Rehabilitation plan recommendation method and device for multiple fractures, electronic equipment, and storage medium

Abstract

The application relates to the field of computer-aided medical technology, and discloses a rehabilitation plan recommendation method for multiple fractures, which comprises the following steps: acquiring a first image for representing multiple fractures, the first image being an image in which multiple fracture position bounding boxes are marked on a preset human skeleton image; determining position information of a concurrent injury position according to the first image; and performing rehabilitation plan recommendation according to the position information of the concurrent injury position. The image in which multiple fracture position bounding boxes are marked on the preset human skeleton image is acquired, then the position information of the concurrent injury position is determined according to the image, and thus the rehabilitation plan recommendation can be performed according to the position information of the concurrent injury position. In this way, the rehabilitation training plan can be recommended for the multiple fracture user. The application further discloses a rehabilitation plan recommendation device for multiple fractures, an electronic device and a storage medium.

Description

Technical Field

[0001] This application relates to the field of computer-aided medical technology, such as a method and apparatus, electronic device, and storage medium for recommending rehabilitation plans for multiple fractures. Background Technology

[0002] Fractures are a common occurrence, and rehabilitation training is usually required after fracture treatment. Multiple fractures typically refer to fractures in multiple parts of the body. If an inappropriate rehabilitation training plan is used for multiple fractures, it can easily lead to secondary injuries in other parts of the body besides the fracture site.

[0003] Because the location of a fracture can vary, the potential sites of complications can also differ. Current technology can only recommend fixed rehabilitation training plans for fracture patients, and cannot recommend specific rehabilitation training plans for patients with multiple fractures. Summary of the Invention

[0004] To provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended as a general commentary, nor is it intended to identify key / important components or describe the scope of protection of these embodiments, but rather as a prelude to the detailed description that follows.

[0005] This disclosure provides a method and apparatus, electronic device, and storage medium for recommending rehabilitation plans for multiple fractures.

[0006] In some embodiments, the recommended rehabilitation program for multiple fractures includes:

[0007] A first image is acquired to characterize multiple fractures. This first image is an image on a pre-defined human skeletal image with bounding boxes marking multiple fracture sites. The location information of concurrent injury sites is determined based on the first image. A rehabilitation plan is recommended based on the location information of the concurrent injury sites; the rehabilitation plan includes rehabilitation exercises and the corresponding exercise durations.

[0008] In some embodiments, a rehabilitation plan recommendation device for multiple fractures includes: an acquisition module configured to acquire a first image characterizing multiple fractures, the first image being an image on a preset human skeletal image with bounding boxes marking multiple fracture sites; a determination module configured to determine location information of concurrent injury sites based on the first image; and a recommendation module configured to recommend a rehabilitation plan based on the location information of the concurrent injury sites; the rehabilitation plan including rehabilitation actions and the corresponding exercise duration.

[0009] In some embodiments, the electronic device includes a processor and a memory storing program instructions, the processor being configured to execute the above-described recommended method for rehabilitation planning of multiple fractures when the program instructions are executed.

[0010] In some embodiments, the storage medium stores program instructions that, when executed, perform the above-described recommended method for rehabilitation planning of multiple fractures.

[0011] The method, apparatus, electronic device, and storage medium for recommending rehabilitation plans for multiple fractures provided in this disclosure can achieve the following technical effects: By acquiring an image with bounding boxes of multiple fracture sites marked on a preset human skeletal image, and then determining the location information of concurrent injury sites based on the image, a rehabilitation plan can be recommended based on the location information of the concurrent injury sites. This allows for targeted recommendations of rehabilitation training plans for users with multiple fractures.

[0012] The above general description and the description below are exemplary and illustrative only and are not intended to limit this application. Attached Figure Description

[0013] One or more embodiments are illustrated by way of example with reference to the accompanying drawings. These illustrations and drawings do not constitute a limitation on the embodiments. Elements having the same reference numerals in the drawings are shown as similar elements. The drawings are not to be scaled. And wherein:

[0014] Figure 1 This is a schematic diagram of a method for recommending a rehabilitation plan for multiple fractures provided in an embodiment of this disclosure;

[0015] Figure 2 This is a schematic diagram of a second image provided in an embodiment of this disclosure;

[0016] Figure 3 This is a schematic diagram of a rehabilitation program recommendation device for multiple fractures provided in an embodiment of this disclosure;

[0017] Figure 4 This is a schematic diagram of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0018] To provide a more detailed understanding of the features and technical content of the embodiments of this disclosure, the implementation of the embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. The accompanying drawings are for illustrative purposes only and are not intended to limit the embodiments of this disclosure. In the following technical description, for ease of explanation, several details are used to provide a full understanding of the disclosed embodiments. However, one or more embodiments may still be implemented without these details. In other cases, well-known structures and devices may be simplified in their depiction to simplify the drawings.

