A method and device for evaluating bone development ability

Abstract

The present invention discloses a method and device for evaluating bone development ability, which relates to the field of image processing technology. The method comprises: receiving preset bone X-ray images of a target user and extracting key features of bone growth; calling a pre-trained bone development ability evaluation model to analyze the key features of bone growth and generate an initial bone development evaluation result; obtaining the preset bone usage information of the target user and comparing it with the model sample parameters, correcting the evaluation result by configuring a feedback coefficient, and generating a personalized target bone development evaluation report. The present invention solves the technical problems that the existing bone development evaluation methods are highly subjective, do not adequately consider individual differences, and lack a dynamic correction mechanism, resulting in low evaluation accuracy and personalization. The present invention achieves the technical effect of improving the accuracy, personalization, and reliability of bone development evaluation by combining automated image analysis, personalized bone usage information, and correction mechanisms.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a method and device for evaluating bone development ability. Background Art

[0002] Bone development assessment is an important medical method used to determine the level of bone development in children and adolescents. Traditional methods mainly rely on X-ray images and manual interpretation to assess bone age and infer future developmental potential. However, traditional methods have certain limitations, mainly reflected in the large amount of manual intervention, the accuracy of the assessment is greatly affected by the operator's experience, and the inability to fully consider the differences between each individual. Although some automated assessment technologies have emerged, most of them fail to effectively integrate factors such as individual living habits, exercise frequency, and medical history, resulting in a low degree of personalization of assessment results when facing different users. In addition, interference factors such as metal artifacts in X-ray images often affect the image quality, and thus affect the accuracy of the assessment. Summary of the Invention

[0003] The present application provides a method and device for evaluating bone development ability, which is used to solve the technical problems that existing bone development assessment methods are highly subjective, do not adequately consider individual differences, and lack a dynamic correction mechanism, resulting in low assessment accuracy and personalization.

[0004] The first aspect of the present application provides a method for evaluating bone development ability, which includes: receiving a preset bone X-ray image of a target user; extracting key features of bone growth from the preset bone X-ray image; calling a pre-trained bone development ability assessment model to analyze the key features of bone growth and generate an initial bone development assessment result; obtaining the preset bone usage information of the target user and comparing it with the sample parameters of the bone development ability assessment model, configuring a feedback coefficient to correct the initial bone development assessment result, and generating a target bone development assessment report.

[0005] The second aspect of the present application provides a device for evaluating bone development ability, the device comprising: a bone X-ray image receiving module, the bone X-ray image receiving module is used to receive a preset bone X-ray image of a target user; a growth key feature extraction module, the growth key feature extraction module is used to extract bone growth key features from the preset bone X-ray image; an initial bone development evaluation module, the initial bone development evaluation module is used to call a pre-trained bone development ability evaluation model to analyze the bone growth key features and generate an initial bone development evaluation result, the bone development ability evaluation model includes multiple evaluation units corresponding to multiple bones, and any evaluation unit has an evaluation contribution weight, and the evaluation contribution weight is the corresponding bone to the bone The accuracy ratio of the developmental ability assessment; an assessment result correction module, the assessment result correction module is used to obtain the preset bone usage information of the target user, and compare it with the sample parameters of the bone development ability assessment model, configure the feedback coefficient to correct the initial bone development assessment result, and generate a target bone development assessment report, specifically including: the preset bone usage information corresponds to the sample parameters, including the preset bone part usage frequency and bone intervention characteristics; compare the difference between the preset bone usage information and the sample parameters to generate a usage difference; configure the feedback coefficient with the usage difference, wherein, through the difference influence layer configuration, the difference influence layer includes a pre-trained usage difference on the bone development assessment result influence curve.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The present application provides a method and device for evaluating bone development ability, which relate to the field of image processing technology. By receiving an X-ray image of the left wrist of a target user and extracting key features of bone growth, a pre-trained bone development evaluation model is called to generate a preliminary bone development evaluation result, the user's bone usage information is obtained and compared with the model sample parameters, and the evaluation result is corrected by configuring a feedback coefficient to generate a personalized target bone development evaluation report. This solves the technical problems of existing bone development evaluation methods, such as high subjectivity, insufficient consideration of individual differences, and lack of a dynamic correction mechanism, which lead to low evaluation accuracy and personalization. It achieves the technical effect of improving the accuracy, personalization and reliability of bone development evaluation by combining automated image analysis, personalized bone usage information and correction mechanism. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0009] Figure 1 A schematic flow chart of a method for evaluating bone development ability provided in an embodiment of the present application;

[0010] Figure 2 A schematic diagram of the structure of a device for evaluating bone development ability provided in an embodiment of the present application.

[0011] Description of the accompanying drawings: bone X-ray image receiving module 11, growth key feature extraction module 12, initial bone development assessment module 13, assessment result correction module 14. DETAILED DESCRIPTION

[0012] The present application provides a method and device for evaluating bone development ability, which is used to solve the technical problems that existing bone development assessment methods are highly subjective, do not adequately consider individual differences, and lack a dynamic correction mechanism, resulting in low assessment accuracy and personalization.

