Method and device for evaluating compression condition of spinal nerve root and electronic equipment

Abstract

The invention relates to the technical field of medical images, and discloses a spinal nerve root compression condition assessment method and device, and electronic equipment, and the compression condition assessment method comprises the steps: recognizing and marking a spine, an intervertebral disc, a lateral recess and a spinal nerve root in an original medical image of a patient, so as to obtain a target medical image; calculating feature parameters of a spine, an intervertebral disc, a lateral recess and a spinal nerve root based on the target medical image; based on the characteristic parameters of the spine, the intervertebral disc and the lateral crypt, whether the spinal nerve root has the risk of compression or not is determined; and under the condition that the spinal nerve root has the compression risk, determining the compression degree of the spinal nerve root based on the characteristic parameters of the spinal nerve root. According to the method, detailed anatomical structure information and quantitative analysis results can be provided, the diagnosis accuracy is remarkably improved, the risks of misdiagnosis and missed diagnosis are further reduced through multi-dimensional risk assessment and compression degree grading, and the compression condition of the spinal nerve root is accurately and efficiently assessed.

Description

Technical Field

[0001] The present disclosure relates to the technical field of medical images, for example, to a method and device for evaluating the compression condition of a spinal nerve root, and an electronic device. Background Art

[0002] With the development of social economy and the accelerated pace of people's lives, spinal diseases, especially various diseases caused by compression of vertebral nerve roots, have become one of the important factors affecting human health. Spinal nerves are an important part of the human nervous system. They are emitted from the spinal cord. There are 31 pairs of spinal nerves. Each pair of spinal nerves is composed of anterior roots and posterior roots. The anterior roots mainly transmit motor information, and the posterior roots mainly transmit sensory information. The complex structure of the spinal nerves determines their susceptibility to compression, especially in the cervical, thoracic, and lumbar vertebrae. Compression of the nerve roots may cause a series of symptoms, such as pain, numbness, muscle weakness, etc., which seriously affect the patient's ability to carry out daily activities. Therefore, accurate diagnosis and effective treatment of spinal nerve root compression are particularly important.

[0003] In the related technologies, commonly used diagnostic methods for spinal nerve root compression include Magnetic Resonance Imaging (MRI) and Computed Tomography (CT). These two technologies can provide detailed images of spinal nerves and their surrounding structures, which can help doctors assess the compression of nerve roots. Although existing medical technologies can help doctors make diagnoses to a certain extent, due to the complexity of the spinal nerve structure and individual differences, traditional manual diagnostic methods have certain limitations. For example, manual film reading is time-consuming, highly subjective, and easily affected by the doctor's experience, and cannot accurately and efficiently assess the compression of the spinal nerve roots.

[0004] In recent years, with the development of artificial intelligence technology, intelligent diagnostic systems have begun to be applied in the medical field to improve the accuracy and efficiency of diagnosis. Especially in the diagnosis of spinal nerve diseases, through technical means such as deep learning algorithms, intelligent diagnostic systems can learn from a large amount of imaging data, identify subtle anatomical changes, and assist doctors in making more accurate diagnoses. Despite this, the intelligent diagnostic products for spinal nerve diseases on the market are still in the research and development stage and have not yet been able to evaluate the compression of the spinal nerve roots.

[0005] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0006] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical components or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0007] The embodiments of the present disclosure provide a method and device for evaluating the compression condition of a spinal nerve root, and an electronic device, which can accurately and efficiently evaluate the compression condition of a spinal nerve root.

[0008] According to a first aspect of the present disclosure, a method for evaluating the compression condition of a spinal nerve root is provided, the method comprising:

[0009] The spine, intervertebral disc, lateral recess and spinal nerve root are identified and marked in the original medical image of the patient to obtain a target medical image;

[0010] Calculate characteristic parameters of the spine, intervertebral disc, lateral recess and spinal nerve root based on the target medical image;

[0011] Determine whether the spinal nerve roots are at risk of compression based on characteristic parameters of the spine, intervertebral disc, and lateral recess;

[0012] When there is a risk of compression of the spinal nerve root, the degree of compression of the spinal nerve root is determined based on characteristic parameters of the spinal nerve root.

[0013] In some embodiments, determining whether a spinal nerve root is at risk of compression based on characteristic parameters of the spine, intervertebral disc, and lateral recess includes:

[0014] Determine whether there is a risk of disc herniation based on the characteristic parameters of the spine and intervertebral disc;

[0015] Based on the characteristic parameters of the lateral recess, determining whether there is a risk of lateral recess stenosis;

[0016] In cases with risk of disc herniation and / or lateral recess stenosis, the risk of spinal nerve root compression is determined.

[0017] In some embodiments, the characteristic parameters of the spine include the longest diameter of each spinal segment in the sagittal image, and the characteristic parameters of the intervertebral disc include the longest diameter of each intervertebral disc segment in the sagittal image;

[0018] Based on the characteristic parameters of the spine and intervertebral disc, the risk of intervertebral disc herniation is determined, including:

[0019] For each intervertebral disc segment, the longest diameter ratio of the intervertebral disc segment in the sagittal image to the longest diameter of its adjacent vertebral segment in the sagittal image was calculated;

[0020] When the longest diameter ratio of each intervertebral disc segment in the sagittal image to the longest diameter of its adjacent vertebral segment in the sagittal image is greater than the length-to-diameter ratio threshold, it is determined that there is a risk of intervertebral disc herniation;

[0021] When the longest diameter ratio of any intervertebral disc segment in the sagittal image to the longest diameter of its adjacent vertebral segment in the sagittal image is not greater than the aspect ratio threshold, it is determined that there is no risk of intervertebral disc herniation.