[0019] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this disclosure described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.

[0020] This application can be applied to electronic devices recommended for rehabilitation programs for multiple fractures. These electronic devices may include, but are not limited to, servers, computers, mobile phones, personal digital assistants (PDAs), wireless handheld devices, tablet computers, personal computers (PCs), PDAs (personal digital assistants), embedded systems, etc.

[0021] Combination Figure 1 As shown, this disclosure provides a method for recommending rehabilitation plans for multiple fractures, including:

[0022] Step S101: Obtain a first image for characterizing multiple fractures. The first image is an image in which the bounding boxes of multiple fracture sites are marked on a preset human skeleton image.

[0023] Step S102: Determine the location information of the concurrent injury site based on the first image.

[0024] Step S103: Recommend a rehabilitation plan based on the location information of the concurrent injury site; the rehabilitation plan includes rehabilitation movements and the corresponding exercise time length for each movement.

[0025] By acquiring images with bounding boxes marking multiple fracture sites on a pre-defined human skeletal image, and then determining the location information of concurrent injuries based on these images, rehabilitation plans can be recommended. This allows for targeted rehabilitation training plans to be recommended for users with multiple fractures.

[0026] In some optional embodiments, the user selects a human skeleton image from a set of preset candidate human skeleton images on a user terminal, and marks the fracture points on the selected human skeleton image using preset fracture site bounding boxes to obtain a first image. In some embodiments, the first image size corresponding to candidate human skeleton images of different sizes is the same; that is, the first image size is always the same, while the candidate human skeleton images have different sizes. Determining the location information of the concurrent injury site based on the first image includes:

[0027] Step 1: Determine the fracture points in the first image. Optionally, any point, such as the center pixel, corresponding to the bounding box of each fracture site in the first image can be determined as a fracture point, and the coordinates of each fracture point in the first image can be used as the fracture point coordinates. Specifically, the horizontal coordinate of the fracture point coordinates is the row number of the fracture point in the first image, and the vertical coordinate is the column number of the fracture point in the first image. For example, if the coordinates of the fracture point are (11, 12), then the fracture point is located in the 11th row and 12th column of the second image.

[0028] Step 2: Connect the fracture points in the first image with lines.

[0029] Step 3: Calculate for each connection line And calculate for each connection. Where Can is the offset value of the fracture point connection line, Canwz is the length value of the fracture point connection line, x1 is the x-coordinate of the first fracture point in the connection line, x2 is the x-coordinate of the second fracture point in the connection line, x1≥x2, y1 is the y-coordinate of the first fracture point in the connection line, y2 is the y-coordinate of the second fracture point in the connection line, and a is a preset constant, 0.01≤a≤0.0000001.

[0030] Step 4: Obtain the fracture point connection features for each connecting line. This involves calculating the fracture point connection features for each connecting line. Obtain the characteristics of the fracture point connection line, where D bf The fracture point connection features are defined by α, where α is the connection offset base and β is the connection length base, both of which are greater than 0. Optionally, different candidate human skeleton images correspond to different α values ​​and different β values. When a user selects a human skeleton image from the candidate images, the α and β values ​​corresponding to the first image are determined. The α and β values ​​corresponding to the first image are also obtained when acquiring the first image. This method reflects the degree of force dispersion between two fracture points through the fracture point connection offset and fracture point connection length values. The location of the fracture area is defined by the midpoint of the line segment. Simultaneously, personalized connection offset and connection length bases are used to correct the user's fracture point connection. This allows for accurate acquisition of corresponding fracture point connection features for users with different body postures, enabling the identification of concurrent injury sites using these fracture point connection features.

[0031] Step 5: Perform a lookup operation in the preset candidate coordinate library to match the candidate coordinates corresponding to the line features of each fracture point. The candidate coordinate library stores the line features of fracture points, candidate coordinates, and the correspondence between them. Optionally, the candidate coordinates are coordinate values ​​in the pixel coordinate system of the first image, that is, the horizontal coordinate value of the candidate coordinate represents the row number in the first image, and the vertical coordinate value of the candidate coordinate represents the column number in the first image.

[0032] Step Six: Define a predetermined number of regions containing candidate coordinates in the first image as candidate regions for concurrent injury sites in the first image. The distance between candidate coordinates within each candidate region is within a predetermined range. Clustering of the candidate coordinates allows for the determination of concurrent injury sites based on the degree of concentration of the candidate coordinates. In some embodiments, by setting a predetermined number, multiple candidate regions for concurrent injury sites in the first image can be clustered.

[0033] Step 7: In the first image, identify any point (e.g., the center pixel) within each candidate region for concurrent damage as a concurrent damage site. Determine the coordinates of this point as the coordinates of the concurrent damage site. The x-coordinate of the center pixel in the first image is its row number, and the y-coordinate is its column number. For example, if the center pixel's coordinates are (11, 12), it is located in the 11th row and 12th column of the first image. This determines the location information of the concurrent damage site.