[0013] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0014] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices.

[0015] Example 1, as Figure 1 As shown, the present application provides a method for evaluating bone development ability, the method comprising:

[0016] P10: Receive a preset bone X-ray image of the target user, wherein the preset bone X-ray image is an X-ray image of the left wrist of the target user.

[0017] It should be understood that the system first receives a preset bone X-ray image provided by the target user. This image is an X-ray image of the target user's left wrist. The reason for choosing the left wrist is that the bone structure of the left wrist is highly representative during the development of an individual. Its characteristics, such as the developmental sequence of the epiphyseal lines, changes in bone density, and the maturity of bone morphology, can clearly reflect the individual's bone development level. At the same time, the left wrist is used relatively less frequently, and the bones are less likely to be damaged by external factors. Therefore, its image can more stably reflect the natural development state of the bones. However, for left-handed users or users who have undergone surgery, the frequency of use and bone condition of the left hand may be different. The system should have the ability to automatically judge and adjust the assessment. For example, if the user is left-handed, it is necessary to automatically identify the situation where the left hand is used more frequently. Or if the left hand has undergone surgery, compensation adjustments should be made based on historical data to ensure the accuracy of the assessment results.

[0018] The image acquisition process requires ensuring high-quality X-ray images and is usually performed in a professional setting. Users should follow the technician's instructions to position their left wrist correctly and ensure it is fully exposed within the X-ray machine's imaging area to avoid image blurring due to improper hand posture or angle issues. X-ray equipment should be set to high-resolution mode to ensure clear images, especially in key areas such as bone detail, epiphyseal lines, and bone density. Furthermore, the equipment must be calibrated before image acquisition to ensure that parameters such as exposure and contrast meet technical standards to capture sufficiently detailed bone features.

[0019] After image acquisition is complete, the image data is uploaded to the evaluation system via a digital image transmission system (such as DICOM format). During the transmission process, the system ensures data integrity and performs preliminary verification of the image files to check for transmission errors or data loss. After the image data is successfully transmitted, the system performs preliminary image processing to determine whether the image meets the evaluation criteria. For example, the system checks for metal artifacts or significant blurring. If the image quality does not meet the requirements, the system prompts the technician to re-acquire the image.

[0020] When the image data passes preliminary verification and is confirmed to meet the standards, the image is pre-processed. This includes using artifact removal technology to identify and process metal artifacts in the image to ensure that the bone area is clearly visible. Image segmentation technology is used to separate the artifact area from the bone area, and the artifact area is repaired or reconstructed through algorithms to ensure the authenticity and reliability of the final image. Image enhancement processing is also performed on the image to enhance the details of the bone area by improving contrast, sharpening edges, etc., to assist in subsequent feature extraction and analysis, and improve evaluation accuracy. For complex cases, more advanced image processing can also be performed, such as local magnification, enhancing bone details, etc., to ensure that each user's image can provide sufficient data information.

[0021] Finally, all imaging data and the user's skeletal information are saved by the system and archived as foundational data for subsequent assessments. The system generates detailed image processing records and data logs for each user, ensuring traceability of the image acquisition, processing, and adjustment process. If the user requires historical data review or further evaluation, the system provides a data access interface, allowing users to access detailed reports of their bone development assessments at any time. The core of the entire process lies in ensuring high-quality imaging data acquisition, precise processing, and personalized adjustment to provide reliable data support for bone development assessments. This not only ensures the accuracy of the assessment results but also ensures adaptability and fairness across diverse user backgrounds.

[0022] Furthermore, after receiving the preset bone X-ray image of the target user, step P10 of the embodiment of the present application further includes:

[0023] P11a: Perform metal artifact analysis based on the preset bone X-ray image to determine whether there are metal artifacts; P12a: If so, perform image reconstruction of the metal artifact area to evaluate bone development ability based on the reconstructed image.

[0024] Optionally, after receiving the preset bone X-ray image of the target user, artifact removal technology can be further used to identify and process metal artifacts in the image to ensure that the final evaluation result is not interfered with by artifacts.

[0025] First, a pre-set bone X-ray image is analyzed for metal artifacts. Metal artifacts are caused by scattering or absorption of X-rays when they pass through metal objects, resulting in distorted areas in the image that do not accurately reflect the true structure of the bone. For example, some users' wrists may contain metal prostheses or surgical implants. These metal objects often produce noticeable artifacts in the image, affecting the accuracy of subsequent bone feature extraction and assessment. Therefore, it is necessary to detect the presence of metal artifacts in the image and determine their location and extent. This analysis can be achieved using image processing algorithms, such as using threshold segmentation techniques to identify high-density areas or edge detection algorithms to identify the boundaries of metal artifacts. Alternatively, machine learning algorithms can be combined with training on a large number of image samples containing metal artifacts to achieve automatic detection and classification of metal artifacts. The system examines each part of the image and identifies areas of distortion that may be caused by metal interference.

