An orthopedic image data analysis platform and method

Abstract

The application discloses a kind of orthopedics image data analysis platform and method, it is related to orthopedics image technical field, including: data acquisition module, the relevant information of patient is acquired from multiple data sources, including: image data unit, through equipment acquisition orthopedics relevant image data and the 3D imaging data of corresponding part of patient;Data processing module, the multimodal data collected by data acquisition module is handled and fused, including: image data processing unit, image enhancement, denoising and registration are carried out to image data;Modeling unit, 3D imaging data is converted into corresponding three-dimensional anatomical model, and image data is docked with three-dimensional anatomical model, image data is mapped to three-dimensional anatomical model, obtains preoperative model;Navigation module in the application utilizes preoperative model and real-time image data to carry out angle matching and dynamic correction, help doctor in the process of surgery real-time monitoring the position and anatomical structure change of patient, can improve the precision of operation.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of orthopedic imaging technology, in particular to an orthopedic imaging data analysis platform and method. BACKGROUND

[0002] With the rapid development of modern medical imaging technology, the role of imaging data in the diagnosis, treatment and prognosis evaluation of orthopedic diseases is becoming increasingly important. Common orthopedic imaging types include X-ray films, CT scans, MRI and ultrasound images, etc. These imaging data provide valuable information for clinicians, helping doctors make more accurate diagnoses and treatment decisions in clinical practice. With the rapid development of computer vision and artificial intelligence technology, automated analysis methods based on image recognition and deep learning have gradually emerged and made certain progress in medical imaging analysis.

[0003] According to the search, the Chinese patent with publication number CN118490364A discloses a full-orthopedic platform surgical robot and its navigation method. The patent includes a core control system which is an embedded high-performance microprocessor used to coordinate the workflow between components and support multi-task concurrent processing; a modular system installed at the end of the surgical robot; a high-precision positioning system used to track the position of surgical instruments in space in real time; an intelligent image fusion system used to fuse preoperative images with real-time images of the operating site. Based on the fused image data, the surgical path is planned and confirmed.

[0004] In the prior art, the orthopedic imaging data analysis platform mainly focuses on the processing of static images and the preliminary diagnosis of lesions, lacks individualization and dynamic tracking capabilities, and the processing of imaging data is mainly concentrated in the preoperative diagnosis stage. However, in the process of patient treatment, the changes in the injured area cannot be reflected in real time through real-time image data updating and monitoring, and there is a lack of analysis capability combined with patient recovery data and big data resources. Therefore, the present application proposes an orthopedic imaging data analysis platform and method. SUMMARY

[0005] The present application aims to provide an orthopedic imaging data analysis platform and method to solve the problems mentioned in the background.

[0006] An orthopedic imaging data analysis platform comprises:

[0007] A data acquisition module acquires the original data of a patient using multiple data units, wherein the data acquisition module includes an image data unit, a clinical data unit and a sensor data unit;

[0008] A data processing module processes and fuses the original data collected by the data acquisition module using an image data processing unit, a modeling unit and a data monitoring unit to obtain a preoperative model.

[0009] The navigation module integrates the preoperative model as the basic navigation data of the operation, and the navigation module obtains the position information of the patient in real time during the operation and compares it with the preoperative model to perform dynamic angle matching and correction.

[0010] Preferably, in the data acquisition module:

[0011] The image data unit obtains orthopedic-related image data and 3D imaging data of the corresponding injured part of the patient through related equipment, and respectively collects and configures each image data and each 3D imaging data as an image data group and a 3D imaging data group;

[0012] The clinical data unit is used to record the patient's medical history, physical examination data, and laboratory examination data.

[0013] The sensor data unit obtains physiological data and self-reported data of the patient through wearable devices or sensors.

[0014] More preferably, the related equipment includes CT equipment, X-ray equipment, and MRI equipment.

[0015] The physiological data includes the patient's exercise amount, joint range of motion, gait, and range of motion; and the self-reported data includes pain score and symptom changes.

