Spine intervertebral fusion detection method, device and equipment based on deep learning

Abstract

The invention provides a deep learning-based spine interbody fusion detection method, apparatus and device, and a computer readable storage medium. The method comprises the following steps: acquiring spine medical image data; preprocessing the medical image data to generate standardized input image data; inputting the preprocessed input image data into a pre-trained deep learning model, and analyzing local and global structural features of a vertebral body and an intervertebral space by the deep learning model through multi-layer convolution, pooling and activation function operation; based on an output result of the deep learning model, classifying fusion states of the vertebral body and the intervertebral space, and identifying whether fusion occurs or not; scoring the fusion degree of different intervertebral spaces to generate a fusion evaluation report; and visually displaying the detection result. According to the embodiment of the invention, spine interbody fusion detection can be more accurately carried out.

Description

Technical Field

[0001] The present application relates to the field of spinal intervertebral fusion, and in particular to a spinal intervertebral fusion detection method, device, equipment and computer-readable storage medium based on deep learning. Background Art

[0002] In modern society, people's lifestyles and working styles have changed dramatically, and this change has also had a great impact on human spinal bone lesions. According to survey statistics, the incidence of cervical spondylosis is 25% in people under 40 years old; the incidence of cervical spondylosis is about 50% in people over 40 years old; and the incidence of cervical spondylosis exceeds 85% when over 60 years old. There are more than 2 million potential surgical patients for cervical spondylosis each year, and the total number of patients is 50 million. Lumbar disc herniation, as another major type of spinal-related disease, is one of the most common causes of low back and leg pain. Bad habits such as long-term sitting, long-term desk work, and long-term driving have gradually increased the incidence of lumbar disc herniation, and the age of the affected population has gradually become younger. Therefore, spinal-related surgical orthopedic surgeries are also on the rise year by year, among which the most typical surgery is intervertebral fusion surgery.

[0003] Bone healing is an important indicator for follow-up observation after orthopedic surgery. Generally speaking, bone healing refers to the formation of a continuous bone bridge between bones. For spinal fusion surgery, the main ways to judge the state of intervertebral fusion include various imaging methods such as X-ray, CT and MRI. The criteria for judging fusion mainly include: (1) There is a bridge-like trabecular connection between the endplates; (2) There is no translucent area between the implant and the endplate; (3) The displacement between the vertebrae in the flexion and extension of the cervical spine; (4) The displacement of the spinous process in the flexion and extension of the cervical spine. Among them, criteria (1) and (2) are the most commonly used indicators, but they are highly subjective. Although criteria (3) and (4) are more objective, different studies have completely different definitions of displacement. It can be seen that the existing intervertebral fusion detection lacks a unified judgment standard and is highly subjective, resulting in inaccurate spinal intervertebral fusion detection.

[0004] Therefore, how to perform spinal intervertebral fusion detection 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 spinal intervertebral fusion detection method, device, equipment and computer-readable storage medium based on deep learning, which can perform spinal intervertebral fusion detection more accurately.

[0006] In a first aspect, an embodiment of the present application provides a spinal intervertebral fusion detection method based on deep learning, comprising:

[0007] Acquiring spinal medical imaging data, wherein the medical imaging data includes images of multiple vertebrae and intervertebral spaces;

[0008] Preprocess the medical image data to generate standardized input image data; the preprocessing step includes the following sub-steps: eliminate random noise in the image through filtering algorithms to improve the clarity of the image; segment the vertebral body and intervertebral space area using algorithms based on threshold, region growing or edge detection; extract the structural information of the vertebral body and intervertebral space in the image based on edge, texture and shape features;

[0009] The preprocessed input image data is fed into a pre-trained deep learning model, which analyzes the local and global structural features of the vertebral body and intervertebral space through multi-layer convolution, pooling, and activation function operations;

[0010] Based on the output results of the deep learning model, the fusion status of the vertebral body and the intervertebral space is classified to identify whether fusion has occurred; the fusion degree of different intervertebral spaces is scored to generate a fusion assessment report;

[0011] The test results are displayed visually, including image annotation of the fusion status of the vertebral bodies and intervertebral discs. The degree of fusion is indicated by color coding, and corresponding diagnostic recommendations are generated.