[0022] In some embodiments, the characteristic parameters of the lateral recess include the diameter of the lateral recess on each side in the sagittal image. Based on the characteristic parameters of the lateral recess, determining whether there is a risk of lateral recess stenosis includes:

[0023] For each side of the lateral recess, the diameter of the lateral recess in the sagittal image was compared with the first diameter threshold;

[0024] When the diameter of any lateral recess in the sagittal image is smaller than the first diameter threshold, it is determined that there is a risk of lateral recess stenosis;

[0025] When the diameter of each recess in the sagittal image is not less than the first diameter threshold, it is determined that there is no risk of lateral recess stenosis.

[0026] In some embodiments, the characteristic parameters of the spinal nerve root include the effective diameter of the spinal nerve root lumen and the ratio of the maximum diameter of the lumen to the minimum diameter of the lumen. The degree of compression includes 0 to 3, where 0 is the lowest level and 3 is the highest level. Determining the degree of compression of the spinal nerve root based on the characteristic parameters of the spinal nerve root includes:

[0027] comparing the effective diameter of the spinal nerve root lumen to a second diameter threshold;

[0028] When the effective diameter of the spinal nerve root lumen is greater than the second diameter threshold, determining that the compression degree of the spinal nerve root is the highest level;

[0029] When the effective diameter of the spinal nerve root lumen is not greater than the second diameter threshold, the compression degree of the spinal nerve root is determined based on the comparison result of the diameter ratio of the spinal nerve root and the corresponding ratio threshold.

[0030] In some embodiments, the spine, intervertebral disc, lateral recess, and spinal nerve root are identified and marked in the original medical image of the patient to obtain a target medical image, including:

[0031] Acquire a first intermediate image including segmentation results of the spine and the intervertebral disc based on the original medical image;

[0032] Acquire a second intermediate image including segmentation results of the lateral recess and spinal nerve roots based on the original medical image;

[0033] Acquire a third intermediate image containing a classification result of the spine based on the original medical image;

[0034] Acquire a fourth intermediate image including a classification result of the intervertebral disc based on the original medical image;

[0035] The first intermediate image, the second intermediate image, the third intermediate image and the fourth intermediate image are combined to obtain a target medical image.

[0036] In some embodiments, obtaining a first intermediate image including segmentation results of the spine and the intervertebral disc based on the original medical image includes: inputting the original medical image into a first segmentation model, and obtaining the first intermediate image including segmentation results of the spine and the intervertebral disc using the first segmentation model. The first segmentation model is trained based on the first original sample medical image and the first original sample mask image, and the original sample mask image is obtained after the labels of the spine, intervertebral disc, lateral recess and spinal nerve root are marked in the original sample medical image.

[0037] In some embodiments, obtaining a second intermediate image including the segmentation results of the lateral recess and the spinal nerve root based on the original medical image includes: inputting the original medical image into a second segmentation model, and obtaining a second intermediate image including the segmentation results of the lateral recess and the spinal nerve root using the second segmentation model. The second segmentation model is trained based on the second original sample medical image and the second original sample mask image, the second original sample medical image is a sub-image including the spine and its surrounding area cropped out of the first original sample medical image, and the second original sample mask image is a sub-image including the spine and its surrounding area cropped out of the second original sample mask image.

[0038] According to a second aspect of the present disclosure, a device for evaluating the compression condition of a spinal nerve root is provided, the device comprising:

[0039] A target image acquisition module is configured to identify and mark the spine, intervertebral disc, lateral recess and spinal nerve root in the original medical image of the patient to obtain a target medical image;

[0040] a feature parameter calculation module configured to calculate feature parameters of the spine, intervertebral disc, lateral recess and spinal nerve root based on the target medical image;

[0041] A compression risk determination module, configured to determine whether a spinal nerve root is at risk of compression based on characteristic parameters of the spine, intervertebral disc, and lateral recess;

[0042] The compression degree determination module is configured to determine the compression degree of the spinal nerve root based on the characteristic parameters of the spinal nerve root when there is a risk of compression of the spinal nerve root.

[0043] According to a third aspect of the present disclosure, an electronic device is provided, comprising a processor and a memory storing program instructions, wherein the processor is configured to execute the method for assessing the compression condition of a spinal nerve root provided by the first aspect of the present disclosure when running the program instructions.

