Acetabular cup prediction system and method based on computed tomography image

Abstract

The embodiment of the invention relates to an acetabular cup prediction system and method based on a computed tomography image, and relates to the technical field of medical image analysis. User information of a target user and the computed tomography image are obtained; performing image segmentation on the computed tomography image to obtain an acetabulum region of interest; the method comprises the following steps: acquiring a Henry unit value and an acetabular center coordinate corresponding to each pixel coordinate based on an acetabular region of interest, determining a screening region of an acetabular cup based on the acetabular center coordinate and a received screening condition, and processing the Henry unit value corresponding to each pixel coordinate based on a preset dynamic threshold method, obtaining a cortical bone Hensi unit average value and a cancellous bone Hensi unit average value of the screening area; and performing prediction analysis based on the user information and the cortical bone Hensi unit average value and the cancellous bone Hensi unit average value of the screening area, and generating a prediction result, 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 particularly to an acetabular cup prediction system and method based on computed tomography images. Background Art

[0002] Currently, the problem of population aging is becoming increasingly severe, and the number of users with various 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 been increasing year by year. The success or failure of total hip arthroplasty directly affects the postoperative recovery and quality of life of users, and the bone quality analysis before acetabular cup implantation is one of the key factors for evaluating the success of the surgery. Although the current total hip arthroplasty technology has been relatively mature, it still faces many clinical problems and challenges, especially in the evaluation of acetabular cup implantation stability and the formulation of individualized treatment plans.

[0003] In related technologies, the bone quality analysis before acetabular cup implantation mainly relies on dual-energy X-ray absorptiometry (DXA), which is an internationally recognized standard method for bone density measurement and also the gold standard used by the World Health Organization for diagnosing osteoporosis. However, DXA has several limitations: First, DXA has a slow measurement speed and low resolution, and can only provide two-dimensional bone density information, with a measurement error of approximately 20%, making it difficult to accurately obtain the overall bone density value; in addition, the DXA measurement results 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 combined value of cancellous bone and cortical bone, and the two are not distinguished, which makes the measurement results mainly reflect the bone density of cortical bone and it is difficult to effectively monitor the bone calcium loss in the cancellous bone part, resulting in low sensitivity. Its limitations make this method urgently need to be further improved. Summary of the Invention

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

[0005] An acetabular cup prediction system based on computed tomography images provided by an embodiment of the present disclosure includes: a data loading module for obtaining user information of a target user and computed tomography images; an image processing module for performing image segmentation on the computed tomography images to obtain an acetabular region of interest; a screening module for obtaining the Hounsfield unit value corresponding to each pixel coordinate and the acetabular center coordinate based on the acetabular region of interest, determining a screening region of the acetabular cup based on the acetabular center coordinate and received screening conditions, and processing the Hounsfield unit value corresponding to each pixel coordinate based on a preset dynamic threshold method to obtain the average cortical bone Hounsfield unit value and the average cancellous bone Hounsfield unit value of the screening region; and a prediction analysis module for performing prediction analysis based on the user information, the average cortical bone Hounsfield unit value, and the average cancellous bone Hounsfield unit value of the screening region to generate a prediction result.

[0006] An acetabular cup prediction method based on computed tomography images provided by an embodiment of the present disclosure includes: obtaining user information of a target user and computed tomography images; performing image segmentation on the computed tomography images to obtain 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 a screening region of the acetabular cup based on the acetabular center coordinate and received screening conditions, and processing the Hounsfield unit value corresponding to each pixel coordinate based on a preset dynamic threshold method to obtain the average cortical bone Hounsfield unit value and the average cancellous bone Hounsfield unit value of the screening region; and performing prediction analysis based on the user information, the average cortical bone Hounsfield unit value, and the average cancellous bone Hounsfield unit value of the screening region to generate a prediction result.

[0007] Optionally, the screening module is configured to process the Hounsfield unit value corresponding to each pixel coordinate based on a preset dynamic threshold method to obtain the average cortical bone Hounsfield unit value and the average cancellous bone Hounsfield unit value of the screening region, specifically including: sorting the Hounsfield unit values 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 the average cortical bone Hounsfield unit value and the average cancellous bone Hounsfield unit value of the acetabular region of interest 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; determining all the Hounsfield unit values of the screening region based on the Hounsfield unit value corresponding to each pixel coordinate and the screening region, and sorting all the 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 the average cortical bone Hounsfield unit value and the average cancellous bone Hounsfield unit value of the screening region based on all the Hounsfield unit values, the second cancellous bone Hounsfield unit threshold, and the second cortical bone Hounsfield unit threshold.

[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 cancellous bone Hounsfield unit threshold and the first cortical bone Hounsfield unit threshold on 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 the 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.

[0009] Optionally, the screening module is further configured to obtain the total number of first Hounsfield unit values and the acetabular center coordinates of the acetabular region of interest, and obtain the total number of second Hounsfield unit values of the screening region for display on the display device; wherein, the acetabular center coordinates are 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; the screening module is further configured to mark the screening conditions, 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 conditions include a screening radius, a screening increment value, a forward tilt angle, and an abduction angle; the screening region and the position of the acetabular cup are determined based on the screening radius, the screening increment value, the forward tilt angle, and the abduction angle.