[0034] Since different users typically have different heights, bone structures, etc., the above method allows users to select human bone images that are similar to their own body shape for labeling. The first image obtained in this way is more accurate in predicting the location of secondary injuries in multiple fractures.

[0035] Optionally, the location information of the concurrent injury site is determined based on the first image, including:

[0036] The first image is input into a preset concurrent injury site prediction model to obtain a second image; the second image is an image marked with the bounding box of the concurrent injury site on a preset human skeleton image.

[0037] The location information of the concurrent injury sites is determined based on the bounding box of the concurrent injury sites.

[0038] The concurrent injury site prediction model is obtained by training a pre-defined neural network model with training samples containing bounding boxes of concurrent injury sites. The training samples include human skeleton images labeled with the bounding boxes of fracture sites. Optionally, the first image and the second image are the same size. The human skeleton images in the training samples and the second image are the same as the human skeleton images in the first image.

[0039] Optionally, the location information of the concurrent injury site is determined based on the bounding box of the concurrent injury site, including:

[0040] In the second image, any point in the region corresponding to the bounding box of the concurrent damage site is determined as a reference point.

[0041] The coordinates of the reference point are used as the location information of the concurrent damage site.

[0042] In some embodiments, any pixel in the region corresponding to the bounding box of the concurrent injury site in the second image is determined as a reference point. Optionally, the center pixel in the region corresponding to the bounding box of the concurrent injury site in the second image is determined as a reference point, and the coordinates of the center pixel in the second image are used as the location information of the concurrent injury site. The horizontal coordinate of the center pixel in the second image is the row number of the center pixel in the second image, and the vertical coordinate is the column number of the center pixel in the second image. For example, if the coordinates of the center pixel are (11, 12), then the center pixel is located in the 11th row and 12th column of the second image.

[0043] like Figure 2 As shown, in some exemplary embodiments, the boxes at points a, b, d, and f in the second image are the bounding boxes of the fracture sites, and the circles at points c and e are the bounding boxes of the concurrent injury sites. In this embodiment, the second image is obtained by predicting concurrent injury sites using a preset concurrent injury site prediction model input from the first image, and the first image input to the concurrent injury site prediction model is compared with... Figure 2 The second image shown is basically the same, except that it does not have the bounding boxes of the concurrent damage sites at points c and e.

[0044] Optionally, rehabilitation plans can be recommended based on the location information of the concurrent injury sites, including:

[0045] In the first image, any point in the region corresponding to the bounding box of each fracture site is determined as the fracture point, and the coordinates of each fracture point are obtained.

[0046] In the preset rehabilitation plan library, the location information of the concurrent injury sites is looked up to obtain alternative rehabilitation plans for multiple fractures. The rehabilitation plan library stores the correspondence between the rehabilitation plan for multiple fractures, the coordinates of the first human body region, and the coordinates of the second human body region. The coordinates of the first human body region are used to represent the fracture point, and the coordinates of the second human body region are used to represent the reference point.

[0047] The coordinates of each fracture point are matched in the alternative multiple fracture rehabilitation plan to obtain the corresponding rehabilitation plan for each fracture point and recommend it to the user; the rehabilitation plan is either an alternative multiple fracture rehabilitation plan with any one fracture point coordinate, or an alternative multiple fracture rehabilitation plan with any number of fracture point coordinates.

[0048] In some embodiments, any pixel in the region corresponding to the bounding box of each fracture site in the first image is determined as a fracture point. Optionally, the center pixel in the region corresponding to the bounding box of each fracture site in the first image is determined as the fracture point corresponding to the bounding box of each fracture site, and the coordinates of each fracture point in the first image are used as the fracture point coordinates of each fracture point. The horizontal coordinate of the fracture point coordinates is the row number of the fracture point in the first image, and the vertical coordinate is the column number of the fracture point in the first image. For example, if the coordinates of the fracture point are (11, 12), then the fracture point is located in the 11th row and 12th column of the second image.

[0049] Optionally, the rehabilitation movements in the alternative multiple fracture rehabilitation plan are preset rehabilitation movements to prevent complications of bone diseases. Further rehabilitation movements to prevent complications of bone diseases are determined as follows: Different fracture points are identified, and for each identified fracture point, the following operations are performed: The corresponding alternative rehabilitation movement, the duration of rehabilitation training performed by the user using that alternative movement, and the results of the user's rehabilitation training using that alternative movement are obtained. These results are used to characterize whether complications of bone diseases occur. Alternative rehabilitation movements for which no complications of bone diseases occur are identified as the corresponding rehabilitation movements to prevent complications of bone diseases for that fracture point, and the duration of rehabilitation training for that alternative movement is identified as the exercise duration corresponding to that rehabilitation movement.

