A preoperative reconstruction system and device for hip arthroplasty based on intelligent learning

Abstract

The application provides a hip replacement preoperative reconstruction system and device based on intelligent learning, and relates to the technical field of auxiliary medical instruments.The hip replacement preoperative reconstruction system based on intelligent learning comprises an image quality evaluation module, an image fusion evaluation module and a prosthesis planning module.The image quality evaluation value obtained through image data is used to determine whether to perform image quality optimization, then the image fusion quality evaluation value obtained based on image fusion quality data is used to determine whether to perform image fusion quality optimization, and finally the prosthesis planning evaluation value obtained based on the prosthesis position data, the image fusion accuracy, the image quality evaluation value and the image fusion quality evaluation value is used to determine whether to perform feedback, so that the selection of the hip joint prosthesis position is optimized, and the correlation between the hip replacement preoperative reconstruction process and image quality is improved, thereby solving the problem of low correlation between the hip replacement preoperative reconstruction process and image quality in the prior art.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of auxiliary medical devices, in particular to a hip arthroplasty preoperative reconstruction system and device based on intelligent learning. BACKGROUND

[0002] Total hip arthroplasty is one of the common ways to treat hip joint abnormalities. In order to restore the function of the affected hip joint, the surgeon often needs to select an appropriate acetabular prosthesis placement position according to the pelvis anatomy. Commonly, the abnormal function of the patient's hip joint is caused by congenital skeletal dysplasia and postnatal hip osteoarthritis. Such patients have normal or slightly smaller pelvis development on the affected side, and often have a clear true acetabulum position. The surgeon usually chooses to place the acetabular prosthesis in the true acetabulum position. The hip arthroplasty preoperative reconstruction system and device based on intelligent learning realizes the intelligent and precise whole process from data acquisition to preoperative planning, which helps to improve the safety and success rate of hip arthroplasty, and brings better treatment effect and life quality to patients.

[0003] In the prior art, by acquiring image data of the patient, the state of the patient's hip joint is automatically analyzed, and a more accurate preoperative reconstruction scheme is provided, which realizes the improvement of the surgical effect and the recovery speed of the patient.

[0004] However, in the process of implementing the technical scheme of the embodiments of the present application, it is found that the above-mentioned technology at least has the following technical problems:

[0005] In the prior art, hip arthroplasty preoperative reconstruction often needs to fuse multiple image data, each data type has its specific imaging characteristics, and due to various reasons, it may cause image quality problems and data fusion processing difficulties, etc., and there is a problem of low correlation between the hip arthroplasty preoperative reconstruction process and the image quality.

[0006] However, there are four types of patients who cannot provide the current preoperative acetabular prosthesis placement preoperative planning: (1) the patient's bilateral hip joint fusion, the acetabular position cannot be identified; (2) the bilateral pelvis development is severely asymmetric, if the acetabular prosthesis is placed in the true acetabular position, it will cause the pelvis to tilt and cause scoliosis; (3) the femoral head is highly dislocated, and the original acetabular position has not developed; (4) the patient has undergone hip-preserving osteotomy surgery, but as the disease progresses, the patient's affected side is dislocated again or the original structure of the pelvis has been completely destroyed due to the surgery. SUMMARY

[0007] The application provides a hip replacement preoperative reconstruction system and device based on intelligent learning, which can not only improve the image quality, reduce the error caused by image noise, blur or unclear, but also optimize the fusion of multi-modal images, make the overlap and docking between different images more accurate, ensure the preoperative image data of hip replacement to be in the best state, and finally realize the improvement of the correlation between the hip replacement preoperative reconstruction process and the image quality.

[0008] To solve the above technical problems, the technical scheme provided by the application is as follows:

[0009] A hip replacement preoperative reconstruction system based on intelligent learning, comprising an image quality evaluation module, an image fusion evaluation module and a prosthesis planning module; wherein the image quality evaluation module is used for evaluating the image quality evaluation value according to the obtained image data, judging whether to perform image quality optimization based on the image quality evaluation value, and the image quality evaluation value is used for evaluating the image quality; the image fusion evaluation module is used for evaluating the image fusion quality evaluation value according to the obtained image fusion quality data, judging whether to perform image fusion quality optimization based on the image fusion quality evaluation value, and the image fusion quality evaluation value is used for evaluating the image fusion quality; and the prosthesis planning module is used for evaluating the prosthesis planning evaluation value according to the prosthesis position data, the image fusion accuracy, the image quality evaluation value obtained after image quality optimization and the image fusion quality evaluation value obtained after image fusion quality optimization if the image optimization is performed, judging whether to perform feedback based on the prosthesis planning evaluation value, the image optimization includes image quality optimization and image fusion quality optimization, and the image fusion quality evaluation value is used for evaluating the rationality of the hip prosthesis position.

[0010] Optionally, the image data includes image signal-to-noise ratio, structural similarity index, information entropy and contrast; the image fusion quality data includes registration error, relative information gain, mutual information and fusion image signal-to-noise ratio; the image fusion accuracy is obtained by processing the ratio of the pixel value of the fusion image to the pixel value of the standard image; the prosthesis position data includes prosthesis anteversion angle, prosthesis insertion depth and prosthesis inclination angle; the image signal-to-noise ratio includes fusion image signal-to-noise ratio, CT image signal-to-noise ratio, MRI image signal-to-noise ratio and X-ray image signal-to-noise ratio; the structural similarity index is obtained by processing the ratio of the pixel average value, pixel standard deviation and pixel square deviation of the image to the pixel average value, pixel standard deviation and pixel square deviation of the standard image, and the structural similarity index includes CT image structural similarity index, MRI image structural similarity index and X-ray image structural similarity index; the information entropy is obtained by processing the frequency of each image pixel value obtained from the constructed image histogram, and the information entropy includes fusion image information entropy, CT image information entropy, MRI image information entropy and X-ray image information entropy; the contrast is obtained by ratio operation of the difference between the maximum image pixel value and the minimum image pixel value and the average image pixel value, and the contrast includes CT image contrast, MRI image contrast and X-ray image contrast; the relative information gain is obtained by processing the ratio operation of the fusion image information entropy, CT image information entropy, MRI image information entropy and X-ray image information entropy to the theoretical maximum entropy value in the database; the mutual information is obtained by processing the joint probability distribution and the marginal probability distribution, and the marginal probability distribution is obtained by ratio operation of the frequency of the pixel value of the corresponding image in the image to the total number of pixels of the corresponding image; the mutual information includes first mutual information, second mutual information, third mutual information, fourth mutual information, fifth mutual information and sixth mutual information, the first mutual information represents the mutual information of the CT image and the MRI image, the second mutual information represents the mutual information of the CT image and the X-ray image, the third mutual information represents the mutual information of the CT image and the fusion image, the fourth mutual information represents the mutual information of the MRI image and the X-ray image, the fifth mutual information represents the mutual information of the MRI image and the fusion image, and the sixth mutual information represents the mutual information of the X-ray image and the fusion image.