[0011] Optionally, the prediction analysis module is configured to perform prediction analysis based on the user information, 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; 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, 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, 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; 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, the average cortical bone sample Hounsfield unit value and the average cancellous bone sample Hounsfield unit value of the sample screening region, and a prediction label; inputting the sample data into a regression model to be trained for training to obtain a prediction training result, and adjusting the 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 computer tomography images further includes: a data preprocessing and extraction module, configured to preprocess the user information and the computer tomography images, and perform data extraction on the preprocessed computer tomography images to obtain user data information for display on a display device.

[0015] An embodiment of the present disclosure also provides an electronic device, comprising: a processor; a memory for storing executable instructions of the processor; the processor is used to read the executable instructions from the memory and execute the instructions to implement the acetabular cup prediction method based on computed tomography images as provided in an embodiment of the present disclosure.

[0016] The embodiment of the present disclosure also provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is used to execute the acetabular cup prediction method based on computer tomography images as provided in the embodiment of the present disclosure.

[0017] The embodiment of the present disclosure also provides a computer program product, including a computer program, wherein the computer program is executed by a processor as the acetabular cup prediction method based on computed tomography images provided in the embodiment of the present application.

[0018] The technical solution provided by the embodiments of the present disclosure has the following advantages over the prior art: the acetabular cup prediction solution based on computer tomography images provided by the embodiments of the present disclosure obtains user information and computer tomography images of target users; performs image segmentation on the computer tomography images to obtain the acetabulum region of interest; obtains the Hounsfield unit value and the acetabulum center coordinates corresponding to each pixel coordinate based on the acetabulum region of interest, determines the acetabular cup screening area based on the acetabulum center coordinates and the received screening conditions, processes the Hounsfield unit value corresponding to each pixel coordinate based on a preset dynamic threshold method, and obtains the average value of the cortical bone Hounsfield unit and the average value of the cancellous bone Hounsfield unit in the screening area; performs prediction analysis based on the user information and the average value of the cortical bone Hounsfield unit and the average value of the cancellous bone Hounsfield unit in the screening area to generate a prediction result. By adopting the above technical solution, combining the Hounsfield unit value of the computed tomography image and the user information, and using the dynamic threshold method to perform personalized analysis of the Hounsfield unit value of the cortical bone and cancellous bone, the prediction results can be obtained, which can provide a more objective and accurate acetabular cup stability assessment, help optimize the acetabular cup selection, improve the success rate of subsequent operations, and reduce the risk of postoperative complications. It also fully considers the individual differences of the target users, so as to tailor the most appropriate treatment plan for each target user. BRIEF DESCRIPTION OF THE 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 accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0020] Figure 1 A schematic diagram of the structure of an acetabular cup prediction system based on computer tomography images provided in an embodiment of the present disclosure; Figure 2 Schematic diagram of another acetabular cup prediction system based on computed tomography images provided by an embodiment of the present disclosure; Figure 3A Example diagram of an acetabulum region of interest provided by an embodiment of the present disclosure; Figure 3B Example diagram of a three-dimensional reconstructed image of the acetabular region provided by an embodiment of the present disclosure; Figure 4 Example diagram of information display provided by an embodiment of the present disclosure; Figure 5 Example diagram of a histogram provided by an embodiment of the present disclosure; Figure 6 Example diagram of model training provided by an embodiment of the present disclosure; Figure 7 Example diagram of a process for acetabular cup prediction based on computed tomography images provided by an embodiment of the present disclosure. Detailed implementation manners

[0021] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Instead, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not used to limit the protection scope of the present disclosure.

[0022] It should be understood that the various steps recited in the method embodiments of the present disclosure can be executed in a different order and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this regard.

[0023] As used herein, the term "including" and its variations are open-ended, that is, "including but not limited to". The term "based on" is "at least partially based 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". The relevant definitions of other terms will be given in the following description.

[0024] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependent relationships.

[0025] It should be noted that the modifications of "one" and "multiple" mentioned in this disclosure are illustrative rather than restrictive. Those skilled in the art should understand that, unless clearly specified otherwise in the context, it should be understood as "one or more".

[0026] The names of the messages or information exchanged between multiple devices in the embodiments of this disclosure are only for illustrative purposes and are not used to limit the scope of these messages or information.

[0027] Specifically, bone density analysis is performed based on the Hounsfield Unit (HU) value in Computed Tomography (CT) (which is used to represent the relative density of tissue structures on CT images and reflects the degree of tissue absorption of X-rays). Compared with traditional Dual-energy X-ray Absorptiometry (DXA), using the HU value of CT images for bone density analysis has significant advantages. First, the radiation dose of CT scanning is lower, effectively reducing the user's radiation exposure and avoiding the high radiation risk in traditional methods; second, the high-resolution three-dimensional imaging technology provided by CT enables more accurate bone density assessment, especially in complex anatomical regions; in addition, CT images can comprehensively evaluate bone microstructure, providing not only bone density data but also reflecting more skeletal health information; the bone density assessment method based on the HU value of CT images can reduce the diagnostic cost and does not require additional scanning procedures, thus saving time and cost. This disclosure performs bone quality analysis through the HU value of CT images. With its advantages of high efficiency, accuracy, and low radiation, it can help diagnose the potential risk of osteoporosis at an early stage and evaluate the bone quality before acetabular cup implantation, providing a scientific basis for the formulation of surgical plans.

[0028] Figure 1 It is a schematic structural diagram of an acetabular cup prediction system based on computed tomography images provided for the embodiments of this disclosure. As Figure 1 shown, the method includes: A data loading module 101, configured to obtain user information and computed tomography images of a target user.

[0029] In the embodiments of this disclosure, a target user refers to a user to undergo acetabular cup implantation.