[0050] Optionally, all rehabilitation plans can be recommended to the user. Alternatively, one rehabilitation plan can be randomly selected from the obtained plans and recommended to the user.

[0051] The above methods not only allow for the matching of rehabilitation training plans to users for each fracture point, making it easier for users to carry out rehabilitation training, but also reduce the risk of complications caused by rehabilitation training for multiple fractures.

[0052] Optionally, rehabilitation plans can be recommended based on the location information of the concurrent injury sites, including:

[0053] The location information of the concurrent injury sites is looked up in the preset rehabilitation plan library to obtain the rehabilitation plan for multiple fractures; the rehabilitation plan library stores the correspondence between rehabilitation plans for multiple fractures and target location information; the target location information is used to characterize the concurrent injury sites.

[0054] We recommend rehabilitation programs for multiple fractures to users.

[0055] In this embodiment, the rehabilitation plan library stores rehabilitation plans for multiple fractures, including concurrent rehabilitation actions. These concurrent rehabilitation actions are determined as follows: different concurrent injury sites are identified, and for each identified concurrent injury site, the following operations are performed: the corresponding rehabilitation action for the concurrent injury site, the duration of rehabilitation training performed by the user using that action, and the result of the user's rehabilitation training using that action are obtained. This result is used to characterize whether rehabilitation has been achieved. Rehabilitation actions for concurrent injury sites with a successful outcome are defined as the concurrent rehabilitation actions corresponding to that injury site, and the duration of rehabilitation training corresponding to that action is defined as the exercise duration corresponding to that action.

[0056] Fracture patients are likely to experience complications before starting rehabilitation training. The above solution predicts the location of the concurrent injury and matches it with a corresponding rehabilitation plan recommended to the user, so that the user can carry out rehabilitation training for the concurrent injury sites other than the fracture site according to the matched rehabilitation plan.

[0057] Furthermore, after recommending a rehabilitation plan based on the location information of the concurrent injury sites, it also includes:

[0058] Obtain the user's heart rate information over a preset time period.

[0059] Based on heart rate information and exercise duration, determine whether the user's rehabilitation behavior carries a risk of fracture malunion.

[0060] If a user's rehabilitation activities pose a risk of malunion of the fracture, the user should be alerted to the risk of malunion.

[0061] Optionally, obtaining the user's heart rate information within a preset time period includes: obtaining the user's heart rate at a preset time, and obtaining the user's heart rate data within the preset time period if the heart rate reaches the preset heart rate value. For example, the exercise duration for knee rehabilitation exercises is half an hour, the preset time period is from 10:00 to 11:00 every day, and the preset time is 9:55. Then, at 9:55 every day, the user's heart rate is checked to see if it reaches the preset heart rate value. If the user's heart rate reaches the preset heart rate value, the user's heart rate data from 10:00 to 11:00 is recorded. This method allows users to trigger the recording of rehabilitation training data through pre-training warm-up, facilitating healthier and safer rehabilitation training.

[0062] Optionally, the risk of malunion of fractures can be determined based on heart rate information and exercise duration, including:

[0063] Obtain the time length corresponding to the heart rate information reaching the preset heart rate threshold.

[0064] If the absolute value of the difference between the duration of rehabilitation and the duration of exercise is greater than a preset risk threshold, the user's rehabilitation behavior is determined to have a risk of malunion of fracture; otherwise, the user's rehabilitation behavior is determined not to have a risk of malunion of fracture.

[0065] Combination Figure 3 As shown, this disclosure provides a rehabilitation plan recommendation device for multiple fractures, comprising:

[0066] The acquisition module 301 is configured to acquire a first image representing multiple fractures, wherein the first image is an image on a preset human skeletal image with bounding boxes marking multiple fracture sites. The determination module 302 is configured to determine the location information of concurrent injury sites based on the first image. The recommendation module 303 is configured to recommend a rehabilitation plan based on the location information of the concurrent injury sites; the rehabilitation plan includes rehabilitation exercises and the corresponding exercise durations.

[0067] This embodiment of the disclosure acquires images of multiple fracture sites marked with bounding boxes on a preset human skeletal image, and then determines the location information of concurrent injuries based on these images. This allows for the recommendation of rehabilitation plans based on the location information of the concurrent injuries. In this way, targeted rehabilitation training plans can be recommended for users with multiple fractures.

[0068] Optionally, the determining module 302 is configured to determine the location information of the concurrent injury site based on the first image by performing the following steps:

[0069] Step 1: Determine the fracture points in the first image. Optionally, any point, such as the center pixel, corresponding to the bounding box of each fracture site in the first image can be determined as a fracture point, and the coordinates of each fracture point in the first image can be used as the fracture point coordinates. Specifically, the horizontal coordinate of the fracture point coordinates is the row number of the fracture point in the first image, and the vertical coordinate is the column number of the fracture point in the first image. For example, if the coordinates of the fracture point are (11, 12), then the fracture point is located in the 11th row and 12th column of the second image.

