Adjacent vertebra disease diagnosis method and device based on deep learning, equipment and storage medium
Through deep learning-based methods, the problem of inaccurate diagnosis of neon spondylosis in the prior art is solved, and accurate identification of degenerative lesions and personalized diagnosis and treatment suggestions are achieved.
Patent Information
- Application Number
- CN202411615598.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-13
- Publication Date
- 2025-03-28
AI Technical Summary
In the prior art, the diagnosis of nephrospondylosis is not accurate enough, and it mainly relies on the experience of doctors, resulting in large differences in diagnosis results.
Using a deep learning method, by obtaining the patient's spinal X-ray image, performing image preprocessing, the image is input into the segmentation model based on a neural network for segmentation, and the segmentation results are obtained, and input it into the adjacent spondylosis diagnosis model to output diagnostic results and diagnostic suggestions.
It has achieved a more accurate diagnosis of adjacent spondylosis, and can identify degenerative lesions in adjacent unfusion segments, including disc degeneration, disc herniation, spondylosis, spinal stenosis, and provides personalized diagnosis and treatment suggestions.
Smart Images
Figure CN119724540A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of adjacent vertebral disease diagnosis, and in particular to an adjacent vertebral disease diagnosis method, device, equipment and computer-readable storage medium based on deep learning. Background Art
[0002] Adjacent Segment Disease (ASD) refers to the degeneration of the movable spinal segments adjacent to the fusion segment after spinal interbody fusion surgery, leading to new clinical symptoms. This situation usually occurs in the first segment above the fusion site, and sometimes it can also occur in the second segment above or the adjacent segment below. The main symptoms of adjacent spondylosis include low back pain and lower limb pain caused by intervertebral disc degeneration, intervertebral disc herniation or annulus fibrosus rupture. Abnormal local stress in the fusion segment may also cause vertebral bone hyperplasia, further leading to low back pain.
[0003] At present, the diagnosis of orthovertebral disease is mainly made by doctors based on their own experience, but each doctor has different experience, which leads to inaccurate diagnosis of orthovertebral disease.
[0004] Therefore, how to diagnose adjacent vertebral disease more accurately is a technical problem that technical personnel in this field urgently need to solve. Summary of the invention
[0005] The embodiments of the present application provide a method, device, equipment and computer-readable storage medium for diagnosing adjacent vertebral disease based on deep learning, which can more accurately diagnose adjacent vertebral disease.
[0006] In a first aspect, an embodiment of the present application provides a method for diagnosing adjacent vertebrae disease based on deep learning, comprising:
[0007] Obtain an X-ray image of the patient's spine;
[0008] Inputting the spinal X-ray image into a preset segmentation model based on a neural network for segmentation to obtain a segmentation result;
[0009] The segmentation results are input into a preset adjacent vertebra disease diagnosis model, and the adjacent vertebra disease diagnosis results and corresponding diagnosis and treatment suggestions are output;
[0010] Among them, the diagnosis results are normal or degenerative lesions in the adjacent unfused segments, and degenerative lesions include intervertebral disc degeneration, intervertebral disc herniation, vertebral slippage, and spinal canal stenosis.
[0011] Optionally, after obtaining the patient's spinal X-ray image, the following steps are also included:
[0012] Perform image preprocessing on the spinal X-ray image; wherein the image preprocessing at least includes: denoising, contrast enhancement and normalization.
[0013] Optionally, the neural network-based segmentation model adopts the following segmentation network structure:
[0014] It includes an upsampling network and a downsampling network connected in sequence, wherein the upsampling network includes a first encoding unit, a second encoding unit, a third encoding unit, a fourth encoding unit and a fifth encoding unit connected in sequence to downsampling; the downsampling network includes a fourth decoding unit, a third decoding unit, a second decoding unit and a first decoding unit connected in sequence to upsampling, and the output layer of the fifth encoding unit is connected to the fourth decoding unit;
[0015] Each of the first encoding unit, the second encoding unit, the third encoding unit, and the fourth encoding unit is connected to a corresponding decoding unit in the downsampling network, and an output end of the third decoding unit is also connected to an input end of the first decoding unit, so that the feature map output by the third decoding unit is used as an input of the first decoding unit;
[0016] Each encoding unit in the upsampling network includes an input layer, a convolution layer, a pooling layer and an output layer connected in sequence; each decoding unit in the downsampling network includes an input layer, a deconvolution layer, a convolution layer and an output layer connected in sequence.