[0030] In the embodiments of this disclosure, the user information includes medical history information authorized by the user, age, gender, etc.; among them, the medical history information includes information related to osteoporosis, rheumatoid arthritis, fracture history, etc., and can be automatically loaded with the medical history information of the user by connecting to the interface of the Electronic Medical Record (EMR) system, further improving the real-time performance and effectiveness of data acquisition.

[0031] In the embodiments of the present disclosure, there are many ways to obtain the computed tomography (CT) image of the target user. The CT scan can be performed on the target user including the acetabular region to obtain the computed tomography image. Alternatively, the computed tomography image can be obtained from loading or importing the user's DICOM (Digital Imaging and Communications in Medicine) file, which further improves the flexibility of data acquisition.

[0032] Thus, the computed tomography image and user information such as clinical information of the target user can be accurately obtained and integrated to prepare for subsequent bone quality analysis and stability prediction, ensuring the accuracy of subsequent processing.

[0033] In some embodiments, as Figure 2 shown, the acetabular cup prediction system based on the computed tomography image further includes a data preprocessing and extraction module 105, which is used to preprocess the user information and the computed tomography image, and extract data from the preprocessed computed tomography image to obtain user data information for display on the display device.

[0034] Specifically, the obtained computed tomography image, i.e., the CT image, is denoised, normalized, and image enhanced to remove unnecessary background noise and air values, and correct the hardening effect and zero drift, thereby ensuring stable image quality and reducing errors and uncertainties in the image.

[0035] In addition, since there may be differences in the Hounsfield unit value calibration of different scanning devices, the CT images can be uniformly normalized to ensure the consistency and comparability of CT images from different scanning devices, further ensuring the accuracy of subsequent acetabular cup prediction based on the computed tomography image.

[0036] Specifically, by using a unified format (such as the HL7 or FHIR protocol), the user information of the target user can be conveniently loaded, ensuring seamless interoperability of data between different medical systems, enabling unified processing and analysis of user information from different sources, and thus improving the reliability of the data and the compatibility of the system.

[0037] Specifically, using OCR (Optical Character Recognition) technology and a natural language processing (NLP) model, the basic information of the target user, such as age, gender, medical history, etc., is automatically extracted from the CT image, and all the extracted information is automatically classified and displayed on the display interface of the display device for the user to view in real time.

[0038] Thus, through data preprocessing and extraction, it is possible to ensure that the processing process of target user data is more efficient and accurate. At the same time, through standardized and automated processing, data from different sources can be smoothly integrated and provide a reliable basis for subsequent analysis.

[0039] The image processing module 102 is used to perform image segmentation on computed tomography (CT) images to obtain the acetabulum region of interest.

[0040] In the embodiment of the present disclosure, bone tissue in the CT image is accurately extracted through an edge detection method to remove irrelevant regions; it is possible to distinguish target structures, such as bone tissue, in complex CT images for subsequent analysis.

[0041] In the embodiment of the present disclosure, an advanced Sobel algorithm is adopted, combined with a morphological method for accurate segmentation of the acetabulum region. That is, edge information of the computed tomography image is extracted through convolution kernels in two directions (horizontal and vertical), thereby extracting bone tissue in the CT image and removing irrelevant regions. Thus, the acetabulum and its surrounding bone structures can be accurately segmented. After segmentation, an ROI (Region of Interest) extraction method is further used to detect edge information in the image through the Sobel operator, thereby determining the ROI region. The Sobel operator can capture the gradient changes in the CT image to ensure that only the acetabulum and its related bone tissue are extracted, and other irrelevant regions are removed, obtaining the acetabulum region of interest.

[0042] It should be noted that a user interactive interface can be provided to enable the user to manually adjust or correct the segmented acetabulum region of interest, avoiding possible errors in the automation process, thereby ensuring the accuracy and reliability of the extraction of the acetabulum region of interest.

[0043] In some embodiments, the image processing module 102 is further used to perform three-dimensional reconstruction based on the acetabulum region of interest to obtain a three-dimensional reconstructed image of the acetabulum region.

[0044] Specifically, a corresponding three-dimensional reconstruction algorithm (such as structured light method, stereovision method, voxel reconstruction method, etc.) is selected according to the CT scan resolution and scan quality of the target user, and three-dimensional reconstruction is performed on the acetabulum region of interest according to the determined three-dimensional reconstruction algorithm to ensure that the acetabulum region can be accurately reconstructed, obtaining a three-dimensional reconstructed image of the acetabulum region. Exemplarily, as Figure 3A shown in the three-dimensional reconstruction of the acetabulum region of interest, the three-dimensional reconstructed image of the acetabulum region is as Figure 3B shown.

[0045] As a result, the image processing module can provide accurate and clear three-dimensional reconstructed images of the acetabular region for subsequent analysis, ensuring the use of high-quality image data in the analysis and prediction processes, thereby further improving the accuracy of acetabular cup stability assessment.

[0046] The screening module 103 is configured to obtain the Hounsfield unit value and the acetabular center coordinates corresponding to each pixel coordinate based on the acetabular region of interest, determine the screening region of the acetabular cup based on the acetabular center coordinates and the received screening conditions, and process the Hounsfield unit value corresponding to each pixel coordinate based on a preset dynamic threshold method to obtain the average cortical bone Hounsfield unit value and the average cancellous bone Hounsfield unit value of the screening region.