[0070] Step 2: Connect the fracture points in the first image with lines.

[0071] Step 3: Calculate for each connection line And calculate for each connection. Where Can is the offset value of the fracture point connection line, Canwz is the length value of the fracture point connection line, x1 is the x-coordinate of the first fracture point in the connection line, x2 is the x-coordinate of the second fracture point in the connection line, x1≥x2, y1 is the y-coordinate of the first fracture point in the connection line, y2 is the y-coordinate of the second fracture point in the connection line, and a is a preset constant, 0.01≤a≤0.0000001.

[0072] Step 4: Obtain the fracture point connection features for each connecting line. This involves calculating the fracture point connection features for each connecting line. Obtain the characteristics of the fracture point connection line, where D bf The fracture point connection features are defined by α, where α is the connection offset base and β is the connection length base, both of which are greater than 0. Optionally, different candidate human skeleton images correspond to different α values ​​and different β values. When a user selects a human skeleton image from the candidate images, the α and β values ​​corresponding to the first image are determined. The α and β values ​​corresponding to the first image are also obtained when acquiring the first image. This method reflects the degree of force dispersion between two fracture points through the fracture point connection offset and fracture point connection length values. The location of the fracture area is defined by the midpoint of the line segment. Simultaneously, personalized connection offset and connection length bases are used to correct the user's fracture point connection. This allows for accurate acquisition of corresponding fracture point connection features for users with different body postures, enabling the identification of concurrent injury sites using these fracture point connection features.

[0073] Step 5: Perform a lookup operation in the preset candidate coordinate library to match the candidate coordinates corresponding to the line features of each fracture point. The candidate coordinate library stores the line features of fracture points, candidate coordinates, and the correspondence between them. Optionally, the candidate coordinates are coordinate values ​​in the pixel coordinate system of the first image, that is, the horizontal coordinate value of the candidate coordinate represents the row number in the first image, and the vertical coordinate value of the candidate coordinate represents the column number in the first image.

[0074] Step Six: Define a predetermined number of regions containing candidate coordinates in the first image as candidate regions for concurrent injury sites in the first image. The distance between candidate coordinates within each candidate region is within a predetermined range. Clustering of the candidate coordinates allows for the determination of concurrent injury sites based on the degree of concentration of the candidate coordinates. In some embodiments, by setting a predetermined number, multiple candidate regions for concurrent injury sites in the first image can be clustered.

[0075] Step 7: In the first image, identify any point (e.g., the center pixel) within each candidate region for concurrent damage as a concurrent damage site. Determine the coordinates of this point as the coordinates of the concurrent damage site. The x-coordinate of the center pixel in the first image is its row number, and the y-coordinate is its column number. For example, if the center pixel's coordinates are (11, 12), it is located in the 11th row and 12th column of the first image. This determines the location information of the concurrent damage site.

[0076] In some embodiments, the first image size corresponding to candidate human skeleton images of different sizes is the same, that is, the first image size is always the same, while the candidate human skeleton images have different sizes.

[0077] Since different users typically have different heights and skeletal structures, the above scheme allows users to select human skeletal images that are similar to their own body shape for labeling, thereby making the prediction of secondary injury sites for multiple fractures more accurate based on human skeletal images that are similar to the user's body shape.

[0078] Optionally, the determining module 302 is configured to determine the location information of the concurrent injury site based on the first image in the following manner:

[0079] The first image is input into a preset concurrent injury site prediction model to obtain a second image; the second image is an image with bounding boxes of concurrent injury sites marked on a preset human skeleton image. The location information of the concurrent injury site is determined based on the concurrent injury site bounding boxes. The concurrent injury site prediction model is obtained by training a preset neural network model using training samples with concurrent injury site bounding boxes; the training samples include human skeleton images marked with fracture site bounding boxes. Optionally, the first and second images are the same size. The human skeleton images in the training samples and the second image are the same as the human skeleton image in the first image.

[0080] Optionally, the determining module 302 is configured to determine the location information of the concurrent damage site based on the concurrent damage site bounding box in the following manner:

[0081] In the second image, any point within the bounding box of the concurrent injury site is designated as a reference point. The coordinates of this reference point are used as the location information of the concurrent injury site.

[0082] In some embodiments, any pixel in the region corresponding to the bounding box of the concurrent injury site in the second image is determined as a reference point. Optionally, the center pixel in the region corresponding to the bounding box of the concurrent injury site in the second image is determined as a reference point, and the coordinates of the center pixel in the second image are used as the location information of the concurrent injury site. The horizontal coordinate of the center pixel in the second image is the row number of the center pixel in the second image, and the vertical coordinate is the column number of the center pixel in the second image. For example, if the coordinates of the center pixel are (11, 12), then the center pixel is located in the 11th row and 12th column of the second image.