[0017] Optionally, the adjacent vertebra disease diagnosis model is specifically a adjacent vertebra disease diagnosis model based on VGG-16 fusion residual network, including:
[0018] The preprocessing layer CRBM, convolution layer module, average pooling layer, fully connected layer and classifier are arranged in sequence. The preprocessing layer CRBM includes a convolution layer, an activation function, a Batch Normalization layer and a maximum pooling layer. A residual network is added to the back end of the convolution layer module. A Batch Normalization layer is added to the last convolution layer module to replace the maximum pooling layer. A dropout layer is arranged between the fully connected layer and the classifier. The convolution layer module includes a convolution layer and a maximum pooling layer, and there are two fully connected layers.
[0019] Optionally, the convolution layer in the preprocessing layer CRBM is used to obtain rich feature maps, the ReLU activation function is used to change the linear structure of the model, enhance nonlinearity, and reduce overfitting, the BatchNormalization layer is used to normalize the image, and the most discriminative intermediate semantic features of the lesion area are extracted through the maximum pooling layer.
[0020] Optionally, after determining the type of degenerative changes in adjacent unfused segments, this also includes:
[0021] Obtain the degree of damage, area, and deformation characteristics of the patient's lesion;
[0022] Based on the degree of damage, area, and degree of deformation, the severity of the degenerative lesion is determined and graded.
[0023] Optionally, after determining the severity of the degenerative lesion and grading it, it also includes:
[0024] Obtain the patient's lesion type, lesion location, lesion severity, patient age, and past medical history;
[0025] Calculate the patient's lesion risk score and generate a personalized diagnosis and treatment recommendation report based on factors such as the patient's lesion type, lesion location, lesion severity, patient age, and previous medical history;
[0026] Among them, the personalized diagnosis and treatment recommendation report includes: treatment method recommendations, rehabilitation training recommendations, personalized medication recommendations and follow-up frequency recommendations.
[0027] In a second aspect, an embodiment of the present application provides a device for diagnosing adjacent vertebrae based on deep learning, comprising:
[0028] An image acquisition module, used for acquiring a spinal X-ray image of a patient;
[0029] An image segmentation module is used to input the spinal X-ray image into a preset segmentation model based on a neural network for segmentation to obtain a segmentation result;
[0030] The adjacent vertebra disease diagnosis module is used to input the segmentation results into the preset adjacent vertebra disease diagnosis model, and output the adjacent vertebra disease diagnosis results and corresponding diagnosis and treatment suggestions;
[0031] Among them, the diagnosis results are normal or degenerative lesions in the adjacent unfused segments, and degenerative lesions include intervertebral disc degeneration, intervertebral disc herniation, vertebral slippage, and spinal canal stenosis.
[0032] 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;
[0033] When the processor executes the computer program instructions, a method for diagnosing adjacent vertebrae disease based on deep learning is implemented.
[0034] 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, implement a method for diagnosing adjacent vertebral disease based on deep learning.
[0035] The xxx method, device, equipment and computer-readable storage medium of the embodiments of the present application can diagnose adjacent vertebral disease more accurately.
[0036] The deep learning-based method for diagnosing adjacent vertebrae disease includes:
[0037] Obtain an X-ray image of the patient's spine;
[0038] Inputting the spinal X-ray image into a preset segmentation model based on a neural network for segmentation to obtain a segmentation result;
[0039] The segmentation results are input into a preset adjacent vertebra disease diagnosis model, and the adjacent vertebra disease diagnosis results and corresponding diagnosis and treatment suggestions are output;
[0040] Among them, the diagnosis results are normal or degenerative lesions in the adjacent unfused segments, and degenerative lesions include intervertebral disc degeneration, intervertebral disc herniation, vertebral slippage, and spinal canal stenosis. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] 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.
