Orthopedic model data acquisition method, device and equipment, medium and computer program product

Abstract

The invention relates to the technical field of image processing, in particular to an orthopedic model data acquisition method, device and equipment, a medium and a computer program product. Filtering is performed on an initial bone image based on a preset filtering model combination, and a filtering effect is analyzed in combination with a corresponding denoised bone image; the preset filtering parameters are dynamically adjusted according to the filtering effect, it is ensured that the filtering parameters are accurately matched with the actual requirements of the image, statistical analysis is conducted on the reference filtering parameters, parameter sub-ranges are divided, the number is counted, a clear data distribution basis is provided for screening target filtering model combinations, the potential law of data can be mined, and the screening efficiency is improved. According to the bone image filtering method and device, parameter selection is optimized, the target filtering model combination of the optimal parameter is determined according to the distribution of the filtering parameters, it is guaranteed that the bone image of each part can obtain an adaptive filtering scheme, the accuracy and reliability of the filtering effect are remarkably improved, the quality of the bone image is effectively improved, and a guarantee is provided for obtaining high-quality orthopedic model data.

Description

Technical Field

[0001] The present disclosure generally relates to the field of image processing technology, and more particularly to a method, device, equipment, medium and computer program product for acquiring orthopedic model data. Background Art

[0002] In orthopedic medical image processing, it is crucial to accurately obtain high-quality orthopedic model data. Therefore, filtering and denoising the collected orthopedic images plays an important role. Traditional image filtering methods have many shortcomings when processing bone images.

[0003] In the field of image filtering, in order to obtain better image effects, combined filtering methods are often used to simply superimpose multiple filtering algorithms or combine them in a fixed order. For example, first use the mean filter for preliminary noise reduction, then use the sharpening filter to enhance the image edge, or first use the Gaussian filter to retain the image edge, then use the median filter to remove salt and pepper noise, and flexibly adjust the weights and order of each filtering method to achieve a better filtering effect.

[0004] However, in bone image processing, bone images of different parts have unique structures and noise characteristics. The existing image combination filtering method does not take into account the noise differences in different parts. It usually adopts a general combination method and fixed filtering parameters, and does not perform personalized optimization processing for bone images of different parts. As a result, the quality of the acquired orthopedic model data is difficult to guarantee, and it is impossible to provide accurate and reliable basic data for the subsequent construction of orthopedic models.

[0005] Therefore, in the task of acquiring orthopedic model data, how to improve the quality of orthopedic model data acquisition becomes an urgent problem to be solved. Summary of the invention

[0006] In view of the above-mentioned defects or deficiencies in the prior art, it is desirable to provide a method, apparatus, device, medium and computer program product for acquiring orthopedic model data.

[0007] In a first aspect, an embodiment of the present application provides a method for obtaining orthopedic model data, and the method for obtaining orthopedic model data comprises the following steps: S1, obtain N part labels, a preset filter model combination corresponding to each part label, several initial bone images corresponding to each part label, and a denoised bone image corresponding to each initial bone image, wherein each preset filter model combination corresponds to a preset filter parameter, N>1.

[0008] S2, for any initial bone image corresponding to any part label, based on the preset filtering model combination corresponding to the current part label, the current initial bone image and the denoised bone image corresponding to the current initial bone image, the preset filtering parameters corresponding to the current part label are updated to obtain the reference filtering parameters of the current part label relative to the current initial bone image.

[0009] S3, according to the preset step size and all reference filtering parameters corresponding to the current part label, obtain several filtering parameter sub-ranges corresponding to the current part label and the number of reference filtering parameters contained in each filtering parameter sub-range.

[0010] S4, acquiring a target filter model combination corresponding to the current part label according to the number of reference filter parameters included in each filter parameter sub-range.

[0011] S5, when the bone image to be processed is obtained, a target filtering model combination corresponding to the bone image to be processed is obtained according to the part label corresponding to the bone image to be processed.

[0012] S6, filtering the bone image to be processed according to the target filtering model combination corresponding to the bone image to be processed, and obtaining a target bone image, wherein the target bone image belongs to orthopedic model data.

[0013] In a second aspect, an embodiment of the present application provides a device for acquiring orthopedic model data, the device for acquiring orthopedic model data comprising: The data acquisition module is used to obtain N part labels, a preset filter model combination corresponding to each part label, a number of initial bone images corresponding to each part label, and a denoised bone image corresponding to each initial bone image, wherein each preset filter model combination corresponds to a preset filter parameter, N>1.

[0014] The parameter updating module is used to update the preset filtering parameters corresponding to the current part label for any initial bone image corresponding to any part label according to the preset filtering model combination corresponding to the current part label, the current initial bone image and the denoised bone image corresponding to the current initial bone image, so as to obtain the reference filtering parameters of the current part label relative to the current initial bone image.