[0083] Optionally, the recommendation module 303 is configured to recommend rehabilitation plans based on the location information of the concurrent injury sites in the following manner:

[0084] In the first image, any point in the region corresponding to the bounding box of each fracture site is determined as the fracture point, and the coordinates of each fracture point are obtained.

[0085] In the preset rehabilitation plan library, the location information of the concurrent injury sites is looked up to obtain alternative rehabilitation plans for multiple fractures. The rehabilitation plan library stores the correspondence between the rehabilitation plan for multiple fractures, the coordinates of the first human body region, and the coordinates of the second human body region. The coordinates of the first human body region are used to represent the fracture point, and the coordinates of the second human body region are used to represent the reference point.

[0086] The coordinates of each fracture point are matched in the alternative multiple fracture rehabilitation plan to obtain the corresponding rehabilitation plan for each fracture point and recommend it to the user; the rehabilitation plan is either an alternative multiple fracture rehabilitation plan with any one fracture point coordinate, or an alternative multiple fracture rehabilitation plan with any number of fracture point coordinates.

[0087] In some embodiments, any pixel in the region corresponding to the bounding box of each fracture site in the first image is determined as a fracture point. Optionally, the center pixel in the region corresponding to the bounding box of each fracture site in the first image is determined as the fracture point corresponding to the bounding box of each fracture site, and the coordinates of each fracture point in the first image are used as the fracture point coordinates of each fracture point. The horizontal coordinate of the fracture point coordinates is the row number of the fracture point in the first image, and the vertical coordinate is the column number of the fracture point in the first image. For example, if the coordinates of the fracture point are (11, 12), then the fracture point is located in the 11th row and 12th column of the second image.

[0088] Optionally, the rehabilitation movements in the alternative multiple fracture rehabilitation plan are preset rehabilitation movements to prevent complications of bone diseases. Further, the rehabilitation movements to prevent complications of bone diseases are determined as follows: different fracture points are identified, and for each identified fracture point, the following operations are performed: obtaining the corresponding alternative rehabilitation movement, the length of time the user performs rehabilitation training with that alternative movement, and the result of the user's rehabilitation training with that alternative movement. This result is used to characterize whether complications of bone diseases occur. Alternative rehabilitation movements for which no complications of bone diseases occur are determined as the corresponding rehabilitation movements to prevent complications of bone diseases for that fracture point, and the length of time corresponding to the rehabilitation training with that alternative movement is determined as the exercise time length corresponding to that rehabilitation movement.

[0089] Optionally, the recommendation module 303 recommends all rehabilitation plans to the user. Optionally, the recommendation module 303 randomly selects one rehabilitation plan from the obtained plans and recommends it to the user.

[0090] The above methods not only allow for the matching of rehabilitation training plans to users for each fracture point, making it easier for users to carry out rehabilitation training, but also reduce the risk of complications caused by rehabilitation training for multiple fractures.

[0091] Optionally, the recommendation module 303 is configured to recommend rehabilitation plans based on the location information of the concurrent injury sites in the following manner:

[0092] The location information of the concurrent injury sites is looked up in the preset rehabilitation plan library to obtain the rehabilitation plan for multiple fractures; the rehabilitation plan library stores the correspondence between rehabilitation plans for multiple fractures and target location information; the target location information is used to characterize the concurrent injury sites.

[0093] We recommend rehabilitation programs for multiple fractures to users.

[0094] In this embodiment, the rehabilitation plan library stores rehabilitation plans for multiple fractures, including concurrent rehabilitation actions. These concurrent rehabilitation actions are determined as follows: different concurrent injury sites are identified, and for each identified concurrent injury site, the following operations are performed: obtaining the corresponding rehabilitation action for the concurrent injury site, the duration of rehabilitation training performed by the user using that action, and the result of the user's rehabilitation training using that action. This result is used to characterize whether rehabilitation has been achieved. Rehabilitation actions for concurrent injury sites with a positive outcome are defined as the concurrent rehabilitation actions corresponding to that concurrent injury site, and the duration of rehabilitation training corresponding to that action is defined as the exercise duration corresponding to that action. Fracture patients may experience concurrent symptoms before rehabilitation training begins. The above scheme predicts concurrent injury sites and matches corresponding rehabilitation plans to the user, facilitating rehabilitation training for concurrent injury sites other than the fracture site according to the matched plan.