[0012] Optionally, the deep learning model uses a convolutional neural network, which extracts spatial features of vertebrae and intervertebral spaces through multi-layer convolution operations, and combines pooling layers and fully connected layers to classify fusion states.

[0013] Optionally, the convolutional neural network is further integrated with a long short-term memory network module, which is used to capture the time series changes between vertebrae and intervertebral spaces to improve the detection accuracy of the spinal status at different time periods.

[0014] Optionally, the preprocessing step of medical image data also includes image enhancement operations, specifically including the following:

[0015] The image contrast is enhanced by histogram equalization to highlight the structural details of the vertebral body and intervertebral space;

[0016] Image denoising technology based on frequency domain transformation is used to further improve image quality.

[0017] Optionally, the output of the deep learning model includes not only the classification of the fusion state, but also a quantitative evaluation of the degree of fusion, which is calculated based on multiple parameters, including but not limited to:

[0018] Relative vertebral displacement: Fusion stability is assessed by calculating the displacement difference between adjacent vertebrae;

[0019] Changes in intervertebral disc thickness: By comparing the thickness changes of different intervertebral disc spaces, the progress of intervertebral fusion can be evaluated;

[0020] Bone density: Bone density is reflected by changes in the grayscale value of the image, which serves as a basis for judging the fusion effect.

[0021] Optionally, a large-scale spinal medical imaging dataset is used in the training process of the deep learning model. The dataset contains case samples of different age groups and different conditions to improve the generalization ability and detection accuracy of the model.

[0022] Optionally, the visual display of the test results further includes a dynamic report generation function, which automatically generates personalized treatment suggestions based on the spinal status of different patients and provides a diagnostic report combining images and text;

[0023] The system includes an adaptive model optimization mechanism that automatically adjusts the parameters of the deep learning model based on the newly input medical imaging data to ensure the model's detection accuracy for different types of spinal images.

[0024] In a second aspect, an embodiment of the present application provides a spinal intervertebral fusion detection device based on deep learning, comprising:

[0025] An image acquisition module, used to acquire spinal medical image data, wherein the medical image data includes images of multiple vertebrae and intervertebral spaces;

[0026] The preprocessing module is used to preprocess the medical image data to generate standardized input image data; the preprocessing step includes the following sub-steps: eliminating random noise in the image through a filtering algorithm to improve the clarity of the image; segmenting the vertebral body and intervertebral space area using an algorithm based on threshold, region growing or edge detection; extracting the structural information of the vertebral body and intervertebral space in the image based on edge, texture and shape features;

[0027] The structural feature analysis module is used to input the preprocessed input image data into a pre-trained deep learning model. The deep learning model analyzes the local and global structural features of the vertebral body and intervertebral space through multi-layer convolution, pooling and activation function operations;

[0028] The fusion status classification module is used to classify the fusion status of the vertebral body and the intervertebral disc based on the output results of the deep learning model, identify whether fusion has occurred, score the fusion degree of different intervertebral discs, and generate a fusion assessment report;

[0029] The visualization display module is used to visualize the test results, including image annotation of the fusion status of the vertebral body and intervertebral space, indicating the degree of fusion through color coding, and generating corresponding diagnostic suggestions.

[0030] 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;

[0031] When the processor executes the computer program instructions, a spinal intervertebral fusion detection method based on deep learning is implemented.

[0032] 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 spinal intervertebral fusion detection method based on deep learning.

[0033] The deep learning-based spinal intervertebral fusion detection method, device, equipment and computer-readable storage medium of the embodiments of the present application can perform spinal intervertebral fusion detection more accurately.

