in memory 301 for:

[0163] Acquire spinal CT images and construct a 3D model of the spine;

[0164] Based on a three-dimensional model of the spine, the vertebrae to be treated and the surgical plan are determined.

[0165] Based on the vertebral body to be processed, determine the fitted portion of the vertebral body;

[0166] Based on the surgical planning and fitting components, the structural parameters of the spinal surgery navigator were determined.

[0167] In one implementation, the processor 303 is further configured to:

[0168] The spinal CT image is input into the segmentation and recognition network to obtain the segmentation and recognition results; the segmentation and recognition results are registered; and a three-dimensional model of the spine is constructed based on the registered segmentation and recognition results.

[0169] In one implementation, the processor 303 is further configured to:

[0170] The spinal CT image is encoded to obtain a multi-layer encoded map; the lowest layer encoded map is segmented and embedded to obtain embedded features; the embedded features are processed by multi-attention to obtain attention features; the attention features and the multi-layer encoded map are segmented and decoded to obtain the segmentation result; the attention features and the multi-layer encoded map are recognized and decoded to obtain the recognition result.

[0171] In this application, Figure 7 The diagram only shows some components and does not mean that the electronic device includes only these components. Figure 7 The components shown.

[0172] The electronic device provided in this embodiment is based on the same inventive concept as the spinal surgery navigator and its design method provided in this application embodiment, and has the same beneficial effects as the methods adopted, run or implemented by the application stored therein.

[0173] 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.

[0174] 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 device that provides the functions specified in one or more boxes.

[0175] 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 instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0176] 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.

[0177] 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.

[0178] This application also provides a computer-readable storage medium corresponding to the spinal surgery navigator and its design method 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 spinal surgery navigator and its design method provided in any of the foregoing embodiments.

[0179] Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can store information using any method or technology. Information can be computer-readable instructions, data structures, program modules, 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, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0180] As defined in this article, computer-readable media do not include transient computer-readable media, such as modulated data signals and carrier waves.

[0181] The computer-readable storage medium provided in the above embodiments of this application and the spinal surgery navigator and its design method provided in the embodiments of this application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application stored therein.

[0182] 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.

[0183] 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.

[0184] 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 spinal surgery navigator, characterized in that, include: Guide boards and signage boards The guide plate is adapted to fit the corresponding vertebral body; The marking plate is fixedly connected to the guide plate and is suitable for marking the position and posture of the guide plate.

2. The spinal surgery navigation device according to claim 1, characterized in that, The guide plate has a fitting surface on one side relative to the marking plate, which is suitable for fitting with the vertebral lamina.

3. The spinal surgery navigation device according to claim 1, characterized in that, The part where the guide plate and the label plate are joined has a semi-circular hole, which is suitable for accommodating fingers to press.

4. The spinal surgery navigator according to claim 3, characterized in that, The surface of the semi-circular cavity is provided with at least one pair of symmetrical protrusions, which are adapted to contact the fingers when pressed.

5. The spinal surgery navigation device according to claim 1, characterized in that, The part where the guide plate and the sign plate are joined is provided with a horizontal groove, and the bottom of the sign plate is engaged in the horizontal groove.

6. The spinal surgery navigator according to claim 5, characterized in that, A vertical groove is provided at one end of the horizontal groove, and the vertical groove passes through the horizontal groove; a vertical protrusion is provided at the bottom of the sign plate, and the vertical protrusion is adapted to be engaged in the vertical groove.

7. A design method for a spinal surgery navigator according to any one of claims 1-6, characterized in that, include: Acquire spinal CT images and construct a 3D model of the spine; Based on a three-dimensional model of the spine, the vertebrae to be treated and the surgical plan are determined. Based on the vertebral body to be processed, determine the fitted portion of the vertebral body; Based on the surgical planning and fitting components, the structural parameters of the spinal surgery navigator were determined.

8. The design method of the spinal surgery navigator according to claim 7, characterized in that, The construction of the three-dimensional model of the spine includes: The spinal CT image is input into the segmentation and recognition network to obtain the segmentation and recognition results. The segmentation results and recognition results are registered; Based on the segmentation and recognition results after registration, a three-dimensional model of the spine is constructed.

9. The design method of the spinal surgery navigator according to claim 8, characterized in that, The process of inputting spinal CT images into a segmentation and recognition network to obtain segmentation and recognition results includes: The spinal CT images are encoded to obtain coded maps of multiple layers; The lowest-level encoding graph is segmented and embedded to obtain the embedded features; Multi-attention processing is applied to the embedded features to obtain attention features; The attention features and the encoding graphs of multiple layers are segmented and decoded to obtain the segmentation result; The attention features and the encoding graphs of multiple layers are recognized and decoded to obtain the recognition results.

10. A design device for a spinal surgery navigator according to any one of claims 1-6, characterized in that, include: The 3D construction module is used to acquire spinal CT images and build a 3D model of the spine. The planning and determination module is used to determine the vertebrae to be treated and the surgical plan based on the three-dimensional model of the spine; The vertebral body fitting module is used to determine the fitting portion of the vertebral body based on the vertebral body to be processed. The navigator determination module is used to determine the structural parameters of the spinal surgery navigator based on the surgical planning and fitting components.

Images