Bilateral hip fusion hip joint multi-disease lesion diagnosis method based on deep learning
Through the contralateral hip fusion method based on deep learning, the hip joint X-ray image is segmented and fused left and right, and the deep learning network model is input, which solves the problem of inaccurate diagnosis of multiple diseases of hip joints in the prior art, and realizes intelligent evaluation and accurate diagnosis of multiple diseases.
Patent Information
- Application Number
- CN202411733660.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-29
- Publication Date
- 2025-03-04
AI Technical Summary
The prior art is difficult to accurately diagnose multiple diseases of hip joints, especially when screening on unilateral images, it is easy to have inaccurate identification, and it is impossible to conduct intelligent evaluation of multiple diseases at the same time.
The contralateral hip fusion method based on deep learning is adopted, and the hip joint X-ray image is obtained, left and right hip segmentation and image fusion are performed, left and right hip fusion images are generated, and the left and right hip fusion images are input into a preset deep learning network model to output the diagnosis results of multiple diseases of hip joints.
It has achieved a more accurate diagnosis of multiple diseases of hip joints, and can evaluate multiple diseases at the same time, such as femoral head necrosis, osteoarthritis, dysplasia and fractures, improving the accuracy of diagnosis and the intelligence of multiple diseases evaluation.
Smart Images
Figure CN119559442A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of diagnosis of multiple diseases and lesions of the hip joint, and in particular, relates to a method, device, equipment and computer-readable storage medium for diagnosis of multiple diseases and lesions of the hip joint in contralateral hip fusion based on deep learning. Background Art
[0002] At present, the screening of single diseases of the hip joint is mainly based on unilateral images of the hip joint to identify the lesions, which may lead to inaccurate identification. Moreover, it is impossible to perform intelligent assessment of multi-disease screening at the same time.
[0003] Therefore, how to more accurately diagnose multiple diseases of the hip joint is a technical problem that technical personnel in this field urgently need to solve. Summary of the invention
[0004] The embodiments of the present application provide a method, device, equipment and computer-readable storage medium for diagnosing multiple diseases of the hip joint in contralateral hip fusion based on deep learning, which can more accurately diagnose multiple diseases of the hip joint.
[0005] In a first aspect, an embodiment of the present application provides a method for diagnosing multiple hip joint lesions in contralateral hip fusion based on deep learning, characterized in that it includes:
[0006] Obtain hip x-rays;
[0007] Perform left and right hip segmentation on the hip joint X-ray image to obtain left hip image and right hip image respectively;
[0008] The left hip image, the right hip image and the left hip image are fused to obtain a left hip fusion image;
[0009] Perform image fusion of the right hip image, the left hip image and the right hip image to obtain a right hip fusion image;
[0010] Input the left hip fusion image or the right hip fusion image into the preset deep learning network model to output the diagnosis results of multiple hip joint diseases;
[0011] Among them, the diagnosis results of multiple hip joint diseases include: hip femoral head necrosis, hip osteoarthritis, hip dysplasia, and hip fracture.
[0012] Optional, the corresponding grades of hip femoral head necrosis include:
[0013] Level 1: The femoral head has a complete appearance and the joint space is normal;
[0014] Level 2: Bone sclerosis, focal osteoporosis or subtle cystic changes in the femoral head, no subchondral fracture, fracture in the necrotic area, and collapse of the femoral head;
[0015] Grade III: subchondral fracture, fracture in the necrotic area, and / or femoral head collapse;
[0016] Grade IV: Narrowing of the joint space, acetabular changes, and joint destruction;
[0017] The corresponding grades of hip osteoarthritis include:
[0018] Level 0: Normal;
[0019] Grade 1: Mild osteophytes;
[0020] Grade II: obvious osteophytes, but without involving the joint space;
[0021] Grade 3: moderate narrowing of the joint space;
[0022] Grade 4: The joint space is significantly narrowed and the subchondral bone is sclerotic.
[0023] Optionally, the left hip image, the right hip image and the left hip image are fused to obtain a left hip fusion image, including:
[0024] Performing image preprocessing on the left hip image and the right hip image; wherein the image preprocessing includes: grayscale conversion, noise reduction, equalization and size normalization;
[0025] Perform feature extraction and image registration on the left hip image and the right hip image after image preprocessing;
[0026] The pixel values of the left hip image and the right hip image are fused using weighted average method, Laplace pyramid fusion or wavelet transform fusion algorithm to preserve important edge information and details;
[0027] The fused image is further fused with the original left hip image to enhance the image quality and detail performance;
[0028] Generate the final left hip fusion image to ensure that the visual effect after image fusion is clear and contains the characteristic information of both hips.
