A surgical navigation positioning method and device, computer equipment and storage medium

Abstract

This application relates to a surgical navigation and positioning method, device, computer equipment, and storage medium. The method includes: acquiring target spinal image data and constructing a basic image model; acquiring navigation marker signals, generating a navigation coordinate system, and combining it with the basic image model to obtain a navigation and positioning model; acquiring probe positioning signals, and combining them with the navigation and positioning model to perform motion estimation and obtain an initial surgical positioning plan; responding to changes in the target body position, obtaining a body position correction factor based on target body position monitoring data; and correcting the initial navigation operation plan based on the body position correction factor to obtain a corrected surgical positioning plan. This method can efficiently construct a high-precision image model and, based on probe positioning signals, correct the surgical positioning plan in real time according to changes in the target body position, thereby improving the accuracy of surgical navigation and positioning, and enhancing surgical precision and safety.

Description

Technical Field

[0001] This application relates to the field of human medical surgery, and in particular to a surgical navigation and positioning method, device, computer equipment, and storage medium for human medical surgery. Background Technology

[0002] In the existing technology, probe-based surgical navigation and positioning systems are widely used in complex surgeries such as spinal surgery. The probe is connected to an external tracking system to obtain its position and movement trajectory in three-dimensional space in real time, providing doctors with accurate positioning data, thereby improving the accuracy and safety of the surgery. Traditional systems usually help surgeons perform real-time navigation by registering image models with navigation coordinate systems and combining the positioning information of the probe.

[0003] However, existing technologies still have significant shortcomings. First, the accuracy of the imaging model directly affects the accuracy of the surgery. Current technologies often rely on a single scan image for constructing the imaging model, resulting in low accuracy and failing to fully consider the complexity of spinal anatomy, which directly affects the accuracy of probe positioning. Furthermore, existing technologies lack dynamic adaptability and do not take into account the deviation between the imaging model and the actual spinal position caused by factors such as changes in body position during surgery. Based on this, relying on probes to obtain a surgical positioning plan will lack accuracy and compromise the safety of imaging surgery. Summary of the Invention

[0004] Therefore, it is necessary to provide a surgical navigation and positioning method, device, computer equipment, and storage medium that can efficiently construct a high-precision image model and, based on probe positioning signals, correct the surgical positioning scheme in real time according to changes in the target body position, thereby improving the accuracy of surgical navigation and positioning and enhancing surgical precision and safety.

[0005] On the one hand, a surgical navigation and positioning method is provided, the method comprising:

[0006] Acquire target spinal imaging data and construct a basic imaging model;

[0007] Obtain navigation marker signals, generate a navigation coordinate system, and combine it with the basic image model to obtain a navigation and positioning model;

[0008] The probe positioning signal is acquired, and combined with the navigation positioning model, motion estimation is performed to obtain the initial surgical positioning plan;

[0009] In response to changes in the target body position, a body position correction factor is obtained based on the target body position monitoring data;

[0010] Based on the body position correction factor, the initial navigation operation plan is modified to obtain a surgical positioning correction plan.

[0011] In one embodiment, the acquisition of target spinal imaging data and the construction of a basic imaging model include:

[0012] Acquire basic imaging data of the target spine, wherein the basic imaging data of the target spine is obtained based on one or more of the following methods: scanning, scanning;

[0013] Image segmentation and key point extraction are performed on the target spine basic image data to obtain several spine key points;

[0014] Using the aforementioned key spinal points as reconstruction anchor points, local image reconstruction is performed to obtain several fragmented image models.

[0015] The basic image model is obtained by stitching together the fragmented image models.

[0016] In one embodiment, the target spinal baseline image data includes at least one of the following: bone structure image data and soft tissue image data. The image segmentation and key point extraction of the target spinal baseline image data yields several spinal key points, including:

[0017] Through the above Scanning to obtain image data of the bone structure;

[0018] Through the above Scanning to acquire the soft tissue image data;

[0019] The bone structure image data and the soft tissue image data are preprocessed to obtain integrated image data, wherein the data preprocessing includes at least one of the following: normalization, image denoising, and resampling;

[0020] pass The model segments the integrated image data to obtain several segmented image data, wherein the... The model includes the following joint loss function:

[0021]

[0022] in, This represents the total loss value, used to guide the... Model training, This represents the cross-entropy loss value. express Coefficient loss value, This indicates the importance of the cross-entropy loss value. Indicates the Importance of coefficient loss values;

[0023] Based on the aforementioned segmented image data, and in conjunction with a key point extraction method, several spinal key points are extracted. The key point extraction method includes at least one or more of the following: geometric center calculation, edge detection, and... network.

[0024] In one embodiment, the step of using the plurality of spinal key points as reconstruction anchor points to perform local image reconstruction, thereby obtaining a plurality of fragmented image models, includes:

[0025] Based on a precision-first reconstruction strategy, the aforementioned key spinal points are used as anchor points, and corresponding image window sizes are selected for image reconstruction to obtain the aforementioned fragmented image models. The image window sizes include: a first image window size and a second image window size.

[0026] The step of using the aforementioned key spinal points as anchor points and selecting corresponding image window sizes includes:

[0027] Based on the correlation between the aforementioned key spinal points and their corresponding surrounding areas, the types of the aforementioned key spinal points are determined, wherein the types of the aforementioned key spinal points include at least: edge-concerned type and edge-distancing type.

[0028] In response to the spinal key point being of peripheral concern type, a first image window size is selected for the local image reconstruction; in response to the spinal key point being of peripheral distance type, a second image window size is selected for the local image reconstruction, wherein the first image window size is larger than the second image window size.

