A computer tomography image based acetabular cup prediction system and method

Abstract

The embodiment of the disclosure relates to a computer tomography image-based acetabular cup prediction system and method, and relates to the technical field of medical image analysis, and the user information and the computer tomography image of a target user are acquired; the computer tomography image is subjected to image segmentation, and an acetabular region of interest is acquired; the corresponding Hounsfield unit value and the acetabular center coordinates of each pixel coordinate are acquired based on the acetabular region of interest, the screening area of the acetabular cup is determined based on the acetabular center coordinates and the received screening conditions, the Hounsfield unit value corresponding to each pixel coordinate is processed based on a preset dynamic threshold method, and the cortical bone Hounsfield unit average value and the cancellous bone Hounsfield unit average value of the screening area are obtained; prediction analysis is carried out based on the user information and the cortical bone Hounsfield unit average value and the cancellous bone Hounsfield unit average value of the screening area, and a prediction result is generated, so that more objective and accurate acetabular cup stability evaluation can be provided based on the prediction result.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of medical image analysis, and in particular, to a hip cup prediction system and method based on computed tomography images. BACKGROUND

[0002] At present, the problem of population aging is increasingly serious, and the number of users of various types of elderly-related diseases has increased significantly; among them, osteoporosis is one of the most common diseases. With the continuous expansion of the elderly population, the demand for total hip arthroplasty (THA) has increased year by year. The success or failure of total hip arthroplasty directly affects the postoperative recovery and quality of life of the user, and the bone quality analysis before the implantation of the acetabular cup is one of the key factors for evaluating the success of the surgery. Although the technology of total hip arthroplasty has been relatively mature, it still faces many clinical problems and challenges, especially in the evaluation of the stability of the acetabular cup implantation and the development of individualized treatment plans.

[0003] In the related art, the bone quality analysis before the implantation of the acetabular cup mainly relies on dual-energy X-ray absorptiometry (DXA), which is an internationally recognized standard method for measuring bone density and is also the gold standard for diagnosing osteoporosis by the World Health Organization. However, DXA has several limitations: first, the measurement speed of DXA is slow, the resolution is low, and it can only provide two-dimensional bone density information, with a measurement error of about 20%, making it difficult to accurately obtain the overall bone density value; in addition, the measurement results of DXA are easily affected by factors such as obesity, abdominal aortic calcification, and spinal deformity, resulting in errors; second, the bone density measured by DXA is a comprehensive value of cancellous bone and cortical bone, and the two are not distinguished, which makes the measurement results mainly reflect the bone density of the cortical bone, making it difficult to effectively monitor the bone calcium loss of the cancellous bone part, resulting in low sensitivity, and the limitations of this method make it necessary to further improve. SUMMARY

[0004] In order to solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides a hip cup prediction system and method based on computed tomography images.

[0005] The embodiment of the present disclosure provides a hip cup prediction system based on a computer tomography image, comprising: a data loading module configured to acquire user information and a computer tomography image of a target user; an image processing module configured to perform image segmentation on the computer tomography image to acquire a hip cup region of interest; a screening module configured to acquire a Hounsfield unit value corresponding to each pixel coordinate and a hip cup center coordinate based on the hip cup region of interest, determine a screening region of the hip cup based on the hip cup center coordinate and a received screening condition, and process the Hounsfield unit value corresponding to each pixel coordinate based on a preset dynamic threshold method to obtain a cortical bone Hounsfield unit average value and a cancellous bone Hounsfield unit average value of the screening region; and a prediction analysis module configured to perform prediction analysis based on the user information and the cortical bone Hounsfield unit average value and the cancellous bone Hounsfield unit average value of the screening region to generate a prediction result.

[0006] The embodiment of the present disclosure also provides a hip cup prediction method based on a computer tomography image, comprising: acquiring user information and a computer tomography image of a target user; performing image segmentation on the computer tomography image to acquire a hip cup region of interest; acquiring a Hounsfield unit value corresponding to each pixel coordinate and a hip cup center coordinate based on the hip cup region of interest, determining a screening region of the hip cup based on the hip cup center coordinate and a received screening condition, and processing the Hounsfield unit value corresponding to each pixel coordinate based on a preset dynamic threshold method to obtain a cortical bone Hounsfield unit average value and a cancellous bone Hounsfield unit average value of the screening region; and performing prediction analysis based on the user information and the cortical bone Hounsfield unit average value and the cancellous bone Hounsfield unit average value of the screening region to generate a prediction result.

[0007] Optionally, the screening module is further configured to: sort the Hounsfield unit value corresponding to each pixel coordinate in ascending order to obtain a first sorting result; determine a first trabecular bone Hounsfield unit threshold value and a first cortical bone Hounsfield unit threshold value based on the sorting result, a preset first percentage value and a preset second percentage value; calculate the cortical bone Hounsfield unit average value and the trabecular bone Hounsfield unit average value of the acetabular region of interest based on the Hounsfield unit value corresponding to each pixel coordinate, the first trabecular bone Hounsfield unit threshold value and the first cortical bone Hounsfield unit threshold value; determine all Hounsfield unit values of the screening region based on the Hounsfield unit value corresponding to each pixel coordinate and the screening region, and sort the all Hounsfield unit values in ascending order to obtain a second sorting result; determine a second trabecular bone Hounsfield unit threshold value and a second cortical bone Hounsfield unit threshold value based on the second sorting result, a preset third percentage value and a preset fourth percentage value; and calculate the cortical bone Hounsfield unit average value and the trabecular bone Hounsfield unit average value of the screening region based on the all Hounsfield unit values, the second trabecular bone Hounsfield unit threshold value and the second cortical bone Hounsfield unit threshold value.

[0008] Optionally, the screening module is further configured to draw a first Hounsfield unit value histogram based on the Hounsfield unit value corresponding to each pixel coordinate, and mark the first trabecular bone Hounsfield unit threshold value and the first cortical bone Hounsfield unit threshold value on the first Hounsfield unit value histogram for display on a display device; and draw a second Hounsfield unit value histogram based on all Hounsfield unit values of the screening region, and mark the second trabecular bone Hounsfield unit threshold value and the second cortical bone Hounsfield unit threshold value on the second Hounsfield unit value histogram for display on the display device.

[0009] Optionally, the screening module is further configured to obtain a first total number of Hounsfield unit values of the acetabular region of interest and an acetabular center coordinate, and obtain a second total number of Hounsfield unit values of the screening region for display on the display device; wherein the acetabular center coordinate is updated based on a user's modification instruction.

[0010] Optionally, the image processing module is further configured to perform three-dimensional reconstruction based on the acetabulum region of interest to obtain a three-dimensional acetabulum region reconstruction image; and the screening module is further configured to mark the screening condition, the screening region, and the position of the acetabular cup in the three-dimensional acetabulum region reconstruction image for display on a display device; wherein the screening condition includes a screening radius, a screening increment value, an anteversion angle, and an abduction angle; and the position of the screening region and the acetabular cup is determined based on the screening radius, the screening increment value, the anteversion angle, and the abduction angle.