[0015] The parameter analysis module is used to obtain several filter parameter sub-ranges corresponding to the current part label and the number of reference filter parameters contained in each filter parameter sub-range according to the preset step size and all reference filter parameters corresponding to the current part label.

[0016] The parameter determination module is used to obtain the target filter model combination corresponding to the current part label according to the number of reference filter parameters contained in each filter parameter sub-range.

[0017] The model acquisition module is used to acquire the target filtering model combination corresponding to the bone image to be processed according to the part label corresponding to the bone image to be processed when the bone image to be processed is acquired.

[0018] The image filtering module is used to filter the bone image to be processed according to the target filtering model combination corresponding to the bone image to be processed, and obtain the target bone image, wherein the target bone image belongs to the orthopedic model data.

[0019] In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the embodiment of the present application when executing the program.

[0020] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in the embodiment of the present application.

[0021] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which implements the method described in the embodiment of the present application when executed by a processor.

[0022] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings: Figure 1 A diagram showing an implementation environment architecture of a method for acquiring orthopedic model data provided in an embodiment of the present application; Figure 2 A schematic diagram showing a flow chart of a method for acquiring orthopedic model data provided in an embodiment of the present application; Figure 3 Another schematic diagram of the process of obtaining orthopedic model data provided by an embodiment of the present application is shown; Figure 4 Another schematic diagram of the process of obtaining orthopedic model data provided by an embodiment of the present application is shown; Figure 5 Another schematic diagram of the process of obtaining orthopedic model data provided by an embodiment of the present application is shown; Figure 6 Another schematic diagram of the process of obtaining orthopedic model data provided by an embodiment of the present application is shown; Figure 7Another schematic diagram of the process of obtaining orthopedic model data provided by an embodiment of the present application is shown; Figure 8 An exemplary structural block diagram of an apparatus for acquiring orthopedic model data provided by an embodiment of the present application is shown; Fig. 9 A schematic diagram of the structure of a computer system of an electronic device or server suitable for implementing an embodiment of the present application is shown.

[0024] Figure numerals: 101-terminal device, 102-server; 800-a device for acquiring orthopedic model data, 81-data acquisition module, 82-parameter updating module, 83-parameter analysis module, 84-parameter determination module, 85-model acquisition module, 86-image filtering module; 901-CPU, 902-ROM, 903-RAM, 904-bus, 905-I / O interface, 906-input part, 907-output part, 908-storage part, 909-communication part, 910-drive, 911-removable medium. DETAILED DESCRIPTION

[0025] The present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the invention are shown in the accompanying drawings.

[0026] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0027] For the specific implementation environment of the orthopedic model data acquisition method proposed in this application, please refer to Figure 1 . Figure 1 The following is a diagram showing the implementation environment architecture of the method for acquiring orthopedic model data provided in an embodiment of the present application.

[0028] like Figure 1 As shown, the implementation environment architecture includes: a terminal device 101 and a server 102 .

[0029] The terminal device 101 can be a desktop computer, a laptop computer, a smart phone, a tablet computer, an e-book reader, smart glasses, a smart watch, etc., but is not limited thereto.

[0030] The server 102 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server 102 is used to provide replacement entries to the terminal device 101 and execute a recognition strategy for abnormal target entries.

[0031] The terminal device 101 and the server 102 are directly or indirectly connected via wired or wireless communication. Optionally, the wireless network or wired network uses standard communication technology and / or protocols. The network is usually the Internet, and can also be any network, including but not limited to a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a private network or any combination of a virtual private network.

[0032] The method for acquiring orthopedic model data proposed in the present application can be implemented by an orthopedic model data acquisition device, and the orthopedic model data acquisition device can be installed on a terminal device or a server.

[0033] In order to further illustrate the technical solution provided by the embodiment of the present application, this is described in detail below in conjunction with the accompanying drawings and specific implementation methods. Although the embodiment of the present application provides the method operation instruction steps shown in the following embodiments or drawings, more or fewer operation instruction steps may be included in the method based on routine or no creative labor. In the steps where there is no necessary causal relationship logically, the execution order of these steps is not limited to the execution order provided by the embodiment of the present application. The method may be executed in the order of the method shown in the embodiment or drawings or in parallel during the actual processing process or when the device is executed.

[0034] It should be noted that the acquisition or use of data in the embodiments of the present application requires the user's consent. The relevant data can only be obtained after the user's authorization and permission, and the acquisition or use of the data complies with relevant legal provisions.

[0035] Please refer to Figure 2 , Figure 2 FIG. 1 is a flow chart showing a method for obtaining orthopedic model data provided by an embodiment of the present application. Figure 2 As shown, the method for obtaining the orthopedic model data includes: S1, obtain N part labels, a preset filter model combination corresponding to each part label, several initial bone images corresponding to each part label, and a denoised bone image corresponding to each initial bone image, wherein each preset filter model combination corresponds to a preset filter parameter, N>1.