[0016] Preferably, in the data processing module, the image data processing unit uses medical image processing technology to perform image enhancement, denoising, and registration on the image data.

[0017] Specifically, the image data processing unit configures the image data obtained by the image data unit for the first time in a time sequence arrangement according to the time point of the date alternation as the reference image data, and the image data in the image data group other than the reference image data is configured as subsequent image data. After processing the reference image data using medical image processing technology, the image data processing unit extracts the key skeletal features therein and calculates the angle information of the reference image data according to the key skeletal features.

[0018] The image data processing unit calculates the angle deviation of the skeletal key point coordinates of the key skeletal features between the subsequent image data and the reference image data using the registration mechanism, and obtains the angle difference between the subsequent image data and the reference image data by measuring the rotation, translation, and other transformation parameters of the subsequent image data compared with the reference image data after registration.

[0019] Further, the image data processing unit is further configured to preset a matching angle threshold, and filter out subsequent image data with a large angle difference, wherein the image data processing unit performs angle matching on the subsequent image data and the reference image data, and when the angle difference is less than the preset matching angle threshold, the subsequent image data is considered as qualified image data, and the qualified subsequent image data is arranged and displayed along a time sequence.

[0020] Further, the image data processing unit is further configured to preset a matching angle threshold, and filter out subsequent image data with a large angle difference, wherein the image data processing unit performs angle matching on the subsequent image data and the reference image data, and when the angle difference is less than the preset matching angle threshold, the subsequent image data is considered as qualified image data, and the qualified subsequent image data is arranged and displayed along a time sequence.

[0021] The image data processing unit performs angle matching on the subsequent image data and the reference image data, and when the angle difference of the subsequent image data exceeds the matching angle threshold, if a group of image data has similarity with a certain image data in the corresponding time sequence and meets the requirement of the correlation angle threshold, the image data is allocated to the time point in the corresponding time sequence, and an expandable copy is established at the time point to accommodate image data corresponding to the correlation angle threshold.

[0022] The similarity is obtained by the following formula:

[0023]

[0024] In the formula, I and J represent two image data to be compared; μ I ,μ J are the average brightness of the images I and J, respectively, and σ J are the brightness variances of the images I and J, respectively, representing the contrast information of the images, and σ IJ is the covariance of the images I and J, used to measure the structural similarity between the two images, and C1 and C2 are constants, used to stabilize the calculation and avoid zero denominator; θ is the angle difference between the current image data and the reference image data; θ m is the matching angle threshold, and θ a is the correlation angle threshold, and α is a constant used to control the influence strength of the angle deviation and the similarity;

[0025] When θ≤θ m , the structural similarity of the two image data is only determined by the content, and is irrelevant to the angle;

[0026] When θ m <θ<θ aWhen the angle difference is greater than the angle threshold, the structural similarity gradually decreases due to the angle difference, and the similarity value of the image gradually decreases, reflecting the influence of the angle deviation.

[0027] When the angle difference is greater than the angle threshold, the structural similarity gradually decreases due to the angle difference, and the similarity value of the image gradually decreases, reflecting the influence of the angle deviation. a When the angle difference is greater than the angle threshold, the structural similarity gradually decreases due to the angle difference, and the similarity value of the image gradually decreases, reflecting the influence of the angle deviation.

[0028] Preferably, in the data processing module, the modeling unit converts the 3D imaging data group collected by the data acquisition module into a three-dimensional anatomical model corresponding to the patient's torso, and the modeling unit docks the image data corresponding to the last time point in the time sequence in the image data group processed by the image data processing unit with the three-dimensional anatomical model, maps the image data to the three-dimensional anatomical model, and obtains a preoperative model.

[0029] Preferably, in the data processing module, the data monitoring unit arranges each image data in the time sequence according to time, detects the injured part of the patient, and matches with big data to obtain recovery data.

