A system and method for analyzing the correlation between bone tissue and soft tissue movement

Abstract

This application relates to a system and method for analyzing the motion correlation between bone and soft tissue, belonging to the field of CT image processing technology. The key technical points include: an image segmentation processing module for receiving analysis instructions, processing the initial CT scan image in the analysis instructions, and segmenting bone and soft tissue; a bone tissue marker association module for identifying and defining marker points on the bone tissue surface, and establishing a correlation between the marker points and soft tissue based on a preset bone tissue association model; and a motion detection output module for monitoring the movement of bone tissue marker points after surgery, determining the deformation of the corresponding soft tissue according to the bone tissue association model and a preset deformation prediction method, and outputting the deformation information. This application improves the efficiency and objectivity of CT scan image analysis.

Description

Technical Field

[0001] This application relates to the field of CT image processing technology, and in particular to a system and method for analyzing the motion correlation between bone tissue and soft tissue. Background Technology

[0002] CT scan is a medical imaging technique that uses X-ray beams to perform tomographic scanning of the human body and uses computer processing to generate detailed images of the body's internal structures. While CT scan images can be used to analyze changes in bone and soft tissues, these changes are typically determined manually using calipers or by visual inspection through comparison of two-dimensional images. This method is inefficient and lacks subjectivity, and therefore requires improvement. Summary of the Invention

[0003] To improve the efficiency and objectivity of CT scan image analysis, this application provides a system and method for analyzing the correlation between bone tissue and soft tissue motion.

[0004] In a first aspect, this application provides a system for analyzing the correlation between bone tissue and soft tissue movement, including:

[0005] The image segmentation processing module is used to receive analysis instructions, process the initial CT scan image in the analysis instructions, and segment bone tissue and soft tissue.

[0006] The bone tissue marker association module is used to identify and define marker points on the surface of bone tissue, and establish an association between the marker points and soft tissue based on a preset bone tissue association model.

[0007] The motion detection output module is used to monitor the movement of bone tissue markers after surgery, determine the deformation of the corresponding soft tissue based on the bone tissue association model and the preset deformation prediction method, and output the deformation information.

[0008] By adopting the above technical solution, traditional subjective manual visual inspection is transformed into high-precision three-dimensional displacement data. By automatically identifying and defining marker points in CT scan images, associating soft tissues, and performing displacement tracking and other automated operations, the time consumption of the analysis is effectively analyzed, thereby improving the objectivity and efficiency of the analysis.

[0009] Optionally, the motion detection output module includes:

[0010] The motion detection unit is used to receive the subsequent CT scan images obtained from the monitoring, analyze the movement of all the marked points in the subsequent CT scan images, and determine and output the total soft tissue deformation field of the soft tissue using the bone tissue association model and the preset deformation prediction method.

[0011] The expression detection unit is used to determine whether the facial expression state in the subsequent CT scan image is a preset neutral expression state through a preset expression detection algorithm.

[0012] The motion output unit is used to correct facial expressions in subsequent CT scan images when the output result of the expression detection unit is a non-neutral expression state, and to determine and output the soft tissue displacement field caused by pure surgery based on the processing result; it is also used to output the total soft tissue deformation field when the output result of the expression detection unit is a non-central expression state.

[0013] By adopting the above technical solution, when the CT scan image is a facial scan image, this solution takes into account that changes in facial expression can easily affect the accuracy of analysis of soft tissue deformation. It proposes to detect the expression in subsequent CT scan images, and when it is determined that the expression is likely to affect the output results (i.e., when it is a non-neutral expression state), the total soft tissue deformation field is separated to separate and output the soft tissue displacement field caused by pure surgery.

[0014] Optionally, the motion output unit is further configured to calculate the facial expression-related deformation components in the subsequent CT scan image based on a preset muscle force distribution model when the output result of the expression detection unit is a non-central expression state; and to separate the expression deformation field and the soft tissue displacement field caused by pure surgery from the total soft tissue deformation field according to the facial expression-related deformation components.

[0015] By adopting the above technical solution, this solution specifically discloses a specific separation scheme for the total soft tissue deformation field during non-neutral facial expressions, which is used to improve the observability of separation of facial expression-related deformation components based on muscle changes.

[0016] Optionally, the bone tissue marker association module is further used to identify and define marker points on the bone tissue surface, and then match an expression sensitivity level for each marker point. The expression sensitivity level is used to characterize the degree of influence of the corresponding marker point's location on facial expression-related components caused by facial expressions.