[0029] The step of stitching together the fragmented image models and then correcting and enhancing them to obtain the basic image model includes:

[0030] Based on a smoothness-optimized reconstruction strategy, the fragmented image models are stitched together. The smoothness-priority reconstruction strategy includes: non-rigid registration and smoothing filtering techniques.

[0031] In one embodiment, the step of acquiring navigation marker signals, generating a navigation coordinate system, and combining the basic image model to obtain a navigation positioning model includes:

[0032] Based on the type of navigation marker, select the corresponding tracking system to acquire the navigation marker signal, wherein the navigation marker has been placed at a preset position in the target area;

[0033] Based on the navigation marker signals, a three-dimensional coordinate system based on the target area is established, which is the navigation coordinate system;

[0034] The basic image model is registered with the navigation coordinate system, and the coordinate system in the basic image model is transformed to the navigation coordinate system to obtain the navigation positioning model.

[0035] In one embodiment, the step of acquiring the probe positioning signal, combining it with the navigation positioning model, performing motion estimation, and obtaining an initial surgical positioning plan includes:

[0036] In response to the probe type being consistent with the navigation marker type, the probe positioning signal is obtained through the corresponding tracking system;

[0037] Based on the probe positioning signal, the probe spatial coordinates are obtained, and based on the navigation coordinate system, the probe spatial coordinates are mapped into the navigation positioning model;

[0038] Determine the initial surgical target location and map the initial surgical target location into the navigation and positioning model;

[0039] In response to the initial surgical target location being determined in the navigation and positioning model, motion estimation of the probe is performed based on the spatial coordinates of the probe in the navigation and positioning model to obtain the simulated path of the probe;

[0040] Surgical tool data is acquired and compared with probe data to obtain a tool correction factor, wherein the tool correction factor is calculated based on the following formula:

[0041]

[0042] in, This represents the tool's correction factor. This represents the spatial position vector of the surgical tool. This represents the spatial position vector of the probe. It is the length of the surgical instrument. It is the length of the probe. It is a unit vector representing the orientation of the surgical tool and the probe tip, indicating the orientation of the surgical tool and the probe in space, wherein, It can be calculated using the following formula:

[0043]

[0044] in, It is the spatial position vector of the end of the surgical tool. It is the spatial position vector of the bottom end of the surgical tool. This refers to the spatial orientation vector of the surgical tool. The magnitude of the spatial orientation vector of the surgical tool;

[0045] Based on the simulated path of the probe, and combined with the tool correction factor, an initial surgical simulation path is obtained;

[0046] Based on the initial surgical simulation path, the initial surgical working area and the initial surgical incision angle are determined;

[0047] The initial surgical simulation path, the initial surgical working area, and the initial surgical incision angle are integrated to obtain the initial surgical positioning scheme.

[0048] In one embodiment, the step of acquiring target body position monitoring data in real time to obtain a body position correction factor includes:

[0049] The target body position monitoring data is acquired in real time through a number of body position monitoring sensors. The number of body position monitoring sensors corresponds to the number of fragment image models. The correspondence includes that at least one body position monitoring sensor is provided on both sides and in the vertical direction of the actual target spinal region corresponding to a fragment image model.

[0050] Based on the aforementioned fragmented image models, the target body position monitoring data is divided to obtain several fragmented body position monitoring data.

[0051] The fragmented body position monitoring data are analyzed to obtain corresponding lateral body position offset data and longitudinal body position offset data, wherein the lateral body position offset data represents the displacement of the spine in the horizontal direction and the longitudinal body position offset data represents the displacement of the spine in the vertical direction.

[0052] Based on the aforementioned lateral and longitudinal body position offset data, body position offset calculations are performed to obtain several fragment body position correction factors. These fragment body position correction factors are calculated using the following formula:

[0053]

[0054] in, Indicates the first Individual fragment position correction factor. Indicates the first The lateral offset of the spinal region of the physical target corresponding to each fragmented image model. Indicates the first The longitudinal offset of the spinal region of the entity target corresponding to each fragmented image model. Indicates the first The weighting coefficients for the lateral offset of the spinal region of the entity target corresponding to each fragmented image model. Indicates the first Weighting coefficients for the longitudinal offset of the spinal region of the entity target corresponding to each fragmented image model;

[0055] Based on the importance of the spinal region of the physical target corresponding to each fragment image model, the several fragment position correction factors are weighted and integrated to obtain the position correction factor, which is obtained based on the following formula:

[0056]

[0057] in, This represents the body position correction factor. This indicates the number of fragmented image models. Indicates the first The weights of fragment position correction factors are given, wherein the weights of the fragment position correction factors are positively correlated with the importance of the spinal region of the entity target corresponding to the fragment image model.

[0058] The method of modifying the initial surgical positioning plan based on the body position correction factor to obtain a modified surgical positioning plan includes:

[0059] Based on the analysis of the initial surgical localization scheme, the several fragmented image models involved in the initial surgical localization scheme are determined and denoted as the initial constituent fragment model;

[0060] Based on the feedback from the aforementioned body position monitoring sensors, it is determined whether the body position of the spinal region of the physical target corresponding to the initial constituent fragment model has changed.

[0061] If the judgment result is yes, then the body position correction factor is obtained, the several fragment body position correction factors are obtained, and combined with the initial constituent fragment model, the initial surgical simulation path, the initial surgical working area and the initial surgical incision angle are adjusted to obtain the surgical positioning correction scheme.