[0042] Figure 1 It is a flowchart of a method for diagnosing adjacent vertebrae disease based on deep learning provided by an embodiment of the present application;
[0043] Figure 2 is a schematic diagram of the network structure of a segmentation model provided by an embodiment of the present application;
[0044] Figure 3 This is a schematic diagram of the network structure of a diagnosis model for adjacent vertebrae disease provided by an embodiment of the present application;
[0045] Figure 4 It is a structural schematic diagram of a device for diagnosing adjacent vertebrae disease based on deep learning provided by an embodiment of the present application;
[0046] Figure 5 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION
[0047] 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.
[0048] 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.
[0049] 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 adjacent vertebrae disease based on deep learning. The following first introduces the method for diagnosing adjacent vertebrae disease based on deep learning provided by the embodiments of the present application.
[0050] Figure 1 FIG. 1 is a flow chart of a method for diagnosing adjacent vertebrae based on deep learning provided by an embodiment of the present application. Figure 1 As shown, the deep learning-based adjacent vertebra disease diagnosis method includes:
[0051] S101, obtaining a spinal X-ray image of the patient;
[0052] S102, inputting the spinal X-ray image into a preset segmentation model based on a neural network for segmentation to obtain a segmentation result;
[0053] S103. Input the segmentation results into a preset adjacent vertebral disease diagnosis model, and output the diagnosis results of the adjacent vertebral disease and corresponding diagnosis and treatment recommendations; wherein the diagnosis results are that the adjacent unfused segments are normal or have degenerative lesions, and the degenerative lesions include intervertebral disc degeneration, intervertebral disc herniation, vertebral slippage, and spinal canal stenosis.
[0054] In one embodiment, after acquiring the spinal X-ray image of the patient, the method further includes:
[0055] Perform image preprocessing on the spinal X-ray image; wherein the image preprocessing at least includes: denoising, contrast enhancement and normalization.
[0056] Figure 2 : is a schematic diagram of the network structure of a segmentation model provided by an embodiment of the present application; in one embodiment, the segmentation model based on a neural network adopts the following segmentation network structure:
[0057] It includes an upsampling network and a downsampling network connected in sequence, wherein the upsampling network includes a first encoding unit, a second encoding unit, a third encoding unit, a fourth encoding unit and a fifth encoding unit connected in sequence to downsampling; the downsampling network includes a fourth decoding unit, a third decoding unit, a second decoding unit and a first decoding unit connected in sequence to upsampling, and the output layer of the fifth encoding unit is connected to the fourth decoding unit;
[0058] Each of the first encoding unit, the second encoding unit, the third encoding unit, and the fourth encoding unit is connected to a corresponding decoding unit in the downsampling network, and an output end of the third decoding unit is also connected to an input end of the first decoding unit, so that the feature map output by the third decoding unit is used as an input of the first decoding unit;
[0059] Each encoding unit in the upsampling network includes an input layer, a convolution layer, a pooling layer and an output layer connected in sequence; each decoding unit in the downsampling network includes an input layer, a deconvolution layer, a convolution layer and an output layer connected in sequence.
[0060] Figure 3 : is a schematic diagram of the network structure of an adjacent vertebra disease diagnosis model provided by an embodiment of the present application; in one embodiment, the adjacent vertebra disease diagnosis model is specifically a adjacent vertebra disease diagnosis model based on a VGG-16 fusion residual network, including:
[0061] The preprocessing layer CRBM, convolution layer module, average pooling layer, fully connected layer and classifier are arranged in sequence. The preprocessing layer CRBM includes a convolution layer, an activation function, a Batch Normalization layer and a maximum pooling layer. A residual network is added to the back end of the convolution layer module. A Batch Normalization layer is added to the last convolution layer module to replace the maximum pooling layer. A dropout layer is arranged between the fully connected layer and the classifier. The convolution layer module includes a convolution layer and a maximum pooling layer, and there are two fully connected layers.