[0011] Optionally, the prediction analysis module is configured to perform prediction analysis based on the user information and the average cortical bone Hounsfield unit value and the average cancellous bone Hounsfield unit value of the screening region to generate a prediction result, specifically including: obtaining a cortical bone standard value and a cancellous bone standard value based on the user information; determining a cortical bone analysis result based on the average cortical bone Hounsfield unit value and the cortical bone standard value, and determining a cancellous bone analysis result based on the average cancellous bone Hounsfield unit value and the cancellous bone standard value; and generating the prediction result based on the cortical bone analysis result and the cancellous bone analysis result.

[0012] Optionally, the prediction analysis module is configured to perform prediction analysis based on the user information and the average cortical bone Hounsfield unit value and the average cancellous bone Hounsfield unit value of the screening region to generate a prediction result, specifically including: inputting the user information and the average cortical bone Hounsfield unit value and the average cancellous bone Hounsfield unit value of the screening region into a pre-trained prediction model to obtain a prediction score; and generating the prediction result based on the prediction score and a preset score threshold.

[0013] Optionally, the prediction analysis module is further configured to obtain sample data, wherein the sample data includes user sample information, average sample cortical bone Hounsfield unit value and average sample cancellous bone Hounsfield unit value of a sample screening region, and a prediction label; input the sample data into a regression model to be trained to obtain a prediction training result, and adjust model parameters of the regression model based on the prediction training result and the prediction label to obtain the prediction model; wherein different user features in the user sample information correspond to different training weights.

[0014] Optionally, the acetabular cup prediction system based on a computed tomography image further includes a data preprocessing and extraction module configured to preprocess the user information and the computed tomography image, and perform data extraction on the preprocessed computed tomography image to obtain user data information for display on a display device.

[0015] The embodiment of the present disclosure further provides an electronic device, comprising: a processor; a memory for storing executable instructions of the processor; the processor is used for reading the executable instructions from the memory and executing the instructions to realize the acetabular cup prediction method based on the computer tomography image provided by the embodiment of the present disclosure.

[0016] The embodiment of the present disclosure further provides a computer readable storage medium, which stores a computer program, and the computer program is used for executing the acetabular cup prediction method based on the computer tomography image provided by the embodiment of the present disclosure.

[0017] The embodiment of the present disclosure further provides a computer program product, comprising a computer program, wherein the computer program is executed by a processor to execute the acetabular cup prediction method based on the computer tomography image provided by the embodiment of the present disclosure.

[0018] The technical scheme provided by the embodiment of the present disclosure has the following advantages compared with the prior art: the acetabular cup prediction scheme based on the computer tomography image provided by the embodiment of the present disclosure, by acquiring user information and a computer tomography image of a target user; performing image segmentation on the computer tomography image to obtain an acetabular region of interest; obtaining a Hounsfield unit value corresponding to each pixel coordinate and an acetabular center coordinate based on the acetabular region of interest, determining a screening area of the acetabular cup based on the acetabular center coordinate and the received screening condition, processing the Hounsfield unit value corresponding to each pixel coordinate based on a preset dynamic threshold method to obtain a cortical bone Hounsfield unit average value and a cancellous bone Hounsfield unit average value of the screening area; performing prediction analysis based on the user information and the cortical bone Hounsfield unit average value and the cancellous bone Hounsfield unit average value of the screening area to generate a prediction result. By using the above technical scheme, the Hounsfield unit value of the computer tomography image and the user information are combined, and the dynamic threshold method is used to perform personalized analysis on the Hounsfield unit values of the cortical bone and the cancellous bone to obtain the prediction result, which can provide more objective and accurate acetabular cup stability evaluation, help optimize acetabular cup selection, improve subsequent surgical success rate, reduce the risk of postoperative complications, and fully consider the individual differences of the target user, thereby tailoring the most suitable treatment scheme for each target user. BRIEF DESCRIPTION OF DRAWINGS

[0019] The above and other features, advantages, and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the original and elements are not necessarily drawn according to the scale.

[0020] Figure 1 A structure schematic diagram of an acetabular cup prediction system based on a computer tomography image provided by the embodiment of the present disclosure;

[0021] Figure 2 Another structural schematic diagram of a hip cup prediction system based on a computer tomography image provided by an embodiment of the present disclosure;

[0022] Figure 3A An acetabular region of interest example diagram provided by an embodiment of the present disclosure;

[0023] Figure 3B A three-dimensional acetabular region reconstruction image example diagram provided by an embodiment of the present disclosure;

[0024] Figure 4 An information display example diagram provided by an embodiment of the present disclosure;

[0025] Figure 5 A histogram example diagram provided by an embodiment of the present disclosure;

[0026] Figure 6 A model training example diagram provided by an embodiment of the present disclosure;

[0027] Figure 7 A flowchart example diagram of a hip cup prediction based on a computer tomography image provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0028] Embodiments of the present disclosure will be described in more detail by referring to the drawings. Although certain embodiments of the present disclosure are shown in the drawings, it is understood that the present disclosure can be implemented in various forms, and should not be construed as being limited to the embodiments set forth herein, but rather the embodiments are provided to more thoroughly and completely understand the present disclosure. It is understood that the drawings and embodiments of the present disclosure are for exemplary purposes only, and are not intended to limit the scope of protection of the present disclosure.

[0029] It is understood that each step recited in the method embodiments of the present disclosure can be executed in different order, and / or in parallel. In addition, the method embodiments can include additional steps and / or omit the execution of the steps shown. The scope of the present disclosure is not limited in this respect.

[0030] The term "comprising" and variations thereof as used herein are open-ended, that is "including, but not limited to". The term "based on" means "based, at least in part, on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Related definitions are given throughout the description.

[0031] It should be noted that the "first", "second", and the like mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0032] It should be noted that the "one", "multiple" modification mentioned in the present disclosure is illustrative and not restrictive, and those skilled in the art should understand that unless the context clearly indicates otherwise, it should be understood as "one or more".

[0033] The names of the messages or information exchanged between the plurality of devices in the embodiments of the present disclosure are only for illustrative purposes, and are not used to limit the scope of the messages or information.