[0044] The method and device for evaluating the compression condition of spinal nerve roots and the electronic device provided in the embodiments of the present disclosure can achieve the following technical effects:

[0045] The method for evaluating the compression condition of the spinal nerve root provided by the embodiment of the present disclosure ensures the accurate identification of key anatomical structures by identifying and marking the spine, intervertebral disc, lateral recess and spinal nerve root. The characteristic parameters of the spine, intervertebral disc, lateral recess and spinal nerve root are accurately calculated based on the markings, providing a specific numerical basis for subsequent risk assessment. Based on the characteristic parameters of the spine, intervertebral disc and lateral recess, it is determined whether the spinal nerve root is at risk of compression. Through multi-dimensional characteristic parameter analysis, potential compression risks can be accurately identified, reducing the possibility of misdiagnosis and missed diagnosis. In the case of determining that the spinal nerve root is at risk of compression, the degree of compression of the spinal nerve root is further determined based on the characteristic parameters of the spinal nerve root. The above process can provide detailed anatomical structure information and quantitative analysis results through precise image recognition and characteristic parameter calculation, significantly improving the accuracy of diagnosis. Multi-dimensional risk assessment and compression degree grading further reduce the risk of misdiagnosis and missed diagnosis. The above method can accurately and efficiently evaluate the compression condition of the spinal nerve root.

[0046] The foregoing general description and the following description are exemplary and explanatory only and are not intended to limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] One or more embodiments are exemplarily described by corresponding drawings, which do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements, and the drawings do not constitute a scale limitation, and wherein:

[0048] Figure 1 It is a flow chart of a method for evaluating the compression condition of a spinal nerve root provided by an embodiment of the present disclosure;

[0049] Figure 2 is a flow chart of another method for evaluating the compression condition of a spinal nerve root provided by an embodiment of the present disclosure;

[0050] Figure 3 is a flow chart of another method for evaluating the compression condition of a spinal nerve root provided by an embodiment of the present disclosure;

[0051] Figure 4is a schematic diagram of the classification of the degree of compression of the spinal nerve roots provided by the embodiment of the present disclosure;

[0052] Figure 5 is a flow chart of another method for evaluating the compression condition of a spinal nerve root provided by an embodiment of the present disclosure;

[0053] Figure 6 is a schematic structural diagram of a spinal nerve root compression condition assessment device provided by an embodiment of the present disclosure;

[0054] Figure 7 It is a schematic diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0055] In order to be able to understand the features and technical contents of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0056] The terms "first", "second", etc. in the specification and claims of the embodiments of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged where appropriate, so that the embodiments of the embodiments of the present disclosure described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0057] Unless otherwise stated, the term "plurality" means two or more.

[0058] In the embodiment of the present disclosure, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B indicates: A or B.

[0059] The term "and / or" is a description of the association relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B.

[0060] The term "correspondence" may refer to an association relationship or a binding relationship. The correspondence between A and B means that there is an association relationship or a binding relationship between A and B.

[0061] The disclosed embodiment provides an electronic device, which may be a device with computing capabilities such as a computer, a terminal, or a server. The electronic device calculates characteristic parameters of the spine, intervertebral disc, lateral recess, and spinal nerve root based on the original medical image of the patient, and determines the degree of compression of the spinal nerve root based on these characteristic parameters.

[0062] In conjunction with the electronic device provided by the embodiment of the present disclosure (hereinafter referred to as the device), the embodiment of the present disclosure provides a method for evaluating the compression condition of a spinal nerve root, such as Figure 1 As shown, methods for evaluating spinal nerve root compression include:

[0063] S101, the device identifies and marks the spine, intervertebral disc, lateral recess and spinal nerve root in the original medical image of the patient to obtain a target medical image.

[0064] In the disclosed embodiment, the original medical image is an image obtained based on a magnetic resonance imaging device, or an image obtained based on a computer tomography device. Here, an image segmentation model can be pre-trained, and the original medical image can be input into the image segmentation model to identify and mark the spine, intervertebral disc, lateral recess and spinal nerve root, and a target medical image can be obtained based on the segmentation result. In the target medical image, the spine, intervertebral disc, lateral recess and spinal nerve root have been marked.

[0065] The spine is made up of multiple spinal segments, all of which are labeled in the target medical diagram. These spinal segments are, from top to bottom, the cervical, thoracic, lumbar, sacral, and coccygeal. There are 7 cervical vertebrae, usually represented by C1 to C7, of which C1 is called the atlas and C2 is called the axis. The main function of the cervical vertebrae is to support the head and allow it to move in various directions. There are 12 thoracic vertebrae, usually represented by T1 to T12. Each thoracic vertebra is connected to a pair of ribs, which together form the thorax and protect important organs such as the heart and lungs. There are 5 lumbar vertebrae, usually represented by L1 to L5. The lumbar vertebrae are larger than the cervical and thoracic vertebrae, mainly bear the weight of the upper body of the human body, and support activities such as bending and twisting. The sacral vertebrae are formed by the fusion of 5 originally independent vertebrae in adulthood into a whole, called the sacrum. The sacrum forms the sacroiliac joint with the hip bone, which is essential for supporting the weight of the body and stability when walking. The coccygeal vertebrae are formed by the fusion of 3-4 very small vertebrae to form the coccyx.

[0066] The intervertebral disc consists of multiple disc segments, each of which is labeled in the target medical diagram. Each disc segment is located between two adjacent vertebral segments, from the cervical spine to the lumbar spine, but does not include the area between the sacrum and coccyx, because these parts are usually fused in adults. The main function of the intervertebral disc is to act as a cushion, reducing the impact and friction of the spine during daily activities, while allowing a certain degree of flexibility in the spine.