[0026] If metal artifacts are detected, image reconstruction of the metal artifact area is required. The purpose of image reconstruction is to remove or reduce the interference of metal artifacts on bone feature analysis through algorithm processing, thereby generating high-quality images that can be used to assess bone development capacity. Metal artifact areas usually appear as black or white areas in the image, or blurred bone parts. Image reconstruction can be achieved through a variety of technologies. One common method is based on an iterative reconstruction algorithm, which optimizes the image reconstruction process through multiple iterations to gradually reduce the impact of metal artifacts. Another method is to use deep learning technology to identify and repair metal artifact areas by training convolutional neural network (CNN) models. These models can be trained on a large amount of image data with metal artifacts to learn how to restore clear bone structures from artifact-containing images.

[0027] After image reconstruction, the resulting reconstructed images will be used for subsequent bone development assessments. The quality of the reconstructed images must meet the following criteria: First, the reconstructed skeletal features must be clearly visible and accurately reflect the morphology and structure of the bones. Second, metal artifacts in the reconstructed images must be effectively removed or significantly reduced to avoid interference with subsequent analysis. Finally, the reconstructed images must maintain consistent anatomical features and proportional relationships with the original images to ensure the accuracy of the assessment results.

[0028] Through the above steps, this application can effectively process X-ray images containing metal artifacts, ensuring the accuracy and reliability of subsequent bone development capacity assessment. The introduction of this step greatly improves the robustness and adaptability of the present invention's solution, especially when processing complex cases, and can effectively avoid errors caused by metal artifacts.

[0029] Furthermore, image reconstruction of the metal artifact area is performed. Step P12a of the embodiment of the present application further includes:

[0030] P12-1a: Determine the healthy pixel point set at the artifact boundary of the metal artifact area, and the healthy pixel point set is evenly distributed at the artifact boundary; P12-2a: Based on the healthy pixel point set, perform radial basis function interpolation on each pixel point in the metal artifact area to complete artifact removal, and then perform transition smoothing on the edge of the repair area to generate the reconstructed image.

[0031] In a possible embodiment of the present application, the image reconstruction process of the metal artifact area may be further refined to ensure the quality and usability of the reconstructed image.

[0032] First, determine the set of healthy pixel points at the artifact boundary of the metal artifact area. The artifact boundary is usually the junction between the artifact area and the normal bone area, and there is a transition phenomenon, which usually manifests as distortion or blurring of the bone image. In order to restore the artifact area, image processing algorithms, such as edge detection algorithms, can accurately identify the boundary of the metal artifact. On this basis, a certain number of healthy pixel points are evenly selected around the artifact boundary. The selection of these pixel points should be based on their grayscale value, texture characteristics, etc. to ensure that they are not affected by the artifact and can be evenly distributed on the artifact boundary, providing an accurate reference for the subsequent interpolation process. The distribution of healthy pixel points will ensure that the interpolation algorithm can more accurately capture the true morphology of the bone at the edge of the artifact area.

[0033] Next, after determining the set of healthy pixels, radial basis function (RBF) interpolation is performed on each pixel in the metal artifact area based on these healthy pixels. Radial basis function is a commonly used interpolation method that effectively fills gaps between data points while maintaining smoothness and accuracy in the interpolated results. Here, the RBF interpolation method calculates each pixel in the artifact area based on the distribution and characteristics of healthy pixels, ensuring that the pixel values ​​in the artifact area are consistent with those in the surrounding healthy areas. This interpolation method restores detail in the artifact area and avoids any distortion.

[0034] After interpolation, there may be discontinuities in grayscale values ​​between the repaired area and the surrounding normal image areas, resulting in unnatural edge transitions. Therefore, smoothing the edges of the repaired area is necessary. Image filtering techniques, such as Gaussian filtering or median filtering, can be used to smooth the edges of the repaired area. By selecting appropriate filters and parameters, sudden grayscale changes can be effectively reduced, resulting in a more natural and continuous transition between the repaired area and the surrounding area.

[0035] Through the above steps, the present application can effectively remove the influence of metal artifacts on bone X-ray images and generate high-quality reconstructed images. This process not only ensures the integrity and accuracy of the images, but also provides a reliable basis for subsequent bone development capacity assessment.

[0036] P20: Extract key features of bone growth from the preset bone X-ray image.

[0037] Specifically, pre-set bone X-ray images are processed to extract key features of bone growth. To ensure that the extracted features can accurately reflect the growth status of bones, the X-ray images must first be preprocessed to optimize image quality and reduce interference factors. Specifically, preprocessing includes converting the images into grayscale images to simplify the subsequent analysis process, adjusting the grayscale value range through normalization operations to make it conform to a unified standard, thereby reducing differences caused by acquisition by different equipment. In addition, a filtering algorithm is used to remove noise to enhance image clarity, and contrast enhancement technology is used to highlight bone details for subsequent analysis.