[0062] On the other hand, a surgical navigation and positioning device is provided, the device comprising:

[0063] The basic image model construction module is used to acquire target spinal image data and construct a basic image model.

[0064] The navigation and positioning model generation module is used to acquire navigation marker signals, generate a navigation coordinate system, and combine it with the basic image model to obtain a navigation and positioning model.

[0065] The initial scheme generation module is used to acquire probe positioning signals, combine them with the navigation positioning model, perform motion estimation, and obtain an initial surgical positioning scheme.

[0066] The correction factor calculation module is used to obtain the postural correction factor based on the target postural monitoring data in response to changes in the target postural position.

[0067] The scheme correction module is used to correct the initial navigation operation scheme based on the body position correction factor to obtain a surgical positioning correction scheme.

[0068] In another aspect, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps:

[0069] Acquire target spinal imaging data and construct a basic imaging model;

[0070] Obtain navigation marker signals, generate a navigation coordinate system, and combine it with the basic image model to obtain a navigation and positioning model;

[0071] The probe positioning signal is acquired, and combined with the navigation positioning model, motion estimation is performed to obtain the initial surgical positioning plan;

[0072] In response to changes in the target body position, a body position correction factor is obtained based on the target body position monitoring data;

[0073] Based on the body position correction factor, the initial navigation operation plan is modified to obtain a surgical positioning correction plan.

[0074] In another aspect, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0075] Acquire target spinal imaging data and construct a basic imaging model;

[0076] Obtain navigation marker signals, generate a navigation coordinate system, and combine it with the basic image model to obtain a navigation and positioning model;

[0077] The probe positioning signal is acquired, and combined with the navigation positioning model, motion estimation is performed to obtain the initial surgical positioning plan;

[0078] In response to changes in the target body position, a body position correction factor is obtained based on the target body position monitoring data;

[0079] Based on the body position correction factor, the initial navigation operation plan is modified to obtain a surgical positioning correction plan.

[0080] The aforementioned surgical navigation and positioning method, device, computer equipment, and storage medium acquire target spinal imaging data, navigation marker signals, and probe positioning signals. By combining these with a basic image model to generate a navigation and positioning model and performing motion estimation, precise surgical positioning can be achieved. Furthermore, the basic image model is obtained by stitching together several fragmented image models, which, compared to traditional techniques, can construct a more accurate image model while maintaining both precision and efficiency. In addition, the navigation and positioning scheme is dynamically adjusted and corrected through correction factors. Especially during surgery, when the target body position changes, correction factors are generated in real-time based on body position monitoring data, enabling timely adjustments to the surgical positioning scheme to ensure consistently high precision. This effectively solves the positioning deviation problem caused by changes in body position in traditional navigation and positioning methods, making surgical navigation more flexible and precise, and significantly improving the success rate of surgery and patient safety. Attached Figure Description

[0081] Figure 1 This is a flowchart illustrating a surgical navigation and positioning method in one embodiment;

[0082] Figure 2 This is a structural block diagram of a surgical navigation and positioning device in one embodiment;

[0083] Figure 3 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0084] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0085] In one embodiment, such as Figure 1 As shown, a surgical navigation and positioning method is provided, including the following steps:

[0086] Step 101: Obtain target spinal imaging data and construct a basic imaging model.

[0087] Specifically, image segmentation and key point extraction are performed on the basic image data of the target spine to obtain several spinal key points; these key points are used as reconstruction anchor points to perform local image reconstruction to obtain several fragmented image models; and these fragmented image models are stitched together to obtain the basic image model.

[0088] Step 102: Obtain navigation marker signals, generate a navigation coordinate system, and combine it with the basic image model to obtain a navigation and positioning model.

[0089] Specifically, based on the type of navigation marker, a corresponding tracking system is selected to acquire the navigation marker signal, wherein the navigation marker has been placed at a preset position in the target area; based on the navigation marker signal, a three-dimensional coordinate system based on the target area is established, which is the navigation coordinate system; the basic image model is registered with the navigation coordinate system, and the coordinate system in the basic image model is transformed to the navigation coordinate system to obtain the navigation positioning model.

[0090] Step 103: Obtain the probe positioning signal, combine it with the navigation positioning model, perform motion estimation, and obtain the initial surgical positioning plan.

[0091] Specifically, in response to the probe type matching the navigation marker type, the probe positioning signal is acquired through the corresponding tracking system; based on the probe positioning signal, the probe spatial coordinates are obtained, and based on the navigation coordinate system, the probe spatial coordinates are mapped into the navigation positioning model; the initial surgical target position is determined, and the initial surgical target position is mapped into the navigation positioning model; in response to the initial surgical target position being determined in the navigation positioning model, the probe motion is estimated based on the probe's spatial coordinates in the navigation positioning model to obtain the probe's simulated path; surgical tool data is acquired and compared with the probe data to obtain the tool correction factor; based on the probe's simulated path and combined with the tool correction factor, the initial surgical positioning scheme is obtained.

[0092] Step 104: In response to changes in the target body position, a body position correction factor is obtained based on the target body position monitoring data.

[0093] Specifically, target position monitoring data is acquired in real time using several position monitoring sensors. These sensors correspond to several fragmented image models, with at least one position monitoring sensor positioned on each side and vertically of the target spine region corresponding to each fragmented image model. Based on these fragmented image models, the target position monitoring data is divided into several fragmented position monitoring data sets. These fragmented position monitoring data sets are analyzed to obtain corresponding lateral and longitudinal position offset data, where lateral offset data represents the horizontal displacement of the spine and longitudinal offset data represents the vertical displacement. Position offset calculations are performed based on these lateral and longitudinal offset data to obtain several fragmented position correction factors. Finally, based on the importance of the target spine region corresponding to each fragmented image model, these fragmented position correction factors are weighted and integrated to obtain the final position correction factor.