[0034] Specifically, the bone density analysis is based on the Hounsfield Unit (HU) value in computed tomography (CT), which is used to represent the relative density of tissue structures on the CT image and reflects the degree of X-ray absorption by the tissue. Compared with traditional DXA, using the HU value of the CT image for bone density analysis has significant advantages. First, the radiation dose of CT scanning is lower, effectively reducing the radiation exposure of users and avoiding the high radiation risk in traditional methods. Second, the high-resolution three-dimensional imaging technology provided by CT makes bone density assessment more accurate, especially in complex anatomical sites. In addition, CT images can comprehensively evaluate bone microstructure, providing not only bone density data but also more bone health information. The bone density evaluation method based on the HU value of the CT image can reduce the cost of diagnosis and does not require additional scanning procedures, thereby saving time and cost. The present disclosure analyzes bone quality through the HU value of the CT image, with the advantages of high efficiency, accuracy, and low radiation, which can help early diagnosis of potential risks of osteoporosis and evaluate bone quality before acetabular cup implantation, providing a scientific basis for the development of surgical plans.

[0035] Figure 1 A structural schematic diagram of an acetabular cup prediction system based on a computer tomography image provided by an embodiment of the present disclosure is shown. As shown in the figure, the method comprises: Figure 1

[0036] The data loading module 101 is configured to obtain user information and a computer tomography image of a target user.

[0037] In the embodiments of the present disclosure, the target user refers to a user to be implanted with an acetabular cup.

[0038] ​In the embodiments of the present disclosure, the user information includes user-authorized medical history information, age, gender, and the like; wherein the medical history information includes relevant information such as osteoporosis, rheumatoid arthritis, and fracture history, and the like, and can be automatically loaded with the user's medical history information by connecting with an electronic medical record system (EMR, Electronic Medical Record) interface, further improving the real-time and effectiveness of data acquisition.

[0039] In the embodiments of the present disclosure, there are many ways to obtain the computed tomography image of the target user, and the computed tomography image can be obtained by performing CT scanning on the acetabular region of the target user; or the computed tomography image can be obtained from the DICOM (Digital Imaging and Communications in Medicine, medical digital imaging and communication) file loaded or imported by the user, further improving the flexibility of data acquisition.

[0040] Therefore, the computed tomography image and the user information such as clinical information of the target user can be accurately obtained and integrated to prepare for subsequent bone analysis and stability prediction, and the accuracy of subsequent processing is ensured.

[0041] In some embodiments, as shown in Figure 2 The acetabular cup prediction system based on the computed tomography image further includes a data preprocessing and extraction module 105 for preprocessing the user information and the computed tomography image, and extracting data from the preprocessed computed tomography image to obtain user data information for display on a display device.

[0042] Specifically, the obtained computed tomography image, i.e. CT image, is denoised, standardized and image enhanced, unnecessary background noise and air values are removed, and hardening effect and zero drift correction are performed, so as to ensure stable image quality, reduce errors and uncertainties in the image.

[0043] In addition, since there may be differences in the Hounsfield unit value calibration of different scanning devices, the CT image can be uniformly standardized to ensure that the CT images from different scanning devices are consistent and comparable, further ensuring the accuracy of the subsequent acetabular cup prediction based on the computed tomography image.

[0044] Specifically, by using a unified format (such as HL7 or FHIR protocol), the user information of the target user can be conveniently loaded, ensuring that the data between different medical systems can be seamlessly interoperated, so that the user information from different sources can be uniformly processed and analyzed, thereby improving the reliability of the data and the compatibility of the system.

[0045] Specifically, the basic information of the target user such as age, gender, medical history, etc. is automatically extracted from the CT image by using the OCR (Optical Character Recognition) technology and the NLP (Natural Language Processing) model, and all the extracted information is automatically classified and displayed on the display interface of the display device for real-time viewing by the user.

[0046] In this way, the processing of the target user data can be more efficient and accurate through data preprocessing and extraction, and different sources of data can be smoothly integrated and provide a reliable basis for subsequent analysis through standardized and automated processing.

[0047] The image processing module 102 is configured to perform image segmentation on the computed tomography image to obtain an acetabulum region of interest.

[0048] In the embodiments of the present disclosure, the bone tissue in the CT image is accurately extracted by the edge detection method, and irrelevant areas are removed; the target structure such as the bone tissue can be distinguished in the complex CT image for subsequent analysis.

[0049] In the embodiments of the present disclosure, the advanced Sobel algorithm is adopted, and the morphological method is used for accurate segmentation of the acetabulum region, that is, the edge information of the computed tomography image is extracted by two direction convolution kernels (horizontal and vertical), so as to extract the bone tissue in the CT image and remove irrelevant areas; thus, the acetabulum and the surrounding bone structure can be accurately segmented, and after the segmentation is completed, the ROI (Region of Interest) extraction method is further used to detect the edge information in the image by the Sobel operator, so as to determine the ROI region. The Sobel operator can capture the gradient change in the CT image, ensure that only the acetabulum and the related bone tissue are extracted, and remove other irrelevant areas to obtain the acetabulum region of interest.

[0050] It should be noted that a user interactive interface can be provided to manually adjust or correct the segmented acetabulum region of interest to avoid errors that may occur in the automatic process, thereby ensuring the accuracy and reliability of the extraction of the acetabulum region of interest.

[0051] In some embodiments, the image processing module 102 is further configured to perform three-dimensional reconstruction based on the acetabulum region of interest to obtain a three-dimensional acetabulum region reconstruction image.

[0052] Specifically, a corresponding three-dimensional reconstruction algorithm (such as a structured light method, a stereo vision method, and a voxel reconstruction method, etc.) is selected according to the CT scan resolution and scan quality of the target user, and a three-dimensional reconstruction is performed on the acetabular region of interest according to the determined three-dimensional reconstruction algorithm, so as to ensure that the acetabular region can be accurately reconstructed, and a three-dimensional acetabular region reconstruction image is obtained, for example, as shown in Figure 3A . Figure 3B .

[0053] Therefore, the image processing module can provide accurate and clear three-dimensional acetabular region reconstruction images for subsequent analysis, ensure that high-quality image data is used in the analysis and prediction process, and further improve the accuracy of acetabular cup stability evaluation.

[0054] The screening module 103 is configured to obtain the Hounsfield unit value corresponding to each pixel coordinate and the acetabular center coordinate based on the acetabular region of interest, determine a screening region of the acetabular cup based on the acetabular center coordinate and the received screening condition, and process the Hounsfield unit value corresponding to each pixel coordinate based on a preset dynamic threshold method to obtain the average Hounsfield unit value of the cortical bone and the average Hounsfield unit value of the cancellous bone in the screening region.

[0055] In the embodiments of the present disclosure, the Hounsfield unit value corresponding to each pixel coordinate in the acetabular region of interest and the acetabular center coordinate of the acetabular region of interest can be obtained; the screening condition input by the user includes a screening radius, a screening increment value, an anteversion angle, an abduction angle, etc., and the screening region can be determined according to the screening condition and the acetabular center coordinate, so as to obtain the Hounsfield unit value corresponding to each pixel coordinate in the screening region. The Hounsfield unit value corresponding to each pixel coordinate in the screening region can be processed by a preset dynamic threshold method, and the average Hounsfield unit value of the cortical bone and the average Hounsfield unit value of the cancellous bone in the screening region can be obtained.