[0062] In one embodiment, the convolution layer in the preprocessing layer CRBM is used to obtain rich feature maps, the ReLU activation function is used to change the linear structure of the model, enhance nonlinearity, and reduce overfitting, the BatchNormalization layer is used to normalize the image, and the most discriminative intermediate semantic features of the lesion area are extracted through the maximum pooling layer.
[0063] In one embodiment, after determining the type of degenerative lesions of the adjacent unfused segments, the method further includes:
[0064] Obtain the degree of damage, area, and deformation characteristics of the patient's lesion;
[0065] Based on the degree of damage, area, and degree of deformation, the severity of the degenerative lesion is determined and graded.
[0066] In one embodiment, after determining the severity of the degenerative lesion and grading it, the method further includes:
[0067] Obtain the patient's lesion type, lesion location, lesion severity, patient age, and past medical history;
[0068] Calculate the patient's lesion risk score and generate a personalized diagnosis and treatment recommendation report based on factors such as the patient's lesion type, lesion location, lesion severity, patient age, and previous medical history;
[0069] Among them, the personalized diagnosis and treatment recommendation report includes: treatment method recommendations, rehabilitation training recommendations, personalized medication recommendations and follow-up frequency recommendations.
[0070] Figure 4 1 is a schematic diagram of the structure of a device for diagnosing adjacent vertebrae based on deep learning provided by an embodiment of the present application; the device for diagnosing adjacent vertebrae based on deep learning comprises:
[0071] An image acquisition module 401 is used to acquire a spinal X-ray image of a patient;
[0072] An image segmentation module 402 is used to input the spinal X-ray image into a preset segmentation model based on a neural network to perform segmentation and obtain a segmentation result;
[0073] The adjacent vertebra disease diagnosis module 403 is used to input the segmentation result into a preset adjacent vertebra disease diagnosis model, and output the adjacent vertebra disease diagnosis result and corresponding diagnosis and treatment suggestions;
[0074] Among them, the diagnosis results are normal or degenerative lesions in the adjacent unfused segments, and degenerative lesions include intervertebral disc degeneration, intervertebral disc herniation, vertebral slippage, and spinal canal stenosis.
[0075] Figure 5A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown.
[0076] The electronic device may include a processor 501 and a memory 502 storing computer program instructions.
[0077] Specifically, the processor 501 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.
[0078] The memory 502 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 502 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 502 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 502 may be inside or outside the electronic device. In a particular embodiment, the memory 502 may be a non-volatile solid-state memory.
[0079] In one embodiment, the memory 502 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.
[0080] The processor 501 reads and executes computer program instructions stored in the memory 502 to implement any one of the deep learning-based adjacent vertebral disease diagnosis methods in the above embodiments.
[0081] In one example, the electronic device may further include a communication interface 503 and a bus 510. Figure 5 As shown, the processor 501, the memory 502, and the communication interface 503 are connected via a bus 510 and communicate with each other.
[0082] The communication interface 503 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.
[0083] Bus 510 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 510 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.
[0084] In addition, in combination with the deep learning-based adjacent vertebral disease diagnosis method in the above embodiments, the present application embodiment 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 adjacent vertebral disease diagnosis methods in the above embodiments is implemented.
[0085] 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.
[0086] 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.
[0087] 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.
[0088] 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.
[0089] 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 adjacent vertebrae based on deep learning, characterized in that: include: Obtain an X-ray image of the patient's spine; Inputting the spinal X-ray image into a preset segmentation model based on a neural network for segmentation to obtain a segmentation result; The segmentation results are input into a preset adjacent vertebra disease diagnosis model, and the adjacent vertebra disease diagnosis results and corresponding diagnosis and treatment suggestions are output; Among them, the diagnosis results are normal or degenerative lesions in the adjacent unfused segments, and degenerative lesions include intervertebral disc degeneration, intervertebral disc herniation, vertebral slippage, and spinal canal stenosis.
2. The method for diagnosing adjacent vertebrae based on deep learning according to claim 1, characterized in that: After obtaining an X-ray of the patient's spine, it also includes: Perform image preprocessing on the spinal X-ray image; wherein the image preprocessing at least includes: denoising, contrast enhancement and normalization.