[0030] Further, the working method of the data monitoring unit comprises the following steps:

[0031] S1, arranging the image data processed by the image data processing unit according to time, extracting the regional features of the injured part, and calculating the change amplitude of the image data at each time point;

[0032] S2, drawing a dynamic recovery curve according to the feature extraction data of each time point to display the recovery progress;

[0033] S3, based on the regional features of the injured part of the patient, extracting identification information, and using a similarity matching algorithm to match with similar cases in the orthopedic big database;

[0034] S4, according to the matched similar cases, extracting the corresponding recovery data benchmark from the orthopedic big database;

[0035] S5, comparing the actual recovery curve of the patient with the recovery benchmark of the big data, calculating the recovery deviation and obtaining the recovery data;

[0036] S6, generating a personalized recovery plan based on the comparison result.

[0037] The application also provides an orthopedic image data analysis method using the orthopedic image data analysis platform of any one of claims 1-9, which comprises the following steps:

[0038] Step one: obtaining the original data of the patient through the multiple data units of the data acquisition module, including image data and 3D imaging data;

[0039] Step two: the data processing module converts the collected 3D imaging data into a three-dimensional anatomical model corresponding to the patient's torso, and sorts the image data in time sequence;

[0040] Step three: the data processing module extracts the regional features of the image data in time sequence and generates a dynamic recovery curve;

[0041] And the data processing module matches the dynamic recovery curve with the orthopedic database to assist the doctor in judging whether the patient's recovery is as expected;

[0042] Step four: during the operation, the data processing module docks the image data at the last time point in the time sequence with the three-dimensional anatomical model, maps the image data to the three-dimensional anatomical model, and obtains the preoperative model;

[0043] At the same time, the navigation module integrates the preoperative model, and in the operation, real-time position information of the patient is obtained and compared with the preoperative model for dynamic angle matching and correction.

[0044] The beneficial effects of the present application are:

[0045] The navigation module in the present application uses the preoperative model and real-time image data for angle matching and dynamic correction, helping the doctor to monitor the patient's injury position and anatomical structure changes in real time during the operation, which can improve the accuracy of the operation and reduce the risk of misoperation; and through the fusion of image data, clinical data and sensor data of the data acquisition module, the scheme can integrate the patient's medical history, physical examination, exercise state and other information, provide comprehensive recovery state evaluation, and better reflect the patient's health status.

[0046] The time sequence dynamic recovery curve in the present application shows the recovery progress of the injured part, quantifies bone density, fracture healing, soft tissue repair, clinical health score and exercise score and other recovery indicators, and the dynamic recovery curve can not only intuitively show the recovery progress, but also can be compared with the big data benchmark to help the doctor understand the patient's recovery situation in time. BRIEF DESCRIPTION OF DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or prior art description. Obviously, the drawings in the following description only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor on the basis of these drawings.

[0048] Figure 1 It is a flowchart of an orthopedic image data analysis method in the present application. DETAILED DESCRIPTION

[0049] The technical solutions in the embodiments of the present application will be apparently and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0050] Please refer to Figure 1 As shown in the figure, the present application provides an orthopedic image data analysis platform, which comprises a data acquisition module, a data processing module and a navigation module.

[0051] The data acquisition module acquires the original data of the patient by using a plurality of data units, including an image data unit, a clinical data unit and a sensor data unit.

[0052] The image data unit acquires the orthopedic related image data and the 3D imaging data of the corresponding injured part of the patient by using relevant equipment in the form of a time sequence arranged according to the date, for example, "year-month-day". For example, the present application acquires the orthopedic related image data and the 3D imaging data of the corresponding injured part of the patient once a day in the XX time period according to the date by using relevant equipment; and the image data and the 3D imaging data are respectively collected and configured as an image data group and a 3D imaging data group. In this embodiment, the relevant equipment includes a CT device, an X-ray device and an MRI device.

[0053] The clinical data unit is used for recording the medical history, physical examination data and laboratory examination data of the patient.

[0054] The sensor data unit acquires the physiological data and self-reporting data of the patient by using the self-reporting and wearable devices or sensors of the patient, wherein the physiological data includes the amount of exercise, joint range of motion, gait and range of motion of the patient; the self-reporting data includes pain score and symptom change.