[0036] S2, for any initial bone image corresponding to any part label, based on the preset filtering model combination corresponding to the current part label, the current initial bone image and the denoised bone image corresponding to the current initial bone image, the preset filtering parameters corresponding to the current part label are updated to obtain the reference filtering parameters of the current part label relative to the current initial bone image.

[0037] S3, according to the preset step size and all reference filtering parameters corresponding to the current part label, obtain several filtering parameter sub-ranges corresponding to the current part label and the number of reference filtering parameters contained in each filtering parameter sub-range.

[0038] S4, acquiring a target filter model combination corresponding to the current part label according to the number of reference filter parameters included in each filter parameter sub-range.

[0039] S5, when the bone image to be processed is obtained, a target filtering model combination corresponding to the bone image to be processed is obtained according to the part label corresponding to the bone image to be processed.

[0040] S6, filtering the bone image to be processed according to the target filtering model combination corresponding to the bone image to be processed, and obtaining a target bone image, wherein the target bone image belongs to orthopedic model data.

[0041] Among them, the part label can be the skull, humerus, femur, tibia, wrist joint, ankle joint, etc., which are used to identify different bone parts.

[0042] Each part label corresponds to a set of preset filter model combinations. For example, the skull structure is relatively complex, with many bone sutures, holes and relatively flat areas. Its morphology, structural details and relationship with surrounding tissues need to be clearly displayed in the image, and noise interference should be suppressed to avoid affecting the observation of subtle structures. Therefore, Gaussian filtering combined with wavelet filtering can be used. Gaussian filtering can effectively remove Gaussian noise in the image, make the image smooth, and retain the general outline of the skull. Wavelet filtering can perform multi-scale analysis on the image, highlight the edge and detail information of the skull, and help observe subtle structures such as sutures. The femur is the longest tubular bone in the human body. In the image, it is necessary to focus on the integrity of the backbone, the thickness of the cortex and the morphology of the joints at both ends. The image contrast and edge clarity are required to be high. Therefore, bilateral filtering combined with Laplace sharpening filtering can be used. Bilateral filtering can better retain the edge information of the femur while removing noise, making the boundaries of the backbone and joints clear. Laplace sharpening filtering can enhance the contrast of the image, highlight the edge features such as the femoral cortex, and facilitate the observation of bone conditions.

[0043] Each preset filter model combination has preset filter parameters, such as the standard deviation of Gaussian filtering, the window size of median filtering, etc.

[0044] The initial bone image is acquired through X-ray, CT and other equipment, and contains noise and other interference information. By performing computer reconstruction and other operations on the initial bone image, the original data obtained from different angles or levels are reconstructed into an intuitive two-dimensional or three-dimensional image, noise interference is removed, image resolution and clarity are enhanced, and detail information is highlighted. The denoised bone image close to the ideal state is obtained as the basis for optimizing the filtering parameters.

[0045] The current initial bone image can be filtered according to the preset filtering model combination corresponding to the current part label, and the filtering effect can be analyzed in combination with the corresponding denoised bone image, so as to update the preset filtering parameters according to the filtering effect to improve the filtering effect of the initial bone image of the corresponding part.

[0046] According to the preset step size, all reference filter parameters under the current part label are analyzed, the reference filter parameters are divided into several filter parameter sub-ranges, and the number of reference filter parameters contained in each sub-range is counted. This will help to find a parameter range that is more representative of the filtering effect through statistical distribution, thereby determining the target filter parameters that are more suitable for the current body part and obtaining a target filter model combination, which is used to filter the bone image to be processed, and obtain a higher quality target bone image as orthopedic model data to be transmitted to the orthopedic model database for subsequent medical research and orthopedic model construction.

[0047] In a specific embodiment, the target filtering model combination includes a first filtering model and a second filtering model, wherein the target filtering parameters include a first filtering parameter and a first weight corresponding to the first filtering model, and a second filtering parameter and a second weight corresponding to the second filtering model.

[0048] The value of each parameter in the target filtering parameters can be obtained by dividing the parameter sub-ranges in step S3, counting the number of parameters and determining the target value in step S4, and further combined to form the target filtering parameters.

[0049] The first filtering parameter obtained according to the above steps is (a 0 , a 1 , a 2 , a 3 , a 4 , a 5 ), the first weight is q 1 , correspondingly, the first filtering model is f(x, y)=a 0 + a 1 ×x+ a 2 ×y+a 3 × 2 + a 4 ×x×y+a 5 ×y 2 The second filter parameters are (Z, Q), and the convolution kernel of size (L, L) is obtained according to Q, where L = (Q-1) / 2. Correspondingly, the second filter model is g(x, y) = (1 / (2×π×Z 2 ))×e^(-((x 2 +y 2 ) / (2×Z 2 ))) represents the coefficient of the convolution kernel at position (x, y), and the second weight is q 2 .