[0056] In some embodiments, the Hounsfield unit values corresponding to each pixel coordinate in the acetabular region of interest are sorted in ascending order to obtain a first sorting result, and a first cancellous bone Hounsfield unit threshold and a first cortical bone Hounsfield unit threshold are determined based on the sorting result, a preset first percentage value, and a preset second percentage value; the Hounsfield unit values corresponding to each pixel coordinate, the first cancellous bone Hounsfield unit threshold, and the first cortical bone Hounsfield unit threshold are calculated to obtain the average Hounsfield unit value of the cortical bone and the average Hounsfield unit value of the cancellous bone in the acetabular region of interest.

[0057] Specifically, the Hounsfield unit value corresponding to each pixel coordinate in the acetabular region of interest is segmented by a dynamic threshold method. First, the Hounsfield unit value corresponding to each pixel coordinate in the acetabular region of interest is sorted in ascending order. Then, a first cancellous bone Hounsfield unit threshold and a first cortical bone Hounsfield unit threshold are determined according to a preset first percentage value, such as the 20% percentile, and a preset second percentage value, such as the 80% percentile. It can be understood that the cancellous bone Hounsfield unit value is within the range of 20% to 80%, and the cortical bone Hounsfield unit value is greater than or equal to the 80% percentile value, so as to distinguish the HU value data according to the threshold, and calculate the cortical bone Hounsfield unit average value and the cancellous bone Hounsfield unit average value of the acetabular region of interest, respectively.

[0058] In some embodiments, based on the Hounsfield unit value corresponding to each pixel coordinate and the screening region, all Hounsfield unit values of the screening region are determined, and all Hounsfield unit values are sorted in ascending order to obtain a second sorting result; based on the second sorting result, a preset third percentage value and a preset fourth percentage value, a second cancellous bone Hounsfield unit threshold and a second cortical bone Hounsfield unit threshold are determined; based on all Hounsfield unit values, the second cancellous bone Hounsfield unit threshold and the second cortical bone Hounsfield unit threshold, the cortical bone Hounsfield unit average value and the cancellous bone Hounsfield unit average value of the screening region are calculated.

[0059] Specifically, after the screening region is determined, the HU values of the cortical bone and cancellous bone in the screening region can be distinguished based on the dynamic threshold algorithm, and the average value of the screened bone region is calculated, that is, the cortical bone Hounsfield unit average value and the cancellous bone Hounsfield unit average value of the screening region are obtained.

[0060] In some embodiments, the screening module 103 is further configured to draw a first Hounsfield unit value histogram based on the Hounsfield unit value corresponding to each pixel coordinate, and mark the first cancellous bone Hounsfield unit threshold and the first cortical bone Hounsfield unit threshold on the first Hounsfield unit value histogram for display on the display device.

[0061] In some embodiments, the screening module 103 is further configured to draw a second Hounsfield unit value histogram based on all Hounsfield unit values of the screening region, and mark the second cancellous bone Hounsfield unit threshold and the second cortical bone Hounsfield unit threshold on the second Hounsfield unit value histogram for display on the display device.

[0062] In some embodiments, the screening module 103 is further configured to obtain a first total number of Hounsfield unit values of the acetabular region of interest and an acetabular center coordinate, and obtain a second total number of Hounsfield unit values of the screening region for display on the display device; wherein the acetabular center coordinate is updated based on a user's modification instruction.

[0063] Specifically, the acetabulum region of interest is taken as a mask to extract the pixel coordinates and corresponding HU values in the region, and a HU value histogram is drawn, which can intuitively show the HU value distribution of the target user and provide a clearer reference. At the same time, the acetabular center coordinates are automatically extracted, and the extracted HU value number and acetabular center coordinates (supporting manual modification) are displayed in the interactive interface, ensuring the accuracy and convenience of the data.

[0064] Specifically, in order to ensure the accuracy of the dynamic threshold, the dynamic threshold is displayed and marked on the histogram to help intuitively analyze and verify the accuracy of the threshold; the calculated results are displayed in real time in the interactive interface.

[0065] Specifically, based on the acetabular cup center coordinates extracted automatically or manually modified, the user inputs the acetabular cup outer edge radius (screening radius) and the relative increment (screening increment value) according to actual needs, which can determine the screening area around the acetabular cup.

[0066] It should be noted that in order to ensure that the screening area meets the actual situation, the acetabular cup area should be hemispherical, that is, the screening area must be located above the Z-axis of the sphere center. In addition, considering the actual clinical situation, the anteversion angle and abduction angle need to be set when the acetabular cup is implanted, and the screening area will be rotated according to these angles to ensure that the screened bone quality area is consistent with the actual implantation direction; the coordinates after rotation combined with the range between the two radii will ensure accurate acquisition of bone quality data around the acetabular cup.

[0067] In some embodiments, the screening module 103 is further configured to mark the screening conditions, the screening area, and the position of the acetabular cup in the three-dimensional acetabular region reconstruction image for display on a display device; wherein the screening conditions include the screening radius, the screening increment value, the anteversion angle, and the abduction angle; and the screening area and the position of the acetabular cup are determined based on the screening radius, the screening increment value, the anteversion angle, and the abduction angle.

[0068] Specifically, when the user inputs the screening conditions (such as the screening radius R1, the screening increment value Ad, the anteversion angle, and the abduction angle, etc.), it will be updated in real time to the three-dimensional visualization area, as shown in Figure 4 The acetabular center coordinates are (368, 249), and the screening conditions such as the screening radius R1 are equal to the Cupsize of 26 mm, and the screening increment value Increment, Ad is 2 mm, etc., so that the screening area can be determined, and the Figure 4 It can be seen that the position of the acetabular cup is marked and the three-dimensional reconstruction result is dynamically viewed; this interactive function enhances the visualization effect and helps the user to more accurately screen the bone quality.

[0069] Specifically, the HU values after screening are further processed by combining the input screening radius and screening increment value with the rotated spherical coordinates; the HU values of the cortical bone and cancellous bone in the screening area are distinguished, and the average value of the bone quality area after screening is calculated; the final screening result (including the number and average value of the HU values after screening) is displayed on the interactive interface, and the dynamic threshold after screening is marked in the histogram, facilitating intuitive evaluation and analysis of data, such as Figure 5 As shown in Figure 5 The left two dashed lines in the middle are the 20% percentile threshold dividing lines, the original cancellous bone threshold is 14, and the processed cancellous bone threshold is 7; the right two dashed lines are the 80% percentile threshold dividing lines, the original cortical bone threshold is 466, and the processed cortical bone threshold is 455.