[0034] The deep learning-based spinal intervertebral fusion detection method includes:

[0035] Acquiring spinal medical imaging data, wherein the medical imaging data includes images of multiple vertebrae and intervertebral spaces;

[0036] Preprocess the medical image data to generate standardized input image data; the preprocessing step includes the following sub-steps: eliminate random noise in the image through filtering algorithms to improve the clarity of the image; segment the vertebral body and intervertebral space area using algorithms based on threshold, region growing or edge detection; extract the structural information of the vertebral body and intervertebral space in the image based on edge, texture and shape features;

[0037] The preprocessed input image data is fed into a pre-trained deep learning model, which analyzes the local and global structural features of the vertebral body and intervertebral space through multi-layer convolution, pooling, and activation function operations;

[0038] Based on the output results of the deep learning model, the fusion status of the vertebral body and the intervertebral space is classified to identify whether fusion has occurred; the fusion degree of different intervertebral spaces is scored to generate a fusion assessment report;

[0039] The test results are displayed visually, including image annotation of the fusion status of the vertebral bodies and intervertebral discs. The degree of fusion is indicated by color coding, and corresponding diagnostic recommendations are generated. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] 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.

[0041] Figure 1 It is a flowchart of a spinal intervertebral fusion detection method based on deep learning provided by an embodiment of the present application;

[0042] Figure 2 It is a flowchart of a spinal intervertebral fusion detection method based on deep learning provided by an embodiment of the present application;

[0043] Figure 3 It is a structural schematic diagram of a spinal intervertebral fusion detection device based on deep learning provided by an embodiment of the present application;

[0044] Figure 4 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0045] 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.

[0046] 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.

[0047] In order to solve the problems of the prior art, the embodiments of the present application provide a spinal intervertebral fusion detection method, device, equipment and computer readable storage medium based on deep learning. The spinal intervertebral fusion detection method based on deep learning provided by the embodiments of the present application is first introduced below.

[0048] Figure 1 FIG. 1 is a flow chart of a spinal intervertebral fusion detection method based on deep learning provided by an embodiment of the present application. Figure 1 As shown, the deep learning-based spinal intervertebral fusion detection method includes:

[0049] S101, acquiring spinal medical image data, wherein the medical image data includes images of multiple vertebrae and intervertebral spaces;

[0050] S102, preprocessing the medical image data to generate standardized input image data; the preprocessing step includes the following sub-steps: eliminating random noise in the image by filtering algorithm to improve the clarity of the image; segmenting the vertebral body and intervertebral space region by using an algorithm based on threshold, region growing or edge detection; extracting structural information of the vertebral body and intervertebral space in the image based on edge, texture and shape features;

[0051] S103, inputting the preprocessed input image data into a pre-trained deep learning model, where the deep learning model analyzes local and global structural features of the vertebral body and intervertebral space through multi-layer convolution, pooling and activation function operations;

[0052] S104. Based on the output results of the deep learning model, classify the fusion status of the vertebral body and the intervertebral disc to identify whether fusion has occurred; score the fusion degree of different intervertebral discs and generate a fusion assessment report;

[0053] S105. Visualizing the detection results, including image annotation of the fusion status of the vertebral body and the intervertebral disc, indicating the degree of fusion through color coding, and generating corresponding diagnostic suggestions.

[0054] Figure 2 A schematic flow chart of a spinal intervertebral fusion detection method based on deep learning provided in another embodiment of the present application is shown.

[0055] In one embodiment, the deep learning model uses a convolutional neural network, which extracts spatial features of vertebrae and intervertebral spaces through multi-layer convolution operations, and combines pooling layers and fully connected layers to classify fusion states.

[0056] In one embodiment, the convolutional neural network is further integrated with a long short-term memory network module, which is used to capture the time series changes between the vertebral bodies and the intervertebral spaces to improve the detection accuracy of the spinal status at different time periods.

[0057] In one embodiment, the preprocessing step of the medical image data further includes an image enhancement operation, specifically including the following:

[0058] The image contrast is enhanced by histogram equalization to highlight the structural details of the vertebral body and intervertebral space;

[0059] Image denoising technology based on frequency domain transformation is used to further improve image quality.

[0060] In one embodiment, the output of the deep learning model includes not only the classification of the fusion state, but also a quantitative evaluation of the degree of fusion, which is calculated based on multiple parameters, including but not limited to:

[0061] Relative vertebral displacement: Fusion stability is assessed by calculating the displacement difference between adjacent vertebrae;

[0062] Changes in intervertebral disc thickness: By comparing the thickness changes of different intervertebral disc spaces, the progress of intervertebral fusion can be evaluated;

[0063] Bone density: Bone density is reflected by changes in the grayscale value of the image, which serves as a basis for judging the fusion effect.