[0011] Optionally, the specific method for obtaining the image quality evaluation value according to the obtained image data is as follows: obtaining signal-to-noise ratio deviation according to the relative relationship between the signal-to-noise ratio and the corresponding preset signal-to-noise ratio in the database; obtaining information entropy deviation according to the relative relationship between the information entropy and the corresponding preset information entropy in the database; obtaining contrast deviation according to the relative relationship between the contrast and the corresponding preset contrast in the database; and processing the signal-to-noise ratio deviation, the information entropy deviation, the contrast deviation and the structural similarity index to obtain the image quality evaluation value.

[0012] Optionally, the specific limit expression of the image quality evaluation value is as follows:

[0013]

[0014] wherein i represents the number of the image type, i=1 represents CT image, i=2 represents MRI image, i=3 represents X-ray image, YXZ i represents the image quality evaluation value of the i-th image type, SNR i represents the signal-to-noise ratio of the i-th image type, SSIM i represents the structural similarity index of the i-th image type, XXS i represents the information entropy of the i-th image type, DBD i represents the contrast of the i-th image type, SNR i.0 represents the preset signal-to-noise ratio of the i-th image type, XXS i.0 represents the preset information entropy of the i-th image type, DBD i.0 represents the preset contrast of the i-th image type.

[0015] Optionally, the specific method for obtaining the image fusion quality evaluation value according to the obtained image fusion quality data is as follows: obtaining the registration error deviation according to the relative relationship between the registration error and the corresponding preset registration error in the database; obtaining the mutual information deviation according to the relative relationship between the total mutual information and the corresponding preset mutual information in the database; obtaining the fusion image signal-to-noise ratio deviation according to the relative relationship between the fusion image signal-to-noise ratio and the corresponding preset fusion image signal-to-noise ratio in the database; and processing the signal-to-noise ratio deviation, the relative information gain, the mutual information deviation and the fusion image signal-to-noise ratio deviation to obtain the image fusion quality evaluation value.

[0016] Optionally, the specific method of obtaining the prosthesis planning evaluation value according to the prosthesis position data, the image fusion accuracy, the image quality evaluation value obtained after image quality optimization, and the image fusion quality evaluation value obtained after image fusion quality optimization is as follows: obtaining an image fusion accuracy deviation according to the relative relationship between the image fusion accuracy and the corresponding preset image fusion accuracy in the database, the image fusion accuracy deviation being obtained by processing the ratio of the image fusion accuracy and the corresponding preset image fusion accuracy in the database; obtaining an image quality optimization coefficient according to the relative relationship between the image quality evaluation value obtained after image quality optimization, the image quality evaluation value obtained before image quality optimization, and the preset image quality threshold; obtaining an image fusion quality optimization coefficient according to the relative relationship between the image fusion quality evaluation value obtained after image fusion quality optimization, the image fusion quality evaluation value obtained before image fusion quality optimization, and the preset image fusion quality threshold; if the prosthesis anteversion angle is not within the preset prosthesis anteversion angle range, obtaining an anteversion angle coefficient according to the relative relationship between the prosthesis anteversion angle and the preset prosthesis anteversion angle, otherwise, recording the anteversion angle coefficient as 1; if the prosthesis insertion depth is not within the preset prosthesis insertion depth range, obtaining a depth coefficient according to the relative relationship between the prosthesis insertion depth and the preset prosthesis insertion depth, otherwise, recording the depth coefficient as 1; if the prosthesis inclination angle is not within the preset prosthesis inclination angle range, obtaining an inclination angle coefficient according to the relative relationship between the prosthesis inclination angle and the preset prosthesis inclination angle, otherwise, recording the inclination angle coefficient as 1; processing the anteversion angle coefficient, the depth coefficient, the inclination angle coefficient, the image fusion accuracy deviation, the image quality optimization coefficient, and the image fusion quality optimization coefficient to obtain the prosthesis planning evaluation value.

[0017] Optionally, the specific process of determining whether to perform feedback based on the prosthesis planning evaluation value is as follows: determining whether the prosthesis planning evaluation value is less than a preset prosthesis planning threshold, if the prosthesis planning evaluation value is less than the preset prosthesis planning threshold, adjusting the wavelet transform layer number, otherwise, not performing feedback; determining whether the prosthesis planning evaluation value obtained after adjusting the wavelet transform layer number is less than the preset prosthesis planning threshold, if the prosthesis planning evaluation value is less than the preset prosthesis planning threshold, adjusting the prosthesis position, otherwise, ending the feedback; determining whether the prosthesis planning evaluation value obtained after adjusting the prosthesis position is less than the preset prosthesis planning threshold, if the prosthesis planning evaluation value is less than the preset prosthesis planning threshold, feeding back to the preset personnel, otherwise, ending the feedback.

[0018] The embodiment of the application provides a device applied to the hip arthroplasty pre-reconstruction system based on intelligent learning, which comprises a data acquisition device, a storage device and a processing device; the data acquisition device is used for collecting image fusion accuracy, image data, prosthesis position data and image fusion quality data of a hip joint, and the data acquisition device comprises an X-ray machine, a computer tomography machine and a magnetic resonance imaging machine; the storage device is used for storing the image fusion accuracy, the image data, the prosthesis position data and the image fusion quality data of the hip joint; and the processing device is used for image evaluation according to the data in the storage device, and the influence evaluation comprises image quality evaluation, image fusion quality evaluation and prosthesis planning evaluation.

[0019] Compared with the prior art, the technical scheme has at least the following beneficial effects:

[0020] 1. The image quality evaluation value obtained through the image data is used to determine whether image quality optimization is performed, then the image fusion quality evaluation value obtained based on the image fusion quality data is used to determine whether image fusion quality optimization is performed, and finally the prosthesis planning evaluation value obtained based on the prosthesis position data, the image fusion accuracy, the image quality evaluation value and the image fusion quality evaluation value is used to determine whether feedback is performed, so that the selection of the prosthesis position is optimized, and the correlation between the hip arthroplasty pre-reconstruction process and image quality is improved, thereby effectively solving the problem of low correlation between the hip arthroplasty pre-reconstruction process and image quality in the prior art.

[0021] 2. The signal-to-noise ratio deviation is obtained through the relative relationship between the signal-to-noise ratio and the corresponding preset signal-to-noise ratio in the database, then the information entropy deviation is obtained according to the relative relationship between the information entropy and the corresponding preset information entropy in the database, then the contrast deviation is obtained according to the relative relationship between the contrast and the corresponding preset contrast in the database, and finally the image quality evaluation value is obtained by processing the signal-to-noise ratio deviation, the information entropy deviation, the contrast deviation and the structural similarity index, so that the image quality is quantitatively evaluated, and optimization support is provided for image fusion in the subsequent hip arthroplasty pre-reconstruction process.