[0070] Therefore, the bone quality HU values around the acetabular cup can be accurately screened, and the cortical bone and cancellous bone can be analyzed, providing high-quality data support for subsequent acetabular cup stability prediction; the three-dimensional position of the acetabular cup and the individual differences of the target user are fully considered in the screening process, ensuring the accuracy and personalization of the analysis results.

[0071] The prediction analysis module 104 is configured to perform prediction analysis based on the user information and the average HU values of the cortical bone and cancellous bone in the screening area, and generate a prediction result.

[0072] In some embodiments, the prediction analysis module 104 is specifically configured to obtain cortical bone standard values and cancellous bone standard values based on the user information, determine a cortical bone analysis result based on the average HU value of the cortical bone and the cortical bone standard values, and determine a cancellous bone analysis result based on the average HU value of the cancellous bone and the cancellous bone standard values; and generate a prediction result based on the cortical bone analysis result and the cancellous bone analysis result.

[0073] Specifically, different standards are set for the HU average values of the cortical bone and cancellous bone of the target user according to the age, gender, and medical history (such as osteoporosis) of the target user, and these standards are compared with the calculated HU average values of the cortical bone and cancellous bone after screening to obtain the final prediction result. Different age, gender, and medical history of the target user will have different standard value settings, and these standard values can be flexibly adjusted and optimized according to actual needs.

[0074] Specifically, the HU average of the cortical bone is divided into three intervals: normal, bone mass reduction, and osteoporosis according to different age groups, genders, and bone density conditions. For example, for the age group of 18 to 40 years old: cortical bone HU average > 700 indicates normal cortical bone density; 350 < cortical bone HU average ≤ 700 indicates bone mass reduction; and cortical bone HU average < 115 indicates a higher risk of osteoporosis; for the age group of 41 to 60 years old: cortical bone HU average > 600 indicates normal cortical bone density; 350 < cortical bone HU average ≤ 600 indicates bone mass reduction; and cortical bone HU average < 110 indicates a higher risk of osteoporosis; and for the age group of more than 60 years old: cortical bone HU average > 500 indicates normal cortical bone density; 350 < cortical bone HU average ≤ 500 indicates bone mass reduction; and cortical bone HU average < 100 indicates a higher risk of osteoporosis.

[0075] It should be noted that the adjustment according to gender is also possible, for example, the cortical bone HU average of a female > 600 indicates normal cortical bone density; and the cortical bone HU average of a male > 700 indicates normal cortical bone density.

[0076] It should be noted that for a target user with a history of osteoporosis or other bone metabolism abnormalities, further analysis and evaluation are performed in combination with the calculated cortical bone HU average and the trabecular bone HU average.

[0077] Specifically, the HU average of the trabecular bone is also divided into three intervals: normal, bone mass reduction, and osteoporosis according to different age groups, genders, and bone density conditions. For the age group of 18 to 40 years old: trabecular bone HU average > 160 indicates normal trabecular bone density; 115 < trabecular bone HU average ≤ 160 indicates bone mass reduction; and trabecular bone HU average < 115 indicates a higher risk of osteoporosis; for the age group of 41 to 60 years old: trabecular bone HU average > 150 indicates normal trabecular bone density; 110 < trabecular bone HU average ≤ 150 indicates bone mass reduction; and trabecular bone HU average < 110 indicates a higher risk of osteoporosis; and for the age group of more than 60 years old: trabecular bone HU average > 130 indicates normal trabecular bone density; 100 < trabecular bone HU average ≤ 130 indicates bone mass reduction; and trabecular bone HU average < 100 indicates a higher risk of osteoporosis.

[0078] It should be noted that the adjustment according to gender is also possible, for example, the trabecular bone HU average of a female > 150 indicates normal trabecular bone density; and the trabecular bone HU average of a male > 160 indicates normal trabecular bone density.

[0079] In some embodiments, the corresponding evaluation suggestion information can also be output according to the HU average values of the cortical bone and the cancellous bone. Specifically, the evaluation suggestion information includes strong bone support: the HU average values of the cortical bone and the cancellous bone are both within the normal range, indicating that the user has strong bone support, and it is recommended to use conventional implant technology; high risk of osteoporosis: the HU average values of the cortical bone and the cancellous bone are both lower than the normal value, indicating a high risk of osteoporosis, and it is suggested to use additional fixation measures or further evaluate the bone quality; cortical bone or cancellous bone problem: if the cortical bone HU average value is low, attention should be paid to the stability of the cortical bone, and special acetabular cup design may be needed; if the cancellous bone HU average value is low, attention should be paid to the stability of the cancellous bone, and additional fixation measures may be needed; insufficient data: if no definite conclusion can be drawn from the data, it is indicated that the data is insufficient, and the user is required to provide more CT data for further analysis.

[0080] In some embodiments, the prediction analysis module 104 is specifically configured to input the user information and the cortical bone HU average value and the cancellous bone HU average value of the screening area into a pre-trained prediction model to obtain a prediction score; and generate a prediction result based on the prediction score and a preset score threshold.

[0081] In some embodiments, the prediction analysis module is further configured to obtain sample data; wherein the sample data includes user sample information, sample cortical bone sample HU average value and sample cancellous bone sample HU average value of a sample screening area, and a prediction label; input the sample data into a regression model to be trained to obtain a prediction training result, and adjust model parameters of the regression model based on the prediction training result and the prediction label to obtain a prediction model; wherein different user features in the user sample information correspond to different training weights.

[0082] Specifically, based on the CT data and user information (such as the HU average values of the cortical bone and the cancellous bone, age, gender, medical history, etc.) of multiple users, a regression model is trained using a machine learning algorithm; wherein the sample data for training includes user data with and without osteoporosis, ensuring that the model has strong generalization ability; cross-validation and other techniques are used to evaluate the model, and the prediction accuracy of the model is continuously optimized; the reliability and prediction accuracy of the model are improved by adjusting the model parameters, increasing the training data, etc. For example, as shown in FIG. 8, the input features include the HU average values of the cortical bone and the cancellous bone, age, gender, and medical history, and different input features correspond to different training weights (w1, w2, w3, and w4 as shown in the figure) to train the model and output a score as a prediction training result, and the model parameters of the regression model are adjusted based on the prediction training result and the prediction label to obtain a prediction model. Figure 6

[0083] ​Specifically, the acetabular cup stability score prediction uses a new user's CT data to enter the prediction model, and the trained prediction model predicts the acetabular cup stability score. For example, if the predicted score is ≥0.85, conventional implantation techniques are recommended; if the score is between 0.70 and 0.85, further evaluation may be required; and if the score is <0.70, additional fixation measures or a specially designed acetabular cup are recommended.

[0084] Specifically, a machine learning regression model is trained using a sample of user data (such as the average HU values ​​for cortical and cancellous bone, as well as other user characteristics such as age, gender, and medical history). Based on the trained regression model and the user's characteristic input, a prediction is made to calculate the acetabular cup stability score.