[0029] Optionally, feature extraction and image registration are performed on the left hip image and the right hip image after image preprocessing, including:
[0030] Perform feature extraction on the preprocessed images, and obtain the significant feature areas of each image through edge detection and key point extraction methods;
[0031] The left hip image is registered with the right hip image using a feature matching algorithm to determine the correspondence between the two images;
[0032] Determine the locations of key points in the left hip image, right hip image, and left hip image for precise alignment during fusion;
[0033] Using the result of feature extraction, the left hip image and the right hip image are geometrically registered, and the position and rotation angle parameters of the right hip image are adjusted to make it coincide with the left hip image;
[0034] Use the transformation matrix to map the right hip image to ensure alignment with the left hip image in the same coordinate system;
[0035] Verify the accuracy of the registration, check the registration effect through superposition, and adjust the parameters until the registration result meets the requirements.
[0036] Optionally, the hip joint X-ray image is segmented into left and right hips to obtain a left hip image and a right hip image, respectively, including:
[0037] Perform image preprocessing on hip joint X-ray images; wherein the image preprocessing includes grayscale processing, filtering noise reduction and image enhancement;
[0038] Image segmentation and left and right hip region extraction are performed on the hip joint X-ray image after image preprocessing to obtain the left hip image and the right hip image respectively.
[0039] Optionally, image segmentation and left and right hip region extraction are performed on the hip joint X-ray image after image preprocessing to obtain a left hip image and a right hip image, respectively, including:
[0040] Based on the anatomical features of the image, a deep learning model is used to automatically detect and locate the hip joint area;
[0041] Use the segmentation model to segment the hip joint area to the left and right. When training the model, label data of the left and right hip joints are required to identify and segment the left and right hips.
[0042] The segmented left and right hip joint regions are further refined, and small mis-segmented regions are removed through morphological operations;
[0043] The segmentation accuracy is evaluated by calculating the IoU or Dice coefficient indicators to ensure the accuracy of the segmentation of the left and right hips;
[0044] Based on the segmentation results, the left hip area and the right hip area are cropped into separate images;
[0045] Save the left and right hip images as separate files for easy subsequent analysis and processing.
[0046] Optionally, the left hip fusion image or the right hip fusion image is input into a preset deep learning network model to output the diagnosis results of multiple hip joint diseases, including:
[0047] Input the left hip fusion image or the right hip fusion image into a preset deep learning network model, extract low-level to high-level features of the image layer by layer through the convolution layer, and gradually capture the lesion pattern and features in the image; the deep learning network model is ResNet, DenseNet, EfficientNet, and 3D-CNN;
[0048] Features are aggregated through pooling layers and fully connected layers, and the Softmax or Sigmoid function is used to output the diagnosis probabilities of multiple diseases and the diagnosis results of multiple hip joint lesions.
[0049] In a second aspect, the embodiment of the present application provides a device for diagnosing multiple hip joint diseases in contralateral hip fusion based on deep learning, characterized in that the device comprises:
[0050] An image acquisition module, used for acquiring an X-ray image of a hip joint;
[0051] A segmentation module is used to segment the hip joint X-ray image into left and right hips to obtain left hip images and right hip images respectively;
[0052] An image fusion module is used to fuse the left hip image, the right hip image and the left hip image to obtain a left hip fusion image; and to fuse the right hip image, the left hip image and the right hip image to obtain a right hip fusion image;
[0053] The lesion diagnosis module is used to input the left hip fusion image or the right hip fusion image into a preset deep learning network model to output the diagnosis results of multiple hip joint lesions; among them, the diagnosis results of multiple hip joint lesions include: hip femoral head necrosis, hip osteoarthritis, hip dysplasia, and hip fracture.
[0054] In a third aspect, an embodiment of the present application provides an electronic device, the electronic device comprising: a processor and a memory storing computer program instructions;
[0055] When the processor executes the computer program instructions, a method for diagnosing multiple hip joint diseases in contralateral hip fusion based on deep learning is implemented.