[0022] 3. The image fusion accuracy deviation is obtained through the image fusion accuracy and the preset image fusion accuracy, then the anteversion angle coefficient is obtained according to the prosthesis anteversion angle and the preset prosthesis anteversion angle, then the depth coefficient is obtained according to the prosthesis insertion depth and the preset prosthesis insertion depth, then the inclination angle coefficient is obtained according to the prosthesis inclination angle and the preset prosthesis inclination angle, and finally the prosthesis planning evaluation value is obtained according to the anteversion angle coefficient, the depth coefficient, the inclination angle coefficient, the image fusion accuracy deviation, the image quality optimization coefficient and the image fusion quality optimization coefficient, so that the rationality of the hip prosthesis position is quantitatively evaluated, and the accuracy of the prosthesis planning is improved. BRIEF DESCRIPTION OF DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiment description. Obviously, the drawings described below are only some of the embodiments of the present application, and other drawings can also be obtained by those of ordinary skill in the art without any creative effort based on these drawings.

[0024] Figure 1 A structure diagram of a preoperative reconstruction system for hip arthroplasty based on intelligent learning is provided for the embodiments of the present application. DETAILED DESCRIPTION

[0025] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the following will combine the drawings of the embodiments of the present application to clearly and completely describe the technical solutions of the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the described embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without any creative effort fall within the scope of protection of the present application.

[0026] Unless otherwise defined, the technical terms or scientific terms used in the present application should be understood as the usual meanings understood by those of ordinary skill in the art to which the present application belongs. The terms "first", "second" and the like used in the present application do not represent any order, number or importance, but are only used to distinguish different components. Similarly, the terms "one", "an" or "the" and the like do not represent a quantity limitation, but represent the existence of at least one. The terms "including", "containing" and the like mean that the elements or objects before the terms cover the elements or objects listed after the terms and their equivalents, and do not exclude other elements or objects. The terms "connected" or "connected" and the like are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect.

[0027] It should be noted that the terms "up", "down", "left", "right", "front", "back" and the like used in the present application are only used to represent relative positional relationships, and when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0028] The present application aims at the problem that the existing preoperative reconstruction process for hip arthroplasty has low correlation with image quality, and provides a preoperative reconstruction system and device for hip arthroplasty based on intelligent learning, which can improve the quality of images, reduce errors caused by image noise, blur or unclearness, and optimize multi-modal image fusion.

[0029] As Figure 1As shown, the embodiment of the present application provides a hip replacement preoperative reconstruction system based on intelligent learning, which comprises an image quality evaluation module, an image fusion evaluation module and a prosthesis planning module; wherein the image quality evaluation module is used for evaluating the image quality evaluation value according to the acquired image data, judging whether to perform image quality optimization based on the image quality evaluation value, and the image quality evaluation value is used for evaluating the image quality; the image fusion evaluation module is used for evaluating the image fusion quality evaluation value according to the acquired image fusion quality data, judging whether to perform image fusion quality optimization based on the image fusion quality evaluation value, and the image fusion quality evaluation value is used for evaluating the image fusion quality; the prosthesis planning module is used for, if the image optimization is performed, evaluating the prosthesis planning evaluation value according to the prosthesis position data, the image fusion accuracy, the image quality evaluation value obtained after the image quality optimization and the image fusion quality evaluation value obtained after the image fusion quality optimization, judging whether to perform feedback based on the prosthesis planning evaluation value, the image optimization includes the image quality optimization and the image fusion quality optimization, and the image fusion quality evaluation value is used for evaluating the rationality of the hip prosthesis position.

[0030] It should be noted that the image includes CT image (Computed Tomography), MRI image (Magnetic Resonance Imaging) and X-ray image; the image data includes image signal-to-noise ratio, structural similarity index, information entropy and contrast; the image fusion quality data includes registration error, relative information gain, mutual information and fusion image signal-to-noise ratio; the image fusion accuracy is obtained by processing the ratio of the fusion image pixel value to the standard image pixel value; and the prosthesis position data includes prosthesis anteversion angle, prosthesis insertion depth and prosthesis inclination angle.

[0031] The image signal-to-noise ratio is obtained by processing the ratio of the average power of the signal area to the average power of the noise area in the image obtained by the image processing software (such as Photoshop), and the image signal-to-noise ratio includes fusion image signal-to-noise ratio, CT image signal-to-noise ratio, MRI image signal-to-noise ratio and X-ray image signal-to-noise ratio.

[0032] The structural similarity index is obtained by processing the ratio of the pixel average value, the pixel standard deviation and the pixel square difference of the image to the pixel average value, the pixel standard deviation and the pixel square difference of the standard image, respectively, and the structural similarity index includes CT image structural similarity index, MRI image structural similarity index and X-ray image structural similarity index.

[0033] The information entropy is obtained by processing the frequency of occurrence of each image pixel value obtained from the constructed image histogram, and the specific formula of the information entropy is: wherein x represents the number of gray levels, x = 1, 2,..., 255, px represents the occurrence probability of the xth gray level; if the occurrence probability of a certain gray level is 0, the information entropy is 0; the information entropy includes fusion image information entropy, CT image information entropy, MRI image information entropy and X-ray image information entropy.

[0034] The contrast is obtained by ratio operation of the difference between the maximum value of image pixel value and the minimum value of image pixel value and the average value of image pixel value; the contrast includes CT image contrast, MRI image contrast and X-ray image contrast.

[0035] The registration error is obtained by the Euclidean distance between the corresponding points between the image obtained by the image registration algorithm and the fusion image; the relative information gain is obtained by ratio operation and processing of the fusion image information entropy, CT image information entropy, MRI image information entropy and X-ray image information entropy and the theoretical maximum entropy value in the database.

[0036] The mutual information is obtained by processing the joint probability distribution and the marginal probability distribution; the joint probability distribution is obtained by ratio operation of the occurrence frequency of each pair of pixel values in the two images in the statistics and the total number of pixels of the two images; the marginal probability distribution is obtained by ratio operation of the occurrence frequency of the pixel value of the corresponding image in the image and the total number of pixels of the corresponding image; the mutual information includes first mutual information, second mutual information, third mutual information, fourth mutual information, fifth mutual information and sixth mutual information; the first mutual information represents the mutual information of CT image and MRI image; the second mutual information represents the mutual information of CT image and X-ray image; the third mutual information represents the mutual information of CT image and fusion image; the fourth mutual information represents the mutual information of MRI image and X-ray image; the fifth mutual information represents the mutual information of MRI image and fusion image; the sixth mutual information represents the mutual information of X-ray image and fusion image.