3. The method for diagnosing adjacent vertebrae disease based on deep learning according to claim 1, characterized in that: The neural network-based segmentation model uses the following segmentation network structure: It includes an upsampling network and a downsampling network connected in sequence, wherein the upsampling network includes a first encoding unit, a second encoding unit, a third encoding unit, a fourth encoding unit and a fifth encoding unit connected in sequence to downsampling; the downsampling network includes a fourth decoding unit, a third decoding unit, a second decoding unit and a first decoding unit connected in sequence to upsampling, and the output layer of the fifth encoding unit is connected to the fourth decoding unit; Each of the first encoding unit, the second encoding unit, the third encoding unit, and the fourth encoding unit is connected to a corresponding decoding unit in the downsampling network, and an output end of the third decoding unit is also connected to an input end of the first decoding unit, so that the feature map output by the third decoding unit is used as an input of the first decoding unit; Each encoding unit in the upsampling network includes an input layer, a convolution layer, a pooling layer and an output layer connected in sequence; each decoding unit in the downsampling network includes an input layer, a deconvolution layer, a convolution layer and an output layer connected in sequence.
4. The method for diagnosing adjacent vertebrae disease based on deep learning according to claim 1, characterized in that: The adjacent vertebra disease diagnosis model is specifically a adjacent vertebra disease diagnosis model based on VGG-16 fusion residual network, including: The preprocessing layer CRBM, convolution layer module, average pooling layer, fully connected layer and classifier are arranged in sequence. The preprocessing layer CRBM includes a convolution layer, an activation function, a Batch Normalization layer and a maximum pooling layer. A residual network is added to the back end of the convolution layer module. A Batch Normalization layer is added to the last convolution layer module to replace the maximum pooling layer. A dropout layer is arranged between the fully connected layer and the classifier. The convolution layer module includes a convolution layer and a maximum pooling layer, and there are two fully connected layers.
5. The method for diagnosing adjacent vertebrae disease based on deep learning according to claim 4, characterized in that: The convolution layer in the preprocessing layer CRBM is used to obtain rich feature maps, the ReLU activation function is used to change the linear structure of the model, enhance nonlinearity, and reduce overfitting, the Batch Normalization layer is used to normalize the image, and the most discriminative intermediate semantic features of the lesion area are extracted through the maximum pooling layer.
6. The method for diagnosing adjacent vertebrae disease based on deep learning according to claim 5, characterized in that: After determining the type of degenerative lesions in the adjacent unfused segments, it also includes: Obtain the degree of damage, area, and deformation characteristics of the patient's lesion; Based on the degree of damage, area, and degree of deformation, the severity of the degenerative lesion is determined and graded.
7. The method for diagnosing adjacent vertebrae disease based on deep learning according to claim 6, characterized in that: After the severity of the degenerative disease is determined and graded, it also includes: Obtain the patient's lesion type, lesion location, lesion severity, patient age, and past medical history; Calculate the patient's lesion risk score and generate a personalized diagnosis and treatment recommendation report based on factors such as the patient's lesion type, lesion location, lesion severity, patient age, and previous medical history; Among them, the personalized diagnosis and treatment recommendation report includes: treatment method recommendations, rehabilitation training recommendations, personalized medication recommendations and follow-up frequency recommendations.
8. A device for diagnosing adjacent vertebrae based on deep learning, characterized in that: The device comprises: An image acquisition module, used for acquiring a spinal X-ray image of a patient; An image segmentation module is used to input the spinal X-ray image into a preset segmentation model based on a neural network for segmentation to obtain a segmentation result; The adjacent vertebra disease diagnosis module is used to input the segmentation results into the preset adjacent vertebra disease diagnosis model, and output the adjacent vertebra disease diagnosis results and corresponding diagnosis and treatment suggestions; Among them, the diagnosis results are normal or degenerative lesions in the adjacent unfused segments, and degenerative lesions include intervertebral disc degeneration, intervertebral disc herniation, vertebral slippage, and spinal canal stenosis.
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 adjacent vertebral disease 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 deep learning-based method for diagnosing adjacent vertebral disease as described in any one of claims 1 to 7.