[0056] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, implements a method for diagnosing multiple hip joint lesions in contralateral hip fusion based on deep learning.
[0057] The deep learning-based diagnosis method, device, equipment and computer-readable storage medium for multiple hip joint lesions in contralateral hip fusion according to the embodiments of the present application can more accurately diagnose multiple hip joint lesions.
[0058] The deep learning-based diagnosis method for multiple hip joint lesions in contralateral hip fusion is characterized by comprising:
[0059] Obtain hip x-rays;
[0060] Perform left and right hip segmentation on the hip joint X-ray image to obtain left hip image and right hip image respectively;
[0061] The left hip image, the right hip image and the left hip image are fused to obtain a left hip fusion image;
[0062] Perform image fusion of the right hip image, the left hip image and the right hip image to obtain a right hip fusion image;
[0063] Input the left hip fusion image or the right hip fusion image into the preset deep learning network model to output the diagnosis results of multiple hip joint diseases;
[0064] Among them, the diagnosis results of multiple hip joint diseases include: hip femoral head necrosis, hip osteoarthritis, hip dysplasia, and hip fracture. BRIEF DESCRIPTION OF THE DRAWINGS
[0065] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0066] Figure 1 It is a flowchart of a method for diagnosing multiple hip joint diseases in contralateral hip fusion based on deep learning provided by an embodiment of the present application;
[0067] Figure 2 It is a schematic diagram of the structure of a device for diagnosing multiple hip joint diseases for contralateral hip fusion based on deep learning provided by an embodiment of the present application;
[0068] Figure 3 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION
[0069] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.
[0070] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
[0071] In order to solve the problems of the prior art, the embodiments of the present application provide a method, device, equipment and computer-readable storage medium for diagnosing multiple diseases of the hip joint in contralateral hip fusion based on deep learning. The following first introduces the method for diagnosing multiple diseases of the hip joint in contralateral hip fusion based on deep learning provided by the embodiments of the present application.
[0072] Figure 1 The flowchart of the method for diagnosing multiple diseases of the hip joint in contralateral hip fusion based on deep learning provided by one embodiment of the present application is shown. Figure 1 As shown, the deep learning-based diagnosis method for multiple hip joint lesions in contralateral hip fusion includes:
[0073] S101, obtaining an X-ray image of the hip joint;
[0074] S102, performing left and right hip segmentation on the hip joint X-ray image to obtain a left hip image and a right hip image respectively;
[0075] S103, fusing the left hip image, the right hip image and the left hip image to obtain a left hip fusion image; fusing the right hip image, the left hip image and the right hip image to obtain a right hip fusion image;
[0076] S104. Input the left hip fusion image or the right hip fusion image into a preset deep learning network model, and output the diagnosis results of multiple hip joint diseases; wherein the diagnosis results of multiple hip joint diseases include: hip femoral head necrosis, hip osteoarthritis, hip dysplasia, and hip fracture.
[0077] In one embodiment, the corresponding grades of hip femoral head necrosis include:
[0078] Level 1: The femoral head has a complete appearance and the joint space is normal;
[0079] Level 2: Bone sclerosis, focal osteoporosis or subtle cystic changes in the femoral head, no subchondral fracture, fracture in the necrotic area, and collapse of the femoral head;
[0080] Grade III: subchondral fracture, fracture in the necrotic area, and / or femoral head collapse;
[0081] Grade IV: Narrowing of the joint space, acetabular changes, and joint destruction;
[0082] The corresponding grades of hip osteoarthritis include:
[0083] Level 0: Normal;
[0084] Grade 1: Mild osteophytes;
[0085] Grade II: obvious osteophytes, but without involving the joint space;
[0086] Grade 3: moderate narrowing of the joint space;
[0087] Grade 4: The joint space is significantly narrowed and the subchondral bone is sclerotic.
[0088] In one embodiment, the left hip image, the right hip image and the left hip image are fused to obtain a left hip fused image, including:
[0089] Performing image preprocessing on the left hip image and the right hip image; wherein the image preprocessing includes: grayscale conversion, noise reduction, equalization and size normalization;
[0090] Perform feature extraction and image registration on the left hip image and the right hip image after image preprocessing;
[0091] The pixel values of the left hip image and the right hip image are fused using weighted average method, Laplace pyramid fusion or wavelet transform fusion algorithm to preserve important edge information and details;
[0092] The fused image is further fused with the original left hip image to enhance the image quality and detail performance;
[0093] Generate the final left hip fusion image to ensure that the visual effect after image fusion is clear and contains the characteristic information of both hips.