[0037] The prosthesis anteversion angle, the prosthesis insertion depth and the prosthesis inclination angle are obtained by preoperative three-dimensional image data analysis and measurement.

[0038] Through the above steps, the image quality evaluation module evaluates the quality of the images based on the acquired CT images, MRI images, and X-ray images, which are crucial in preoperative reconstruction of hip replacement because they provide detailed information about joint structure, bone condition, and potential complications, ensuring the accuracy of preoperative planning and reducing the risk of surgery due to image quality problems; the image fusion evaluation module evaluates the quality of the fused multi-modal images, which can provide more comprehensive and accurate joint structure information in preoperative reconstruction of hip replacement, helping doctors to develop more accurate surgical plans and ensuring the accuracy and reliability of preoperative planning; the prosthesis planning module continuously optimizes image quality and fusion quality to further improve the accuracy and practicality of preoperative planning for hip replacement; comprehensive evaluation and optimization of image quality and image fusion quality are achieved, thereby improving the correlation between the preoperative reconstruction process of hip replacement and image quality.

[0039] The specific method of obtaining the image quality evaluation value according to the acquired image data is as follows: obtaining a signal-to-noise ratio deviation according to the relative relationship between the signal-to-noise ratio and the corresponding preset signal-to-noise ratio in the database The signal-to-noise ratio deviation is obtained by processing the ratio of the signal-to-noise ratio and the corresponding preset signal-to-noise ratio in the database; obtaining an information entropy deviation according to the relative relationship between the information entropy and the corresponding preset information entropy in the database The information entropy deviation is obtained by processing the ratio of the information entropy and the corresponding preset information entropy in the database; obtaining a contrast deviation according to the relative relationship between the contrast and the corresponding preset contrast in the database The contrast deviation is obtained by processing the ratio of the contrast and the corresponding preset contrast in the database; and processing the signal-to-noise ratio deviation, the information entropy deviation, the contrast deviation, and the structural similarity index to obtain the image quality evaluation value.

[0040] The specific limit expression of the image quality evaluation value is:

[0041]

[0042] In the formula, i represents the number of image types, i = 1 represents CT images, i = 2 represents MRI images, and i = 3 represents X-ray images, YXZ i represents the image quality evaluation value of the i-th image type, SNR i represents the signal-to-noise ratio of the i-th image type, SSIM i represents the structural similarity index of the i-th image type, XXS i represents the information entropy of the i-th image type, DBD i represents the contrast of the i-th image type, SNR i.0preset signal-to-noise ratio of the i-th image type, XXS i.0 preset information entropy of the i-th image type, DBD i.0 preset contrast of the i-th image type.

[0043] In the embodiment, the preset signal-to-noise ratio, the preset information entropy and the preset contrast are all set according to industry standards, for example, the preset signal-to-noise ratio is set to 35 dB, the preset information entropy is set to 7 bits, and the preset contrast is set to 0.7.

[0044] In the algorithm, the image quality evaluation value involves processing a plurality of independent variables (image signal-to-noise ratio, structural similarity index, information entropy and contrast), and there is a mutual influence relationship between these independent variables; the higher the image signal-to-noise ratio, the lower the noise of the image, and thus it is easier to obtain a higher structural similarity index in terms of structure and detail retention; because a low-noise image contains more effective information, the higher the image signal-to-noise ratio, the greater the information entropy; the higher the image signal-to-noise ratio, the more obvious the brightness difference of the image, and the stronger the contrast; the higher the structural similarity index, the similarity of the image structure may increase, which may lead to an increase in information entropy, because a high-quality image usually contains more details and rich information; the greater the contrast, the more details and structures in the image are enhanced, so that the structural similarity index of the image is higher; the higher the contrast of the image, the more details and changes it usually contains, so the information entropy may also be higher; the image signal-to-noise ratio, the structural similarity index, the information entropy and the contrast are positively correlated with the image quality evaluation value.

[0045] Through the above steps, the advantages and disadvantages of the image quality are quantitatively evaluated, the overall quality of the image is effectively reflected, and then the optimization support for the subsequent image fusion in the pre-reconstruction process of hip joint replacement is realized.

[0046] A1, determining whether the image quality evaluation value is less than a preset image quality threshold value, if the image quality evaluation value is less than the preset image quality threshold value, executing A2, otherwise, not performing image quality optimization; A2, performing denoising processing, determining whether the image quality evaluation value obtained after denoising is less than the preset image quality threshold value, if the image quality evaluation value is less than the preset image quality threshold value, executing A3, otherwise, ending the image quality optimization; A3, performing contrast enhancement, determining whether the image quality evaluation value obtained after contrast enhancement is less than the preset image quality threshold value, if the image quality evaluation value is less than the preset image quality threshold value, executing A4, otherwise, ending the image quality optimization; A4, performing image reconstruction and repair, determining whether the image quality evaluation value obtained after image reconstruction and repair is less than the preset image quality threshold value, if the image quality evaluation value is less than the preset image quality threshold value, executing A5, otherwise, ending the image quality optimization; A5, performing structure optimization, determining whether the image quality evaluation value obtained after structure optimization is less than the preset image quality threshold value, if the image quality evaluation value is less than the preset image quality threshold value, performing feedback, otherwise, ending the image quality optimization.

[0047] In the embodiment, the preset image quality threshold value is represented by the maximum value of the image quality evaluation values of qualified images in a historical time period; the denoising processing is processed by a feed-forward denoising convolutional neural network method (DnCNN) according to the local noise characteristics of the image; the contrast enhancement is adjusted by a convolutional neural network; the image reconstruction and repair are reconstructed by a generative adversarial network; the structure optimization is optimized by a super-resolution technology and an edge enhancement technology; through the above steps, the image quality in the preoperative reconstruction process of hip replacement is improved.

[0048] The specific method of obtaining the image fusion quality evaluation value according to the obtained image fusion quality data is as follows: the registration error deviation (i.e., the specific method of obtaining the image fusion quality evaluation value in ) is obtained according to the relative relationship between the registration error and the corresponding preset registration error in the database; the registration error deviation is obtained by processing the ratio of the registration error and the corresponding preset registration error in the database; the mutual information deviation (i.e., the specific method of obtaining the image fusion quality evaluation value in ), the mutual information deviation is obtained by processing the ratio operation of the total mutual information and the corresponding preset mutual information in the database, and the total mutual information represents the average value of the mutual information; the fusion image signal-to-noise ratio deviation (i.e., the specific method of obtaining the image fusion quality evaluation value in the method) is obtained according to the relative relationship between the fusion image signal-to-noise ratio and the corresponding preset fusion image signal-to-noise ratio in the database. ), the fusion image signal-to-noise ratio deviation is obtained by processing the ratio operation of the fusion image signal-to-noise ratio and the corresponding preset fusion image signal-to-noise ratio in the database; and the image fusion quality evaluation value is obtained by processing the signal-to-noise ratio deviation, the relative information gain, the mutual information deviation and the fusion image signal-to-noise ratio deviation.