[0038] After the preprocessing is completed, the key feature extraction stage is entered. For example, the key features of bone growth mainly include epiphyseal line features, bone density features, bone morphological features and bone maturity features. Among them, the epiphyseal line is a key sign of bone growth, and its morphology, width and degree of closure can reflect the development stage of the bone. Through image segmentation technology, the position of the epiphyseal line can be accurately identified, and its length, width and morphological features can be extracted. For example, the width of the epiphyseal line can be quantified by calculating its pixel width on the image, while the morphological features can be evaluated by analyzing the smoothness or irregularity of its edges.

[0039] Bone density is an important indicator of bone health and can be indirectly reflected by analyzing the grayscale distribution of X-ray images. Specifically, calculating statistical quantities such as the mean grayscale value and standard deviation of the bone region can provide quantitative information on bone density. Furthermore, texture analysis methods can be used to extract texture features of the bone region, such as texture uniformity and contrast. These features are also closely related to bone density and can further enrich the assessment dimensions of bone density.

[0040] Bone morphological characteristics include length, width, and curvature. Image measurement technology allows for precise measurement of bone length and width, as well as calculation of curvature. For example, for long bones, curvature can be calculated by fitting the centerline of the bone, thereby assessing the bone's morphological development. These morphological characteristics not only reflect the current state of the bone but also provide a basis for predicting future developmental trends.

[0041] Finally, skeletal maturity can be assessed by analyzing the development of ossification centers. For example, in the wrist bones, skeletal maturity can be determined by identifying and measuring the number, size, and location of ossification centers. These characteristics are important indicators for assessing bone developmental capacity and can provide key information for clinical diagnosis and treatment.

[0042] A variety of image processing and analysis techniques can be employed to extract these key features. For example, edge detection algorithms can be used to identify bone outlines, region growing algorithms can be used to segment bone regions, and convolutional neural networks (CNNs) can be used to automatically extract complex features. As a powerful deep learning model, CNNs can automatically learn feature representations from images, thereby improving the accuracy and efficiency of feature extraction. Furthermore, to ensure the accuracy and reliability of feature extraction, the extracted features must be validated and calibrated. This can be achieved by comparing them with known bone development standards or by using expertly annotated data to ensure that the extracted features truly reflect bone growth.

[0043] P30: Call the pre-trained bone development ability assessment model to analyze the key characteristics of bone growth and generate initial bone development assessment results.

[0044] The bone development ability assessment model includes multiple assessment units corresponding to multiple bones, and any assessment unit has an assessment contribution weight, which is the accuracy ratio of the corresponding bone for the bone development ability assessment.

[0045] It should be understood that the pre-trained bone development ability assessment model is called to analyze the extracted key features of bone growth and generate preliminary bone development assessment results. First, the bone development ability assessment model is a deep learning model trained with a large amount of bone development data. The model is capable of processing based on multiple assessment units corresponding to multiple bones. Each assessment unit is responsible for analyzing the growth characteristics of a specific bone part and performing a comprehensive assessment based on the developmental characteristics of different bone parts.

[0046] In model construction, each assessment unit is associated with a specific skeletal region (such as the radius, ulna, metacarpals, etc.). Each bone corresponding to an assessment unit has a specific assessment contribution weight, which represents the proportion of that bone's contribution to the bone development assessment. Different skeletal regions have different influences on bone development. The development of certain regions may have a higher accuracy in assessing overall bone development capacity, so the assessment units of these regions are assigned higher weights. Meanwhile, assessment units of other skeletal regions may be assigned relatively lower weights due to their lesser influence on the assessment results.

[0047] The system generates preliminary bone development assessment results by matching and calculating the extracted key features of bone growth with the models of each assessment unit. During this process, the assessment model considers the growth characteristics of each skeletal region, combines them with their corresponding weights, accurately predicts the developmental status of that region, and derives an overall bone development assessment result through comprehensive analysis of these units. For example, if the epiphyseal line development in the wrist region is relatively typical and clear, and the assessment contribution weight of this area is high, then the assessment result of this area will have a greater impact on the overall assessment result.

[0048] Ultimately, the assessment results of these individual skeletal regions are combined according to the pre-defined weighting ratios to generate a preliminary bone development assessment. This result includes an estimated bone age, the level of skeletal development, and the risk of abnormalities or developmental delays. This preliminary assessment provides data support for subsequent bone development capacity assessments and forms the basis for individualized evaluations.

[0049] Furthermore, the construction of the bone development ability assessment model in this embodiment of the application further includes step P30a, which further includes:

[0050] P31a: For the multiple bones, collect multiple bone key feature sample sets and corresponding multiple bone age assessment sample sets; P32a: Train the multiple evaluation units after combining the multiple bone key feature sample sets and the multiple bone age assessment sample sets according to the corresponding relationship; P33a: Construct a fusion layer with the evaluation contribution weights, connect it with the multiple evaluation units, and generate the bone development ability assessment model.

[0051] Optionally, the process of constructing the bone development ability assessment model can be further detailed.