[0055] It should be noted that the self-reporting is a WOMAC scale for joint pain, the pain score is a subjective quantitative index, which is obtained by the self-reporting of the patient; and the symptom change can be obtained by the self-reporting and wearable devices or sensors. The wearable devices or sensors are accelerometers and gyroscopes.

[0056] In the technical solution, the data processing module processes and fuses the original data collected by the data acquisition module by using an image data processing unit and a modeling unit.

[0057] The image data processing unit uses medical image processing technology to perform image enhancement, denoising, and registration on each image data in the image data set. Specifically, the image data processing unit configures the image data obtained for the first time according to the date replacement time sequence arrangement as the reference image data. After processing the reference image data using the image enhancement and denoising technology disclosed in the patent with publication number CN118490364A, the key skeletal features such as joints and bone edges are extracted, and the angle information of the reference image data is calculated based on the key skeletal features.

[0058] It should be particularly noted that the calculation method of the angle information of the reference image data includes:

[0059] Step 1: Identify the skeletal profile of the key skeletal feature through Canny edge detection.

[0060] Step 2: Use key point detection algorithms such as Harris corner points and SIFT feature points to determine the skeletal key point coordinates of the key skeletal feature.

[0061] Step 3: Calculate the angle information of the reference image data through the vector angle formula based on the obtained skeletal key point coordinates.

[0062] Through the above calculation of the angle information of the reference image data, the reference image data can serve as an angle reference for other image data in the time sequence in terms of angle information.

[0063] Specifically, when processing the subsequent image data in the image data set using the image data processing unit, the registration mechanism is used to calculate the angle deviation of the skeletal key point coordinates of the key skeletal feature between the subsequent image data and the reference image data, and the rotation, translation, and other transformation parameters of the subsequent image data relative to the reference image data are measured to obtain the angle difference between the subsequent image data and the reference image data.

[0064] In the above embodiment, the angle deviation is the angle error caused by the rotation or change between the subsequent image data and the reference image data, which is calculated through the transformation parameters such as the difference in rotation angle; the angle difference is the actual observed angle difference between the image data, which is a result of the angle deviation, and is used for subsequent matching and filtering judgment;

[0065] In addition, the image data processing unit is further provided with a preset matching angle threshold value, which is used to filter out subsequent image data with a large angle difference, and when the angle difference between the subsequent image data and the reference image data is within the threshold value range, it is considered that the subsequent image data meets the matching condition, and the subsequent image data meeting the matching condition is arranged and displayed along the time axis in the image data processing unit; and when each subsequent image data is arranged and displayed along the time axis, the corresponding shooting date, time and key information of the patient are displayed on each subsequent image data, so as to facilitate the dynamic observation and tracking of medical staff.

[0066] On this basis, the image data processing unit is further provided with an associated angle threshold value, which is used to determine those subsequent image data which, although not matching the matching angle threshold value, still have similarity or association with the target image data, wherein the target image data includes the reference image data or the subsequent image data at a time point adjacent to the reference image data.

[0067] The association refers to that the image data and the reference image have a certain degree of similarity in spatial structure, time point or morphological characteristics, which is quantified by a similarity measurement index or an angle deviation, and is used to detect image data having a certain similar structure or time characteristic overlap with the reference image;

[0068] Specifically, when the angle difference of the subsequent image data exceeds the matching angle threshold value range, if a group of image data group has a similarity with a certain image data in the corresponding time sequence which meets the association threshold value requirement, the image data is assigned to the time point in the corresponding time axis, and an expandable copy is established at the time point, which is used to accommodate image data corresponding to the association angle threshold value.

[0069] The similarity refers to that the subsequent image data has the following similarities with the target image data, including:

[0070] Structural features: whether the bone contour, joint morphology and soft tissue morphology in the subsequent image data are similar to the target image data;

[0071] Angle features: whether the difference between the angle deviation of the subsequent image data and the angle deviation of the target image data is within an acceptable range;

[0072] Texture and gray scale distribution: whether the gray scale distribution and texture features of the subsequent image data are close to the target image data.