[0094] Step 105: Based on the body position correction factor, the initial navigation operation plan is modified to obtain the surgical positioning correction plan.

[0095] Specifically, based on the initial surgical positioning plan, several fragmented image models involved in the initial surgical positioning plan are identified and denoted as the initial constituent fragment model. Based on the feedback from several position monitoring sensors, it is determined whether the position of the target spinal region corresponding to the initial constituent fragment model has changed. In response to the determination result being yes, position correction factors are obtained, resulting in several fragment position correction factors. Combined with the initial constituent fragment model, the initial surgical positioning plan is adjusted to obtain the surgical positioning correction plan.

[0096] In the aforementioned surgical navigation and positioning method, by acquiring target spinal imaging data, navigation marker signals, and probe positioning signals, and combining them with a basic image model to generate a navigation and positioning model and perform motion estimation, precise surgical positioning can be achieved. Furthermore, the basic image model is obtained by stitching together several fragmented image models, which, compared to traditional techniques, can construct a more accurate image model while maintaining both accuracy and efficiency. In addition, correction factors are used to dynamically adjust and correct the navigation and positioning scheme. Especially during surgery, when the target body position changes, correction factors are generated in real time based on body position monitoring data, enabling timely adjustments to the surgical positioning scheme to ensure consistently high accuracy. This effectively solves the positioning deviation problem caused by changes in body position in traditional navigation and positioning methods, making surgical navigation more flexible and precise, and significantly improving the success rate of surgery and patient safety.

[0097] In one embodiment, target spinal imaging data is acquired, and a basic imaging model is constructed, including...

[0098] Acquire basic imaging data of the target spine, wherein the basic imaging data of the target spine is obtained based on one or more of the following methods: scanning, scanning;

[0099] Image segmentation and key point extraction were performed on the basic image data of the target spine to obtain several key points of the spine.

[0100] Several key points of the spine were used as reconstruction anchor points, and local image reconstruction was performed to obtain several fragmented image models.

[0101] Several fragmented image models are stitched together to obtain a basic image model.

[0102] Specifically, in this embodiment, a basic image model is constructed, including based on and The processing of scanned spinal image data can generate detailed and accurate three-dimensional spinal image models. By employing image segmentation and key point extraction techniques, higher precision spinal localization can be achieved, ensuring the accuracy and reliability of the basic image model.

[0103] In one embodiment, the target spine baseline imaging data includes at least one of the following: bone structure imaging data and soft tissue imaging data. Image segmentation and key point extraction are performed on the target spine baseline imaging data to obtain several spinal key points, including:

[0104] pass Scanning to obtain bone structure imaging data;

[0105] pass Scanning to acquire soft tissue imaging data;

[0106] Bone structure imaging data and soft tissue imaging data are preprocessed to obtain integrated imaging data. The data preprocessing includes at least one of the following: normalization, image denoising, and resampling.

[0107] pass The model segments the integrated image data to obtain several segmented image data, wherein the... The model includes the following joint loss function:

[0108]

[0109] in, This represents the total loss value, used to guide the... Model training, This represents the cross-entropy loss value. express Coefficient loss value, This indicates the importance of the cross-entropy loss value. Indicates the Importance of coefficient loss values;

[0110] Based on the aforementioned segmented image data, and in conjunction with a key point extraction method, several spinal key points are extracted. The key point extraction method includes at least one or more of the following: geometric center calculation, edge detection, and... network.

[0111] Specifically, in this embodiment, through The model processes image data and combines it with key point extraction methods to achieve accurate spinal image segmentation and key point extraction, ensuring accurate identification of the target area and providing more reliable basic image data for subsequent navigation and positioning.

[0112] In one embodiment, several key spinal points are used as reconstruction anchor points to perform local image reconstruction, resulting in several fragmented image models, including:

[0113] Based on a precision-first reconstruction strategy, several key points of the spine are used as anchor points, and corresponding image window sizes are selected for image reconstruction to obtain several fragmented image models. The image window sizes include: a first image window size and a second image window size.

[0114] Using several key spinal points as anchor points, corresponding image window sizes were selected, including:

[0115] Based on the correlation between several key spinal points and their corresponding surrounding areas, the types of several key spinal points are determined. Among them, the types of several key spinal points include at least: peripheral concern type and peripheral alienation type.

[0116] In response to the spinal key point being of peripheral concern type, a first image window size is selected for local image reconstruction; in response to the spinal key point being of peripheral distance type, a second image window size is selected for local image reconstruction, wherein the first image window size is larger than the second image window size.

[0117] Several fragmented image models are stitched together, and then corrected and enhanced to obtain a basic image model, including:

[0118] Based on a smoothness-optimized reconstruction strategy, several fragmented image models are stitched together. The smoothness-priority reconstruction strategy includes: non-rigid registration and smoothing filtering techniques.

[0119] Specifically, this embodiment effectively optimizes the accuracy of image reconstruction and ensures the accuracy of the image model by using a precision-first reconstruction strategy and selecting the image window size according to the type of spinal key points for local image reconstruction. In addition, the use of a smoothness optimization strategy for image stitching effectively reduces the errors and discontinuities that may occur during the reconstruction process, and can reduce the burden of model generation to a certain extent, thereby improving the efficiency of model construction.