[0052] First, we collect key feature sample sets for multiple bones and corresponding bone age assessment sample sets. These sample sets are obtained by analyzing a large amount of bone imaging data and clinical case data. They contain key feature data for multiple skeletal regions (such as the radius, ulna, metacarpal bones, etc.), and each feature data corresponds to a professionally assessed bone age value. The key feature sample set of bones includes indicators such as bone morphology, epiphyseal width, and bone density in the image, while the bone age assessment sample set is the result of judging the stage of bone development using professional standards. The system uses this data as input to ensure that the evaluation model can be trained based on diverse bone features.

[0053] Next, the collected multiple bone key feature sample sets and bone age assessment sample sets are combined according to the corresponding relationship, and multiple evaluation units are trained in combination with deep learning technology. Each evaluation unit is specifically used to analyze and process the feature data of a specific bone area. By training on these data sets, the relationship between different bone areas and bone age development is learned, providing each evaluation unit with powerful prediction capabilities. Exemplarily, machine learning or deep learning algorithms, such as convolutional neural networks (CNNs), train models with a large amount of sample data, enabling them to automatically learn the mapping relationship between features and bone age. During the training process, the model continuously adjusts internal parameters to minimize the error between the predicted results and the actual bone age assessment, thereby improving the prediction accuracy of each evaluation unit. By training the evaluation units, each unit can accurately analyze a specific bone area and extract the most representative bone growth characteristics.

[0054] Finally, in order to integrate multiple assessment units into a complete bone development capacity assessment model, a fusion layer needs to be constructed. The role of the fusion layer is to weightedly fuse the output results of each assessment unit according to the assessment contribution weight of each assessment unit. The assessment contribution weight reflects the importance of each bone in the overall bone development capacity assessment. These weights can be set or optimized based on clinical experience and experimental data. Through the fusion layer, the prediction results of multiple assessment units are comprehensively processed to generate the final bone development capacity assessment model. This model can comprehensively consider the developmental characteristics of multiple skeletal parts and their contribution to the overall bone development capacity, thereby providing a comprehensive and accurate bone development assessment result.

[0055] Through these steps, the system can build a comprehensive and accurate bone development assessment model, which can not only independently analyze the growth characteristics of each bone area, but also combine the comprehensive information of these areas to generate a personalized bone development capacity assessment report.

[0056] P40: Obtain the preset bone usage information of the target user and compare it with the sample parameters of the bone development ability assessment model, configure the feedback coefficient to correct the initial bone development assessment result, and generate a target bone development assessment report.

[0057] Furthermore, step P40 in this embodiment of the present application further includes:

[0058] P41: The preset bone usage information corresponds to the sample parameters, including the usage frequency of preset bone parts and bone intervention characteristics; P42: Compare the difference between the preset bone usage information and the sample parameters to generate usage differences; P43: Configure the feedback coefficient based on the usage differences, wherein the difference influence layer is configured through the difference influence layer, and the difference influence layer includes a curve of the influence of pre-trained usage differences on bone development assessment results.

[0059] It should be understood that the personalized correction process of bone development ability assessment can be further refined to ensure that the assessment results can more accurately reflect the actual bone development status of the target user.

[0060] Specifically, it is first necessary to obtain the target user's preset bone usage information. This information includes the frequency of use of the preset bone parts and bone intervention characteristics (such as whether they have undergone surgery or have had fractures). This usage information is compared with the sample parameters in the bone development ability assessment model. The sample parameters are trained based on a large amount of sample data and reflect the relationship between bone development and usage under normal circumstances. Through comparison, the system can identify the difference between the target user's bone usage information and the sample parameters, that is, the usage difference.

[0061] Subsequently, the feedback coefficient is configured according to the identified usage differences. This process is achieved through the differential impact layer, which includes the pre-trained usage difference impact curves on the bone development assessment results. These impact curves are trained based on a large amount of sample data and can reflect the specific degree of impact of different usage differences on the bone development assessment results. The differential impact layer will look for the corresponding correction coefficient on the pre-trained impact curve based on the identified usage differences. For example, if the target user's preset bone part usage frequency is much higher than the average level in the sample parameters, and the part has undergone surgery, the differential impact layer will find the corresponding correction coefficient on the impact curve based on these differences. These correction coefficients will be used to adjust the initial bone development assessment results to more accurately reflect the actual bone development status of the target user.

[0062] The configuration and application of feedback coefficients can be achieved through a mathematical model. The specific formula can be expressed as: Corrected bone development assessment result = Initial bone development assessment result × Feedback coefficient. The feedback coefficient is found in the difference impact layer based on usage differences and can quantify the impact of usage differences on bone development assessment results.

[0063] After the aforementioned correction process, the system will generate a target bone development assessment report. This report not only includes the initial bone development assessment results, but also reflects the personalized corrections made based on the target user's preset bone usage information. The report will detail the reasons and basis for the corrections, such as the target user's frequent bone use or previous surgery, and the specific impact of these factors on the bone development assessment results. In this way, the target bone development assessment report can provide clinicians with more accurate and targeted diagnostic evidence, thereby better serving patients' treatment and rehabilitation.