[0047] 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 coordinates of the acetabular region of interest can be obtained; when the received screening conditions input by the user include a screening radius, a screening increment value, a forward tilt angle, an abduction angle, etc., the screening region can be determined according to the screening conditions and the acetabular center coordinates, so as to obtain the Hounsfield unit value corresponding to each pixel coordinate in the screening region, and by processing the Hounsfield unit value corresponding to each pixel coordinate in the screening region through a preset dynamic threshold method, the average cortical bone Hounsfield unit value and the average cancellous bone Hounsfield unit value of the screening region can be obtained.

[0048] 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; 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, calculations are performed to obtain the average cortical bone Hounsfield unit value and the average cancellous bone Hounsfield unit value of the acetabular region of interest.

[0049] Specifically, by using the dynamic threshold method to segment the Hounsfield unit values corresponding to each pixel coordinate in the acetabular region of interest, first, the Hounsfield unit values corresponding to each pixel coordinate in the acetabular region of interest are sorted in ascending order, and then a first cancellous bone Hounsfield unit threshold and a first cortical bone Hounsfield unit threshold are respectively determined according to a preset first percentage value, such as the 20th percentile, and a preset second percentage value, such as the 80th percentile. It can be understood that the cancellous bone Hounsfield unit values are within the range of 20% to 80%, while the cortical bone Hounsfield unit values are greater than or equal to the 80th percentile value, so as to distinguish the HU value data according to this threshold and calculate the average cortical bone Hounsfield unit value and the average cancellous bone Hounsfield unit value of the acetabular region of interest respectively.

[0050] In some embodiments, based on the Hounsfield unit values corresponding to each pixel coordinate and the screening region, all the Hounsfield unit values of the screening region are determined, and all the 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 the Hounsfield unit values, the second cancellous bone Hounsfield unit threshold, and the second cortical bone Hounsfield unit threshold, calculations are performed to obtain the average cortical bone Hounsfield unit value and the average cancellous bone Hounsfield unit value of the screening region.

[0051] Specifically, after determining the screening region, the HU values of the cortical bone and cancellous bone within 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 average cortical bone Hounsfield unit value and the average cancellous bone Hounsfield unit value of the screening region are obtained.

[0052] In some embodiments, the screening module 103 is further configured to draw a first Hounsfield unit value histogram based on the Hounsfield unit values 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 a display device.

[0053] In some embodiments, the screening module 103 is further configured to draw a second Hounsfield unit value histogram based on all the 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 a display device.

[0054] In some embodiments, the screening module 103 is further configured to obtain the total number of first Hounsfield unit values and the acetabular center coordinates of the acetabular region of interest, and obtain the total number of second Hounsfield unit values of the screening region for display on a display device; wherein, the acetabular center coordinates are updated based on a user's modification instruction.

[0055] Specifically, taking the acetabular region of interest as a mask to extract the pixel coordinates and corresponding HU values within this region and draw a HU value histogram can visually display the HU value distribution of the target user, providing a clearer reference. At the same time, the acetabular center coordinates are automatically extracted, and the extracted number of HU values and the acetabular center coordinates (supporting manual modification) are displayed in the interaction interface to ensure the accuracy and convenience of the data.

[0056] Specifically, to ensure the accuracy of the dynamic threshold, the dynamic threshold is displayed and marked on the histogram to help visually analyze and verify the accuracy of the threshold; the calculated results will be displayed in real time in the interaction interface.

[0057] Specifically, based on the acetabular cup center coordinates obtained through automated extraction or manual modification, the user can input the outer edge radius (screening radius) and relative increment (screening increment value) of the acetabular cup according to actual needs to determine the screening area around the acetabular cup.

[0058] It should be noted that to ensure that the screening area conforms to the actual situation, the acetabular cup area should be hemispherical, that is, the screening area must be above the Z-axis of the center of the sphere. In addition, considering the actual clinical situation, the anteversion angle and abduction angle need to be set during acetabular cup implantation, and the screening area will be rotated according to these angles to ensure that the screened bone area is consistent with the actual implantation direction; the rotated coordinates combined with the range between the two radii will ensure accurate acquisition of the bone data around the acetabular cup.

[0059] In some embodiments, the screening module 103 is further configured to mark the screening conditions, 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, screening increment value, anteversion angle, and abduction angle; the screening area and the position of the acetabular cup are determined based on the screening radius, screening increment value, anteversion angle, and abduction angle.

[0060] Specifically, when the user inputs the screening conditions (such as screening radius R1, screening increment value Δd, anteversion angle, and abduction angle, etc.), it will be updated in real time to the three-dimensional visualization area. As Figure 4 shown, the acetabular center coordinates are (368, 249), and the screening conditions such as the screening radius R1 is equal to Cupsize of 26mm, the screening increment value Increment, Δd is 2mm, etc., so that the screening area can be determined. From Figure 4 it can be seen to mark the position of the acetabular cup and dynamically view the changes in the three-dimensional reconstruction results; this interactive function enhances the visualization effect and helps the user to perform bone screening more precisely.

[0061] Specifically, through the rotated spherical coordinates combined with the input screening radius and screening increment value, the screened HU values are further processed; the HU values of cortical bone and cancellous bone in the screening area are distinguished, and the average value of the screened bone area is calculated; the final screening results (including the number and average value of the screened HU values) will be displayed on the interactive interface, and the dynamic threshold after screening will be marked in the histogram, which is convenient for intuitive evaluation and analysis of data. As Figure 5 shown, Figure 5 the two left dotted lines in it are the 20% percentile threshold dividing lines, the original cancellous bone threshold is 14, and the processed cancellous bone threshold is 7; the two right dotted lines are the 80% percentile threshold dividing lines, the original cortical bone threshold is 466, and the processed cortical bone threshold is 455.