[0120] In one embodiment, navigation marker signals are acquired, a navigation coordinate system is generated, and a navigation and positioning model is obtained by combining it with a basic image model, including:

[0121] Select the corresponding tracking system based on the type of navigation marker and obtain the navigation marker signal, wherein the navigation marker has been placed at a preset position in the target area;

[0122] Based on the navigation marker signals, a three-dimensional coordinate system based on the target area is established, which is the navigation coordinate system;

[0123] The basic image model is registered with the navigation coordinate system, and the coordinate system in the basic image model is transformed to the navigation coordinate system to obtain the navigation and positioning model.

[0124] Specifically, this embodiment establishes a navigation coordinate system by acquiring navigation marker signals and combining them with a basic image model, which can ensure high-precision registration between the image and the real world during surgical navigation, thereby improving navigation accuracy and positioning reliability.

[0125] In one embodiment, the probe positioning signal is acquired, and combined with the navigation positioning model, motion estimation is performed to obtain an initial surgical positioning plan, including:

[0126] If the probe type matches the navigation marker type, the probe positioning signal is obtained through the corresponding tracking system.

[0127] Based on the probe positioning signal, the probe spatial coordinates are obtained, and based on the navigation coordinate system, the probe spatial coordinates are mapped to the navigation and positioning model;

[0128] Determine the initial surgical target location and map it into the navigation and positioning model;

[0129] In response to the initial surgical target location being determined in the navigation and positioning model, the motion of the probe is estimated based on the spatial coordinates of the probe in the navigation and positioning model to obtain the simulated path of the probe.

[0130] Surgical tool data is acquired and compared with probe data to obtain a tool correction factor, wherein the tool correction factor is calculated based on the following formula:

[0131]

[0132] in, This represents the tool's correction factor. This represents the spatial position vector of the surgical tool. This represents the spatial position vector of the probe. It is the length of the surgical instrument. It is the length of the probe. It is a unit vector representing the orientation of the surgical tool and the probe tip, indicating the orientation of the surgical tool and the probe in space, wherein, It can be calculated using the following formula:

[0133]

[0134] in, It is the spatial position vector of the end of the surgical tool. It is the spatial position vector of the bottom end of the surgical tool. This refers to the spatial orientation vector of the surgical tool. The magnitude of the spatial orientation vector of the surgical tool;

[0135] Based on the probe-based simulation path, combined with the tool correction factor, the initial surgical simulation path is obtained;

[0136] Based on the initial surgical simulation path, determine the initial surgical working area and the initial surgical entry angle;

[0137] The initial surgical simulation path, initial surgical working area, and initial surgical incision angle are integrated to obtain the initial surgical positioning scheme.

[0138] Specifically, in this embodiment, by acquiring the probe positioning signal and combining it with the navigation positioning model for motion estimation, the surgical positioning path can be accurately calculated. Furthermore, by optimizing the probe positioning scheme based on the tool correction factor, the initial positioning scheme can be made more accurate, providing a reliable reference for actual surgical operations.

[0139] In one embodiment, target posture monitoring data is acquired in real time to obtain a posture correction factor, including:

[0140] The system acquires target position monitoring data in real time through several position monitoring sensors. The position monitoring sensors correspond to several fragmented image models. The correspondence includes that at least one position monitoring sensor is set on both sides and vertically of the spinal region of the actual target corresponding to a fragmented image model.

[0141] Based on several fragmented image models, the target body position monitoring data is divided to obtain several fragmented body position monitoring data.

[0142] Analysis of several fragmented body position monitoring data yielded several corresponding lateral body position offset data and several longitudinal body position offset data. The lateral body position offset data represents the displacement of the spine in the horizontal direction, and the longitudinal body position offset data represents the displacement of the spine in the vertical direction.

[0143] Based on the aforementioned lateral and longitudinal body position offset data, body position offset calculations are performed to obtain several fragment body position correction factors. These fragment body position correction factors are calculated using the following formula:

[0144]

[0145] in, Indicates the first Individual fragment position correction factor. Indicates the first The lateral offset of the spinal region of the physical target corresponding to each fragmented image model. Indicates the first The longitudinal offset of the spinal region of the entity target corresponding to each fragmented image model. Indicates the first The weighting coefficients for the lateral offset of the spinal region of the entity target corresponding to each fragmented image model. Indicates the first Weighting coefficients for the longitudinal offset of the spinal region of the entity target corresponding to each fragmented image model;

[0146] Based on the importance of the spinal region of the physical target corresponding to each fragment image model, the several fragment position correction factors are weighted and integrated to obtain the position correction factor, which is obtained based on the following formula:

[0147]

[0148] in, This represents the body position correction factor. This indicates the number of fragmented image models. Indicates the first The weights of fragment position correction factors are given, wherein the weights of the fragment position correction factors are positively correlated with the importance of the spinal region of the entity target corresponding to the fragment image model.

[0149] Based on the body position correction factor, the initial surgical positioning plan is modified to obtain a surgical positioning correction plan, including:

[0150] Based on the analysis of the initial surgical localization plan, several fragmented image models involved in the initial surgical localization plan were identified, and denoted as the initial constituent fragmented model.

[0151] Based on feedback from several body position monitoring sensors, it is determined whether the body position of the spinal region of the physical target corresponding to the initial fragment model has changed.

[0152] If the judgment result is yes, the body position correction factor is obtained, and several fragment body position correction factors are obtained. Combined with the initial constituent fragment model, the initial surgical simulation path, the initial surgical working area and the initial surgical entry angle are adjusted to obtain the surgical positioning correction scheme.