[0050] The pixel value at the position (x, y) in the bone image to be processed is h(x, y). Then, the bone image to be processed is filtered according to the target filter model combination corresponding to the bone image to be processed, and the pixel value at the position (x, y) in the target bone image is obtained as c(x, y)=q 1 ×(h(x, y)×f(x, y))+q 2 ×(Σ u=-L L (Σ v=-L L (h(x+u, y+v)×g(u, v)))). Wherein, h(x+u, y+v) is the value of the pixel at the position (x+u, y+v) in the bone image to be processed.

[0051] In the above, the initial bone image is filtered based on the preset filtering model combination, and the filtering effect is analyzed in combination with the corresponding denoised bone image, so that the preset filtering parameters are dynamically adjusted according to the filtering effect to ensure that the filtering parameters are accurately matched with the actual needs of each image, and the reference filtering parameters are statistically analyzed, the parameter sub-ranges are divided and the number is counted, so as to provide a clear data distribution basis for screening the target filtering parameters, which is helpful to explore the potential laws of the data, optimize the parameter selection, and determine the optimal target filtering parameters and target filtering model combination according to the distribution of the filtering parameters, so as to ensure that the bone images of each part can obtain an adaptive filtering scheme, which significantly improves the accuracy and reliability of the filtering effect, effectively improves the quality of bone images, and provides a guarantee for the acquisition of high-quality orthopedic model data.

[0052] Please refer to Figure 3 , Figure 3 The flowchart of step S2 provided in an embodiment of the present application is shown, and S2 includes the following steps: S21, filtering the current initial bone image according to the preset filter model combination corresponding to the current part label, and obtaining the intermediate bone image corresponding to the current initial bone image.

[0053] S22, obtaining the image difference degree according to the intermediate bone image and the denoised bone image corresponding to the current initial bone image.

[0054] S23, for all the initial bone images corresponding to the current part label and the denoised bone image corresponding to each initial bone image, construct an objective function according to the degree of image difference, and update the preset filtering parameters corresponding to the preset filtering model combination corresponding to the current part label by the gradient descent method until the objective function converges, and determine the updated preset filtering parameters corresponding to the objective function when the convergence of the objective function as the reference filtering parameters of the current part label relative to the current initial bone image.

[0055] Among them, the intermediate bone image is compared with the denoised bone image to quantify the degree of difference, which reflects the gap between the processing effect of the preset filtering model combination on the initial bone image under the current preset filtering parameters and the ideal denoising effect. By clarifying the effect gap, it provides direction and basis for the subsequent adjustment of the filtering parameters.

[0056] In a specific implementation, the grayscale value difference between each pixel in the intermediate bone image and the pixel at the same position in the denoised bone image is obtained respectively, and the average value of the grayscale value differences between all the pixels is determined as the image difference degree between the intermediate bone image and the denoised bone image corresponding to the current initial bone image.

[0057] The gradient descent method can quickly and effectively find the parameter value that minimizes the objective function, that is, the filtering parameter that minimizes the difference between the intermediate bone image and the denoised bone image. Therefore, the updated preset filtering parameters corresponding to the convergence are determined as the reference filtering parameters, which realizes the optimization of the preset filtering parameters, making the filtering parameters more in line with the actual characteristics of the bone image of the current part, thereby improving the filtering effect.

[0058] As mentioned above, from the initial filtering to generate the intermediate bone image, to the quantification of the degree of image difference, and then to the use of the optimization algorithm to update the preset filtering parameters, the reference filtering parameters for the initial bone image of the current part are finally obtained, which helps to better adapt to the characteristics of bone images in different parts, improves the accuracy of the filtering processing, and enables the subsequently processed images to more clearly present the structure and characteristics of the bones, thereby improving the quality of the orthopedic model data.

[0059] Please refer to Figure 4 , Figure 4 The flowchart of step S3 provided in an embodiment of the present application is shown, and S3 includes the following steps: S31, acquiring a total range of filtering parameters corresponding to the current part label according to all reference filtering parameters corresponding to the current part label.

[0060] S32, acquiring a plurality of sub-ranges of filtering parameters corresponding to the current part label according to the preset step size and the total range of filtering parameters corresponding to the current part label.

[0061] S33, according to the inclusion relationship between each reference filtering parameter and each filtering parameter sub-range, obtaining the number of reference filtering parameters included in each filtering parameter sub-range.

[0062] The preset step size determines the fineness of the sub-range, and the specific value of the preset step size can be set by the implementer according to the actual situation, or according to the total range of the filtering parameters. For example, the preset step size d = 0.1 × (ba), where b refers to the upper limit of the total range of the filtering parameters, and a refers to the lower limit of the total range of the filtering parameters.