[0064] In one embodiment, a large-scale spinal medical imaging dataset is used in the training process of the deep learning model. The dataset contains case samples of different age groups and different diseases to improve the generalization ability and detection accuracy of the model.

[0065] In one embodiment, the visual display of the test results further includes a dynamic report generation function, which automatically generates personalized treatment suggestions based on the spinal status of different patients and provides a diagnostic report combining images and text;

[0066] The system includes an adaptive model optimization mechanism that automatically adjusts the parameters of the deep learning model based on the newly input medical imaging data to ensure the model's detection accuracy for different types of spinal images.

[0067] Figure 3 1 is a schematic diagram of the structure of a spinal intervertebral fusion detection device based on deep learning provided by an embodiment of the present application; the spinal intervertebral fusion detection device based on deep learning includes:

[0068] An image acquisition module 301 is used to acquire spinal medical image data, wherein the medical image data includes images of multiple vertebrae and intervertebral spaces;

[0069] The preprocessing module 302 is used to preprocess the medical image data to generate standardized input image data; the preprocessing step includes the following sub-steps: eliminating random noise in the image by filtering algorithm to improve the clarity of the image; segmenting the vertebral body and intervertebral space region by using an algorithm based on threshold, region growing or edge detection; extracting the structural information of the vertebral body and intervertebral space in the image based on edge, texture and shape features;

[0070] The structural feature analysis module 303 is used to input the pre-processed input image data into a pre-trained deep learning model, and the deep learning model analyzes the local and global structural features of the vertebral body and the intervertebral space through multi-layer convolution, pooling and activation function operations;

[0071] The fusion status classification module 304 is used to classify the fusion status of the vertebral body and the intervertebral disc based on the output results of the deep learning model, identify whether fusion has occurred, score the fusion degree of different intervertebral discs, and generate a fusion assessment report;

[0072] The visualization display module 305 is used to visualize the detection results, including image annotation of the fusion status of the vertebral body and the intervertebral space, indicating the degree of fusion through color coding, and generating corresponding diagnostic suggestions.

[0073] Figure 4 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application.

[0074] The electronic device may include a processor 401 and a memory 402 storing computer program instructions.

[0075] Specifically, the processor 401 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.

[0076] Memory 402 may include a large capacity memory for data or instructions. By way of example and not limitation, memory 402 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. In appropriate cases, memory 402 may include a removable or non-removable (or fixed) medium. In appropriate cases, memory 402 may be inside or outside of an electronic device. In a particular embodiment, memory 402 may be a non-volatile solid-state memory.

[0077] In one embodiment, the memory 402 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.

[0078] The processor 401 reads and executes computer program instructions stored in the memory 402 to implement any one of the deep learning-based spinal intervertebral fusion detection methods in the above embodiments.

[0079] In one example, the electronic device may further include a communication interface 403 and a bus 410. Figure 4 As shown, the processor 401, the memory 402, and the communication interface 403 are connected via a bus 410 and communicate with each other.

[0080] The communication interface 403 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0081] Bus 410 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 410 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.

[0082] In addition, in combination with the spinal intervertebral fusion detection method based on deep learning 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 spinal intervertebral fusion detection methods based on deep learning in the above embodiments is implemented.

[0083] 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.

[0084] 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.

[0085] 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.

[0086] 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.

[0087] 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 spinal intervertebral fusion detection method based on deep learning, characterized in that: include: Acquiring spinal medical imaging data, wherein the medical imaging data includes images of multiple vertebrae and intervertebral spaces; Preprocessing the medical image data to generate standardized input image data; the preprocessing step includes the following sub-steps: eliminating random noise in the image through a filtering algorithm to improve the clarity of the image; segmenting the vertebral body and intervertebral disc area using an algorithm based on threshold, region growing or edge detection; Extract the structural information of vertebral bodies and intervertebral spaces in the image based on edge, texture and shape features; The preprocessed input image data is fed into a pre-trained deep learning model, which analyzes the local and global structural features of the vertebral body and intervertebral space through multi-layer convolution, pooling, and activation function operations; Based on the output of the deep learning model, the fusion status of the vertebral body and intervertebral space is classified to identify whether fusion has occurred; Score the fusion degree of different intervertebral spaces and generate a fusion assessment report; The test results are displayed visually, including image annotation of the fusion status of the vertebral bodies and intervertebral discs. The degree of fusion is indicated by color coding, and corresponding diagnostic recommendations are generated.