[0017] The motion detection output module is also used to add an analysis accuracy label to each marker point after calculating the soft tissue displacement field caused by pure surgery. The analysis accuracy label is inversely proportional to the facial expression sensitivity level, so that the final output is a soft tissue displacement field with the analysis accuracy labels corresponding to all marker points.

[0018] By adopting the above technical solution, in order to further improve the accuracy and objectivity of the analysis, after identifying and defining the marker points, an expression sensitivity level is defined for each marker point. The expression sensitivity level is used to characterize the sensitivity of the corresponding marker point location to facial expressions (e.g., the nasolabial fold is highly sensitive, and the forehead is low sensitive). Then, in the final output of the soft tissue deformation field caused by pure surgery, an accuracy label is attached to each marker point location, and it is believed that the lower the expression sensitivity level of the marker point, the higher the accuracy level of the accuracy label attached to it.

[0019] Optionally, an anomaly verification module is also included, which is used to compare the subsequent CT scan image with a preset stiff expression template when the output result of the expression detection unit is a neutral expression, and when the similarity index is higher than a preset threshold, output an expression action interaction command so that the user can capture and feed back a facial image with an expression related to the benchmark expression according to the benchmark expression contained in the expression action interaction command; it is also used to analyze the facial image fed back by the user, compare the similarity between the actual expression in the facial image and the corresponding benchmark expression, and if the similarity is lower than a preset similarity, output a verification result of stiff expression.

[0020] By adopting the above technical solution, the analysis is further optimized in terms of objectivity, accuracy and comprehensiveness by combining static pre-screening (i.e., analyzing subsequent CT scan images) with dynamic verification (i.e., giving the user facial expression instructions and verifying the user's feedback facial images).

[0021] Optionally, it also includes an activity change analysis module, which integrates and processes the soft tissue displacement fields caused by pure surgery corresponding to all subsequent CT scan images of the same user received at different times within a historical period, and outputs a deformation evolution diagram showing the change of deformation over time, so that the corresponding user can know the deformation evolution diagram.

[0022] By adopting the above technical solution, a deformation evolution diagram showing the changes in deformation over time can be output, so as to more intuitively and vividly demonstrate the deformation changes.

[0023] Optionally, the activity change analysis module is further configured to determine the deformation change rate based on the deformation evolution diagram, determine the analysis frequency based on the deformation change rate, and feed back the analysis frequency to the corresponding user; the analysis frequency represents the time interval between the next reception time of subsequent CT scan images and the most recent reception time.

[0024] By adopting the above technical solution, the frequency of sending subsequent scan images can be calculated based on the deformation rate, so as to analyze deformation changes regularly and in a timely manner and achieve timely detection of abnormal situations.

[0025] Secondly, this application provides a method for analyzing the correlation between bone tissue and soft tissue movement, including:

[0026] Receive analysis instructions, process the initial CT scan image in the analysis instructions, and segment bone tissue and soft tissue;

[0027] Marker points are identified and defined on the surface of bone tissue, and based on a preset bone tissue association model, the marker points are associated with soft tissue.

[0028] The movement of bone tissue markers is monitored after surgery. Based on the bone tissue association model and the preset deformation prediction method, the deformation of the corresponding soft tissue is determined and the deformation is output.

[0029] Thirdly, this application provides a system device for analyzing the motion correlation between bone tissue and soft tissue, characterized in that it includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executed as described in the second aspect.

[0030] Fourthly, this application provides a computer-readable storage medium, characterized in that it stores a computer program capable of being loaded by a processor and executing the method described in the second aspect.

[0031] In summary, this application includes at least one of the following beneficial technical effects:

[0032] 1. This application transforms traditional subjective manual visual inspection into high-precision three-dimensional displacement data. By automatically identifying and defining marker points in CT scan images, associating soft tissues, and performing displacement tracking and other automated operations, it effectively analyzes the time consumption, improves the objectivity and efficiency of the analysis;

[0033] 2. Furthermore, when the CT scan image is a facial scan image, this scheme takes into account that changes in facial expressions can easily affect the accuracy of the analysis of soft tissue deformation. It proposes to detect facial expressions in subsequent CT scan images, and when it is determined that the facial expression is likely to affect the output results (i.e., when it is a non-neutral facial expression state), the total soft tissue deformation field is separated to separate and output the soft tissue displacement field caused by the pure surgery. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1This is a structural block diagram of a bone and soft tissue motion correlation analysis system disclosed in an embodiment of this application.