[0064] Through the above steps, this application achieves personalized correction of bone development ability assessment. It not only takes into account the individual differences of the target users, but also ensures the scientific and accurate correction process through the pre-trained difference influence layer and feedback coefficient configuration. The resulting target bone development assessment report can more realistically reflect the target user's bone development status, providing strong support for clinical diagnosis and treatment.

[0065] Furthermore, step P40 in this embodiment of the present application further includes:

[0066] P44: Extract the actual bone age assessment result based on the revised bone development assessment result; P45: Read the user attribute information of the target user, including age, gender, height and parents' height; P46: Call the residual height growth potential analysis model to combine the actual bone age assessment result and the user attribute information to predict the adult height growth potential, and generate a target growth potential prediction result. The residual height growth potential analysis model uses historical data samples based on neural network training; P47: Generate the target bone development assessment report based on the actual bone age assessment result and the target growth potential prediction result.

[0067] Specifically, the process of bone development ability assessment can be further refined, not only to personalize the initial bone development assessment results, but also to predict the adult height growth potential based on the detailed information of the target user, and ultimately generate a comprehensive target bone development assessment report.

[0068] First, the actual bone age assessment result is extracted based on the revised bone development assessment results. After the aforementioned correction steps, the system has optimized and adjusted the initial bone development assessment results, making the assessment results more personalized to the user. At this point, the system extracts the actual bone age from the revised assessment results. This bone age value reflects the user's true stage of skeletal development and serves as the basis for subsequent growth potential predictions.

[0069] Next, the system reads the target user's attribute information, including age, gender, height, and parental height. This personal attribute information is crucial for predicting growth potential. For example, gender and parental height significantly influence the prediction of adult height. By reading this attribute information, the system can combine the user's growth background with other data to provide the necessary input for growth potential prediction.

[0070] Furthermore, the residual height growth potential analysis model is called to combine the actual bone age assessment results and user attribute information to predict the adult height growth potential. The residual height growth potential analysis model is based on neural network training. This model is learned through a large number of historical data samples and can analyze the impact of the user's bone age and growth background (such as age, gender, parents' height, etc.) on the final adult height. The system inputs the actual bone age and user attribute information into the model. The model predicts the user's future height growth potential based on this information and derives a predicted value for adult height. Specifically, the model will judge the target user's current bone development stage based on the actual bone age assessment results, and combine factors such as their age, gender, current height, and parents' height to predict their height growth potential in adulthood through a neural network algorithm.

[0071] Finally, the actual bone age assessment results and the target growth potential prediction results are combined to generate a target bone development assessment report. This report not only contains the target user's current actual bone development level, but also provides a prediction of their future height growth potential. The report details the discrepancy between the target user's bone age and actual age, their current bone development status, and their predicted adult height based on their genetics and current growth status. The report also provides relevant explanations and recommendations. For example, if the prediction results indicate that the target user has insufficient height growth potential, the report may recommend further medical examinations or interventions.

[0072] In summary, this application not only provides a personalized assessment of bone development capacity, but also expands the scope of this assessment to include predictions of future growth potential. This report provides users with a comprehensive and accurate assessment of both current bone development and future growth potential, ensuring the scientific, personalized, and accurate nature of the assessment results.

[0073] Furthermore, after extracting the actual bone age assessment result, step P40 of the embodiment of the present application further includes:

[0074] P45a: Compare the actual bone age assessment result with the current age of the target user to determine the bone age deviation, and the bone age deviation carries a deviation direction identifier; P46a: Generate bone age abnormality reminder information based on the bone age deviation.

[0075] Optionally, after extracting the actual bone age assessment results, the assessment process can be further expanded to add functions for analyzing bone age deviations and generating bone age abnormality reminder information.

[0076] First, after completing the personalized correction of the initial bone development assessment results and extracting the actual bone age assessment results, the system compares the actual bone age assessment results with the current age of the target user to determine the bone age deviation. Bone age deviation refers to the difference between the actual bone age and the current actual age of the target user. It can reflect whether the target user's bone development is consistent with that of his peers. Specifically, the bone age deviation can be positive or negative, indicating that the bone age is higher or lower than the actual age, respectively. In order to more clearly express this difference, the bone age deviation also carries a deviation direction indicator to clearly indicate whether the bone age is advanced or delayed. For example, if the actual bone age is 12 years old and the current age of the target user is 10 years old, the bone age deviation is +2 years old, and the deviation direction is marked as "advanced"; conversely, if the actual bone age is 8 years old and the current age of the target user is 10 years old, the bone age deviation is -2 years old, and the deviation direction is marked as "delayed".