[0094] In one embodiment, feature extraction and image registration are performed on the left hip image and the right hip image after image preprocessing, including:
[0095] Perform feature extraction on the preprocessed images, and obtain the significant feature areas of each image through edge detection and key point extraction methods;
[0096] The left hip image is registered with the right hip image using a feature matching algorithm to determine the correspondence between the two images;
[0097] Determine the locations of key points in the left hip image, right hip image, and left hip image for precise alignment during fusion;
[0098] Using the result of feature extraction, the left hip image and the right hip image are geometrically registered, and the position and rotation angle parameters of the right hip image are adjusted to make it coincide with the left hip image;
[0099] Use the transformation matrix to map the right hip image to ensure alignment with the left hip image in the same coordinate system;
[0100] Verify the accuracy of the registration, check the registration effect through superposition, and adjust the parameters until the registration result meets the requirements.
[0101] In one embodiment, performing left and right hip segmentation on a hip joint X-ray image to obtain a left hip image and a right hip image respectively includes:
[0102] Perform image preprocessing on hip joint X-ray images; wherein the image preprocessing includes grayscale processing, filtering noise reduction and image enhancement;
[0103] Image segmentation and left and right hip region extraction are performed on the hip joint X-ray image after image preprocessing to obtain the left hip image and the right hip image respectively.
[0104] In one embodiment, image segmentation and left and right hip region extraction are performed on the hip joint X-ray image after image preprocessing to obtain a left hip image and a right hip image respectively, including:
[0105] Based on the anatomical features of the image, a deep learning model is used to automatically detect and locate the hip joint area;
[0106] Use the segmentation model to segment the hip joint area to the left and right. When training the model, label data of the left and right hip joints are required to identify and segment the left and right hips.
[0107] The segmented left and right hip joint regions are further refined, and small mis-segmented regions are removed through morphological operations;
[0108] The segmentation accuracy is evaluated by calculating the IoU or Dice coefficient indicators to ensure the accuracy of the segmentation of the left and right hips;
[0109] Based on the segmentation results, the left hip area and the right hip area are cropped into separate images;
[0110] Save the left and right hip images as separate files for easy subsequent analysis and processing.
[0111] In one embodiment, the left hip fusion image or the right hip fusion image is input into a preset deep learning network model to output the diagnosis results of multiple hip joint diseases, including:
[0112] Input the left hip fusion image or the right hip fusion image into a preset deep learning network model, extract low-level to high-level features of the image layer by layer through the convolution layer, and gradually capture the lesion pattern and features in the image; the deep learning network model is ResNet, DenseNet, EfficientNet, and 3D-CNN;
[0113] Features are aggregated through pooling layers and fully connected layers, and the Softmax or Sigmoid function is used to output the diagnosis probabilities of multiple diseases and the diagnosis results of multiple hip joint lesions.
[0114] Figure 2 It is a schematic diagram of the structure of a device for diagnosing multiple hip joint diseases for contralateral hip fusion based on deep learning provided by an embodiment of the present application;
[0115] The device for diagnosing multiple hip joint diseases in contralateral hip fusion based on deep learning comprises:
[0116] An image acquisition module 201 is used to acquire an X-ray image of a hip joint;
[0117] The segmentation module 202 is used to segment the hip joint X-ray image into left and right hips to obtain a left hip image and a right hip image respectively;
[0118] The image fusion module 203 is used to fuse the left hip image, the right hip image and the left hip image to obtain a left hip fusion image; and to fuse the right hip image, the left hip image and the right hip image to obtain a right hip fusion image;
[0119] The lesion diagnosis module 204 is used to input the left hip fusion image or the right hip fusion image into a preset deep learning network model, and output the diagnosis results of multiple hip joint lesions; wherein, the diagnosis results of multiple hip joint lesions include: hip femoral head necrosis, hip osteoarthritis, hip dysplasia, and hip fracture.
[0120] Figure 3 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application.
[0121] The electronic device may include a processor 301 and a memory 302 storing computer program instructions.