[0153] Specifically, by monitoring changes in the target spinal region in real time and obtaining correction factors, the initial positioning plan can be dynamically adjusted during the operation to ensure that the surgical plan can adapt to changes in the position of the spine during the operation, thereby improving the accuracy and flexibility of the operation.

[0154] It should be understood that, although Figure 1 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0155] In one embodiment, such as Figure 2 As shown, a surgical navigation and positioning device is provided, including: a basic image model construction module, a navigation and positioning model generation module, an initial plan generation module, a correction factor calculation module, and a plan correction module, wherein:

[0156] The basic image model construction module is used to acquire target spinal image data and construct a basic image model.

[0157] The navigation and positioning model generation module is used to acquire navigation marker signals, generate a navigation coordinate system, and combine it with the basic image model to obtain the navigation and positioning model.

[0158] The initial scheme generation module is used to acquire probe positioning signals, combine them with the navigation positioning model, perform motion estimation, and obtain an initial surgical positioning scheme.

[0159] The correction factor calculation module is used to obtain the postural correction factor based on the target postural monitoring data in response to changes in the target postural position.

[0160] The scheme correction module is used to correct the initial navigation operation scheme based on the body position correction factor to obtain the surgical positioning correction scheme.

[0161] This basic image model building module is also used to acquire basic image data of the target spine, wherein the basic image data of the target spine is obtained based on one or more of the following methods: scanning, Scanning; performing image segmentation and key point extraction on the basic image data of the target spine to obtain several spinal key points; using these key points as reconstruction anchor points, performing local image reconstruction to obtain several fragmented image models; stitching together these fragmented image models to obtain the basic image model.

[0162] This basic image model building module is also used to... Scanning to acquire bone structure imaging data; through Scanning is performed to acquire soft tissue imaging data; the bone structure imaging data and soft tissue imaging data are preprocessed to obtain integrated imaging data, wherein the data preprocessing includes at least one of the following: normalization, image denoising, and resampling; through The model segments the integrated image data to obtain several segmented image data. Based on these segmented image data, and combined with key point extraction methods, several spinal key points are extracted. The key point extraction methods include at least one or more of the following: geometric center calculation, edge detection, and... network.

[0163] The basic image model construction module is also used to perform image reconstruction based on a precision-first reconstruction strategy, using several key points of the spine as anchor points, selecting corresponding image window sizes, and obtaining several fragmented image models. The image window sizes include: a first image window size and a second image window size.

[0164] Using several spinal key points as anchor points, corresponding image window sizes are selected, including: determining the types of several spinal key points based on their correlation with the corresponding surrounding areas, wherein the types of several spinal key points include at least: edge-concerned and edge-distancing; responding to the spinal key point being edge-concerned, a first image window size is selected for local image reconstruction, and responding to the spinal key point being edge-distancing, a second image window size is selected for local image reconstruction, wherein the first image window size is larger than the second image window size; stitching together several fragmented image models and performing correction and enhancement to obtain a basic image model, including: stitching together several fragmented image models based on a smoothness-optimized reconstruction strategy, wherein the smoothness-priority reconstruction strategy includes: non-rigid registration and smoothing filtering techniques.

[0165] The navigation and positioning model generation module is also used to select the corresponding tracking system according to the type of navigation marker, obtain the navigation marker signal, wherein the navigation marker has been placed at a preset position in the target area; establish a three-dimensional coordinate system based on the target area according to the navigation marker signal, which is the navigation coordinate system; register the basic image model with the navigation coordinate system, and transform the coordinate system in the basic image model to the navigation coordinate system to obtain the navigation and positioning model.

[0166] The initial scheme generation module is also used to: If the probe type matches the navigation marker type, acquire the probe positioning signal through the corresponding tracking system; obtain the probe spatial coordinates based on the probe positioning signal, and map the probe spatial coordinates to the navigation positioning model based on the navigation coordinate system; determine the initial surgical target position and map it to the navigation positioning model; if the initial surgical target position is determined in the navigation positioning model, estimate the probe motion based on the probe's spatial coordinates in the navigation positioning model to obtain the probe's simulated path; acquire surgical tool data and compare it with the probe data to obtain a tool correction factor; obtain the initial surgical simulation path based on the probe's simulated path and the tool correction factor; determine the initial surgical working area and the initial surgical incision angle based on the initial surgical simulation path; and integrate the initial surgical simulation path, the initial surgical working area, and the initial surgical incision angle to obtain the initial surgical positioning scheme.

[0167] The correction factor calculation module is also used to acquire target position monitoring data in real time through several position monitoring sensors. These sensors correspond to several fragmented image models, with at least one position monitoring sensor installed on each side and vertically of the target spine region corresponding to each fragmented image model. Based on these fragmented image models, the target position monitoring data is divided into several fragmented position monitoring data. The fragmented position monitoring data is analyzed to obtain corresponding lateral and longitudinal position offset data, where lateral offset data represents the horizontal displacement of the spine and longitudinal offset data represents the vertical displacement. Position offset calculations are performed based on these lateral and longitudinal offset data to obtain several fragmented position correction factors. Finally, based on the importance of the target spine region corresponding to each fragmented image model, these fragmented position correction factors are weighted and integrated to obtain the final position correction factor.