[0062] Thus, the bone 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 the subsequent prediction of acetabular cup stability; during the screening process, the three-dimensional position of the acetabular cup and the individual differences of the target user are fully considered to ensure the accuracy and personalization of the analysis results.

[0063] The prediction analysis module 104 is used to perform prediction analysis based on the user information, the average cortical bone Hounsfield unit value, and the average cancellous bone Hounsfield unit value of the screening area, and generate a prediction result.

[0064] In some embodiments, the prediction analysis module 104 is specifically configured to obtain the cortical bone standard value and the cancellous bone standard value based on the user information, determine the cortical bone analysis result based on the average cortical bone Hounsfield unit value and the cortical bone standard value, and determine the cancellous bone analysis result based on the average cancellous bone Hounsfield unit value and the cancellous bone standard value; generate a prediction result based on the cortical bone analysis result and the cancellous bone analysis result.

[0065] Specifically, different standards are set for the average HU values of the cortical bone and cancellous bone of the target user according to the age, gender, and medical history (such as osteoporosis, etc.) of the target user, and these standards are compared with the average HU values of the cortical bone and cancellous bone calculated after screening to obtain the final prediction result. Among them, different target users with different ages, genders, and medical histories will have different standard value settings, and these standard values can be flexibly adjusted and optimized according to actual needs.

[0066] Specifically, the average HU value of the cortical bone is divided into three intervals according to different age groups, genders, and bone density conditions: normal, osteopenia, and osteoporosis. For example, for the age range of 18 to 40 years old: an average cortical bone HU value > 700 indicates normal cortical bone density; 350 < average cortical bone HU value ≤ 700 indicates osteopenia; an average cortical bone HU value < 115 indicates a high risk of osteoporosis; for the age range of 41 to 60 years old: an average cortical bone HU value > 600 indicates normal cortical bone density; 350 < average cortical bone HU value ≤ 600 indicates osteopenia; an average cortical bone HU value < 110 indicates a high risk of osteoporosis; for the age range over 60 years old: an average cortical bone HU value > 500 indicates normal cortical bone density; 350 < average cortical bone HU value ≤ 500 indicates osteopenia; an average cortical bone HU value < 100 indicates a high risk of osteoporosis.

[0067] It should be noted that adjustments can also be made according to gender. For example, for women, an average cortical bone HU value > 600 indicates normal cortical bone density; for men, an average cortical bone HU value > 700 indicates normal cortical bone density.

[0068] It should be noted that for target users with a history of osteoporosis or other bone metabolism disorders, further analysis and evaluation are carried out by combining the calculated average HU value of cortical bone and the average HU value of cancellous bone.

[0069] Specifically, the average HU value of cancellous bone is also divided into three intervals according to different age groups, genders, and bone density conditions: normal, osteopenia, and osteoporosis. For the age range of 18 to 40 years old: an average HU value of cancellous bone > 160 indicates normal cancellous bone density; 115 < average HU value of cancellous bone ≤ 160 indicates osteopenia; an average HU value of cancellous bone < 115 indicates a high risk of osteoporosis. For the age range of 41 to 60 years old: an average HU value of cancellous bone > 150 indicates normal cancellous bone density; 110 < average HU value of cancellous bone ≤ 150 indicates osteopenia; an average HU value of cancellous bone < 110 indicates a high risk of osteoporosis. For those over 60 years old: an average HU value of cancellous bone > 130 indicates normal cancellous bone density; 100 < average HU value of cancellous bone ≤ 130 indicates osteopenia; an average HU value of cancellous bone < 100 indicates a high risk of osteoporosis.

[0070] It should be noted that adjustments can also be made according to gender. For example, an average HU value of cancellous bone > 150 in women indicates normal cancellous bone density; an average HU value of cancellous bone > 160 in men indicates normal cancellous bone density.

[0071] In some embodiments, corresponding evaluation and recommendation information can also be output based on the average HU values of cortical bone and cancellous bone. Specifically, the evaluation and recommendation information includes strong bone support: the average HU values of both cortical bone and cancellous bone are within the normal range, indicating that the user has strong bone support and it is recommended to use conventional implantation techniques; high risk of osteoporosis: the average HU values of both cortical bone and cancellous bone are lower than the normal value, indicating a high risk of osteoporosis, and it is recommended to use additional fixation measures or further evaluate bone quality; problems with cortical bone or cancellous bone: if the average HU value of cortical bone is low, attention should be paid to the stability of cortical bone and a special acetabular cup design may be required; if the average HU value of cancellous bone is low, attention should be paid to the stability of cancellous bone and additional fixation measures may be required; insufficient data: if no clear conclusion can be drawn from the data, it is prompted that the data is insufficient and the user is required to provide more CT data for further analysis.

[0072] In some embodiments, the prediction analysis module 104 is specifically configured to input the user information, the average Hounsfield unit value of cortical bone, and the average Hounsfield unit value of cancellous bone in the selected 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.

[0073] In some embodiments, the predictive analysis module is further configured to obtain sample data, where the sample data includes user sample information, the average Hounsfield unit value of the cortical bone sample and the average Hounsfield unit value of the cancellous bone sample in the sample screening region, and a prediction label; input the sample data into a regression model to be trained for training to obtain a prediction training result, and adjust the model parameters of the regression model based on the prediction training result and the prediction label to obtain a prediction model, where different user characteristics in the user sample information correspond to different training weights.