[0073] Based on the above features, the similarity is obtained by the following formula:

[0074]

[0075] In the formula, I, J represent two image data to be compared; μ I ,μ J are the average brightness of images I and J respectively, and σ J are the brightness variance of images I and J respectively, representing the contrast information of the image, and σ IJ is the covariance of images I and J, used to measure the structural similarity between the two images, and C1, C2 are constants, used to stabilize the calculation to avoid zero denominator; θ is the angle difference between the current image data and the reference image data; θ m is the matching angle threshold, θ a is the associated angle threshold, and α is a constant controlling the influence strength of the angle deviation and the similarity;

[0076] When θ≤θ m , the structural similarity of the two image data is only determined by its content, and is irrelevant to the angle deviation;

[0077] When θ m <θ<θ a , the structural similarity will gradually be affected by the angle difference, and the similarity value of the image will gradually decrease, reflecting the influence of the angle deviation;

[0078] When θ is greater than θ a , the similarity is set to 0, indicating that the angle difference is too large, and the image data no longer meets the matching or association condition;

[0079] The modeling unit converts the 3D imaging data collected by the image data unit into a three-dimensional anatomical model corresponding to the patient's torso, and locates the part of interest in the orthopedic surgery in the model, and the modeling unit interfaces the image data processed by the image data processing unit with the three-dimensional anatomical model, maps the image data to the three-dimensional anatomical model, and obtains a preoperative model;

[0080] The mapping includes image registration technology, image reconstruction and 3D modeling technology, and image data and model fusion technology;

[0081] Image registration is a technology that aligns image data of different sources, different times or different modalities in the same space, ensuring that the spatial coordinates between the data are consistent;

[0082] Image reconstruction and 3D modeling generate a three-dimensional anatomical model from the collected CT or CT through surface reconstruction method;

[0083] Image data and model fusion technology maps the image data after registration and reconstruction to the three-dimensional model to form a preoperative model;

[0084] The modeling unit performs multi-channel processing on the constructed three-dimensional anatomical model to extract key information, including bone damage site, joint surface structure, and blood vessel and nerve relative position;

[0085] The multi-channel processing refers to simultaneously using CT, MRI, and X-ray to perform multi-scale and multi-feature analysis on single image data in medical image processing to extract different types of information.

[0086] The surgical site is determined based on bone density analysis and edge detection, wherein the bone density analysis is obtained based on CT images, and the edge detection is obtained based on X-ray;

[0087] The joint surface structure is segmented from MRI images by threshold segmentation method to obtain joint surface and soft tissue, and joint mobility is determined by angle calculation to provide reference information for joint replacement;

[0088] The relative position of blood vessels and nerves is identified by MRI images to generate corresponding spatial position markers to avoid accidental injury during surgery;

[0089] The data monitoring unit arranges the image data in time axis according to time, detects the injured part of the patient, and matches with big data to obtain recovery data;

[0090] The working method of the data monitoring unit includes the following steps:

[0091] S1, arrange the image data processed by the image data processing unit in time axis, extract the regional features of the injured part, including fracture length, bone density change, soft tissue damage degree, joint mobility, and calculate the change amplitude of the image data at each time point to quantify the recovery progress of the injured part;

[0092] S2, draw a dynamic recovery curve according to the regional features at each time point to show the recovery progress;

[0093] The dynamic recovery curve adopts the formula:

[0094] R(t) = ωB × B(t) + ωF × F(t) + ωT × T(t) + ωC × C(t) + ωS × S(t);

[0095] Wherein, R(t) is the recovery state value of the patient at time t;

[0096] B(t) is the change of bone density with time, which comes from the image data processing unit and is analyzed by the gray value of CT images;

[0097] F(t) is the change of fracture healing state with time, which comes from the image data processing unit and is estimated by the change of image edge detection and fracture length;

[0098] T(t) is the change of soft tissue repair over time, from the image data processing unit, assessed by MRI images;

[0099] C(t) is the health score from the clinical data unit, obtained based on patient's medical history, physical examination data, laboratory examination data;