[0077] Then, based on the determined bone age deviation, a bone age abnormality reminder message is further generated. The purpose of this reminder message is to promptly notify the target user that there is a significant difference between the bone age and the actual age. The bone age abnormality reminder message will include the specific value of the bone age deviation, the deviation direction identifier, and relevant explanations. For example, if the bone age deviation is large and the direction is early, the reminder message may indicate that the target user may be at risk of precocious puberty and recommend further medical examinations; if the bone age deviation is large and the direction is delayed, the reminder message may prompt the target user that there may be growth retardation and recommend a nutritional assessment or endocrine examination. If the user's bone age deviation exceeds the normal growth range, the system will generate relevant abnormality reminder information based on this deviation. The reminder message will specify the direction and degree of the bone age deviation, and combined with information such as the user's age and gender, provide a judgment on whether there is an abnormality.

[0078] Through this process, users receive detailed feedback on their bone development. The calculation of bone age deviations and the generation of abnormality alerts enable the system to provide personalized, timely health guidance, helping users identify potential developmental issues early on.

[0079] In summary, the embodiments of the present application have at least the following technical effects:

[0080] This application improves the accuracy of bone development assessments and reduces errors caused by manual intervention through automated image analysis and deep learning models. At the same time, it combines the target user's bone usage information (such as frequency of use, exercise habits, medical history, etc.) to provide personalized assessment results. Metal artifact analysis and image reconstruction technology eliminate artifact interference, ensuring image clarity and reliable assessment results. Furthermore, the system is configured with a feedback coefficient to correct the initial assessment results based on the user's individual characteristics, ensuring that the assessment results are more consistent with the actual bone development status. Ultimately, it automatically generates a comprehensive bone development assessment report, providing users with scientific and accurate health management support.

[0081] The technical effect of improving the accuracy, personalization and reliability of bone development assessment was achieved by combining automated image analysis, personalized bone usage information and correction mechanism.

[0082] Example 2, based on the same inventive concept as the method for evaluating bone development ability in the above example, Figure 2 As shown, the present application provides a device for evaluating bone development ability. The device and method embodiments in the present application are based on the same inventive concept. The device includes:

[0083] The skeleton X-ray image receiving module 11 is used to receive a preset skeleton X-ray image of a target user, wherein the preset skeleton X-ray image is an X-ray image of the left wrist of the target user.

[0084] The key growth feature extraction module 12 is used to extract key bone growth features from the preset bone X-ray image.

[0085] An initial bone development assessment module 13 is configured to call a pre-trained bone development capacity assessment model to analyze the key features of bone growth and generate an initial bone development assessment result. The bone development capacity assessment model includes multiple assessment units corresponding to multiple bones, and each assessment unit has an assessment contribution weight, which is the accuracy ratio of the corresponding bone to the bone development capacity assessment.

[0086] The evaluation result correction module 14 is used to obtain the preset bone usage information of the target user, compare it with the sample parameters of the bone development ability evaluation model, configure the feedback coefficient to correct the initial bone development evaluation result, and generate a target bone development evaluation report.

[0087] Furthermore, the bone X-ray image receiving module 11 is further configured to perform the following steps:

[0088] A metal artifact analysis is performed based on the preset bone X-ray image to determine whether there is a metal artifact; if so, image reconstruction of the metal artifact area is performed to evaluate bone development ability using the reconstructed image.

[0089] Furthermore, the bone X-ray image receiving module 11 is further configured to perform the following steps:

[0090] A set of healthy pixel points at the artifact boundary of the metal artifact area is determined, and the healthy pixel point set is evenly distributed at the artifact boundary; based on the healthy pixel point set, radial basis function interpolation is performed on each pixel point in the metal artifact area to complete artifact removal, and then transition smoothing is performed on the edge of the repair area to generate the reconstructed image.

[0091] Furthermore, the initial bone development assessment module 13 is further configured to perform the following steps:

[0092] For the multiple bones, multiple bone key feature sample sets and corresponding multiple bone age assessment sample sets are collected; the multiple bone key feature sample sets and the multiple bone age assessment sample sets are combined according to the corresponding relationship to train the multiple assessment units; a fusion layer is constructed with the assessment contribution weights, and is connected to the multiple assessment units to generate the bone development ability assessment model.

[0093] Furthermore, the evaluation result correction module 14 is further configured to perform the following steps:

[0094] The preset bone usage information corresponds to the sample parameters, including the usage frequency of preset bone parts and bone intervention characteristics; the difference between the preset bone usage information and the sample parameters is compared to generate a usage difference; the feedback coefficient is configured with the usage difference, wherein, through the difference influence layer configuration, the difference influence layer includes a pre-trained usage difference influence curve on the bone development evaluation result.

[0095] Furthermore, the evaluation result correction module 14 is further configured to perform the following steps:

[0096] The actual bone age assessment result is extracted based on the corrected bone development assessment result; the user attribute information of the target user is read, including age, gender, height and parents' height; the residual height growth potential analysis model is called to combine the actual bone age assessment result and the user attribute information to predict the adult height growth potential, and generate a target growth potential prediction result. The residual height growth potential analysis model uses historical data samples based on neural network training; the target bone development assessment report is generated based on the actual bone age assessment result and the target growth potential prediction result.