[0074] Specifically, based on the CT data and user information of multiple users (such as the average HU values of cortical bone and cancellous bone, age, gender, medical history, etc.), a regression model is trained using machine learning algorithms. The training sample data includes user data with and without osteoporosis to ensure that the model has strong generalization ability. Techniques such as cross-validation are used to evaluate the model, and the prediction accuracy of the model is continuously optimized. By adjusting model parameters, increasing training data, and other means, the reliability and prediction accuracy of the model are improved. Exemplarily, as Figure 6 shown, the input features include the average HU values of cortical bone and cancellous bone, age, gender, and medical history. Different input features correspond to different training weights (such as w1, w2, w3, and w4 shown in the figure) to train the model and output a score as the prediction training result. The model parameters of the regression model are adjusted based on the prediction training result and the prediction label to obtain a prediction model.

[0075] Specifically, for the prediction of the acetabular cup stability score, the CT data of a new user is input into the prediction model, and the stability score of the acetabular cup is predicted through the trained prediction model. For example, if the predicted score ≥ 0.85, it is recommended to use conventional implantation techniques; if the score is between 0.70 and 0.85, it is indicated that further evaluation may be required; if the score < 0.70, it is recommended to use additional fixation measures or a specially designed acetabular cup.

[0076] Specifically, through a regression model of machine learning, combined with user data of a certain sample (such as the average HU values of cortical bone and cancellous bone, and other user characteristics such as age, gender, medical history, etc.), model training is carried out. Based on the trained regression model, combined with the input of user characteristics for prediction, the acetabular cup stability score is calculated as the prediction result.

[0077] For example, if the predicted score ≥ a score threshold such as 0.85, it is determined that the acetabular cup has good stability, and conventional implantation techniques are recommended; score threshold 0.70 ≤ predicted score < score threshold 0.85: the acetabular cup has general stability, and further evaluation may be required; predicted score < score threshold 0.70: the acetabular cup has poor stability, and it is recommended to use additional fixation measures or a special acetabular cup design.

[0078] Thus, through dynamic threshold evaluation and / or machine learning model prediction, it is possible to combine the individual differences and specific conditions of users to provide more accurate predictions and suggestions for the stability of acetabular cups, optimize the hip replacement surgery plan, and improve the success rate of the surgery.

[0079] 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.; among them, 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 reconstructed image of the acetabular region. Through three-dimensional reconstruction technology, a three-dimensional image of the acetabular region is generated to intuitively display the implantation position of the acetabular cup and the surrounding bone quality; the dynamic marker information includes key parameters showing the acetabular region, such as the screening radius (outer edge radius R1), screening increment value (increment Δd), anteversion angle, and 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 values 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 thresholds for segmented cortical bone and cancellous bone.

[0080] Among them, the key thresholds include parameters such as the screening radius, screening increment value, anteversion angle, and abduction angle, etc., which 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, extracting and displaying the center coordinates of the acetabulum to provide a positioning reference for subsequent stability evaluation; the average HU values of the original cortical bone and cancellous bone, providing the average HU values of the bone quality before screening for reference; the average HU values of the cortical bone and cancellous bone after screening, showing the average HU values of the cortical bone and cancellous bone after screening for accurate judgment; the number of HU values before and after screening, counting and displaying the number of valid HU values in the acetabular region before and after screening to understand the integrity of the data volume; the judgment standard values include the judgment standard values of cortical bone and cancellous bone for different age groups, genders, etc. These thresholds are set based on clinical experience and expert suggestions to ensure the personalization and accuracy of the judgment results; the prediction result, based on the calculated average HU values of cortical bone and cancellous bone and the model prediction score, provides the final conclusion of the acetabular cup stability evaluation; for example, if the bone support is strong, it is recommended to use conventional implantation techniques; if the risk of osteoporosis is high, it is recommended to use additional fixation measures or further evaluate the bone quality; if there are problems with cortical bone or cancellous bone, targeted acetabular cup design suggestions will be provided according to specific problems; if the data is insufficient, it is reminded that more data is needed to improve the evaluation.

[0081] As an example, import the user's CT images and user information for storage and classification; perform standardization and homogenization processing on the extracted CT images and user information (such as denoising, image enhancement, HU value homogenization, medical history information format unification, etc.), and transmit the processed data to the image processing module; use an image segmentation algorithm to accurately extract the bone tissue in the CT image and remove irrelevant regions; through the ROI extraction method, calibrate key information in the segmented acetabular region to ensure that the extracted region only includes the bone tissue around the acetabulum and avoid missegmentation; 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 region extracted by ROI; screen the bone HU values and calculate: use the mask of the segmented acetabular region to further extract the pixel coordinates and HU values in this region, and draw the corresponding HU value histogram to visually display the HU value distribution of the user; through the dynamic threshold method, use the 20th percentile and 80th percentile to segment the cortical bone and cancellous bone HU values in the acetabular region, distinguish the cortical bone and cancellous bone, and calculate the average HU values of the cortical bone and cancellous bone respectively.