[0067] The lateral recess is a part of the spinal canal, located on both sides of the spinal canal, close to the inner side of the pedicle. It is a relatively narrow space, through which the nerve root and the dura mater sac around it pass. The lateral recess is very important for the transition of the nerve root from the spinal cord to the intervertebral foramen. The lateral recess is divided into the left lateral recess and the right lateral recess, which are located on the left and right sides of the midline of the spine, respectively. The left lateral recess and the right lateral recess are marked in the target medical diagram.

[0068] S102, the device calculates characteristic parameters of the spine, intervertebral disc, lateral recess and spinal nerve root based on the target medical image.

[0069] In the disclosed embodiment, image processing technology can be used to calculate characteristic parameters of the spine, intervertebral disc, lateral recess and spinal nerve root based on the target medical image, wherein the calculated characteristic parameters are parameters related to the compression of the spinal nerve root.

[0070] Optionally, the characteristic parameters of the spine include the longest diameter of each spinal segment in the sagittal plane of the image, and the characteristic parameters of the intervertebral disc include the longest diameter of each intervertebral disc segment in the sagittal plane of the image.

[0071] Optionally, the characteristic parameters of the lateral recess include the diameter of the lateral recess on each side in the sagittal plane of the image.

[0072] S103, the device determines whether the spinal nerve root is at risk of compression based on characteristic parameters of the spine, intervertebral disc and lateral recess.

[0073] In the disclosed embodiment, based on the characteristic parameters of the spine, intervertebral disc and lateral recess, it can be determined whether there is a risk of intervertebral disc herniation and lateral recess stenosis, and based on the risk of intervertebral disc herniation and lateral recess stenosis, it can be determined whether there is a risk of spinal nerve root compression.

[0074] S104, when there is a risk of compression of the spinal nerve root, the device determines the degree of compression of the spinal nerve root based on characteristic parameters of the spinal nerve root.

[0075] Optionally, the starting point, center line, length, outline, effective diameter of the lumen, maximum diameter of the lumen, minimum diameter of the lumen, grayscale, mean, variance, etc. of the spinal nerve root are calculated. Among them, the characteristic parameters of the spinal nerve root include the effective diameter of the spinal nerve root lumen and the ratio of the maximum diameter of the lumen to the minimum diameter of the lumen. These characteristic parameters are parameters related to the degree of compression of the spinal nerve root.

[0076] The method for evaluating the compression condition of the spinal nerve root provided by the embodiment of the present disclosure ensures the accurate identification of key anatomical structures by identifying and marking the spine, intervertebral disc, lateral recess and spinal nerve root. The characteristic parameters of the spine, intervertebral disc, lateral recess and spinal nerve root are accurately calculated based on the markings, providing a specific numerical basis for subsequent risk assessment. Based on the characteristic parameters of the spine, intervertebral disc and lateral recess, it is determined whether the spinal nerve root is at risk of compression. Through multi-dimensional characteristic parameter analysis, potential compression risks can be accurately identified, reducing the possibility of misdiagnosis and missed diagnosis. In the case of determining that the spinal nerve root is at risk of compression, the degree of compression of the spinal nerve root is further determined based on the characteristic parameters of the spinal nerve root. The above process can provide detailed anatomical structure information and quantitative analysis results through precise image recognition and characteristic parameter calculation, significantly improving the accuracy of diagnosis. Multi-dimensional risk assessment and compression degree grading further reduce the risk of misdiagnosis and missed diagnosis. The above method can accurately and efficiently evaluate the compression condition of the spinal nerve root.

[0077] In the above method, detailed quantitative and qualitative evaluation indicators provide doctors with comprehensive information about the patient's condition and support the development of personalized diagnosis and treatment plans. The preoperative and postoperative support functions help evaluate the treatment effect, adjust the treatment plan, and improve the overall effect of the treatment. The multi-level analysis method and detailed evaluation indicators ensure the comprehensiveness and accuracy of the diagnosis, and reduce misdiagnosis and missed diagnosis caused by a single factor. The decision-making support function helps doctors make more accurate judgments in complex clinical situations. This method not only improves the accuracy and efficiency of diagnosis, but also supports personalized diagnosis and treatment, provides doctors with a powerful auxiliary tool, and provides strong support for the diagnosis and treatment of spinal nerve root compression.

[0078] In some embodiments, based on the characteristic parameters of the spine, intervertebral disc and lateral recess, determining whether a spinal nerve root is at risk of compression includes: determining whether there is a risk of intervertebral disc herniation based on the characteristic parameters of the spine and intervertebral disc; determining whether there is a risk of lateral recess stenosis based on the characteristic parameters of the lateral recess; and determining whether a spinal nerve root is at risk of compression in the event of a risk of intervertebral disc herniation and / or a risk of lateral recess stenosis.

[0079] Combination Figure 2 As shown, the embodiment of the present disclosure provides another method for evaluating the compression condition of a spinal nerve root, and the method for evaluating the compression condition of a spinal nerve root includes:

[0080] S201, the device identifies and marks the spine, intervertebral disc, lateral recess and spinal nerve roots in the original medical image of the patient to obtain a target medical image.

[0081] S202, the device calculates characteristic parameters of the spine, intervertebral disc, lateral recess and spinal nerve root based on the target medical image.

[0082] S203: The device determines whether there is a risk of intervertebral disc herniation based on characteristic parameters of the spine and intervertebral disc.