[0095] Combination Figure 4 As shown, this disclosure provides an electronic device including a processor 400 and a memory 401. Optionally, the device may further include a communication interface 402 and a bus 403. The processor 400, communication interface 402, and memory 401 can communicate with each other via the bus 403. The communication interface 402 can be used for information transmission. The processor 400 can call logical instructions in the memory 401 to execute the rehabilitation plan recommendation method for multiple fractures described in the above embodiments.

[0096] The electronic device provided in this disclosure acquires images of multiple fracture sites marked with bounding boxes on a preset human skeletal image, and then determines the location information of concurrent injuries based on these images. This allows for the recommendation of rehabilitation plans based on the location information of the concurrent injuries. In this way, targeted rehabilitation training plans can be recommended for users with multiple fractures.

[0097] Alternatively, the electronic device may be a server, computer, tablet, or smartphone.

[0098] The user selects a pre-defined human skeleton image using a pre-defined bounding box on their user terminal, thus marking the fracture points and obtaining a first image. The electronic device receives this first image from the user's terminal and determines the location information of any concurrent injuries based on it. Then, the electronic device recommends a rehabilitation plan based on the location information of the concurrent injuries.

[0099] In some embodiments, the fracture point and reference point are only used to represent the coordinate position in the first or second image. The fracture point and reference point may not be on the human skeleton image, but they can still achieve the recommendation of the rehabilitation plan.

[0100] Furthermore, the logic instructions in the aforementioned memory 401 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium.

[0101] The memory 401, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as program instructions / modules corresponding to the methods in the embodiments of this disclosure. The processor 400 executes functional applications and data processing by running the program instructions / modules stored in the memory 401, that is, implementing the rehabilitation plan recommendation method for multiple fractures in the above embodiments.

[0102] The memory 401 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the terminal device. Furthermore, the memory 401 may include high-speed random access memory and may also include non-volatile memory.

[0103] This disclosure provides a storage medium storing program instructions that, when executed, perform the above-described recommended rehabilitation plan method for multiple fractures.

[0104] The aforementioned storage media can be transient computer-readable storage media or non-transitory computer-readable storage media, including: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks or optical disks, and other media that can store program code.

[0105] The foregoing description and accompanying drawings fully illustrate embodiments of this disclosure to enable those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, procedural, and other changes. The embodiments represent only possible variations. Individual components and functions are optional unless explicitly required, and the order of operation may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the terminology used in this application is for describing embodiments only and is not intended to limit the claims. As used in the description of embodiments and claims, the singular forms “a,” “an,” and “the” are intended to equally include the plural forms unless the context clearly indicates otherwise. Similarly, the term “and / or” as used in this application means including one or more of the associated listed items and all possible combinations thereof. Additionally, when used in this application, the term "comprise" and its variations "comprises" and / or "comprising" refer to the presence of stated features, integrals, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof. Without further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the process, method, or apparatus that includes said element. In this document, each embodiment may focus on the differences from other embodiments, and similar or identical parts between embodiments can be referred to mutually. For methods, products, etc., disclosed in the embodiments, if they correspond to the method section disclosed in the embodiments, the relevant parts can be referred to the description of the method section.

[0106] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments of this disclosure. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0107] The methods and products (including but not limited to devices and equipment) disclosed in the embodiments herein can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units may be merely a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed units may be through some interfaces, and the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected to implement this embodiment according to actual needs. Furthermore, the functional units in the embodiments of this disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0108] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than that shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. Each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

Claims

1. A method for recommending rehabilitation programs for multiple fractures, characterized in that, include: Acquire a first image for characterizing multiple fractures, wherein the first image is an image in which the bounding boxes of multiple fracture sites are marked on a preset human skeletal image; The location information of the concurrent injury site is determined based on the first image; A rehabilitation plan is recommended based on the location information of the concurrent injury site; the rehabilitation plan includes rehabilitation movements and the corresponding exercise duration. The determination of the location information of the concurrent injury site based on the first image includes: Step 1: In the first image, determine any point in the region corresponding to the bounding box of each fracture site as the fracture point, and use the coordinates of each fracture point in the first image as the fracture point coordinates of each fracture point. Step 2: Connect each pair of fracture points in the first image with a line; Step 3: Calculate for each connection line And calculate for each connection. Where Can is the offset value of the fracture point connection line, Canwz is the length value of the fracture point connection line, x1 is the x-coordinate of the first fracture point in the connection line, x2 is the x-coordinate of the second fracture point in the connection line, x1≥x2, y1 is the y-coordinate of the first fracture point in the connection line, y2 is the y-coordinate of the second fracture point in the connection line, and a is a preset constant. Step 4: Calculate for each connection line Obtain the characteristics of the fracture point connection line; where D bf The characteristics of the fracture point connection line are defined by α, where α is the baseline for line offset and β is the baseline for line length. Both α and β are greater than 0. Step 5: Perform a lookup operation in the preset candidate coordinate library to match the candidate coordinates corresponding to the line features of each fracture point; the candidate coordinate library stores the line features of fracture points, candidate coordinates, and the correspondence between them; Step 6: Determine the area containing a preset number of candidate coordinates in the first image as the candidate area for concurrent injury in the first image, and the distance between each candidate coordinate in the candidate area for concurrent injury is within a preset range. Step 7: In the first image, determine any point in the candidate area of ​​each concurrent injury site as the concurrent injury site, and determine the coordinates of any point in the candidate area of ​​each concurrent injury site in the first image as the coordinates of the concurrent injury site.