[0168] The scheme correction module is also used to analyze the initial surgical positioning scheme, determine several fragmented image models involved in the initial surgical positioning scheme, and denoted as the initial constituent fragment model; based on the feedback of several position monitoring sensors, determine whether the position of the actual target spinal region corresponding to the initial constituent fragment model has changed; in response to the judgment result being yes, obtain the position correction factor, obtain several fragment position correction factors, and combine them with the initial constituent fragment model to adjust the initial surgical simulation path, the initial surgical working area, and the initial surgical incision angle to obtain the surgical positioning correction scheme.

[0169] Specific limitations regarding surgical navigation and positioning devices can be found in the limitations of surgical navigation and positioning methods described above, and will not be repeated here. Each module in the aforementioned surgical navigation and positioning device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0170] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 3 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores surgical navigation and positioning data. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements a surgical navigation and positioning method.

[0171] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0172] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps:

[0173] Acquire target spinal imaging data and construct a basic imaging model;

[0174] Acquire navigation marker signals, generate a navigation coordinate system, and combine it with a basic image model to obtain a navigation and positioning model;

[0175] The probe positioning signal is acquired and combined with the navigation positioning model to perform motion estimation and obtain the initial surgical positioning plan;

[0176] In response to changes in the target body position, a body position correction factor is obtained based on the target body position monitoring data;

[0177] Based on the body position correction factor, the initial navigation operation plan is modified to obtain the surgical positioning correction plan.

[0178] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0179] Acquire target spinal imaging data and construct a basic imaging model;

[0180] Acquire navigation marker signals, generate a navigation coordinate system, and combine it with a basic image model to obtain a navigation and positioning model;

[0181] The probe positioning signal is acquired and combined with the navigation positioning model to perform motion estimation and obtain the initial surgical positioning plan;

[0182] In response to changes in the target body position, a body position correction factor is obtained based on the target body position monitoring data;

[0183] Based on the body position correction factor, the initial navigation operation plan is modified to obtain the surgical positioning correction plan.

[0184] Those skilled in the art will understand that implementing all or part of the processes in the above embodiments can be accomplished by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory. Programmable Electrically programmable Electrically erasable programmable Or flash memory. Volatile memory may include random access memory. Alternatively, an external cache memory. This is for illustrative purposes only and not as a limitation. It can be obtained in various forms, such as static ,dynamic ,synchronous Double data rate Enhanced Synchronization Link Memory bus direct Direct Memory Bus Dynamics and memory bus dynamics wait.

[0185] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0186] The above embodiments merely illustrate several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A surgical navigation and positioning method, characterized in that, include: Acquire target spinal imaging data and construct a basic imaging model, including: Acquire basic imaging data of the target spine, wherein the basic imaging data of the target spine is obtained based on one or more of the following methods: scanning, scanning; The target spinal baseline imaging data shall include at least one of the following: bone structure imaging data or soft tissue imaging data; Image segmentation and key point extraction were performed on the basic image data of the target spine to obtain several spinal key points, including: Through the above Scanning to obtain image data of the bone structure; Through the above Scanning to acquire the soft tissue image data; The bone structure image data and the soft tissue image data are preprocessed to obtain integrated image data, wherein the data preprocessing includes at least one of the following: normalization, image denoising, and resampling; pass The model segments the integrated image data to obtain several segmented image data, wherein the... The model includes the following joint loss function: in, This represents the total loss value, used to guide the... Model training, This represents the cross-entropy loss value. express Coefficient loss value, This indicates the importance of the cross-entropy loss value. Indicates the Importance of coefficient loss values; Based on the aforementioned segmented image data, and in conjunction with a key point extraction method, several spinal key points are extracted. The key point extraction method includes at least one or more of the following: geometric center calculation, edge detection, and... network; Using the aforementioned key spinal points as reconstruction anchor points, local image reconstruction is performed to obtain several fragmented image models. The basic image model is obtained by stitching together the fragmented image models. Obtain navigation marker signals, generate a navigation coordinate system, and combine it with the basic image model to obtain a navigation and positioning model; The probe positioning signal is acquired, and combined with the navigation positioning model, motion estimation is performed to obtain the initial surgical positioning plan; In response to changes in the target body position, a body position correction factor is obtained based on the target body position monitoring data; Based on the aforementioned body position correction factor, the initial navigation operation plan is modified to obtain a surgical positioning correction plan.

2. The surgical navigation and positioning method according to claim 1, characterized in that, The process involves using the aforementioned key spinal points as reconstruction anchor points to perform local image reconstruction, resulting in several fragmented image models, including: Based on a precision-first reconstruction strategy, the aforementioned key spinal points are used as anchor points, and corresponding image window sizes are selected for image reconstruction to obtain the aforementioned fragmented image models. The image window sizes include: a first image window size and a second image window size. The step of using the aforementioned key spinal points as anchor points and selecting corresponding image window sizes includes: Based on the correlation between the aforementioned key spinal points and their corresponding surrounding areas, the types of the aforementioned key spinal points are determined, wherein the types of the aforementioned key spinal points include at least: edge-concerned type and edge-distancing type. In response to the spinal key point being of peripheral concern type, a first image window size is selected for the local image reconstruction; in response to the spinal key point being of peripheral distance type, a second image window size is selected for the local image reconstruction, wherein the first image window size is larger than the second image window size. The step of stitching together the fragmented image models and then correcting and enhancing them to obtain the basic image model includes: Based on a smoothness-optimized reconstruction strategy, the fragmented image models are stitched together. The smoothness-priority reconstruction strategy includes: non-rigid registration and smoothing filtering techniques.