[0049] The specific method of obtaining the image fusion quality evaluation value is as follows:

[0050]

[0051] In the formula, i represents the number of the image type, i = 1 represents the CT image, i = 2 represents the MRI image, i = 3 represents the X-ray image, RHZ represents the image fusion quality evaluation value, YXZ i ′ represents the image quality evaluation value obtained after the image quality optimization of the i-th image type, PZWC represents the registration error, ZEY represents the relative information gain, HXX represents the mutual information, SNR represents the fusion image signal-to-noise ratio, SNR0 represents the preset fusion image signal-to-noise ratio, MI 1,2 represents the first mutual information, MI 1,3 represents the second mutual information, MI 1,4 represents the third mutual information, MI 2,3 represents the fourth mutual information, MI 2,4 represents the fifth mutual information, MI 3,4 represents the sixth mutual information, PZWC0 represents the preset registration error, and HXX0 represents the preset mutual information.

[0052] In the embodiment, the preset registration error is represented by the average value of the registration errors in a historical time period; the preset mutual information is represented by the average value of the mutual information in the historical time period; and the preset fusion image signal-to-noise ratio is set according to the industry standard, for example, the preset fusion image signal-to-noise ratio is set to 35 dB.

[0053] The image fusion quality evaluation value in the algorithm involves processing multiple independent variables (registration error, relative information gain, mutual information and fused image signal-to-noise ratio), and there is a mutual influence relationship between these independent variables; when the registration error is larger, the fused image may have obvious misplacement or ghosting phenomenon, thereby leading to the decrease of the fused image signal-to-noise ratio; the relative information gain and the mutual information are both indicators for measuring the amount of information, and the relative information gain can be regarded as a supplement to the mutual information; if the signal-to-noise ratio of the fused image is low, useful information may not be effectively extracted, thereby leading to the decrease of the relative information gain and the mutual information; the registration error is negatively correlated with the image fusion quality evaluation value, and the relative information gain, the mutual information and the fused image signal-to-noise ratio are positively correlated with the image fusion quality evaluation value.

[0054] Through the above steps, the fusion effect between the multi-modal images is quantitatively evaluated, and then a reference basis is provided for subsequent image fusion optimization.

[0055] The specific process of judging whether to perform image fusion quality optimization based on the image fusion quality evaluation value is as follows: judging whether the image fusion quality evaluation value is less than a preset image fusion quality threshold value, if the image fusion quality evaluation value is less than the preset image fusion quality threshold value, performing image quality optimization on the fused image, otherwise not performing image fusion quality optimization; judging whether the image fusion quality evaluation value obtained after the image quality optimization is less than the preset image fusion quality threshold value, if the image fusion quality evaluation value is less than the preset image fusion quality threshold value, performing wavelet transform optimization, otherwise ending the image fusion quality optimization.

[0056] In the embodiment, the preset image fusion quality threshold value is represented by the maximum value of the image fusion quality evaluation values of the images with qualified fusion quality in a historical time period; the wavelet transform optimization is performed by multi-resolution decomposition of the image through wavelet transform, and fusion is performed on different frequency bands; optimization is performed in the low-frequency part, because the low-frequency part usually contains the approximate structure and background information of the image, and optimization of the low-frequency part improves the overall effect of the image; fusion is performed in the high-frequency part, because the high-frequency part contains the detailed information of the image, and optimization of the details improves the definition and detail retention of the image; for example, if the sampling frequency of the original signal is 1000Hz, the highest frequency is 500Hz, the low-frequency part is 0-250Hz (less than half of the highest frequency), and the high-frequency part is 250-500Hz (not less than half of the highest frequency);

[0057] Through the cyclic adjustment of the quantitative evaluation and optimization measures, it is ensured that the quality of the finally fused image meets the expected requirements, which helps to improve the effect of image fusion in the pre-reconstruction process of hip joint replacement

[0058] The specific method for obtaining the prosthesis planning evaluation value based on prosthesis location data, image fusion accuracy, and the image quality evaluation value obtained after image quality optimization is as follows: The image fusion accuracy deviation is obtained based on the relative relationship between the image fusion accuracy and the corresponding preset image fusion accuracy in the database (i.e., the method for obtaining the prosthesis planning evaluation value). The image fusion accuracy deviation is obtained by processing the ratio of the image fusion accuracy to the corresponding preset image fusion accuracy in the database; the image quality optimization coefficient (i.e., YX in the specific method for obtaining the prosthesis planning evaluation value) is obtained based on the relative relationship between the image quality evaluation value obtained after image quality optimization, the image quality evaluation value obtained before image quality optimization, and the preset image quality threshold; the image fusion quality optimization coefficient (i.e., RH in the specific method for obtaining the prosthesis planning evaluation value) is obtained based on the relative relationship between the image fusion quality evaluation value obtained after image fusion quality optimization, the image fusion quality evaluation value obtained before image fusion quality optimization, and the preset image fusion quality threshold; if the prosthesis tilt angle is not within the preset prosthesis tilt angle range, then the relative relationship between the prosthesis tilt angle and the preset prosthesis tilt angle is used. Obtain the tilt angle coefficient (i.e., JD in the specific method for obtaining the prosthesis planning evaluation value), otherwise record the tilt angle coefficient as 1; if the prosthesis insertion depth is not within the preset prosthesis insertion depth range, obtain the depth coefficient (i.e., JS in the specific method for obtaining the prosthesis planning evaluation value) according to the relative relationship between the prosthesis insertion depth and the preset prosthesis insertion depth, otherwise record the depth coefficient as 1; if the prosthesis pitch angle is not within the preset prosthesis pitch angle range, obtain the pitch angle coefficient (i.e., JF in the specific method for obtaining the prosthesis planning evaluation value) according to the relative relationship between the prosthesis pitch angle and the preset prosthesis pitch angle, otherwise record the pitch angle coefficient as 1; process the tilt angle coefficient, depth coefficient, pitch angle coefficient, image fusion accuracy deviation, image quality optimization coefficient, and image fusion quality optimization coefficient to obtain the prosthesis planning evaluation value.