2. The method according to claim 1, characterized in that, Determining the location information of the concurrent injury site based on the first image also includes: The first image is input into a preset concurrent injury site prediction model to obtain a second image; the second image is an image marked with the bounding box of the concurrent injury site on a preset human skeleton image; The location information of the concurrent damage site is determined based on the bounding box of the concurrent damage site; The concurrent injury site prediction model is obtained by training a preset neural network model with training samples containing bounding boxes of concurrent injury sites; the training samples include human skeleton images marked with bounding boxes of fracture sites.

3. The method according to claim 2, characterized in that, The location information of the concurrent injury site is determined based on the bounding box of the concurrent injury site, including: In the second image, any point in the region corresponding to the bounding box of the concurrent injury site is determined as a reference point; The coordinates of the reference point are used as the location information of the concurrent damage site.

4. The method according to claim 3, characterized in that, A rehabilitation plan is recommended based on the location information of the concurrent injury site, including: In the first image, any point in the region corresponding to the bounding box of each fracture site is determined as a fracture point, and the coordinates of each fracture point are obtained. A lookup operation is performed on the location information of the concurrent injury sites in a preset rehabilitation plan library to obtain alternative rehabilitation plans for multiple fractures. The rehabilitation plan library stores the correspondence between rehabilitation plans for multiple fractures, coordinates of the first human body region, and coordinates of the second human body region. The coordinates of the first human body region are used to characterize the fracture point, and the coordinates of the second human body region are used to characterize the reference point. In the alternative rehabilitation plans for multiple fractures, a table lookup operation is performed on the coordinates of each fracture point to determine the rehabilitation plan recommended to the user; the rehabilitation plan is either an alternative rehabilitation plan for multiple fractures corresponding to any one fracture point coordinate, or an alternative rehabilitation plan for multiple fractures corresponding to any number of fracture point coordinates.

5. The method according to claim 3, characterized in that, A rehabilitation plan is recommended based on the location information of the concurrent injury site, including: A lookup operation is performed on the location information of the concurrent injury sites in a preset rehabilitation plan library to obtain a rehabilitation plan for multiple fractures; the rehabilitation plan library stores the correspondence between rehabilitation plans for multiple fractures and target location information; the target location information is used to characterize the concurrent injury sites; The multiple fracture rehabilitation program will be recommended to users.

6. The method according to claim 1, characterized in that, After recommending a rehabilitation plan based on the location information of the concurrent injury site, the plan also includes: Obtain the user's heart rate information over a preset time period; Based on the heart rate information and the duration of exercise, determine whether the user's rehabilitation behavior carries a risk of fracture malunion. If a user's rehabilitation activities pose a risk of malunion of the fracture, the user should be alerted to the risk of malunion.

7. The method according to claim 6, characterized in that, Determining whether a user's rehabilitation behavior carries a risk of malunion of fractures based on the heart rate information and the duration of exercise includes: Obtain the time length corresponding to the heart rate information reaching the preset heart rate threshold; If the absolute value of the difference between the duration of the exercise and the duration of the training is greater than a preset risk threshold, it is determined that the user's rehabilitation behavior carries a risk of malunion of the fracture; otherwise, it is determined that the user's rehabilitation behavior does not carry a risk of malunion of the fracture.

8. A device for recommending rehabilitation plans for multiple fractures, characterized in that, The device includes the method for recommending rehabilitation programs for multiple fractures as described in any one of claims 1 to 7, wherein the device comprises: The acquisition module is configured to acquire a first image for characterizing multiple fractures, wherein the first image is an image in which the bounding boxes of multiple fracture sites are marked on a preset human skeletal image; The determination module is configured to determine the location information of the concurrent injury site based on the first image; The recommendation module is configured to recommend rehabilitation plans based on the location information of the concurrent injury site; the rehabilitation plan includes rehabilitation movements and the corresponding exercise time lengths for the rehabilitation movements.

9. An electronic device comprising a processor and a memory storing program instructions, characterized in that, The processor is configured to, when running the program instructions, execute the recommended method for rehabilitation planning for multiple fractures as described in any one of claims 1 to 7.

10. A storage medium storing program instructions, characterized in that, When the program instructions are executed, they perform the recommended rehabilitation plan method for multiple fractures as described in any one of claims 1 to 7.

Images