3. The surgical navigation and positioning method according to claim 2, characterized in that, The process of acquiring navigation marker signals, generating a navigation coordinate system, and combining it with the basic image model to obtain a navigation and positioning model includes: Based on the type of navigation marker, select the corresponding tracking system to acquire the navigation marker signal, wherein the navigation marker has been placed at a preset position in the target area; Based on the navigation marker signals, a three-dimensional coordinate system based on the target area is established, which is the navigation coordinate system; The basic image model is registered with the navigation coordinate system, and the coordinate system in the basic image model is transformed to the navigation coordinate system to obtain the navigation positioning model.

4. The surgical navigation and positioning method according to claim 3, characterized in that, The process of acquiring the probe positioning signal, combining it with the navigation positioning model, performing motion estimation, and obtaining an initial surgical positioning plan includes: In response to the probe type being consistent with the navigation marker type, the probe positioning signal is obtained through the corresponding tracking system; Based on the probe positioning signal, the probe spatial coordinates are obtained, and based on the navigation coordinate system, the probe spatial coordinates are mapped into the navigation positioning model; Determine the initial surgical target location and map the initial surgical target location into the navigation and positioning model; In response to the initial surgical target location being determined in the navigation and positioning model, motion estimation of the probe is performed based on the spatial coordinates of the probe in the navigation and positioning model to obtain the simulated path of the probe; Surgical tool data is acquired and compared with probe data to obtain a tool correction factor, wherein the tool correction factor is calculated based on the following formula: in, This represents the tool's correction factor. This represents the spatial position vector of the surgical tool. This represents the spatial position vector of the probe. It is the length of the surgical instrument. It is the length of the probe. It is a unit vector representing the orientation of the surgical tool and the probe tip, indicating the orientation of the surgical tool and the probe in space, wherein, It can be calculated using the following formula: in, It is the spatial position vector of the end of the surgical tool. It is the spatial position vector of the bottom end of the surgical tool. This refers to the spatial orientation vector of the surgical tool. The magnitude of the spatial orientation vector of the surgical tool; Based on the simulated path of the probe, and combined with the tool correction factor, an initial surgical simulation path is obtained; Based on the initial surgical simulation path, the initial surgical working area and the initial surgical incision angle are determined; The initial surgical simulation path, the initial surgical working area, and the initial surgical incision angle are integrated to obtain the initial surgical positioning scheme.

5. The surgical navigation and positioning method according to claim 4, characterized in that, Real-time acquisition of target posture monitoring data yields posture correction factors, including: The target body position monitoring data is acquired in real time through a number of body position monitoring sensors. The number of body position monitoring sensors corresponds to the number of fragment image models. The correspondence includes that at least one body position monitoring sensor is provided on both sides and in the vertical direction of the actual target spinal region corresponding to a fragment image model. Based on the aforementioned fragmented image models, the target body position monitoring data is divided to obtain several fragmented body position monitoring data. The fragmented body position monitoring data are analyzed to obtain corresponding lateral body position offset data and longitudinal body position offset data, wherein the lateral body position offset data represents the displacement of the spine in the horizontal direction and the longitudinal body position offset data represents the displacement of the spine in the vertical direction. Based on the aforementioned lateral and longitudinal body position offset data, body position offset calculations are performed to obtain several fragment body position correction factors. These fragment body position correction factors are calculated using the following formula: in, Indicates the first Individual fragment position correction factor. Indicates the first The lateral offset of the spinal region of the physical target corresponding to each fragmented image model. Indicates the first The longitudinal offset of the spinal region of the entity target corresponding to each fragmented image model. Indicates the first The weighting coefficients for the lateral offset of the spinal region of the entity target corresponding to each fragmented image model. Indicates the first Weighting coefficients for the longitudinal offset of the spinal region of the entity target corresponding to each fragmented image model; Based on the importance of the spinal region of the physical target corresponding to each fragment image model, the several fragment position correction factors are weighted and integrated to obtain the position correction factor, which is obtained based on the following formula: in, This represents the body position correction factor. This indicates the number of fragmented image models. Indicates the first The weights of fragment position correction factors are given, wherein the weights of the fragment position correction factors are positively correlated with the importance of the spinal region of the entity target corresponding to the fragment image model. Based on the body position correction factor, the initial surgical positioning plan is modified to obtain a surgical positioning correction plan, including: Based on the analysis of the initial surgical localization scheme, the several fragmented image models involved in the initial surgical localization scheme are determined and denoted as the initial constituent fragment model; Based on the feedback from the aforementioned body position monitoring sensors, it is determined whether the body position of the spinal region of the physical target corresponding to the initial constituent fragment model has changed. If the judgment result is yes, then the body position correction factor is obtained, the several fragment body position correction factors are obtained, and combined with the initial constituent fragment model, the initial surgical simulation path, the initial surgical working area and the initial surgical incision angle are adjusted to obtain the surgical positioning correction scheme.

6. A surgical navigation and positioning device, characterized in that, The device includes: The basic image model construction module is used to acquire target spinal image data and construct a basic image model. The navigation and positioning model generation module is used to acquire navigation marker signals, generate a navigation coordinate system, and combine it with the basic image model to obtain a navigation and positioning model. The initial scheme generation module is used to acquire probe positioning signals, combine them with the navigation positioning model, perform motion estimation, and obtain an initial surgical positioning scheme. The correction factor calculation module is used to obtain the postural correction factor based on the target postural monitoring data in response to changes in the target postural position. The scheme correction module is used to correct the initial navigation operation scheme based on the body position correction factor to obtain a surgical positioning correction scheme.

7. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images