[0059] The specific method for obtaining the prosthesis planning evaluation value is as follows:

[0060]

[0061] In the formula, YXH represents the prosthesis planning evaluation value, RHJ represents the image fusion accuracy, RHJ0 represents the preset image fusion accuracy, YX represents the image quality optimization coefficient, RH represents the image fusion quality optimization coefficient, and YXZ represents the image fusion quality optimization coefficient. i ′ Y represents the image quality evaluation value obtained after image quality optimization for the i-th image type. i Y represents the image quality assessment value for the i-th image type, YXZ0 represents the preset image quality threshold, and RHZ represents the image quality assessment value for the i-th image type. ′RHZ = JD * JS * JF * JTD / (JD * JS * JF * JTD + JD * JS * JF * JTS + JD * JS * JF * JTF) RHZ0 = 1 JD = 1 JS = 1 JF = 1 JTD = JTD0 / (JTD0 + JTS0 + JTF0) JTS = JTS0 / (JTD0 + JTS0 + JTF0) JTF = JTF0 / (JTD0 + JTS0 + JTF0) min JTD0 = 15° max JTS0 = 9.1mm min JTF0 = 45° max JTD0 = 15° min JTS0 = 9.1mm max JTF0 = 45°

[0062] In this embodiment, the preset image fusion accuracy is represented by the average value of the image fusion accuracy qualified in the historical period; the anteversion angle refers to the angle between the prosthesis and the front of the acetabulum, which affects the stability of the prosthesis and the femoral head; the preset prosthesis anteversion angle range is set according to the industry standard, for example, the preset anteversion angle range is usually 20°±5°, the preset minimum prosthesis anteversion angle is set to 15°, the preset maximum prosthesis anteversion angle is set to 25°, and the preset prosthesis anteversion angle is set to the median value 20° of the preset anteversion angle range; preoperative three-dimensional image data analysis (such as CT, MRI) can measure the anteversion angle of the acetabulum to obtain a personalized anteversion angle.

[0063] The inclination angle is the angle between the prosthesis and the pelvic plane when the prosthesis is inserted, which affects the contact surface and stability of the prosthesis; the preset prosthesis inclination angle range is set according to the industry standard, for example, the preset prosthesis inclination angle range is usually set to 40° to 50°, the preset minimum prosthesis inclination angle is set to 40°, the preset maximum prosthesis inclination angle is set to 50°, and the preset prosthesis inclination angle is set to the median value 45° of the preset prosthesis inclination angle range; through preoperative image reconstruction, the anatomical morphology of the patient's pelvis can be measured, and a personalized inclination angle can be set according to the data.

[0064] The depth of the prosthesis is usually determined based on the anatomical depth of the acetabulum, and the adjustment of the depth should balance the stability of the prosthesis and the compression of the soft tissue; the preset prosthesis insertion depth range is set according to the industry standard and the individual situation of the patient, for example, the preset prosthesis insertion depth range is usually set to 50% to 70% of the depth of the acetabulum, the depth of the acetabulum of the patient is 13mm, then the preset prosthesis insertion depth range is 6.5-9.1, the preset minimum prosthesis insertion depth is 6.5mm, the preset maximum prosthesis insertion depth is 9.1mm, and the preset prosthesis insertion depth is set to the median value 7.8mm of the preset prosthesis insertion depth range.

[0065] The prosthesis planning evaluation value in the algorithm involves processing a plurality of independent variables (an anteversion angle coefficient, a depth coefficient, a tilt angle coefficient, an image fusion accuracy deviation, an image quality optimization coefficient, and an image fusion quality optimization coefficient), and there is a mutual influence relationship between the independent variables; the prosthesis anteversion angle and the prosthesis tilt angle jointly determine the spatial position and direction of the prosthesis, and then affect the stability and function of the prosthesis, and adjusting the prosthesis anteversion angle can affect the prosthesis tilt angle; if the prosthesis anteversion angle is not within the preset prosthesis anteversion angle range, the overall stability and function of the prosthesis can be ensured by adjusting the insertion depth for compensation; if the prosthesis insertion depth is not within the preset prosthesis insertion depth range, the matching between the prosthesis and the acetabulum can be ensured by adjusting the tilt angle; the higher the image fusion accuracy, the closer the fused image pixel value is to the standard image pixel value, and the higher the image quality optimization coefficient; the improvement of the image fusion accuracy helps to improve the image fusion quality optimization coefficient, because the high-precision fusion result can retain more original information, thereby showing better performance in fusion quality; the improvement of the image quality helps to improve the fusion quality, because better quality provides more useful information for the fusion process; the anteversion angle coefficient, the depth coefficient, the tilt angle coefficient, the image fusion accuracy deviation, the image quality optimization coefficient, and the image fusion quality optimization coefficient are positively correlated with the prosthesis planning evaluation value.

[0066] Taking the preset image fusion accuracy as 1 as an example, the change statistical table of the prosthesis planning evaluation value is shown in Table 1:

[0067] Table 1 Change statistical table of prosthesis planning evaluation value

[0068]

[0069] From the first and second groups of data in the table, it can be seen that the prosthesis planning evaluation value increases with the increase of the image fusion accuracy; from the second and third groups of data, it can be seen that the prosthesis planning evaluation value increases with the increase of the image quality optimization coefficient; from the third and fourth groups of data, it can be seen that the prosthesis planning evaluation value increases with the increase of the image fusion quality optimization coefficient; from the fourth and fifth groups of data, it can be seen that the anteversion angle coefficient increases with the increase of the image fusion quality optimization coefficient; from the fifth and sixth groups of data, it can be seen that the depth coefficient increases with the increase of the image fusion quality optimization coefficient; and from the sixth and seventh groups of data, it can be seen that the tilt angle coefficient increases with the increase of the image fusion quality optimization coefficient.

[0070] Through the above steps, the rationality of the hip joint prosthesis position is quantified, and the accuracy of the hip joint prosthesis position planning is improved.

[0071] The specific process of judging whether to perform feedback based on the prosthesis planning evaluation value is as follows: judging whether the prosthesis planning evaluation value is less than a preset prosthesis planning threshold value, if the prosthesis planning evaluation value is less than the preset prosthesis planning threshold value, adjusting the wavelet transform layer number, otherwise, not performing feedback; judging whether the prosthesis planning evaluation value obtained after adjusting the wavelet transform layer number is less than the preset prosthesis planning threshold value, if the prosthesis planning evaluation value is less than the preset prosthesis planning threshold value, adjusting the prosthesis position, otherwise, ending the feedback; judging whether the prosthesis planning evaluation value obtained after adjusting the prosthesis position is less than the preset prosthesis planning threshold value, if the prosthesis planning evaluation value is less than the preset prosthesis planning threshold value, feeding back to the preset personnel, otherwise, ending the feedback.

[0072] In the embodiment, the preset prosthesis planning threshold value is represented by the maximum value of the prosthesis planning evaluation value in a historical time period;

[0073] The wavelet transform layer number is adjusted by increasing the number of wavelet transform layers, for example, the initial state is to use 3 layers of wavelet transform to process the image, and then 4 layers of wavelet transform is adjusted.