[0085] For example, if the predicted score is ≥ the scoring threshold, such as 0.85, the acetabular cup is determined to be stable and conventional implantation technology is recommended; if the scoring threshold is 0.70≤predicted score<score threshold 0.85: the acetabular cup stability is average and further evaluation may be required; if the predicted score is <score threshold 0.70: the acetabular cup stability is poor, and additional fixation measures or special acetabular cup design are recommended.

[0086] Therefore, through dynamic threshold evaluation and / or machine learning model prediction, it is possible to combine the individual differences and specific circumstances of users to provide more accurate acetabular cup stability predictions and suggestions, optimize hip replacement surgery plans, and improve the success rate of surgery.

[0087] In some embodiments, the acetabular cup prediction system based on computed tomography images may further include a report printing module for printing content including user basic information, visualization diagrams, key thresholds, etc.; wherein the user basic information includes basic information such as name, gender, age, date of birth and medical history to ensure the personalization and accuracy of the report; the visualization diagram includes a three-dimensional acetabular area reconstructed image, which generates a three-dimensional image of the acetabular area through three-dimensional reconstruction technology, intuitively displaying the acetabular cup implantation position and the surrounding bone conditions; dynamic marking information includes displaying key parameters of the acetabular area, such as the screening radius (outer edge radius R1), the screening increment value (increment Δd), the anteversion angle and the abduction angle, etc. These parameters will be dynamically displayed in the diagram to better understand the stability of the acetabular cup implantation; HU value histogram and dynamic threshold: including providing a histogram of the user's HU value, and marking the dynamic threshold and its marking line. The histogram can clearly reflect the HU value distribution of cortical bone and cancellous bone, and the marking line can intuitively display the segmented cortical bone and cancellous bone thresholds.

[0088] Among them, the key threshold values include screening radius, screening increment value, anteversion angle and abduction angle, etc. The parameters will be listed in the report, and the analysis results of the bone quality around the acetabular cup screened based on these values will be provided; the acetabular center coordinates are extracted and displayed, providing positioning reference for subsequent stability evaluation; the average values of the original cortical bone and cancellous bone HU values are provided for reference; the average values of the cortical bone and cancellous bone HU values after screening are displayed to make accurate judgments; the number of HU values before and after screening is counted and displayed to understand the integrity of the data quantity; the evaluation standard values include the evaluation standard values of cortical bone and cancellous bone of different age groups, genders and other groups. These threshold values are set according to clinical experience and expert recommendations to ensure the individualization and accuracy of the evaluation results; the prediction results are based on the calculated average values of the cortical bone and cancellous bone HU and the model prediction score to provide the final conclusion of the acetabular cup stability evaluation; for example, the bone quality support is strong, and it is recommended to use conventional implant technology; the risk of osteoporosis is high, and it is recommended to use additional fixation measures or further evaluate the bone quality; the cortical bone or cancellous bone has problems, and specific acetabular cup design suggestions are provided according to the specific problems; insufficient data, reminding that more data is needed to improve the evaluation.

[0089] As an example, import user CT images and user information and store and classify them; standardize and homogenize the extracted CT images and user information (such as denoising, image enhancement, HU value homogenization, and history information format unification, etc.), and transmit the processed data to the image processing module; accurately extract the bone tissue in the CT image using image segmentation algorithm, and remove irrelevant areas; calibrate key information in the segmented acetabular region through ROI extraction method, ensure that the extracted region only includes the bone tissue around the acetabulum, and avoid false segmentation; among them, the segmentation result can be manually adjusted through an interactive graphical interface to ensure accuracy, and three-dimensional reconstruction is performed based on the ROI extracted region; screen the bone HU value and calculate: use the segmented acetabular region mask to further extract the pixel coordinates and HU values in the region, and draw the corresponding HU value histogram to intuitively display the HU value distribution of the user; use 20% percentile and 80% percentile to segment the cortical bone and cancellous bone HU values of the acetabular region through dynamic threshold method, distinguish the cortical bone and cancellous bone, and calculate the average HU values of the cortical bone and cancellous bone respectively.

[0090] Further, input screening and constraint conditions: input the acetabular cup radius R1, increment Δd, anteversion angle and abduction angle based on the preliminary known information of the user, ensure that the screened bone area meets the implant direction of the actual acetabular cup; based on the extracted acetabular center and HU value coordinates within the screening range, use the dynamic threshold method to distinguish the cortical bone and cancellous bone HU values within the acetabular cup after screening and calculate their average values; dynamically update the display, after inputting the screening conditions, the three-dimensional visualization area will be updated in real time, mark the acetabular cup position and related numerical values, and the histogram displays the dynamic threshold dividing line; according to the user's age, gender, medical history and calculated HU values of the cortical bone and cancellous bone after screening, dynamic threshold judgment is performed; for example, if the user is a 60-year-old male, the cortical bone HU value is above 500, and the cancellous bone HU value is above 130, it will be displayed that the bone quality support is strong, and the conventional implantation technology is recommended.

[0091] In addition, by analyzing the user's HU value and other user information (such as age, gender, medical history, etc.) through a machine learning model, the stability score of the acetabular cup is predicted; assuming that the stability score of this user is 0.88, the prediction result is "acetabular cup stability is good, recommend conventional implantation technology"; after the data analysis is completed, the user's acetabular cup implant stability analysis report is automatically generated; the report includes the user's basic information, HU value histogram, three-dimensional view, analysis results of cortical bone and cancellous bone, predicted stability score, related suggestions, etc., the report can be exported in PDF format, etc., for easy viewing and printing.

[0092] Therefore, by combining the HU value of the CT image and the user information (such as age, gender, medical history, etc.), and using the dynamic threshold judgment method to analyze the HU values of the cortical bone and cancellous bone individually; combined with the machine learning regression model, further use the user's HU value, age, gender, medical history, etc. as input data for training, predict the stability score of the acetabular cup; according to the prediction result and combined with the dynamic threshold judgment result, provide personalized implantation suggestions or risk prompts; through this automatic analysis and personalized prediction method, the present disclosure provides a more objective and accurate acetabular cup stability evaluation, which helps to optimize the selection of acetabular cup, improve the success rate of surgery, reduce the risk of postoperative complications, and fully considers the individual differences of the user, thereby tailoring the most suitable treatment plan for each user.