[0083] In the disclosed embodiment, the characteristic parameters of the spine include the longest diameter of each spinal segment in the sagittal image, and the characteristic parameters of the intervertebral disc include the longest diameter of each intervertebral disc segment in the sagittal image. Based on the characteristic parameters of the spine and the intervertebral disc, determining whether there is a risk of intervertebral disc herniation includes: for each intervertebral disc segment, calculating the longest diameter ratio of the longest diameter of the intervertebral disc segment in the sagittal image to the longest diameter of the adjacent spinal segment in the sagittal image; when the longest diameter ratio of the longest diameter of each intervertebral disc segment in the sagittal image to the longest diameter of the adjacent spinal segment in the sagittal image is greater than the aspect ratio threshold, determining that there is a risk of intervertebral disc herniation; when the longest diameter ratio of the longest diameter of any intervertebral disc segment in the sagittal image to the longest diameter of the adjacent spinal segment in the sagittal image is not greater than the aspect ratio threshold, determining that there is no risk of intervertebral disc herniation.

[0084] It is understandable that each intervertebral disc segment is located between two adjacent vertebral body segments, so each intervertebral disc segment is adjacent to two vertebral body segments. Therefore, for each intervertebral disc segment, the longest diameter in the sagittal position of the image needs to be compared with the two adjacent vertebral body segments.

[0085] When the longest diameter ratio of the intervertebral disc segment in the sagittal image to the longest diameter of the adjacent vertebral segment in the sagittal image is greater than the length-to-diameter ratio threshold, it indicates that the intervertebral disc segment is abnormal. When the longest diameter ratio of the intervertebral disc segment in the sagittal image to the longest diameter of the adjacent vertebral segment in the sagittal image is not greater than the length-to-diameter ratio threshold, it indicates that the intervertebral disc segment is normal. If all intervertebral disc segments are normal, it is determined that there is no risk of intervertebral disc herniation. If any intervertebral disc segment is abnormal, it is determined that there is a risk of intervertebral disc herniation.

[0086] S204: The device determines whether there is a risk of lateral recess stenosis based on characteristic parameters of the lateral recess.

[0087] In the disclosed embodiment, the characteristic parameters of the lateral recess include the diameter of the lateral recess on each side in the sagittal image. Based on the characteristic parameters of the lateral recess, determining whether there is a risk of lateral recess stenosis includes: for each side of the lateral recess, comparing the diameter of the lateral recess in the sagittal image with a first diameter threshold; when the diameter of any side recess in the sagittal image is less than the first diameter threshold, determining that there is a risk of lateral recess stenosis; when the diameter of each recess in the sagittal image is not less than the first diameter threshold, determining that there is no risk of lateral recess stenosis.

[0088] In the disclosed embodiment, the lateral recess is divided into the left lateral recess and the right lateral recess. Therefore, it is necessary to compare the diameters of the left lateral recess and the right lateral recess in the sagittal image with the first diameter threshold value respectively. When the diameters of the left lateral recess and the right lateral recess in the sagittal image are both less than the first diameter threshold value, it is determined that there is a risk of lateral recess stenosis. When the diameters of the left lateral recess and the right lateral recess in the sagittal image are not less than the first diameter threshold value, it is determined that there is no risk of lateral recess stenosis. Among them, the first diameter threshold value can be determined according to actual design needs.

[0089] S205, the device determines that a spinal nerve root is at risk of compression when there is a risk of intervertebral disc herniation and / or a risk of lateral recess stenosis.

[0090] In the embodiment of the present disclosure, if there is at least one of the risk of intervertebral disc herniation and the risk of lateral recess stenosis, it is determined that the spinal nerve root is at risk of compression. If there is no risk of intervertebral disc herniation and no risk of lateral recess stenosis, it is determined that there is no risk of spinal nerve root compression.

[0091] S206, when there is a risk of compression of the spinal nerve root, the device determines the degree of compression of the spinal nerve root based on characteristic parameters of the spinal nerve root.

[0092] In the disclosed embodiment, the characteristic parameters of the spinal nerve root include the effective diameter of the spinal nerve root lumen, and the diameter ratio of the maximum diameter of the lumen to the minimum diameter of the lumen, and the degree of compression includes 0 to 3 levels, wherein 0 is the lowest level and 3 is the highest level. Determining the degree of compression of the spinal nerve root based on the characteristic parameters of the spinal nerve root includes: comparing the effective diameter of the spinal nerve root lumen with a second diameter threshold; when the effective diameter of the spinal nerve root lumen is greater than the second diameter threshold, determining the degree of compression of the spinal nerve root to be the highest level; when the effective diameter of the spinal nerve root lumen is not greater than the second diameter threshold, determining the degree of compression of the spinal nerve root based on the comparison result of the diameter ratio of the spinal nerve root and the corresponding ratio threshold.

[0093] Combination Figure 3 As shown, the embodiment of the present disclosure provides another method for evaluating the compression condition of a spinal nerve root, and the method for evaluating the compression condition of a spinal nerve root includes:

[0094] S301, the device identifies and marks the spine, intervertebral disc, lateral recess and spinal nerve root in the original medical image of the patient to obtain a target medical image.

[0095] S302, the device calculates characteristic parameters of the spine, intervertebral disc, lateral recess and spinal nerve root based on the target medical image.