[0036] Figure labeling: 101, Image segmentation processing module; 102, Bone tissue marker association module; 103, Motion detection output module; 1031, Motion detection unit; 1032, Expression detection unit; 1033, Motion output unit; 104, Anomaly verification module; 105, Activity change analysis module. Detailed Implementation

[0037] The following is in conjunction with the appendix Figure 1 This application will be described in further detail.

[0038] This application discloses a system for analyzing the correlation between bone and soft tissue movement (hereinafter referred to as the analysis system). See also... Figure 1 The system includes an image segmentation processing module 101, a bone tissue marker association module 102, and a motion detection output module 103. The image segmentation processing module 101 receives analysis instructions, processes the initial CT scan image in the instructions, and segments bone tissue and soft tissue. The bone tissue marker association module 102 identifies and defines marker points on the bone tissue surface, and establishes associations between the marker points and soft tissue based on a preset bone tissue association model. The motion detection output module 103 monitors the movement of bone tissue marker points after surgery, determines the deformation of the corresponding soft tissue according to the bone tissue association model and a preset deformation prediction method, and outputs the deformation results.

[0039] Specifically, the motion detection output module 103 includes:

[0040] The motion detection unit 1031 is used to receive the subsequent CT scan images obtained from the monitoring, analyze the movement of all the marker points in the subsequent CT scan images, and determine and output the total soft tissue deformation field of the soft tissue using the bone tissue association model and the preset deformation prediction method.

[0041] The expression detection unit 1032 is used to determine whether the facial expression state in the subsequent CT scan image is a preset neutral expression state by using a preset expression detection algorithm.

[0042] The motion output unit 1033 is used to correct facial expressions in subsequent CT scan images when the output result of the expression detection unit is a non-neutral expression state, and to determine and output the soft tissue displacement field caused purely by surgery based on the processing result; it is also used to output the total soft tissue deformation field when the output result of the expression detection unit is a non-central expression state. The motion output unit 1033 is also used to calculate facial expression-related deformation components in subsequent CT scan images based on a preset muscle force distribution model when the output result of the expression detection unit is a non-central expression state; and to separate the facial expression-related deformation field and the soft tissue displacement field caused purely by surgery from the total soft tissue deformation field based on the facial expression-related deformation components.

[0043] In practice, users can access the analysis system via a webpage and upload initial CT scan images to trigger analysis commands. The analysis system is used to segment bone and soft tissue in CT scan images based on deep learning. For example, it employs a U-Net architecture (i.e., an encoder-decoder architecture combined with skip connections to preserve spatial information). The U-Net architecture is pre-trained using labeled CT datasets as training data, enabling it to output the locations of soft and bone tissue based on the input CT scan images.

[0044] Next, the image segmentation processing module 101 is used to identify and define marker points in the initial CT scan image based on the segmented soft tissue and bone tissue. For example, it uses 3D Harris corner detection or SIFT / SURF feature point detection algorithms to identify anatomical landmarks on the surface of bone tissue. It combines curvature analysis (such as Gaussian curvature or mean curvature) to select points with obvious set features, performs clustering and non-maximum suppression on the detection points to ensure that the marker points are evenly distributed, and finally realizes the identification and determination of the marker points.

[0045] The bone tissue association model is a hybrid model combining a biomechanical model and a statistical shape model. The bone tissue marker association module 102 is used to pre-establish a finite element model (FEM), using marker points as nodes to define mechanical coupling parameters (such as elastic modulus and Poisson's ratio) between bone and soft tissue. The calculations are simplified using a mass and spring model to form the biomechanical model. For the statistical shape model: the bone tissue marker association module 102 pre-establishes a statistical shape model of bone and soft tissue using principal component analysis (PCV), and establishes a mapping relationship between marker point locations and soft tissue deformation using PLSR (partial least squares regression) to form the statistical shape model.

[0046] The motion detection unit 1031 is used to receive subsequent CT scan images uploaded by the user, and register the preoperative and subsequent CT scan images using the Demons algorithm or B-spline free deformation (FFD). It establishes local feature descriptions for each marker point, and then uses KD-tree for nearest neighbor matching. Combined with RANSAC to remove the match, it realizes a one-to-one correspondence between the marker points before and after the operation. Then, it uses the deformation field calculation engine (including RBF difference and FEM solver) to calculate the displacement of the soft tissue before and after the operation, that is, the total soft tissue deformation field.