[0093] The hip cup prediction scheme based on a computer tomography image provided by the embodiments of the present disclosure combines CT image data and user information of a user, and realizes accurate evaluation of the stability of a hip cup after implantation through multi-level data processing and analysis; a data loading module loads CT scan data of the user and imports user information (such as medical history, age, gender, etc.); then a data preprocessing and extraction module performs denoising, standardization and image enhancement processing on the data, automatically extracts basic information of the user, and reduces errors that may be caused by manual input; an image processing module performs image segmentation using an edge detection method, and provides a visual acetabular region through a three-dimensional reconstruction technology, so as to facilitate analysis and observation; then a HU value module of bone around the hip cup extracts HU values of the bone around the hip cup in combination with a screening condition and a rotation coordinate, and calculates average values of cortical bone and cancellous bone, thereby providing basic data for subsequent prediction; finally, a prediction analysis module predicts the stability of the hip cup and gives personalized implantation suggestions through a dynamic threshold evaluation method and a machine learning model in combination with the HU values of the user and the user information; through accurate data analysis and model prediction, more reliable acetabular cup stability evaluation is provided for a hip replacement surgery, the risk of postoperative complications is reduced, the surgical plan is optimized, and therefore the success rate of the surgery and the postoperative recovery quality of the user are improved.

[0094] Figure 7 The flowchart of another hip cup prediction method based on a computer tomography image provided by the embodiments of the present disclosure, the embodiments further optimize the above-mentioned hip cup prediction method based on a computer tomography image on the basis of the above-mentioned embodiments. As shown in the figure, Figure 7 the method comprises:

[0095] Step 201: obtaining user information and a computer tomography image of a target user.

[0096] Step 202: performing image segmentation on the computer tomography image to obtain an acetabular region of interest.

[0097] Step 203: obtaining a Hounsfield unit value corresponding to each pixel coordinate and an acetabular center coordinate based on the acetabular region of interest, determining a screening region of the hip cup based on the acetabular center coordinate and a received screening condition, and processing the Hounsfield unit value corresponding to each pixel coordinate based on a preset dynamic threshold method to obtain a cortical bone Hounsfield unit average value and a cancellous bone Hounsfield unit average value of the screening region.

[0098] Step 204: performing prediction analysis based on the user information and the cortical bone Hounsfield unit average value and the cancellous bone Hounsfield unit average value of the screening region to generate a prediction result.

[0099] The acetabular cup prediction method based on a computer tomography image provided in the embodiments of the present disclosure can execute the acetabular cup prediction system based on a computer tomography image provided in any of the embodiments of the present disclosure, and has the corresponding function modules and beneficial effects of the execution method.

[0100] The embodiments of the present disclosure also provide a computer program product, which comprises computer programs / instructions, and the computer programs / instructions are executed by a processor to implement the acetabular cup prediction method based on a computer tomography image provided in any of the embodiments of the present disclosure.

[0101] It should be noted that the computer readable medium of the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or apparatus. In the present disclosure, the computer readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, which carries computer readable program code. Such a propagated data signal can take many forms, including but not limited to an electromagnetic signal, an optical signal or any suitable combination of the above. The computer readable signal medium can also be any computer readable medium other than the computer readable storage medium, which can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, device or apparatus. The program code contained in the computer readable medium can be transmitted by any suitable medium, including but not limited to a wire, a cable, an RF (radio frequency) or the like, or any suitable combination of the above.

[0102] In some embodiments, the client, server, or other computing machines utilized by the system can communicate information using any known or future developed end-to-end communication protocol, such as the Hyper Text Transfer Protocol (HTTP), and can be interconnected via any form or medium of digital data communication (for example, a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet, and peer-to-peer networks (for example, ad hoc peer-to-peer networks), as well as any current or future developed network.

[0103] The computer-readable medium described above can be included in the electronic device described above; alternatively, the computer-readable medium can exist as a standalone entity.

[0104] The computer-readable medium described above carries one or more programs which, when executed by the electronic device, enable the electronic device to perform the acetabular cup prediction method based on computed tomography images.

[0105] Computer program code for carrying out operations of the present disclosure can be written in any of one or more programming languages, including but not limited to object oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network ("LAN") or a wide area network ("WAN"), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0106] The computer program product of the first aspect can include one or more non-transitory computer-readable media storing instructions that, when executed, cause one or more processors to perform the operations of the corresponding method aspects. The computer program product of the first aspect can include one or more non-transitory computer-readable media storing instructions that, when executed, cause one or more processors to perform the operations of the corresponding method aspects.

[0107] The units described in the embodiments of the present disclosure can be implemented by software, or by hardware, or by a combination of software and hardware. In some cases, the names of the units do not constitute a limitation on the units themselves.

[0108] The functions described in this description above can be implemented in hardware, software, or any combination thereof. If implemented in software, the functions can be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media include both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media can be any available media that can be accessed by a general purpose or special purpose computer. By way of example, and not limitation, such computer-readable media can comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code means in the form of instructions or data structures and that can be accessed by a general-purpose or special-purpose computer, or a general-purpose or special-purpose processor. Also, functional

[0109] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more of: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0110] According to one or more embodiments of the present disclosure, the present disclosure provides an electronic device, comprising:

[0111] a processor;

[0112] a memory for storing the processor-executable instructions;

[0113] the processor, configured to read the executable instructions from the memory and execute the instructions to implement any of the computer tomography image based acetabular cup prediction methods provided by the present disclosure.

[0114] According to one or more embodiments of the present disclosure, the present disclosure provides a computer readable storage medium, which stores a computer program for executing any of the computer tomography image based acetabular cup prediction methods provided by the present disclosure.

[0115] The above description merely provides preferred embodiments of the present disclosure and a description of the technical principles of the present disclosure. It should be understood by those skilled in the art that the disclosed scope of the present disclosure is not limited to the technical solutions with the specific combinations of the above technical features, and also covers other technical solutions formed by combining the above technical features or equivalent features without departing from the technical concepts disclosed above. For example, the technical solutions formed by replacing the above features with other technical features disclosed in the present disclosure (but not limited to) with similar functions.

[0116] In addition, although each operation is depicted in a particular order, this should not be understood as requiring the operations to be performed in the particular order shown or in a sequential order. In certain circumstances, multitasking and parallel processing can be advantageous. Similarly, although several implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Certain features described in the context of separate embodiments can also be combined in a single embodiment. Conversely, various features described in the context of a single embodiment can also be implemented separately or in any suitable subcombination.