[0096] S303, the device determines whether the spinal nerve root is at risk of compression based on characteristic parameters of the spine, intervertebral disc and lateral recess.

[0097] S304, when there is a risk of compression of the spinal nerve root, the device compares the effective diameter of the spinal nerve root lumen with a second diameter threshold.

[0098] In the embodiment of the present disclosure, the specific value of the second diameter threshold can be determined according to actual design requirements. For example, the value of the second diameter threshold is close to 0. Optionally, the second diameter threshold is 0.

[0099] S305, when the effective diameter of the spinal nerve root lumen is greater than the second diameter threshold, the device determines that the compression degree of the spinal nerve root is the highest level.

[0100] S306, when the effective diameter of the spinal nerve root lumen is not greater than the second diameter threshold, the device determines the degree of compression of the spinal nerve root based on the comparison result of the diameter ratio of the spinal nerve root and the corresponding ratio threshold.

[0101] The degree of compression of the spinal nerve roots can be divided into four levels: 0 (normal), 1 (mild compression), 2 (moderate compression) and 3 (severe compression), among which 3 is the highest level. Figure 4 As shown:

[0102] Grade 0: Normal imaging findings, no nerve root compression, and clear nerve root images.

[0103] Grade 1: adjacent to or in contact with the nerve root but showing no signs of displacement or deformation; the nerve root is adjacent to or in contact with the herniated disc (fragment); acute early cloverleaf-shaped lateral recess angle change.

[0104] Grade 2: Intervertebral disc herniation causes nerve root displacement (deviation) or deformation; cloverleaf-shaped or angular pinch-like changes in the lateral recess cause nerve root displacement (deviation) or deformation.

[0105] Grade 3: The nerve root is clearly compressed (displaced, deformed) or the nerve root image is completely invisible.

[0106] exist Figure 4 Among them, sub-figures A to D are the conditions of nerve root compression associated with intervertebral disc herniation, and sub-figures E to J are the conditions of nerve root compression associated with lateral recess stenosis.

[0107] In some embodiments, a first ratio threshold, a second ratio threshold, and a third ratio threshold may be set, the first ratio threshold being greater than the second ratio threshold, and the second ratio threshold being greater than the third ratio threshold. When the effective diameter of the spinal nerve root lumen is greater than the second diameter threshold, the device determines the degree of compression of the spinal nerve root by:

[0108] The diameter ratio of the spinal nerve root is greater than or equal to the first ratio threshold, and the compression degree of the spinal nerve root is determined to be level 0 (normal);

[0109] The diameter ratio of the spinal nerve root is less than the first ratio threshold and greater than or equal to the second ratio threshold, and the compression degree of the spinal nerve root is determined to be level 1 (mild compression);

[0110] The diameter ratio of the spinal nerve root is less than the second ratio threshold and greater than or equal to the third ratio threshold, and the compression degree of the spinal nerve root is determined to be level 2 (moderate compression);

[0111] The diameter ratio of the spinal nerve root is less than the third ratio threshold value, and the compression degree of the spinal nerve root is determined to be level 3 (severe compression).

[0112] In some embodiments, the spinal nerve roots can be classified and named using the results of the spine and spinal nerve root segmentation in the target medical image. Based on the spine segmentation label, the pixel area of ​​each spinal segment is identified, and the positional relationship between the spinal nerve root and the spinal segment is calculated. The nerve root above the pixel area of ​​the first cervical segment is recorded as the first cervical nerve, and the first cervical nerve to the eighth cervical nerve, the first thoracic nerve to the twelfth thoracic nerve, the first lumbar nerve to the fifth lumbar nerve, the first sacral nerve to the fifth sacral nerve and the coccygeal nerve are named in sequence downward.

[0113] Combination Figure 5 As shown, the embodiment of the present disclosure provides another method for evaluating the compression condition of a spinal nerve root, and the method for evaluating the compression condition of a spinal nerve root includes:

[0114] S501, the device identifies and marks the spine, intervertebral disc, lateral recess and spinal nerve root in the original medical image of the patient to obtain a target medical image.

[0115] S502, the device calculates characteristic parameters of the spine, intervertebral disc, lateral recess and spinal nerve root based on the target medical image.

[0116] S503: The device determines whether there is a risk of intervertebral disc herniation based on characteristic parameters of the spine and intervertebral disc.

[0117] S504: The device determines whether there is a risk of lateral recess stenosis based on characteristic parameters of the lateral recess.

[0118] S505, the device determines that there is a risk of compression of the spinal nerve root when there is a risk of intervertebral disc herniation and / or a risk of lateral recess stenosis.

[0119] S506, when there is a risk of compression of the spinal nerve root, the device compares the effective diameter of the spinal nerve root lumen with a second diameter threshold.

[0120] S507, when the effective diameter of the spinal nerve root lumen is greater than the second diameter threshold, the device determines that the compression degree of the spinal nerve root is the highest level.

[0121] S508, when the effective diameter of the spinal nerve root lumen is not greater than the second diameter threshold, the device determines the degree of compression of the spinal nerve root based on the comparison result of the diameter ratio of the spinal nerve root and the corresponding ratio threshold.