[0100] S(t) is the motion score from the sensor data unit, obtained based on patient's physiological data and self-reported data;

[0101] ωB, ωF, ωT, ωC, ωS are the weight coefficients of the corresponding items, and ωB+ωF+ωT+ωC+ωS=1;

[0102] S3, based on the regional characteristics of the patient's injured part, extract identification information, including injury type, soft tissue injury type, recovery progress, use similarity matching algorithm to match similar cases in the orthopedic database, specifically use cosine similarity algorithm for matching;

[0103] S4, according to the matched similar cases, extract the corresponding recovery data benchmark from the orthopedic database, including healing time, recovery curve, surgery and rehabilitation suggestions;

[0104] S5, compare the patient's actual recovery curve with the recovery benchmark of big data, calculate the recovery deviation, and deviation analysis can help doctors judge whether the patient's recovery is in line with expectations;

[0105] Specifically, the actual recovery curve is generated by collecting the multi-modal data at the connection time points during the patient's treatment, including data collection, feature extraction and quantification, dynamic recovery curve generation and visualization of CT images, X-ray, MRI images;

[0106] The curve generation includes horizontal and vertical axes, the horizontal axis is time, and the vertical axis is the recovery state value of the patient;

[0107] Based on the comparison result, a personalized recovery plan is generated;

[0108] The navigation module integrates the preoperative model as the basic navigation data for the surgery, and identifies each key point, marker line, fracture line and joint surface related to the patient's anatomy structure, and the navigation module acquires the patient's position information in real time during the surgery, and compares it with the preoperative model to perform dynamic angle matching and correction;

[0109] The modeling unit uses the image data at the last time point in the time axis to dock with the three-dimensional anatomical model.

[0110] Finally, it should be noted that the above only describes the preferred embodiments of the present application and is not intended to limit the present application. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art will appreciate that the technical solutions described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalent features, and any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. An orthopedic image data analysis platform, characterized by, The method comprises the following steps: A data acquisition module acquires original data of a patient by using a plurality of data units, wherein the data acquisition module comprises an image data unit, a clinical data unit, and a sensor data unit; An image data processing unit configures image data acquired for the first time in a time sequence arrangement mode according to a date alternation time point as reference image data, and image data in the image data group other than the reference image data is configured as subsequent image data. After processing the reference image data by using a medical image processing technology, the image data processing unit extracts key skeletal features in the reference image data and calculates angle information of the reference image data according to the key skeletal features; The image data processing unit calculates an angle deviation of skeletal key point coordinates of the key skeletal features between the subsequent image data and the reference image data by using a registration mechanism, and obtains an angle difference between the subsequent image data and the reference image data by measuring rotation, translation, and other transformation parameters of the subsequent image data after registration compared with the reference image data. When the angle difference is less than a set matching angle threshold, the subsequent image data is considered to be qualified image data, and the qualified subsequent image data is arranged and displayed along the time sequence; When the angle difference of the subsequent image data exceeds the matching angle threshold, if a group of image data has similarity with certain image data in the corresponding time sequence and meets the requirement of an association angle threshold, the image data is assigned to the time point in the corresponding time sequence and an expandable copy is established at the time point to accommodate image data matching the association angle threshold; A data processing module processes and fuses the original data acquired by the data acquisition module by using an image data processing unit, a modeling unit, and a data monitoring unit to obtain a preoperative model; In the data processing module, the modeling unit converts a 3D imaging data group acquired by the data acquisition module into a three-dimensional anatomical model corresponding to a patient's torso, and the modeling unit docks image data corresponding to the last time point arranged in a time sequence after the image data processing unit processes the image data group, maps the image data to the three-dimensional anatomical model, and obtains the preoperative model; A navigation module integrates the preoperative model as basic navigation data for surgery, and the navigation module acquires position information of the patient in real time during surgery and compares it with the preoperative model to perform dynamic angle matching and correction.