[0063] By determining the filter parameter sub-range to which each reference filter parameter belongs, the number of reference filter parameters contained in each filter parameter sub-range is counted, and the filter parameter values ​​corresponding to the filter parameter sub-range that appears frequently are more suitable for filtering the part with better effect.

[0064] As mentioned above, from determining the total range of filtering parameters to dividing the filtering parameters into sub-ranges, and then to counting the number of parameters contained in the sub-ranges of filtering parameters, the distribution characteristics of the filtering parameters are gradually and deeply excavated, which is helpful to discover the concentration trend and discrete degree of parameters of bone images in different parts when the filtering processing effect is better, thereby improving the reliability of obtaining subsequent target filtering parameters.

[0065] Please refer to Figure 5 , Figure 5 The flowchart of step S4 provided in an embodiment of the present application is shown, and S4 includes the following steps: S41, determining a filter parameter sub-range corresponding to the maximum value of the number of reference filter parameters as an intermediate range corresponding to the current part label.

[0066] S42, determining the filter parameter corresponding to the center of the middle range as the target filter parameter corresponding to the current part label; S43, obtaining a target filter model combination according to the target filter parameters corresponding to the current part label.

[0067] Among them, the center value of the middle range has certain representativeness and stability, and integrates the characteristics of many reference filter parameters in the range. Therefore, using the center value as the target filter parameter not only avoids the blindness of random selection among many parameters, but also balances the differences of parameters in the range to a certain extent, so that the target filter parameter can better adapt to the filtering needs of the bone image in this part, thereby improving the filtering effect.

[0068] Please refer to Figure 6 , Figure 6 Another flow chart of a method for acquiring orthopedic model data provided by an embodiment of the present application is shown. Each target filter model combination includes M preset filter models of different types, M>1, and the method for acquiring orthopedic model data also includes the following steps: S7, grouping the N part labels according to the target filter model combination corresponding to each part label, and obtaining a plurality of part label combinations, wherein all part labels in the same part label combination correspond to the same M preset filter models.

[0069] S8, for any part label combination, cluster all target filter parameters corresponding to the current part label combination to obtain several isolated target filter parameters corresponding to the current part label combination, several filter parameter sets and the filter parameter center corresponding to each filter parameter set.

[0070] S9, correcting the target filtering parameter corresponding to each part label in the current part label combination according to a number of isolated target filtering parameters corresponding to the current part label combination, a number of filtering parameter sets, and a filtering parameter center corresponding to each filtering parameter set.

[0071] Among them, N part labels are grouped according to the target filtering model combination, and the part labels using the same M preset filtering models are grouped together, which helps to uniformly manage and process parts with similar filtering requirements and reduce repeated operations and calculations.

[0072] By grouping, the filtering strategy can be optimized for each group of part labels, and a common filtering strategy can be formulated for some parts, thereby improving the efficiency of acquiring orthopedic model data.

[0073] For each part label combination, all the corresponding target filter parameters are clustered, similar target filter parameters are grouped together to form a filter parameter set, and the center of each set is found. At the same time, isolated target filter parameters are identified, which helps to discover the inherent laws and distribution patterns between the target filter parameters and provide a basis for subsequent correction of the filter parameters.

[0074] As mentioned above, the part labels with the same filtering model are integrated, which reduces repeated processing steps, improves the efficiency of the entire orthopedic model data acquisition process, and deeply explores the relationship between the target filtering parameters. By correcting the target filtering parameters, the filtering parameters of each part are made more reasonable and accurate, which helps to improve the filtering effect and reduce the filtering error caused by unreasonable parameters, thereby improving the quality of orthopedic model data.

[0075] Please refer to Figure 7 , Figure 7 The flowchart of step S9 provided in an embodiment of the present application is shown, and S9 includes the following steps: S91, for any part label in the current part label combination, if the target filtering parameter corresponding to the current part label is an isolated target filtering parameter, the target filtering parameter corresponding to the current part label is kept unchanged.

[0076] S92: If the target filtering parameter corresponding to the current part label is in the filtering parameter set, the target filtering parameter corresponding to the current part label is corrected to the filtering parameter center corresponding to the corresponding filtering parameter set.

[0077] Among them, the isolated target filtering parameters represent that the part has unique image characteristics or filtering requirements, which are quite different from other parts. Therefore, the unique filtering settings of this part are retained to ensure that the filtering processing for these special parts can accurately reflect their actual conditions, avoid poor filtering effects due to forced unification of parameters, and ensure the accuracy of image processing of special parts.

[0078] The parameters in the filter parameter set have certain similarities and represent a group of parts with similar filtering requirements. Therefore, using the center of the set as the corrected parameter can comprehensively consider the characteristics of all parameters in the set, making the filtering parameters of this part more reasonable and representative, thereby balancing the filtering effects of each part in the set and improving the overall filtering quality and consistency.