[0117] Although the subject matter has been described in language specific to structural features and / or methodological acts, it is to be understood that the subject defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

Claims

1. A computer tomography image based acetabular cup prediction system, characterized in that, The system comprises: a data loading module configured to acquire user information of a target user and a computed tomography image; an image processing module configured to perform image segmentation on the computed tomography image to obtain an acetabulum region of interest; a screening module configured to acquire a Hounsfield unit value corresponding to each pixel coordinate and an acetabulum center coordinate based on the acetabulum region of interest, determine a screening region of an acetabular cup based on the acetabulum center coordinate and a received screening condition, and process the Hounsfield unit value corresponding to each pixel coordinate based on a preset dynamic threshold method to obtain a cortical bone Hounsfield unit average value and a cancellous bone Hounsfield unit average value of the screening region; a prediction analysis module configured to perform prediction analysis based on the user information and the cortical bone Hounsfield unit average value and the cancellous bone Hounsfield unit average value of the screening region to generate a prediction result. In the screening module, the Hounsfield unit value corresponding to each pixel coordinate is sorted in ascending order to obtain a first sorting result, a first cancellous bone Hounsfield unit threshold and a first cortical bone Hounsfield unit threshold are determined based on the sorting result, a preset first percentage value and a preset second percentage value, a cortical bone Hounsfield unit average value and a cancellous bone Hounsfield unit average value of the acetabulum region of interest are calculated based on the Hounsfield unit value corresponding to each pixel coordinate, the first cancellous bone Hounsfield unit threshold and the first cortical bone Hounsfield unit threshold, all Hounsfield unit values of the screening region are determined based on the Hounsfield unit value corresponding to each pixel coordinate and the screening region, the all Hounsfield unit values are sorted in ascending order to obtain a second sorting result, a second cancellous bone Hounsfield unit threshold and a second cortical bone Hounsfield unit threshold are determined based on the second sorting result, a preset third percentage value and a preset fourth percentage value, and the cortical bone Hounsfield unit average value and the cancellous bone Hounsfield unit average value of the screening region are calculated based on the all Hounsfield unit values, the second cancellous bone Hounsfield unit threshold and the second cortical bone Hounsfield unit threshold.

2. The system of claim 1, wherein the screening module is further configured to draw a first Hounsfield unit value histogram based on the Hounsfield unit value corresponding to each pixel coordinate, and mark the first cancellous bone Hounsfield unit threshold and the first cortical bone Hounsfield unit threshold in the first Hounsfield unit value histogram for display on a display device; the screening module is further configured to draw a second Hounsfield unit value histogram based on all Hounsfield unit values of the screening region, and mark the second cancellous bone Hounsfield unit threshold and the second cortical bone Hounsfield unit threshold in the second Hounsfield unit value histogram for display on the display device.

3. The system of claim 2, wherein ​ ​ ​ ​ ​ ​ The screening module is further configured to acquire a total number of first Hounsfield unit values of the acetabular region of interest and a center coordinate of the acetabulum, and acquire a total number of second Hounsfield unit values of the screening region for display on the display device; and update the center coordinate of the acetabulum based on a modification instruction of a user.

4. The system of claim 1, wherein, The image processing module is further configured to perform three-dimensional reconstruction based on the acetabular region of interest to obtain a three-dimensional acetabular region reconstruction image. The screening module is further configured to mark positions of the screening condition, the screening region, and the acetabular cup in the three-dimensional acetabular region reconstruction image for display on the display device; wherein the screening condition includes a screening radius, a screening increment value, an anteversion angle, and an abduction angle; and the positions of the screening region and the acetabular cup are determined based on the screening radius, the screening increment value, the anteversion angle, and the abduction angle.

5. The system of claim 1, wherein, The prediction analysis module is configured to perform prediction analysis based on the user information and average values of cortical bone Hounsfield units and cancellous bone Hounsfield units of the screening region to generate a prediction result, specifically including: acquiring standard values of cortical bone and cancellous bone based on the user information; determining a cortical bone analysis result based on the average values of cortical bone Hounsfield units and the standard values of cortical bone, and determining a cancellous bone analysis result based on the average values of cancellous bone Hounsfield units and the standard values of cancellous bone; generating the prediction result based on the cortical bone analysis result and the cancellous bone analysis result.

6. The system of claim 1, wherein, The prediction analysis module is configured to perform prediction analysis based on the user information and average values of cortical bone Hounsfield units and cancellous bone Hounsfield units of the screening region to generate a prediction result, specifically including: inputting the user information and the average values of cortical bone Hounsfield units and cancellous bone Hounsfield units of the screening region into a pre-trained prediction model to obtain a prediction score; generating the prediction result based on the prediction score and a preset score threshold.

7. The system of claim 6, wherein, The prediction analysis module is further configured to acquire sample data, wherein the sample data includes user sample information, average values of sample cortical bone Hounsfield units and sample cancellous bone Hounsfield units of a sample screening region, and a prediction label; training a regression model to be trained by inputting the sample data to obtain a prediction training result, and adjusting model parameters of the regression model based on the prediction training result and the prediction label to obtain the prediction model; wherein different user features in the user sample information correspond to different training weights.

8. The system of claim 1, wherein, The acetabular cup prediction system based on computed tomography images further includes: a data preprocessing and extraction module configured to preprocess the user information and the computed tomography images, and extract data from the preprocessed computed tomography images to acquire user data information for display on a display device.

9. A computer tomography image based acetabular cup prediction method, characterized in that, including: acquiring user information and computed tomography images of a target user; performing image segmentation on the computed tomography images to acquire an acetabular region of interest; Obtaining the Hounsfield unit value corresponding to each pixel coordinate and the acetabular center coordinate based on the acetabular region of interest, determining the screening area of the acetabular cup based on the acetabular center coordinate and the received screening condition, and processing the Hounsfield unit value corresponding to each pixel coordinate based on the preset dynamic threshold method to obtain the average value of the cortical bone Hounsfield unit and the cancellous bone Hounsfield unit of the screening area; Performing prediction analysis based on the user information and the average value of the cortical bone Hounsfield unit and the cancellous bone Hounsfield unit of the screening area to generate a prediction result; The processing of the Hounsfield unit value corresponding to each pixel coordinate based on the preset dynamic threshold method to obtain the average value of the cortical bone Hounsfield unit and the cancellous bone Hounsfield unit of the screening area includes: Sorting the Hounsfield unit value corresponding to each pixel coordinate in ascending order to obtain a first sorting result; Determining a first cancellous bone Hounsfield unit threshold and a first cortical bone Hounsfield unit threshold based on the sorting result, a preset first percentage value and a preset second percentage value; Calculating based on the Hounsfield unit value corresponding to each pixel coordinate, the first cancellous bone Hounsfield unit threshold and the first cortical bone Hounsfield unit threshold to obtain the average value of the cortical bone Hounsfield unit and the cancellous bone Hounsfield unit of the acetabular region of interest; Determining all Hounsfield unit values of the screening area based on the Hounsfield unit value corresponding to each pixel coordinate and the screening area, and sorting all Hounsfield unit values in ascending order to obtain a second sorting result; Determining a second cancellous bone Hounsfield unit threshold and a second cortical bone Hounsfield unit threshold based on the second sorting result, a preset third percentage value and a preset fourth percentage value; Calculating based on all Hounsfield unit values, the second cancellous bone Hounsfield unit threshold and the second cortical bone Hounsfield unit threshold to obtain the average value of the cortical bone Hounsfield unit and the cancellous bone Hounsfield unit of the screening area.

Images