[0122] In some embodiments, the spine, intervertebral disc, lateral recess and spinal nerve roots are identified and marked in the original medical image of the patient to obtain a target medical image, including: acquiring a first intermediate image containing segmentation results of the spine and intervertebral disc based on the original medical image; acquiring a second intermediate image containing segmentation results of the lateral recess and spinal nerve roots based on the original medical image; acquiring a third intermediate image containing classification results of the spine based on the original medical image; acquiring a fourth intermediate image containing classification results of the intervertebral disc based on the original medical image; and merging the first intermediate image, the second intermediate image, the third intermediate image and the fourth intermediate image to obtain the target medical image.

[0123] In the disclosed embodiment, the first intermediate image is labeled with the labels of the spine and intervertebral disc, the second intermediate image is labeled with the labels of the lateral recess and spinal nerve roots, the third intermediate image is labeled with the labels of each spinal segment, and the fourth intermediate image is labeled with the labels of each intervertebral disc segment.

[0124] In the embodiment of the present disclosure, the first to fourth intermediate images can be merged according to a preset merging order. Specifically, the first intermediate image is used as the base layer, and the second intermediate image is used as the last layer. When merging, the third intermediate image is first merged into the first intermediate image to obtain a first merged image, and then the fourth intermediate image is merged into the first merged image to obtain a second merged image, and finally the second intermediate image is merged into the second merged image to obtain a target medical image.

[0125] For two images that need to be merged, when the labels of the two images in the same area are different, the label of the later image shall prevail. Specifically, when the labels of the first intermediate image and the third intermediate image in the same area are different, the label of the third intermediate image shall prevail; when the labels of the first merged image and the fourth intermediate image in the same area are different, the label of the fourth intermediate image shall prevail; when the labels of the second merged image and the second intermediate image in the same area are different, the label of the second intermediate image shall prevail.

[0126] Optionally, in order to reduce boundary discontinuity or noise, the merged target medical image may be smoothed in the last step, for example, using morphological operations (such as opening and closing operations) or neighborhood-based smoothing algorithms.

[0127] Optionally, according to actual needs, some post-processing may be performed, such as removing small isolated areas, filling holes, etc., to improve the quality of the segmentation result.

[0128] In some embodiments, obtaining a first intermediate image including segmentation results of the spine and intervertebral disc based on the original medical image includes: inputting the original medical image into a first segmentation model, and obtaining a first intermediate image including segmentation results of the spine and intervertebral disc using the first segmentation model.

[0129] In some embodiments, obtaining a second intermediate image including segmentation results of the lateral recess and the spinal nerve root based on the original medical image includes: inputting the original medical image into a second segmentation model, and obtaining a second intermediate image including segmentation results of the lateral recess and the spinal nerve root using the second segmentation model;

[0130] In some embodiments, obtaining a third intermediate image including classification results of the spine based on the original medical image includes: inputting the original medical image into a third segmentation model, and obtaining the third intermediate image including classification results of the spine using the third segmentation model.

[0131] In some embodiments, acquiring a fourth intermediate image including a classification result of the intervertebral disc based on the original medical image includes: inputting the original medical image into a fourth segmentation model, and acquiring a fourth intermediate image including a classification result of the intervertebral disc using the fourth segmentation model.

[0132] In the disclosed embodiment, the segmentation model is a convolutional neural network model that can handle multiple segmentation tasks simultaneously and combines a hybrid attention mechanism, such as Unet and ResNet. In order to train the segmentation model, it is necessary to construct a data set and perform data annotation. Specifically, collect images containing the spine obtained based on a magnetic resonance imaging device, or images containing the spine obtained based on a computer tomography device, set the image to a preset size (such as 512*512), and expand the data set by applying rotation, scaling and other technologies to improve the robustness of the algorithm. Divide the data set into training sets, tuning sets and test sets according to the proportion of the images.

[0133] The images in the training set of the dataset are manually annotated accurately, and the tissue labels such as spine, intervertebral disc, dural sac, lateral recess, nerve root, etc. are marked. The spine includes cervical spine (C1-C7), thoracic spine (T1-T12), lumbar spine (L1-L5), sacral spine (S1-S5) and coccyx (CO), and different spine / intervertebral disc segments are marked with different labels. The nerve roots on the left and right sides of each spine are marked as nerve tissue labels. The lateral recesses in the range of L4, L5 to S1 are marked as lateral recess labels. In addition, the original images before labeling are also retained in the training set. For ease of understanding and description, the unlabeled images in the dataset used for segmentation model training are defined as the first original sample medical images, and the labeled images in the dataset used for segmentation model training are defined as the first original sample mask images.

[0134] In the embodiment of the present disclosure, the first segmentation model is trained based on the first original sample medical image and the first original sample mask image, and the original sample mask image is obtained after marking the labels of the spine, intervertebral disc, lateral recess and spinal nerve roots in the original sample medical image.

[0135] In an embodiment of the present disclosure, the second segmentation model is trained based on a second original sample medical image and a second original sample mask image, wherein the second original sample medical image is a sub-image including the spine and its surrounding area cropped out from the first original sample medical image, and the second original sample mask image is a sub-image including the spine and its surrounding area cropped out from the second original sample mask image.

[0136] Combination Figure 6 As shown, an embodiment of the present disclosure provides a spinal nerve root compression condition assessment device 600, which includes a target image acquisition module 601, a characteristic parameter calculation module 602, a compression risk determination module 603 and a compression degree determination module 604.