2. The orthopaedic image data analysis platform of claim 1, wherein: In the data acquisition module: An image data unit acquires orthopedic-related image data and 3D imaging data of a corresponding injured part of a patient by using related equipment, and configures each image data and each 3D imaging data as an image data group and a 3D imaging data group, respectively; A clinical data unit is used to record the medical history, physical examination data, and laboratory examination data of the patient; A sensor data unit acquires physiological data and self-reported data of the patient by using wearable devices or sensors.

3. The orthopaedic image data analysis platform of claim 2, wherein: The related equipment includes CT equipment, X-ray equipment, and MRI equipment; The physiological data includes the patient's exercise amount, joint range of motion, gait, and range of motion; and the self-reported data includes pain score and symptom change.

4. The orthopaedic image data analysis platform of claim 1, wherein: In the data processing module, the image data processing unit uses medical image processing technology to perform image enhancement, noise reduction and registration on the image data.

5. The orthopaedic image data analysis platform of claim 4, wherein: The image data processing unit also has a preset matching angle threshold value for filtering out subsequent image data with a large angle difference.

6. The orthopaedic image data analysis platform of claim 5, wherein: The image data processing unit also has a preset correlation angle threshold value for determining subsequent image data with a similar angle difference to the target image data, although the angle difference does not match the matching angle threshold value, wherein the target image data includes the reference image data or the subsequent image data at a time point adjacent to the reference image data. The similarity is determined by the following formula: ， wherein, denotes two image data to be compared; are the average luminance of images I and J, respectively, and , are the luminance variance of images I and J, respectively, representing the contrast information of the images, and , ; is the covariance of images I and J, used to measure the structural similarity between the two images, and ; , is a constant used to stabilize the calculation to avoid a zero denominator; is the angular difference between the current image data and the reference image data; is the matching angle threshold, is the correlation angle threshold, and a is a constant controlling the influence strength of the angle deviation and the similarity. When ≤ , the structural similarity of the two image data is only determined by their content, and is irrelevant to the angle. When < < The structural similarity is gradually affected by the angle difference, and the image similarity value gradually decreases, reflecting the influence of the angle deviation. When greater than the similarity is set to 0, indicating that the angle difference is too large, and the image data no longer satisfies the matching or association condition.

7. The orthopaedic image data analysis platform of claim 6, wherein: In the data processing module, the data monitoring unit arranges each image data in the time sequence according to time, detects the injured part of the patient, matches with big data, and obtains recovery data.

8. The orthopaedic image data analysis platform of claim 7, wherein: The working method of the data monitoring unit includes the following steps: S1, arrange the image data processed by the image data processing unit according to time, extract the regional features of the injured part, and calculate the change amplitude of the image data at each time point; S2, draw a dynamic recovery curve according to the feature extraction data at each time point to display the recovery progress; S3, based on the regional features of the patient's injured part, extract the identification information, and use a similarity matching algorithm to match with similar cases in the orthopedic big database; S4, according to the matched similar cases, extract the corresponding recovery data reference from the orthopedic big database; S5, compare the actual recovery curve of the patient with the recovery reference of the big data, calculate the recovery deviation and obtain the recovery data; S6, based on the comparison result, generate a personalized recovery plan.

9. An orthopedic image data analysis method, using the orthopedic image data analysis platform of any one of claims 1-8, characterized in that: The method includes the following steps: Step one: obtain the original data of the patient through the multiple data units of the data acquisition module, including image data and 3D imaging data; Step two: the data processing module converts the collected 3D imaging data into a three-dimensional anatomical model corresponding to the patient's torso, and sorts each image data according to the time sequence; Step three: the data processing module extracts the regional features of the image data in the time sequence and generates a dynamic recovery curve; And the data processing module matches the dynamic recovery curve with the orthopedic big database to assist the doctor in judging whether the patient's recovery meets the expectations; Step four: during the operation, the data processing module connects the image data at the last time point in the time sequence with the three-dimensional anatomical model, maps the image data to the three-dimensional anatomical model, and obtains the preoperative model; At the same time, the navigation module integrates the preoperative model, and in the operation, real-time acquires the position information of the patient and compares it with the preoperative model to perform dynamic angle matching and correction.

Images