2. The deep learning-based spinal intervertebral fusion detection method according to claim 1, characterized in that: The deep learning model uses a convolutional neural network, which extracts the spatial features of vertebrae and intervertebral spaces through multi-layer convolution operations, and combines pooling layers and fully connected layers to classify the fusion state.

3. The deep learning-based spinal intervertebral fusion detection method according to claim 2, characterized in that: The convolutional neural network is further integrated with a long short-term memory network module, which is used to capture the time series changes between vertebrae and intervertebral spaces to improve the detection accuracy of the spinal status at different time periods.

4. The deep learning-based spinal intervertebral fusion detection method according to claim 1, characterized in that: The preprocessing steps of medical image data also include image enhancement operations, which include the following: The image contrast is enhanced by histogram equalization to highlight the structural details of the vertebral body and intervertebral space; Image denoising technology based on frequency domain transformation is used to further improve image quality.

5. The deep learning-based spinal intervertebral fusion detection method according to claim 1, characterized in that: The output of the deep learning model includes not only the classification of the fusion state, but also a quantitative evaluation of the degree of fusion, which is calculated based on multiple parameters, including but not limited to: Relative vertebral displacement: Fusion stability is assessed by calculating the displacement difference between adjacent vertebrae; Changes in intervertebral disc thickness: By comparing the thickness changes of different intervertebral disc spaces, the progress of intervertebral fusion can be evaluated; Bone density: Bone density is reflected by changes in the grayscale value of the image, which serves as a basis for judging the fusion effect.

6. The deep learning-based spinal intervertebral fusion detection method according to claim 1, characterized in that: A large-scale spinal medical imaging dataset was used in the training process of the deep learning model. The dataset contained case samples of different age groups and different conditions to improve the generalization ability and detection accuracy of the model.

7. The deep learning-based spinal intervertebral fusion detection method according to claim 1, characterized in that: The visual display of test results further includes a dynamic report generation function, which automatically generates personalized treatment recommendations based on the spinal status of different patients and provides a diagnostic report combining images and text; The system includes an adaptive model optimization mechanism that automatically adjusts the parameters of the deep learning model based on the newly input medical imaging data to ensure the model's detection accuracy for different types of spinal images.

8. A spinal intervertebral fusion detection device based on deep learning, characterized in that: The device comprises: An image acquisition module, used to acquire spinal medical image data, wherein the medical image data includes images of multiple vertebrae and intervertebral spaces; The preprocessing module is used to preprocess the medical image data to generate standardized input image data; the preprocessing step includes the following sub-steps: eliminating random noise in the image through a filtering algorithm to improve the clarity of the image; segmenting the vertebral body and intervertebral space area using an algorithm based on threshold, region growing or edge detection; extracting the structural information of the vertebral body and intervertebral space in the image based on edge, texture and shape features; The structural feature analysis module is used to input the preprocessed input image data into a pre-trained deep learning model. The deep learning model analyzes the local and global structural features of the vertebral body and intervertebral space through multi-layer convolution, pooling and activation function operations; The fusion status classification module is used to classify the fusion status of the vertebral body and the intervertebral disc based on the output results of the deep learning model, identify whether fusion has occurred, score the fusion degree of different intervertebral discs, and generate a fusion assessment report; The visualization display module is used to visualize the test results, including image annotation of the fusion status of the vertebral body and intervertebral space, indicating the degree of fusion through color coding, and generating corresponding diagnostic suggestions.

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, the deep learning-based spinal intervertebral fusion detection method as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by the processor, the deep learning-based spinal intervertebral fusion detection method according to any one of claims 1 to 7 is implemented.

Images