[0082] Furthermore, input screening and constraint conditions: for the user's preliminary known information, input the acetabular cup radius R1, increment Δd, anteversion angle, and abduction angle to ensure that the screened bone region conforms to the implantation direction of the actual acetabular cup; based on the extracted acetabular center and the HU values within the coordinate screening range, use the dynamic threshold method to distinguish the cortical bone and cancellous bone HU values around the screened acetabular cup 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, marking the position of the acetabular cup and related values, and the histogram will display the dynamic threshold segmentation line; perform dynamic threshold evaluation based on the user's age, gender, medical history, and the calculated HU values of the screened cortical bone and cancellous bone; 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 indicate that the bone support force is strong, and the conventional implantation technique is recommended.

[0083] In addition, analyze the user's HU values and other user information (such as age, gender, medical history, etc.) through a machine learning model to predict the stability score of the acetabular cup; assume that the stability score of this user is 0.88, then the prediction result is "The acetabular cup has good stability, and the conventional implantation technique is recommended"; after the data analysis is completed, automatically generate an analysis report on the stability of the user's acetabular cup implantation; 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, relevant suggestions, etc. The report can be exported in formats such as PDF for easy viewing and printing.

[0084] Therefore, by combining the HU values of CT images with user information (such as age, gender, medical history, etc.), and using a dynamic threshold judgment method to perform personalized analysis on the HU values of cortical bone and cancellous bone; in combination with a machine learning regression model, further using multi-dimensional features such as the user's HU value, age, gender, medical history, etc. as input data for training to predict the acetabular cup stability score; according to the prediction result and combined with the dynamic threshold judgment result, providing personalized implantation suggestions or risk warnings; through this method of automated analysis and personalized prediction, the present disclosure provides a more objective and accurate acetabular cup stability assessment, helps optimize the selection of acetabular cups, improve the success rate of surgery, reduce the risk of postoperative complications, and fully considers the individual differences of users, so as to customize the most suitable treatment plan for each user.

[0085] The acetabular cup prediction solution based on computer tomography images provided by the embodiments of the present disclosure combines the user's CT image data and user information, and through multi-level data processing and analysis, realizes the accurate assessment of the stability of the acetabular cup after implantation; the data loading module loads the user's CT scan data and imports user information (such as medical history, age, gender, etc.); then the data preprocessing and extraction module performs denoising, standardization and image enhancement processing on the data, automatically extracts the user's basic information, and reduces the errors that may be generated by manual input; the image processing module uses edge detection methods for image segmentation and provides a visualized acetabular region through three-dimensional reconstruction technology for easy analysis and observation; subsequently, the module for screening the HU values of the bone around the acetabular cup combines the screening conditions and rotation coordinates, extracts the HU values of the bone around the acetabular cup, and calculates the average values of cortical bone and cancellous bone to provide basic data for subsequent prediction; finally, the prediction analysis module predicts the acetabular cup stability and gives personalized implantation suggestions through a dynamic threshold judgment method and a machine learning model; through accurate data analysis and model prediction, it provides a more reliable acetabular cup stability assessment for hip replacement surgery, reduces the risk of postoperative complications, optimizes the surgical plan, and thus improves the success rate of surgery and the postoperative recovery quality of users.

[0086] Figure 7 FIG. is a schematic flow chart of another acetabular cup prediction method based on computer tomography images provided by the embodiments of the present disclosure. On the basis of the above embodiments, the above-mentioned acetabular cup prediction method based on computer tomography images is further optimized. As Figure 7 shown, the method includes: Step 201, obtain the user information and computer tomography images of the target user.

[0087] Step 202, perform image segmentation on the computer tomography images to obtain the acetabular region of interest.

[0088] Step 203: Obtain the Hounsfield unit value corresponding to each pixel coordinate and the acetabular center coordinate based on the acetabulum region of interest, determine the screening region of the acetabular cup based on the acetabular center coordinate and the received screening conditions, and process the Hounsfield unit value corresponding to each pixel coordinate based on a preset dynamic threshold method to obtain the average cortical bone Hounsfield unit value and the average cancellous bone Hounsfield unit value of the screening region.

[0089] Step 204: Perform predictive analysis based on the user information, the average cortical bone Hounsfield unit value, and the average cancellous bone Hounsfield unit value of the screening region to generate a prediction result.

[0090] The acetabular cup prediction method based on computer tomography images provided by the embodiments of the present disclosure can execute the acetabular cup prediction system based on computer tomography images provided by any embodiment of the present disclosure, and has corresponding functional modules and beneficial effects for executing the method.

[0091] The embodiments of the present disclosure further provide a computer program product, including computer programs / instructions, which, when executed by a processor, implement the acetabular cup prediction method based on computer tomography images provided by any embodiment of the present disclosure.

[0092] It should be noted that the above-mentioned computer-readable medium in the present disclosure may be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, 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, a computer-readable storage medium may be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, and this computer-readable signal medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0093] In some embodiments, the client and the server can communicate using any currently known or future-developed network protocol such as HTTP (Hyper Text Transfer Protocol), and can be interconnected with digital data communication in any form or medium (for example, a communication network). Examples of communication networks include local area networks ("LAN"), wide area networks ("WAN"), the Internet (for example, the Internet), and end-to-end networks (for example, ad hoc end-to-end networks), as well as any currently known or future-developed networks.

[0094] The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist separately and not be assembled into the electronic device.

[0095] The above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device can execute the acetabular cup prediction method based on computed tomography images.

[0096] Computer program code for performing the operations of this disclosure can be written in one or more programming languages or combinations thereof. The foregoing programming languages include, but are not limited to, object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" 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 case of a remote computer, 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 it can be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0097] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions noted in the blocks may occur in a different order than noted in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0098] The units involved in the embodiments described in this disclosure can be implemented in software or in hardware. Wherein, the name of the unit does not constitute a limitation on the unit itself in some cases.