[0079] In the above, the uniqueness of the isolated target filtering parameters is taken into account, and the commonality of the set of parts with similar filtering requirements is also paid attention to. By adopting different processing methods, the personalized filtering settings of special parts can be retained, and the parts with similar characteristics can be uniformly optimized, making the filtering processing in the entire orthopedic model data acquisition process more comprehensive and reasonable, thereby improving the accuracy and effectiveness of the filtering processing, and providing a guarantee for obtaining high-quality orthopedic model data.

[0080] It should be noted that although the operations of the method of the present application are described in a particular order in the drawings, this does not require or imply that these operations must be performed in this particular order or that all the operations shown must be performed to achieve the desired results.

[0081] Please refer to Figure 8 , Figure 8 FIG. 8 is a block diagram showing an exemplary structure of an orthopedic model data acquisition device 800 provided in an embodiment of the present application. Figure 8 As shown, the orthopedic model data acquisition device 800 includes: The data acquisition module 81 is used to obtain N part labels, a preset filter model combination corresponding to each part label, a number of initial bone images corresponding to each part label, and a denoised bone image corresponding to each initial bone image, wherein each preset filter model combination corresponds to a preset filter parameter, N>1.

[0082] The parameter updating module 82 is used to update the preset filtering parameters corresponding to the current part label for any initial bone image corresponding to any part label according to the preset filtering model combination corresponding to the current part label, the current initial bone image and the denoised bone image corresponding to the current initial bone image, so as to obtain the reference filtering parameters of the current part label relative to the current initial bone image.

[0083] The parameter analysis module 83 is used to obtain several filter parameter sub-ranges corresponding to the current part label and the number of reference filter parameters contained in each filter parameter sub-range according to the preset step size and all reference filter parameters corresponding to the current part label.

[0084] The parameter determination module 84 is used to obtain the target filter model combination corresponding to the current part label according to the number of reference filter parameters contained in each filter parameter sub-range.

[0085] The model acquisition module 85 is used to acquire the target filtering model combination corresponding to the bone image to be processed according to the part label corresponding to the bone image to be processed when the bone image to be processed is acquired.

[0086] The image filtering module 86 is used to filter the bone image to be processed according to the target filtering model combination corresponding to the bone image to be processed, and obtain the target bone image, wherein the target bone image belongs to the orthopedic model data.

[0087] In a specific implementation, the parameter updating module 82 includes: The image filtering submodule is used to filter the current initial bone image according to the preset filtering model combination corresponding to the current part label, and obtain the intermediate bone image corresponding to the current initial bone image.

[0088] The difference degree acquisition submodule is used to acquire the image difference degree according to the intermediate bone image and the denoised bone image corresponding to the current initial bone image.

[0089] The parameter updating submodule is used to construct an objective function according to the degree of image difference for all initial bone images corresponding to the current part label and the denoised bone image corresponding to each initial bone image, and to update the preset filtering parameters corresponding to the preset filtering model combination corresponding to the current part label by the gradient descent method until the objective function converges, and the updated preset filtering parameters corresponding to the objective function convergence are determined as the reference filtering parameters of the current part label relative to the current initial bone image.

[0090] In a specific implementation, the parameter analysis module 83 includes: The parameter total range acquisition submodule is used to obtain the total range of filtering parameters corresponding to the current part label based on all reference filtering parameters corresponding to the current part label.

[0091] The parameter sub-range acquisition sub-module is used to acquire several filter parameter sub-ranges corresponding to the current part label according to the preset step size and the total filter parameter range corresponding to the current part label.

[0092] The parameter quantity acquisition submodule is used to acquire the quantity of reference filtering parameters included in each filtering parameter subrange according to the inclusion relationship between each reference filtering parameter and each filtering parameter subrange.

[0093] In a specific implementation, the parameter determination module 84 includes: The middle range acquisition submodule is used to determine the filter parameter subrange corresponding to the maximum value of the number of reference filter parameters as the middle range corresponding to the current part label.

[0094] The target filter parameter acquisition submodule is used to determine the filter parameter corresponding to the center of the middle range as the target filter parameter corresponding to the current part label; The target filter model combination acquisition submodule is used to acquire the target filter model combination according to the target filter parameters corresponding to the current part label.

[0095] In a specific implementation, each target filter model combination includes M preset filter models of different types, M>1, and the orthopedic model data acquisition device further includes: The part label combination acquisition module is used to group N part labels according to the target filter model combination corresponding to each part label, and obtain several part label combinations, wherein all part labels in the same part label combination correspond to the same M preset filter models.

[0096] The parameter clustering module is used to cluster all target filter parameters corresponding to the current part label combination for any part label combination, and obtain several isolated target filter parameters corresponding to the current part label combination, several filter parameter sets and the filter parameter center corresponding to each filter parameter set.