[0074] The prosthesis position is adjusted by a random search method; the random search method means that a series of candidate positions are randomly generated around the current prosthesis position, the prosthesis planning evaluation value of each candidate position is calculated, and the position with the highest prosthesis planning evaluation value is selected as the new prosthesis position.

[0075] Through the above steps, the accuracy of hip replacement in the preoperative reconstruction process of hip replacement is improved.

[0076] The embodiment of the application provides a device of a hip replacement preoperative reconstruction system based on intelligent learning, which comprises a data acquisition device, a storage device and a processing device; wherein the data acquisition device is used for acquiring image fusion accuracy, image data, prosthesis position data and image fusion quality data of a hip joint, the data acquisition device comprises an X-ray machine, a computer tomography machine and a magnetic resonance imaging machine; the storage device is used for storing the image fusion accuracy, the image data, the prosthesis position data and the image fusion quality data of the hip joint, and also comprises storage of corresponding historical data; the processing device is used for image quality evaluation of the image data, image fusion quality evaluation of the image fusion quality data, and prosthesis planning evaluation of the prosthesis position data, the image fusion accuracy, the image quality evaluation value obtained after image quality optimization and the image fusion quality evaluation value obtained after image fusion quality optimization.

[0077] In the embodiment, the hip replacement surgery represents a surgical procedure for treating hip joint diseases or injuries, restoring joint function by replacing damaged hip joint parts (such as the femoral head and acetabulum); the image quality evaluation module optimizes image quality through intelligent learning, improving image quality; the image fusion evaluation module and the prosthesis planning module optimize image fusion quality through intelligent learning, improving image fusion quality; through the above steps, effective optimization of image quality and optimization of multi-modal image fusion are realized, and the correlation between the preoperative reconstruction process of the hip replacement surgery and the image quality is improved.

[0078] In summary, in the embodiment of the application, the image quality evaluation value obtained from the image data is used to determine whether to optimize the image quality, then the image fusion quality evaluation value obtained from the image fusion quality data is used to determine whether to optimize the image fusion quality, and finally the prosthesis planning evaluation value obtained from the optimized image quality evaluation value and the optimized image fusion quality evaluation value is used to determine whether to perform feedback, thereby optimizing the fusion of multi-modal images and improving the correlation between the preoperative reconstruction process of the hip replacement surgery and the image quality, effectively solving the problem of low correlation between the preoperative reconstruction process of the hip replacement surgery and the image quality in the prior art.

[0079] The following points need to be explained:

[0080] (1) The drawings of the embodiment of the application only involve the structures involved in the embodiment of the application, and other structures can be referred to the usual design.

[0081] (2) For the sake of clarity, in the drawings used to describe the embodiments of the application, the thickness of a layer or region is exaggerated or reduced, that is, the drawings are not drawn according to the actual proportions. It can be understood that when an element such as a layer, film, region or substrate is referred to as being located "on" or "under" another element, the element can be "directly" located on or under another element or there can be an intermediate element.

[0082] (3) In the case of no conflict, the embodiments of the application and the features in the embodiments can be combined with each other to obtain new embodiments.

[0083] The above is only a specific embodiment of the application, but the protection scope of the application is not limited thereto, and the protection scope of the application should be subject to the protection scope of the claims.

Claims

1. A preoperative reconstruction system for hip arthroplasty based on intelligent learning, characterized in that, The application relates to a medical image quality evaluation system, which comprises an image quality evaluation module, an image fusion evaluation module and a prosthesis planning module. The image quality evaluation module is used for evaluating image quality evaluation values according to acquired image data, and judging whether image quality optimization is needed based on the image quality evaluation values, wherein the image quality evaluation values are used for evaluating image quality. The image data comprises image signal-to-noise ratio, structural similarity index, information entropy and contrast. The image signal-to-noise ratio comprises fusion image signal-to-noise ratio, CT image signal-to-noise ratio, MRI image signal-to-noise ratio and X-ray image signal-to-noise ratio. The structural similarity index is obtained by processing the ratio of the pixel average value, the pixel standard deviation and the pixel square difference of the image to the pixel average value, the pixel standard deviation and the pixel square difference of a standard image, and the structural similarity index comprises CT image structural similarity index, MRI image structural similarity index and X-ray image structural similarity index. The information entropy is obtained by processing the frequency of each image pixel value obtained from a constructed image histogram, and the information entropy comprises fusion image information entropy, CT image information entropy, MRI image information entropy and X-ray image information entropy. The contrast is obtained by processing the ratio of the difference between the maximum image pixel value and the minimum image pixel value to the average image pixel value, and the contrast comprises CT image contrast, MRI image contrast and X-ray image contrast. The specific expression of the image quality evaluation value is as follows: The image fusion evaluation module is used for evaluating image fusion quality evaluation values according to acquired image fusion quality data, and judging whether image fusion quality optimization is needed based on the image fusion quality evaluation values, wherein the image fusion quality evaluation values are used for evaluating image fusion quality. ； wherein i represents a number of an image type, represents a CT image, represents an MRI image, represents an X-ray image, represents an image quality evaluation value of the i-th image type, represents a signal-to-noise ratio of the i-th image type, represents a structural similarity index of the i-th image type, represents an information entropy of the i-th image type, represents a contrast of the i-th image type, represents a preset signal-to-noise ratio of the i-th image type, represents a preset information entropy of the i-th image type, represents a preset contrast of the i-th image type. If image optimization is needed, the prosthesis planning module is used for evaluating prosthesis planning evaluation values according to prosthesis position data, image fusion accuracy, the image quality evaluation values obtained after image quality optimization and the image fusion quality evaluation values obtained after image fusion quality optimization, and judging whether feedback is needed based on the prosthesis planning evaluation values, wherein the image optimization comprises image quality optimization and image fusion quality optimization, and the image fusion quality evaluation values are used for evaluating the rationality of the position of a hip joint prosthesis. The image fusion quality data comprises registration error, relative information gain, mutual information and fusion image signal-to-noise ratio.

2. The intelligent learning based pre-operative reconstruction system for hip arthroplasty of claim 1, wherein, The image fusion accuracy is obtained by processing the ratio of the fusion image pixel value to the standard image pixel value. The prosthesis position data comprises prosthesis anteversion angle, prosthesis insertion depth and prosthesis inclination angle. The relative information gain is obtained by processing the ratio of the fusion image information entropy, the CT image information entropy, the MRI image information entropy and the X-ray image information entropy to the theoretical maximum entropy value in a database. The mutual information is obtained by processing joint probability distribution and edge probability distribution, and the edge probability distribution is obtained by processing the ratio of the frequency of the pixel value of a corresponding image in an image to the total pixel number of the corresponding image. ​ The mutual information includes first mutual information, second mutual information, third mutual information, fourth mutual information, fifth mutual information and sixth mutual information, the first mutual information represents mutual information of the CT image and the MRI image, the second mutual information represents mutual information of the CT image and the X-ray image, the third mutual information represents mutual information of the CT image and the fusion image, the fourth mutual information represents mutual information of the MRI image and the X-ray image, the fifth mutual information represents mutual information of the MRI image and the fusion image, and the sixth mutual information represents mutual information of the X-ray image and the fusion image.