[0122] Specifically, the processor 301 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.
[0123] The memory 302 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 302 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. Where appropriate, the memory 302 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 302 may be inside or outside the electronic device. In a particular embodiment, the memory 302 may be a non-volatile solid-state memory.
[0124] In one embodiment, the memory 302 may be a read-only memory (ROM). In one embodiment, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or a flash memory, or a combination of two or more of these.
[0125] The processor 301 reads and executes computer program instructions stored in the memory 302 to implement any one of the deep learning-based methods for diagnosing multiple hip joint diseases in contralateral hip fusion in the above-mentioned embodiments.
[0126] In one example, the electronic device may further include a communication interface 303 and a bus 310. Figure 3 As shown, the processor 301, the memory 302, and the communication interface 303 are connected via a bus 310 and communicate with each other.
[0127] The communication interface 303 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.
[0128] Bus 310 includes hardware, software or both, and the parts of electronic equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 310 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the application considers any suitable bus or interconnection.
[0129] In addition, in combination with the deep learning-based diagnosis method for multiple diseases of the hip joint with contralateral hip fusion in the above embodiments, the embodiment of the present application can provide a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any one of the deep learning-based diagnosis method for multiple diseases of the hip joint with contralateral hip fusion in the above embodiments is implemented.
[0130] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.
[0131] The functional modules shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. Programs or code segments can be stored in machine-readable media, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable media" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.
[0132] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.
[0133] The above reference is according to the method of the embodiment of the present application, the flow chart of the device (system) and the computer program product and / or the block diagram described various aspects of the present application.It should be understood that each square box in the flow chart and / or the block diagram and the combination of each square box in the flow chart and / or the block diagram can be realized by computer program instructions.These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the realization of the function / action specified in one or more square boxes of the flow chart and / or the block diagram.Such a processor can be but is not limited to a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit.It can also be understood that each square box in the block diagram and / or the flow chart and the combination of the square boxes in the block diagram and / or the flow chart can also be realized by the dedicated hardware that performs the specified function or action, or can be realized by the combination of dedicated hardware and computer instructions.
[0134] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.
Claims
1. A method for diagnosing multiple hip joint lesions in contralateral hip fusion based on deep learning, characterized in that: include: Obtain hip x-rays; Perform left and right hip segmentation on the hip joint X-ray image to obtain left hip image and right hip image respectively; The left hip image, the right hip image and the left hip image are fused to obtain a left hip fusion image; Perform image fusion of the right hip image, the left hip image and the right hip image to obtain a right hip fusion image; Input the left hip fusion image or the right hip fusion image into the preset deep learning network model to output the diagnosis results of multiple hip joint diseases; Among them, the diagnosis results of multiple hip joint diseases include: hip femoral head necrosis, hip osteoarthritis, hip dysplasia, and hip fracture.
2. The method for diagnosing multiple hip joint diseases in contralateral hip fusion based on deep learning according to claim 1, characterized in that: The corresponding grades of hip femoral head necrosis include: Level 1: The femoral head has a complete appearance and the joint space is normal; Level 2: Bone sclerosis, focal osteoporosis or subtle cystic changes in the femoral head, no subchondral fracture, fracture in the necrotic area, and collapse of the femoral head; Grade III: subchondral fracture, fracture in the necrotic area, and / or femoral head collapse; Grade IV: Narrowing of the joint space, acetabular changes, and joint destruction; The corresponding grades of hip osteoarthritis include: Level 0: Normal; Grade 1: Mild osteophytes; Grade II: obvious osteophytes, but without involving the joint space; Grade 3: moderate narrowing of the joint space; Grade 4: The joint space is significantly narrowed and the subchondral bone is sclerotic.
3. The method for diagnosing multiple hip joint diseases in contralateral hip fusion based on deep learning according to claim 1, characterized in that: The left hip image, the right hip image and the left hip image are fused to obtain a left hip fusion image, including: Performing image preprocessing on the left hip image and the right hip image; wherein the image preprocessing includes: grayscale conversion, noise reduction, equalization and size normalization; Perform feature extraction and image registration on the left hip image and the right hip image after image preprocessing; The pixel values of the left hip image and the right hip image are fused using weighted average method, Laplace pyramid fusion or wavelet transform fusion algorithm to preserve important edge information and details; The fused image is further fused with the original left hip image to enhance the image quality and detail performance; Generate the final left hip fusion image to ensure that the visual effect after image fusion is clear and contains the characteristic information of both hips.