[0047] For example, the calculation logic for soft tissue deformation is as follows:

[0048] A deformation vector field corresponding to the B-spline free deformation (FFD) control grid is established. The displacement calculation model for each marker point is: ∇u=∑(B_i (u,v,w)∙Φ_i); where B_i (u,v,w) is the three-variable B-spline basis function, and Φ_i is the displacement vector of the i-th control point. The FFD deformation field is applied as a global transformation to the preoperative marker point set, and the coordinate position after deformation is calculated as p_i^'=p_i+Δu(p_i ),Δu(p_i )=∑(B_j (u,v,w)∙Φ_j ), (where (u_i,v_i,w_i) represents the normalized coordinates of marker point p_i in the parameter space). Next, the feature point matching algorithm p_i^'↔q_j=argmin‖p_i^'-q_j‖_2 is used. KD-tree acceleration and robust RANSAC matching are employed to establish a preliminary correspondence. Then, a bidirectional consistency check is used to remove outlier matching pairs. The final output of the accurate registration result should include at least the following data formats: displacement field of deformation control points, coordinates and error table of matching point pairs, and heatmap of registration error distribution.

[0049] The expression detection unit 1032 incorporates an expression detection algorithm. Specifically, the expression detection algorithm can be based on motion analysis of optical scanning feature points using a Facial Action Coding System (FACS), or detection of surface electromyography signal amplitude (if the amplitude is less than a specified amplitude, it is determined to be a neutral expression), or a deep learning classifier (ResNet-3d) to identify the spacing between muscle attachment points in subsequent CT scan images (if the spacing is less than a preset spacing value, it is determined to be a neutral expression).

[0050] The motion output unit 1033 incorporates a muscle force distribution model, and the calculation logic of the muscle force distribution model is as follows:

[0051] A muscle vector field corresponding to FACS (Facial Action Coding System) is established, with the force contribution model for each muscle as: F = a * f * v; where a is the activation intensity, f is the relationship between muscle length and tension, and v is the direction vector. Muscle force is applied as a boundary condition to the soft tissue, and the displacement field caused by facial expression Δu_expression = Σ(a_m * φ_m(x,y,z)) is calculated (where φ_m(x,y,z) represents the displacement field generated by the unit activation of the m-th muscle, and a_m is the activation intensity of the m-th muscle). Then, using a pre-defined deformation decomposition algorithm (Δu_total = Δu_surgery + Δu_expression + ε; where Δu_surgery is the soft tissue displacement field caused by pure surgery, and ε is the noise / error term), the least squares method is used to solve the problem. Finally, Helmholtz decomposition is used to decompose the displacement field into facial expression-related deformation components and deformation components caused by pure surgery (i.e., the soft tissue displacement field caused by pure surgery). The final output of soft tissue displacement locations caused by pure surgery should include at least the following data formats: three-dimensional vector displacement field (OVTK format), key anatomical point displacement scale (CSV format), and deformation heat map (PNG format).

[0052] Optionally, the bone tissue marker association module 102 is further configured to identify and define marker points on the bone tissue surface, and then match an expression sensitivity level for each marker point. The expression sensitivity level is used to characterize the degree of influence of the corresponding marker point's location on facial expression-related components caused by facial expressions. The motion detection output module 103 is further configured to add an analysis accuracy label to each marker point after calculating the soft tissue displacement field caused by pure surgery. The analysis accuracy label is inversely proportional to the expression sensitivity level, so that the final output is a soft tissue displacement field with analysis accuracy labels corresponding to all marker points.

[0053] In implementation, the motion detection output module 103 pre-stores a correspondence table, which includes several expression sensitivity levels (which can be represented by sensitivity coefficients, with higher coefficients indicating higher sensitivity), the facial region corresponding to each expression sensitivity level, and the analysis accuracy label corresponding to each expression sensitivity level. For example, high sensitivity corresponds to muscle attachment areas such as the nasolabial folds and glabella; medium sensitivity corresponds to indirectly affected areas such as the cheekbone surface; and low sensitivity corresponds to static areas such as the forehead and cranial vault. Furthermore, when finally outputting the soft tissue displacement field, the analysis accuracy label corresponding to each labeled point is displayed.