[0097] Furthermore, the evaluation result correction module 14 is further configured to perform the following steps:

[0098] The actual bone age assessment result is compared with the current age of the target user to determine the bone age deviation, where the bone age deviation carries a deviation direction identifier; and bone age abnormality reminder information is generated based on the bone age deviation.

[0099] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0100] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

[0101] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. A method for evaluating bone development ability, characterized in that: include: Receive a preset bone X-ray image of a target user; Extracting key features of bone growth from the preset bone X-ray image; Calling a pre-trained bone development capacity assessment model to analyze the key features of bone growth and generate an initial bone development assessment result, wherein the bone development capacity assessment model includes multiple assessment units corresponding to multiple bones, and each assessment unit has an assessment contribution weight, and the assessment contribution weight is the accuracy ratio of the corresponding bone to the bone development capacity assessment; Obtaining the preset bone usage information of the target user and comparing it with the sample parameters of the bone development ability assessment model, configuring a feedback coefficient to correct the initial bone development assessment result, and generating a target bone development assessment report, specifically including: The preset bone usage information corresponds to the sample parameters, including the preset bone part usage frequency and bone intervention characteristics; comparing the preset bone usage information with the sample parameters to generate a usage difference; The feedback coefficient is configured based on the usage difference, wherein the feedback coefficient is configured through a difference influence layer, wherein the difference influence layer includes a pre-trained curve of the influence of the usage difference on the bone development assessment result; After receiving the preset bone X-ray image of the target user, the method further includes: Performing metal artifact analysis based on the preset bone X-ray image to determine whether metal artifacts exist; If so, image reconstruction of the metal artifact area was performed and the reconstructed image was used to evaluate bone development ability; The image reconstruction of the metal artifact area is performed, including: Determine a healthy pixel point set at an artifact boundary of the metal artifact area, where the healthy pixel point set is evenly distributed at the artifact boundary; Based on the healthy pixel point set, radial basis function interpolation is performed on each pixel point in the metal artifact area to complete artifact removal, and then transition smoothing is performed on the edge of the repair area to generate the reconstructed image.

2. The method for evaluating bone development ability according to claim 1, wherein: The preset bone X-ray image is an X-ray image of the left wrist of the target user.

3. The method for evaluating bone development ability according to claim 1, wherein: The steps of constructing the bone development ability assessment model include: For the multiple bones, collecting multiple bone key feature sample sets and corresponding multiple bone age assessment sample sets; The plurality of bone key feature sample sets and the plurality of bone age assessment sample sets are combined according to a corresponding relationship to train the plurality of assessment units; A fusion layer is constructed using the evaluation contribution weights and connected to the multiple evaluation units to generate the bone development ability evaluation model.

4. The method for evaluating bone development ability according to claim 1, wherein: The feedback coefficient is configured to modify the initial bone development assessment result to generate a target bone development assessment report, including: The actual bone age assessment results were extracted based on the revised bone development assessment results; Read the user attribute information of the target user, including age, gender, height and parents' height; Invoking a residual height growth potential analysis model to predict adult height growth potential in combination with the actual bone age assessment result and the user attribute information to generate a target growth potential prediction result, wherein the residual height growth potential analysis model is trained based on a neural network using historical data samples; The target bone development assessment report is generated based on the actual bone age assessment result and the target growth potential prediction result.

5. The method for evaluating bone development ability according to claim 4, wherein: After extracting the actual bone age assessment results, it also includes: Comparing the actual bone age assessment result with the current age of the target user to determine a bone age deviation, wherein the bone age deviation carries a deviation direction identifier; Bone age abnormality reminder information is generated based on the bone age deviation.

6. A device for evaluating bone development ability, characterized in that: The method for implementing the bone development ability evaluation method according to any one of claims 1 to 5, wherein the device comprises: A bone X-ray image receiving module, wherein the bone X-ray image receiving module is used to receive a preset bone X-ray image of a target user; A growth key feature extraction module, the growth key feature extraction module is used to extract the bone growth key features from the preset bone X-ray image; An initial bone development assessment module, which is used to call a pre-trained bone development capacity assessment model to analyze the key characteristics of bone growth and generate an initial bone development assessment result. The bone development capacity assessment model includes multiple assessment units corresponding to multiple bones, and each assessment unit has an assessment contribution weight, which is the accuracy ratio of the corresponding bone to the bone development capacity assessment; The evaluation result correction module is used to obtain the preset bone usage information of the target user, compare it with the sample parameters of the bone development ability evaluation model, configure the feedback coefficient to correct the initial bone development evaluation result, and generate a target bone development evaluation report, specifically including: The preset bone usage information corresponds to the sample parameters, including the preset bone part usage frequency and bone intervention characteristics; comparing the preset bone usage information with the sample parameters to generate a usage difference; The feedback coefficient is configured based on the usage difference, wherein the feedback coefficient is configured through a difference influence layer, and the difference influence layer includes a pre-trained curve of the influence of the usage difference on the bone development assessment result.

Images