[0097] The parameter correction module is used to correct the target filtering parameters corresponding to each part label in the current part label combination according to several isolated target filtering parameters corresponding to the current part label combination, several filtering parameter sets and the filtering parameter center corresponding to each filtering parameter set.

[0098] In a specific implementation, the parameter correction module includes: The first parameter correction submodule is used for keeping the target filtering parameter corresponding to the current part label unchanged for any part label in the current part label combination if the target filtering parameter corresponding to the current part label is an isolated target filtering parameter.

[0099] The second parameter correction submodule is used to correct the target filtering parameter corresponding to the current part label to the filtering parameter center corresponding to the corresponding filtering parameter set if the target filtering parameter corresponding to the current part label is in the filtering parameter set.

[0100] It should be understood that the modules or modules recorded in the orthopedic model data acquisition device 800 are similar to those in the reference Figure 2The steps in the method described above correspond to each other. Thus, the operations and features described above for the method are also applicable to the acquisition device 800 of orthopedic model data and the modules contained therein, and will not be repeated here. The acquisition device 800 of orthopedic model data can be pre-implemented in a browser or other security application of an electronic device, or loaded into a browser or its security application of an electronic device by downloading or the like. The corresponding modules in the acquisition device 800 of orthopedic model data can cooperate with the modules in the electronic device to implement the scheme of the embodiment of the present application.

[0101] For the several modules or units mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0102] Reference below Fig. 9 , Fig. 9 A schematic diagram of the structure of a computer system of an electronic device or server suitable for implementing an embodiment of the present application is shown.

[0103] like Fig. 9 As shown, the computer system includes a CPU 901 (central processing unit), which can perform various appropriate actions and processes according to a program stored in a ROM 902 (read-only memory) or a program loaded from a storage part 908 into a RAM 903 (random access memory). In the RAM 903, various programs and data required for the operation instructions of the system are also stored. The CPU 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0104] The following components are connected to the I / O interface 905: an input section 906 including a keyboard, a mouse, etc.; an output section 907 including a CRT (cathode ray tube), an LCD (liquid crystal display), etc., and a speaker, etc.; a storage section 908 including a hard disk, etc.; and a communication section 909 including a network interface card such as a LAN card, a modem, etc. The communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the I / O interface 905 as needed. A removable medium 911, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 910 as needed so that a computer program read therefrom is installed into the storage section 908 as needed.

[0105] In particular, according to an embodiment of the present application, the above reference flow chart Figure 2The described process can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer readable medium, and the computer program includes a program code for executing the method shown in the flow chart. In such an embodiment, the computer program includes a program code for executing the method shown in the flow chart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 909, and / or installed from the removable medium 911. When the computer program is executed by the CPU 901, the above-mentioned functions defined in the system of the present application are executed.

[0106] It should be noted that the computer-readable medium shown in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, RAM, ROM, an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a CD-ROM (portable compact disk read-only memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium such as a computer-readable storage medium that can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, device or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0107] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operating instructions of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the aforementioned module, program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, the boxes represented by two connections can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operating instruction, or can be implemented with a combination of dedicated hardware and computer instructions.

[0108] The units or modules involved in the embodiments described in the present application may be implemented by software or hardware. The units or modules described may also be arranged in a processor. The names of these units or modules do not, in some cases, constitute limitations on the units or modules themselves.

[0109] As another aspect, the present application further provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiment, or may exist independently without being assembled into the electronic device. The above computer-readable storage medium stores one or more programs, and when the above programs are used by one or more processors to execute the method for acquiring orthopedic model data described in the present application.

[0110] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present application (but not limited to) by each other to form a technical solution.

Claims

1. A method for acquiring orthopedic model data, characterized in that: The acquisition method comprises: S1, obtaining N part labels, a preset filter model combination corresponding to each part label, a number of initial bone images corresponding to each part label, and a denoised bone image corresponding to each initial bone image, wherein each preset filter model combination corresponds to a preset filter parameter, N>1; S2, for any initial bone image corresponding to any part label, according to the preset filtering model combination corresponding to the current part label, the current initial bone image and the denoised bone image corresponding to the current initial bone image, the preset filtering parameters corresponding to the current part label are updated to obtain the reference filtering parameters of the current part label relative to the current initial bone image; S3, according to the preset step size and all reference filtering parameters corresponding to the current part label, obtaining several filtering parameter sub-ranges corresponding to the current part label and the number of reference filtering parameters contained in each filtering parameter sub-range; S4, obtaining a target filter model combination corresponding to the current part label according to the number of reference filter parameters contained in each filter parameter sub-range; S5, when the bone image to be processed is obtained, according to the part label corresponding to the bone image to be processed, obtaining the target filtering model combination corresponding to the bone image to be processed; S6, filtering the bone image to be processed according to the target filtering model combination corresponding to the bone image to be processed to obtain a target bone image, wherein the target bone image belongs to orthopedic model data.