[0054] Optionally, it also includes an anomaly verification module 104, which is used to compare the similarity of the subsequent CT scan image with the preset stiff expression template when the output result of the expression detection unit is a neutral expression, and when the similarity index is higher than a preset threshold, output an expression action interaction command so that the user can capture and feed back a facial image with an expression related to the benchmark expression according to the benchmark expression contained in the expression action interaction command; it is also used to analyze the facial image fed back by the user, compare the similarity between the actual expression in the facial image and the corresponding benchmark expression, and if the similarity is lower than the preset similarity, output the verification result of stiff expression.

[0055] In implementation, when the output of the expression detection unit 1032 is a neutral expression, the anomaly verification module 104 is activated and compares the similarity of the expression detected in the subsequent CT scan image with the preset rigid expression template. For example, when the expression detection algorithm is the deep learning classifier (ResNet-3d) mentioned above, which identifies the distance between muscle attachment points in the subsequent CT scan image (if the distance is less than the preset distance value, it is determined to be a neutral expression), the difference between the distance corresponding to the expression detected in the subsequent CT scan image and the preset rigid expression template is used as the similarity. When the similarity is higher than the preset threshold, the error is sent to the user interaction terminal. An expression action interaction command is sent to the user to make a baseline expression, and the corresponding image (i.e., facial image) is captured and uploaded. Then, the anomaly verification module 104 sends an expression detection request to the expression detection unit 1032 so that the expression detection unit 1032 can detect and output the actual expression of the facial image. Similarly, the similarity between the actual expression and the corresponding baseline expression is compared (i.e., the difference between the corresponding distances is calculated). If the similarity is lower than the preset similarity, the user's expression is considered to be stiff. The verification result is output for human reference. The verification result is combined with the final soft tissue displacement field for comprehensive and thorough analysis.

[0056] Optionally, it also includes an activity change analysis module 105, which integrates and processes the soft tissue displacement fields caused by pure surgery corresponding to all subsequent CT scan images of the same user received at different receiving times within a historical period, and outputs a deformation evolution diagram showing the changes in deformation over time, so that the corresponding user can know about it.

[0057] The activity change analysis module 105 is also used to determine the deformation change rate based on the deformation evolution diagram, and to determine the analysis frequency based on the deformation change rate, and to feed back the analysis frequency to the corresponding user; the analysis frequency represents the time interval between the next reception time of subsequent CT scan images and the most recent reception time.

[0058] In implementation, the receiving time refers to the moment when the motion detection unit 1031 receives the subsequent CT scan image. The deformation rate is equal to the displacement difference of the maximum displacement in the soft tissue displacement field corresponding to two adjacent receiving times, and the time difference between two adjacent receiving times. The activity change analysis module 105 pre-stores several deformation rate ranges and the analysis frequency range corresponding to each deformation rate range. Therefore, the activity change analysis module 105 is used to determine the analysis frequency based on the aforementioned stored content and send the analysis frequency to the corresponding user so that the user can determine the time for periodically sending subsequent CT scan images.

[0059] This application also discloses a method for analyzing the correlation between bone tissue and soft tissue movement, including:

[0060] Receive analysis instructions, process the initial CT scan image in the analysis instructions, and segment bone tissue and soft tissue;

[0061] Marker points are identified and defined on the surface of bone tissue, and based on a preset bone tissue association model, the marker points are associated with soft tissue.

[0062] The movement of bone tissue markers is monitored after surgery. Based on the bone tissue association model and the preset deformation prediction method, the deformation of the corresponding soft tissue is determined and the deformation is output.

[0063] This application also discloses a bone tissue and soft tissue motion correlation analysis device, which includes a memory and a processor. The memory stores a computer program that can be loaded by the processor and executed as described above for bone tissue and soft tissue motion correlation analysis.