4. The method for diagnosing multiple hip joint diseases in contralateral hip fusion based on deep learning according to claim 3, characterized in that: Perform feature extraction and image registration on the left hip image and the right hip image after image preprocessing, including: Perform feature extraction on the preprocessed images, and obtain the significant feature areas of each image through edge detection and key point extraction methods; The left hip image is registered with the right hip image using a feature matching algorithm to determine the correspondence between the two images; Determine the locations of key points in the left hip image, right hip image, and left hip image for precise alignment during fusion; Using the result of feature extraction, the left hip image and the right hip image are geometrically registered, and the position and rotation angle parameters of the right hip image are adjusted to make it coincide with the left hip image; Use the transformation matrix to map the right hip image to ensure alignment with the left hip image in the same coordinate system; Verify the accuracy of the registration, check the registration effect through superposition, and adjust the parameters until the registration result meets the requirements.
5. The method for diagnosing multiple hip joint diseases in contralateral hip fusion based on deep learning according to claim 1, characterized in that: The hip joint X-ray image is segmented into left and right hips to obtain left hip images and right hip images respectively, including: Perform image preprocessing on hip joint X-ray images; wherein the image preprocessing includes grayscale processing, filtering noise reduction and image enhancement; Image segmentation and left and right hip region extraction are performed on the hip joint X-ray image after image preprocessing to obtain the left hip image and the right hip image respectively.
6. The method for diagnosing multiple hip joint diseases in contralateral hip fusion based on deep learning according to claim 5, characterized in that: The hip joint X-ray image after image preprocessing is segmented and the left and right hip regions are extracted to obtain the left hip image and the right hip image respectively, including: Based on the anatomical features of the image, a deep learning model is used to automatically detect and locate the hip joint area; Use the segmentation model to segment the hip joint area to the left and right. When training the model, label data of the left and right hip joints are required to identify and segment the left and right hips. The segmented left and right hip joint regions are further refined, and small mis-segmented regions are removed through morphological operations; The segmentation accuracy is evaluated by calculating the IoU or Dice coefficient indicators to ensure the accuracy of the segmentation of the left and right hips; Based on the segmentation results, the left hip area and the right hip area are cropped into separate images; Save the left and right hip images as separate files for easy subsequent analysis and processing.
7. The method for diagnosing multiple hip joint diseases in contralateral hip fusion based on deep learning according to claim 1, characterized in that: Input the left hip fusion image or the right hip fusion image into the preset deep learning network model to output the diagnosis results of multiple hip joint diseases, including: Input the left hip fusion image or the right hip fusion image into a preset deep learning network model, extract low-level to high-level features of the image layer by layer through the convolution layer, and gradually capture the lesion pattern and features in the image; the deep learning network model is ResNet, DenseNet, EfficientNet, and 3D-CNN; Features are aggregated through pooling layers and fully connected layers, and the Softmax or Sigmoid function is used to output the diagnosis probabilities of multiple diseases and the diagnosis results of multiple hip joint lesions.
8. A deep learning-based diagnostic device for multiple hip joint lesions in contralateral hip fusion, characterized in that: The device comprises: An image acquisition module, used for acquiring an X-ray image of a hip joint; A segmentation module is used to segment the hip joint X-ray image into left and right hips to obtain left hip images and right hip images respectively; An image fusion module is used to fuse the left hip image, the right hip image and the left hip image to obtain a left hip fusion image; and to fuse the right hip image, the left hip image and the right hip image to obtain a right hip fusion image; The lesion diagnosis module is used to input the left hip fusion image or the right hip fusion image into a preset deep learning network model to output the diagnosis results of multiple hip joint lesions; among them, the diagnosis results of multiple hip joint lesions include: hip femoral head necrosis, hip osteoarthritis, hip dysplasia, and hip fracture.
9. An electronic device, characterized in that: The electronic device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it implements the deep learning-based method for diagnosing multiple hip joint diseases in contralateral hip fusion as described in any one of claims 1-7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the method for diagnosing multiple hip joint diseases in contralateral hip fusion based on deep learning as described in any one of claims 1 to 7.