2. The method for acquiring orthopedic model data according to claim 1, characterized in that: S2 includes the following steps: S21, filtering the current initial bone image according to the preset filter model combination corresponding to the current part label, and obtaining the intermediate bone image corresponding to the current initial bone image; S22, obtaining the degree of image difference according to the intermediate bone image and the denoised bone image corresponding to the current initial bone image; S23, for all the initial bone images corresponding to the current part label and the denoised bone image corresponding to each initial bone image, construct an objective function according to the degree of image difference, and update the preset filtering parameters corresponding to the preset filtering model combination corresponding to the current part label by the gradient descent method until the objective function converges, and determine the updated preset filtering parameters corresponding to the objective function when the objective function converges as the reference filtering parameters of the current part label relative to the current initial bone image.

3. The method for acquiring orthopedic model data according to claim 1, characterized in that: S3 includes the following steps: S31, acquiring a total range of filtering parameters corresponding to the current part label according to all reference filtering parameters corresponding to the current part label; S32, acquiring a plurality of sub-ranges of filtering parameters corresponding to the current part label according to the preset step size and the total range of filtering parameters corresponding to the current part label; S33, according to the inclusion relationship between each reference filtering parameter and each filtering parameter sub-range, obtaining the number of reference filtering parameters included in each filtering parameter sub-range.

4. The method for acquiring orthopedic model data according to claim 3, characterized in that: S4 includes the following steps: S41, determining the filter parameter sub-range corresponding to the maximum value of the number of reference filter parameters as the middle range corresponding to the current part label; S42, determining the filtering parameter corresponding to the center of the middle range as the target filtering parameter corresponding to the current part label; S43, obtaining a target filter model combination according to the target filter parameters corresponding to the current part label.

5. The method for acquiring orthopedic model data according to claim 4, characterized in that: Each target filter model combination includes M preset filter models of different types, M>1, and the method for obtaining orthopedic model data also includes the following steps: S7, grouping the N part labels according to the target filter model combination corresponding to each part label, and obtaining a plurality of part label combinations, wherein all part labels in the same part label combination correspond to the same M preset filter models; S8, for any part label combination, clustering all target filter parameters corresponding to the current part label combination, obtaining a number of isolated target filter parameters corresponding to the current part label combination, a number of filter parameter sets, and a filter parameter center corresponding to each filter parameter set; S9, correcting the target filtering parameter corresponding to each part label in the current part label combination according to a number of isolated target filtering parameters corresponding to the current part label combination, a number of filtering parameter sets, and a filtering parameter center corresponding to each filtering parameter set.

6. The method for acquiring orthopedic model data according to claim 5, characterized in that: S9 includes the following steps: S91, for any part label in the current part label combination, if the target filter parameter corresponding to the current part label is an isolated target filter parameter, keep the target filter parameter corresponding to the current part label unchanged; S92: If the target filtering parameter corresponding to the current part label is in the filtering parameter set, the target filtering parameter corresponding to the current part label is corrected to the filtering parameter center corresponding to the corresponding filtering parameter set.

7. A device for acquiring orthopedic model data, characterized in that: The device for acquiring orthopedic model data comprises: A data acquisition module is used to acquire N part labels, a preset filter model combination corresponding to each part label, a number of initial bone images corresponding to each part label, and a denoised bone image corresponding to each initial bone image, wherein each preset filter model combination corresponds to a preset filter parameter, N>1; A parameter updating module is used to update the preset filtering parameters corresponding to the current part label for any initial bone image corresponding to any part label according to the preset filtering model combination corresponding to the current part label, the current initial bone image and the denoised bone image corresponding to the current initial bone image, so as to obtain the reference filtering parameters of the current part label relative to the current initial bone image; A parameter analysis module, used to obtain several filter parameter sub-ranges corresponding to the current part label and the number of reference filter parameters contained in each filter parameter sub-range according to a preset step size and all reference filter parameters corresponding to the current part label; A parameter determination module, used to obtain a target filter model combination corresponding to the current part label according to the number of reference filter parameters contained in each filter parameter sub-range; A model acquisition module is used to acquire a target filtering model combination corresponding to the bone image to be processed according to the part label corresponding to the bone image to be processed when the bone image to be processed is acquired; The image filtering module is used to filter the bone image to be processed according to the target filtering model combination corresponding to the bone image to be processed, so as to obtain the target bone image, wherein the target bone image belongs to orthopedic model data.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for acquiring orthopedic model data as described in any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for acquiring orthopedic model data as described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method for acquiring orthopedic model data according to any one of claims 1 to 6 are implemented.

Images