[0064] This application also discloses a computer-readable storage medium that stores a computer program that can be loaded by a processor and executed as described above in the bone tissue and soft tissue motion correlation analysis method. The computer-readable storage medium includes, for example, various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0065] It should be noted that in this paper, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0066] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit the scope of protection of the application. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on these embodiments, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

Claims

1. A system for analyzing the correlation between bone tissue and soft tissue movement, characterized in that, include: The image segmentation processing module (101) is used to receive analysis instructions, process the initial CT scan image in the analysis instructions, and segment bone tissue and soft tissue. The bone tissue marker association module (102) is used to identify and define marker points on the surface of bone tissue, and establish an association relationship between the marker points and soft tissue based on a preset bone tissue association model. The motion detection output module (103) is used to monitor the movement of bone tissue markers after surgery, determine the deformation of the corresponding soft tissue according to the bone tissue association model and the preset deformation prediction method, and output the deformation. The motion detection output module (103) includes: The motion detection unit (1031) is used to receive the subsequent CT scan images obtained by monitoring, analyze the movement of all the marker points in the subsequent CT scan images, and determine and output the total soft tissue deformation field of the soft tissue using the bone tissue association model and the preset deformation prediction method. The expression detection unit (1032) is used to determine whether the facial expression state in the subsequent CT scan image is a preset neutral expression state by using a preset expression detection algorithm. The motion output unit (1033) is used to perform facial expression correction processing on the facial expression in the subsequent CT scan image when the output result of the expression detection unit (1032) is a non-neutral expression state, and determine and output the soft tissue displacement field caused by pure surgery based on the processing result; it is also used to output the total soft tissue deformation field when the output result of the expression detection unit (1032) is a non-central expression state. The motion output unit (1033) is also used to calculate the facial expression-related deformation components in the subsequent CT scan image based on a preset muscle force distribution model when the output result of the expression detection unit (1032) is a non-central expression state; and to separate the expression deformation field and the soft tissue displacement field caused by pure surgery from the total soft tissue deformation field according to the facial expression-related deformation components.

2. The bone and soft tissue motion correlation analysis system according to claim 1, characterized in that, The bone tissue marker association module (102) is also used to identify and define marker points on the bone tissue surface, and then match an expression sensitivity level for each marker point. The expression sensitivity level is used to characterize the degree of influence of the corresponding marker point's location on facial expression-related components. The motion detection output module (103) is also used to add an analysis accuracy label to each marker point after calculating the soft tissue displacement field caused by pure surgery, and the analysis accuracy label is inversely proportional to the facial expression sensitivity level, so that the final output is a soft tissue displacement field with the analysis accuracy labels corresponding to all marker points.

3. The bone and soft tissue motion correlation analysis system according to claim 1, characterized in that, It also includes an anomaly verification module (104), which is used to compare the subsequent CT scan image with a preset rigid expression template when the output result of the expression detection unit (1032) is a neutral expression, and output an expression action interaction command when the similarity index is higher than a preset threshold, so that the user can capture and feed back a facial image with an expression related to the benchmark expression according to the benchmark expression contained in the expression action interaction command. It is also used to analyze facial images provided by users, compare the actual expressions in the facial images with the corresponding baseline expressions, and output a verification result of stiff expression if the similarity is lower than the preset similarity.

4. The bone and soft tissue motion correlation analysis system according to claim 1, characterized in that, It also includes an activity change analysis module (105), which integrates and processes the soft tissue displacement field caused by pure surgery corresponding to all subsequent CT scan images of the same user received at different times during the historical period, and outputs a deformation evolution diagram showing the change of deformation over time. The deformation evolution diagram is output for the corresponding user to know.

5. The bone and soft tissue motion correlation analysis system according to claim 4, characterized in that, The activity change analysis module (105) is also used to determine the deformation change rate based on the deformation evolution diagram, determine the analysis frequency based on the deformation change rate, and feed back the analysis frequency to the corresponding user. The analysis frequency represents the time interval between the next reception time of a subsequent CT scan image and the most recent reception time.

6. A method for analyzing the correlation between bone tissue and soft tissue movement, applied to the bone tissue and soft tissue movement correlation analysis system described in claim 1, characterized in that, The method includes: Receive analysis instructions, process the initial CT scan image in the analysis instructions, and segment bone tissue and soft tissue; Marker points are identified and defined on the surface of bone tissue, and based on a preset bone tissue association model, the marker points are associated with soft tissue. The movement of bone tissue markers is monitored after surgery. Based on the bone tissue association model and the preset deformation prediction method, the deformation of the corresponding soft tissue is determined and the deformation is output.

7. A system device for analyzing the correlation between bone tissue and soft tissue movement, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executed as described in claim 6.

8. A computer-readable storage medium, characterized in that, The computer program is stored that can be loaded by a processor and executed as described in claim 6.

Images