3. The intelligent learning based pre-operative reconstruction system for hip arthroplasty of claim 1, wherein, The specific process of judging whether to perform image quality optimization based on the image quality evaluation value is as follows: A1, judging whether the image quality evaluation value is less than a preset image quality threshold value, if the image quality evaluation value is less than the preset image quality threshold value, executing A2, otherwise, not performing image quality optimization; A2, performing denoising processing, judging whether the image quality evaluation value obtained after denoising is less than the preset image quality threshold value, if the image quality evaluation value is less than the preset image quality threshold value, executing A3, otherwise, ending the image quality optimization; A3, performing contrast enhancement, judging whether the image quality evaluation value obtained after contrast enhancement is less than the preset image quality threshold value, if the image quality evaluation value is less than the preset image quality threshold value, executing A4, otherwise, ending the image quality optimization; A4, performing image reconstruction and repair, judging whether the image quality evaluation value obtained after image reconstruction and repair is less than the preset image quality threshold value, if the image quality evaluation value is less than the preset image quality threshold value, executing A5, otherwise, ending the image quality optimization; A5, performing structure optimization, judging whether the image quality evaluation value obtained after structure optimization is less than the preset image quality threshold value, if the image quality evaluation value is less than the preset image quality threshold value, performing feedback, otherwise, ending the image quality optimization.

4. The intelligent learning based pre-operative reconstruction system for hip arthroplasty of claim 2, wherein, The specific method of obtaining the image fusion quality evaluation value according to the obtained image fusion quality data is as follows: obtaining the registration error deviation according to the relative relationship between the registration error and the corresponding preset registration error in the database; obtaining the mutual information deviation according to the relative relationship between the total mutual information and the corresponding preset mutual information in the database; obtaining the fusion image signal-to-noise ratio deviation according to the relative relationship between the fusion image signal-to-noise ratio and the corresponding preset fusion image signal-to-noise ratio in the database; processing the signal-to-noise ratio deviation, the relative information gain, the mutual information deviation and the fusion image signal-to-noise ratio deviation to obtain the image fusion quality evaluation value.

5. The intelligent learning based pre-operative reconstruction system for hip arthroplasty of claim 4, wherein, The specific process of judging whether to perform image fusion quality optimization based on the image fusion quality evaluation value is as follows: judging whether the image fusion quality evaluation value is less than a preset image fusion quality threshold value, if the image fusion quality evaluation value is less than the preset image fusion quality threshold value, performing image quality optimization on the fusion image, otherwise, not performing image fusion quality optimization; judging whether the image fusion quality evaluation value obtained after image quality optimization is less than the preset image fusion quality threshold value, if the image fusion quality evaluation value is less than the preset image fusion quality threshold value, performing wavelet transform optimization, otherwise, ending the image fusion quality optimization.

6. The intelligent learning based pre-operative reconstruction system for hip arthroplasty of claim 2, wherein, The specific method for obtaining the prosthesis planning evaluation value according to the prosthesis position data, the image fusion accuracy, the image quality evaluation value obtained after image quality optimization, and the image fusion quality evaluation value obtained after image fusion quality optimization is as follows: An image fusion accuracy deviation is obtained according to the relative relationship between the image fusion accuracy and the corresponding preset image fusion accuracy in the database, and the image fusion accuracy deviation is obtained by processing the ratio of the image fusion accuracy to the corresponding preset image fusion accuracy in the database; An image quality optimization coefficient is obtained according to the relative relationship between the image quality evaluation value obtained after image quality optimization, the image quality evaluation value obtained before image quality optimization, and the preset image quality threshold value; An image fusion quality optimization coefficient is obtained according to the relative relationship between the image fusion quality evaluation value obtained after image fusion quality optimization, the image fusion quality evaluation value obtained before image fusion quality optimization, and the preset image fusion quality threshold value; If the prosthesis anteversion angle is not within the preset prosthesis anteversion angle range, an anteversion angle coefficient is obtained according to the relative relationship between the prosthesis anteversion angle and the preset prosthesis anteversion angle, otherwise the anteversion angle coefficient is recorded as 1; If the prosthesis insertion depth is not within the preset prosthesis insertion depth range, a depth coefficient is obtained according to the relative relationship between the prosthesis insertion depth and the preset prosthesis insertion depth, otherwise the depth coefficient is recorded as 1; If the prosthesis inclination angle is not within the preset prosthesis inclination angle range, an inclination angle coefficient is obtained according to the relative relationship between the prosthesis inclination angle and the preset prosthesis inclination angle, otherwise the inclination angle coefficient is recorded as 1; The prosthesis planning evaluation value is obtained by processing the anteversion angle coefficient, the depth coefficient, the inclination angle coefficient, the image fusion accuracy deviation, the image quality optimization coefficient, and the image fusion quality optimization coefficient.

7. The intelligent learning based pre-operative reconstruction system for hip arthroplasty of claim 1, wherein, The specific process of determining whether to perform feedback based on the prosthesis planning evaluation value is as follows: Determine whether the prosthesis planning evaluation value is less than the preset prosthesis planning threshold value, if the prosthesis planning evaluation value is less than the preset prosthesis planning threshold value, adjust the wavelet transform layer number, otherwise do not perform feedback; Determine whether the prosthesis planning evaluation value obtained after adjusting the wavelet transform layer number is less than the preset prosthesis planning threshold value, if the prosthesis planning evaluation value is less than the preset prosthesis planning threshold value, adjust the prosthesis position, otherwise end the feedback; Determine whether the prosthesis planning evaluation value obtained after adjusting the prosthesis position is less than the preset prosthesis planning threshold value, if the prosthesis planning evaluation value is less than the preset prosthesis planning threshold value, feedback to the preset personnel, otherwise end the feedback.

8. A device applied to the intelligent learning based preoperative reconstruction system of hip arthroplasty according to any one of claims 1-7, characterized in that, It includes: Data acquisition equipment, storage equipment, and processing equipment; The data acquisition equipment is used to collect the image fusion accuracy, image data, prosthesis position data, and image fusion quality data of the hip joint, and the data acquisition equipment includes an X-ray machine, a computed tomography machine, and a magnetic resonance imaging machine; The storage equipment is used to store the image fusion accuracy, image data, prosthesis position data, and image fusion quality data of the hip joint; The processing equipment is used to perform image evaluation according to the data in the storage equipment, and the image evaluation includes image quality evaluation, image fusion quality evaluation, and prosthesis planning evaluation.

Images