[0099] The functions described above herein can be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that can be used include: field programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), system on a chip (SOC), complex programmable logic devices (CPLD), and so on.

[0100] In the context of the present disclosure, a machine-readable medium may be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0101] According to one or more embodiments of the present disclosure, the present disclosure provides an electronic device, comprising: a processor; a memory for storing executable instructions of the processor; the processor, configured to read the executable instructions from the memory and execute the instructions to implement any one of the acetabular cup prediction methods based on computed tomography images provided by the present disclosure.

[0102] According to one or more embodiments of the present disclosure, the present disclosure provides a computer-readable storage medium storing a computer program for executing any one of the acetabular cup prediction methods based on computed tomography images provided by the present disclosure.

[0103] The above description is only a preferred embodiment of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosure concept. For example, the technical solutions formed by mutually replacing the above features with (but not limited to) the technical features having similar functions disclosed in the present disclosure.

[0104] In addition, although the operations are depicted in a particular order, this should not be construed as requiring that the operations be performed in the particular order shown or in sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the foregoing description, these should not be construed as limitations on the scope of the present disclosure. Certain features that are described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment may also be implemented separately or in any suitable sub-combination in multiple embodiments.

[0105] 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 matter 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 merely example forms of implementing the claims.

Claims

1. A prediction system for acetabular cups based on computed tomography images, characterized in that, Including: A data loading module for obtaining user information of a target user and computed tomography images; An image processing module for performing image segmentation on the computed tomography images to obtain an acetabulum region of interest; A screening module for obtaining the Hounsfield unit value and acetabulum center coordinates corresponding to each pixel coordinate based on the acetabulum region of interest, determining a screening region of the acetabular cup based on the acetabulum center coordinates and received screening conditions, and processing the Hounsfield unit value corresponding to each pixel coordinate based on a preset dynamic threshold method to obtain the average cortical bone Hounsfield unit value and the average cancellous bone Hounsfield unit value of the screening region; A prediction and analysis module for performing prediction and analysis based on the user information, the average cortical bone Hounsfield unit value, and the average cancellous bone Hounsfield unit value of the screening region to generate a prediction result.

2. The system according to claim 1, wherein The screening module, when used for processing the Hounsfield unit value corresponding to each pixel coordinate based on a preset dynamic threshold method to obtain the average cortical bone Hounsfield unit value and the average cancellous bone Hounsfield unit value of the screening region, specifically includes: Performing ascending sorting on the Hounsfield unit values corresponding to each pixel coordinate 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 cortical bone Hounsfield unit value and the average cancellous bone Hounsfield unit value of the acetabulum region of interest; Determining all the Hounsfield unit values of the screening region based on the Hounsfield unit value corresponding to each pixel coordinate and the screening region, and performing ascending sorting on all the Hounsfield unit values 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 the Hounsfield unit values, the second cancellous bone Hounsfield unit threshold, and the second cortical bone Hounsfield unit threshold to obtain the average cortical bone Hounsfield unit value and the average cancellous bone Hounsfield unit value of the screening region.

3. The system according to claim 2, 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 on 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 the 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.

4. The system according to claim 3, wherein The screening module is further configured to obtain the total number of Hounsfield unit values and the acetabular center coordinates of the acetabular region of interest, and obtain the total number of Hounsfield unit values of the screening region for display on the display device; wherein, the acetabular center coordinates are updated based on a modification instruction of the user.

5. The system according to 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 reconstructed image of the acetabular region; the screening module is further configured to mark the positions of the screening conditions, the screening region, and the acetabular cup in the three-dimensional reconstructed image of the acetabular region for display on the display device; wherein, the screening conditions include a screening radius, a screening increment value, a forward tilt angle, and an abduction angle; the positions of the screening region and the acetabular cup are determined based on the screening radius, the screening increment value, the forward tilt angle, and the abduction angle.

6. The system according to claim 1, wherein The prediction and analysis module is configured to perform prediction and analysis based on the user information, 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; generating the prediction result based on the cortical bone analysis result and the cancellous bone analysis result.

7. The system according to claim 1, wherein The prediction and analysis module is configured to perform prediction and analysis based on the user information, 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, 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; generating the prediction result based on the prediction score and a preset score threshold.

8. The system according to claim 7, wherein the prediction and analysis module is further configured to obtain sample data; wherein, the sample data includes user sample information, the average cortical bone sample Hounsfield unit value and the average cancellous bone sample Hounsfield unit value of the sample screening region, and a prediction label; inputting the sample data into a regression model to be trained for training to obtain a prediction training result, and adjusting the model parameters of the regression model based on the prediction training result and the prediction label to obtain the prediction model; wherein, different user characteristics in the user sample information correspond to different training weights.

9. The system according to 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 perform data extraction on the preprocessed computed tomography images to obtain user data information for display on the display device.

10. A prediction method for acetabular cups based on computed tomography images, characterized in that, including: obtaining user information and computed tomography images of a target user; performing image segmentation on the computed tomography images to obtain an acetabular region of interest; Obtain the Hounsfield unit value corresponding to each pixel coordinate and the acetabular center coordinate based on the acetabular region of interest, determine the screening region of the acetabular cup based on the acetabular center coordinate and the received screening conditions, 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; Perform predictive analysis based on the user information, the average Hounsfield unit value of the cortical bone, and the average Hounsfield unit value of the cancellous bone in the screening region to generate a prediction result.

Images