[0137] The target image acquisition module 601 is configured to identify and mark the spine, intervertebral disc, lateral recess and spinal nerve root in the original medical image of the patient to obtain a target medical image.

[0138] The feature parameter calculation module 602 is configured to calculate the feature parameters of the spine, intervertebral disc, lateral recess and spinal nerve root based on the target medical image.

[0139] The compression risk determination module 603 is configured to determine whether the spinal nerve root is at risk of compression based on characteristic parameters of the spine, intervertebral disc and lateral recess.

[0140] The compression degree determination module 604 is configured to determine the compression degree of the spinal nerve root based on the characteristic parameters of the spinal nerve root when there is a risk of compression of the spinal nerve root.

[0141] The compression condition assessment device for spinal nerve roots provided by the embodiment of the present disclosure ensures accurate identification of key anatomical structures by identifying and marking the spine, intervertebral disc, lateral recess and spinal nerve roots. The characteristic parameters of the spine, intervertebral disc, lateral recess and spinal nerve roots are accurately calculated based on the markings, providing a specific numerical basis for subsequent risk assessment. Based on the characteristic parameters of the spine, intervertebral disc and lateral recess, it is determined whether the spinal nerve roots are at risk of compression. Through multi-dimensional characteristic parameter analysis, potential compression risks can be accurately identified, reducing the possibility of misdiagnosis and missed diagnosis. In the case of determining that the spinal nerve roots are at risk of compression, the degree of compression of the spinal nerve roots is further determined based on the characteristic parameters of the spinal nerve roots. The above process can provide detailed anatomical structure information and quantitative analysis results through precise image recognition and characteristic parameter calculation, significantly improving the accuracy of diagnosis. Multi-dimensional risk assessment and compression degree grading further reduce the risk of misdiagnosis and missed diagnosis. The compression condition of the spinal nerve roots can be accurately and efficiently assessed through the above device.

[0142] In some embodiments, the compression risk determination module 603 is configured to:

[0143] Determine whether there is a risk of disc herniation based on the characteristic parameters of the spine and intervertebral disc;

[0144] Based on the characteristic parameters of the lateral recess, determining whether there is a risk of lateral recess stenosis;

[0145] In cases with risk of disc herniation and / or lateral recess stenosis, the risk of spinal nerve root compression is determined.

[0146] In some embodiments, the characteristic parameters of the spine include the longest diameter of each spinal segment in the sagittal image, and the characteristic parameters of the intervertebral disc include the longest diameter of each intervertebral disc segment in the sagittal image. The compression risk determination module 603 is configured to:

[0147] For each intervertebral disc segment, the longest diameter ratio of the intervertebral disc segment in the sagittal image to the longest diameter of its adjacent vertebral segment in the sagittal image was calculated;

[0148] When the longest diameter ratio of each intervertebral disc segment in the sagittal image to the longest diameter of its adjacent vertebral segment in the sagittal image is greater than the length-to-diameter ratio threshold, it is determined that there is a risk of intervertebral disc herniation;

[0149] When the longest diameter ratio of any intervertebral disc segment in the sagittal image to the longest diameter of its adjacent vertebral segment in the sagittal image is not greater than the aspect ratio threshold, it is determined that there is no risk of intervertebral disc herniation.

[0150] In some embodiments, the characteristic parameter of the lateral recess includes the diameter of the lateral recess on each side in the sagittal image. The compression risk determination module 603 is configured to:

[0151] For each side of the lateral recess, the diameter of the lateral recess in the sagittal image was compared with the first diameter threshold;

[0152] When the diameter of any lateral recess in the sagittal image is smaller than the first diameter threshold, it is determined that there is a risk of lateral recess stenosis;

[0153] When the diameter of each recess in the sagittal image is not less than the first diameter threshold, it is determined that there is no risk of lateral recess stenosis.

[0154] In some embodiments, the characteristic parameters of the spinal nerve root include the effective diameter of the spinal nerve root lumen and the ratio of the maximum diameter of the lumen to the minimum diameter of the lumen. The compression degree includes 0 to 3 levels, wherein 0 is the lowest level and 3 is the highest level. The compression degree determination module is configured as follows:

[0155] comparing the effective diameter of the spinal nerve root lumen to a second diameter threshold;

[0156] When the effective diameter of the spinal nerve root lumen is greater than the second diameter threshold, determining that the compression degree of the spinal nerve root is at the highest level;

[0157] When the effective diameter of the spinal nerve root lumen is not greater than the second diameter threshold, the compression degree of the spinal nerve root is determined based on the comparison result of the diameter ratio of the spinal nerve root and the corresponding ratio threshold.

[0158] In some embodiments, the target image acquisition module 601 is configured to:

[0159] Acquire a first intermediate image including segmentation results of the spine and the intervertebral disc based on the original medical image;

[0160] Acquire a second intermediate image including segmentation results of the lateral recess and spinal nerve roots based on the original medical image;

[0161] Acquire a third intermediate image containing a classification result of the spine based on the original medical image;

[0162] acquiring a fourth intermediate image including a classification result of the intervertebral disc based on the original medical image;

[0163] The first intermediate image, the second intermediate image, the third intermediate image and the fourth intermediate image are combined to obtain a target medical image.

[0164] In some embodiments, the target image acquisition module 601 is configured to: input the original medical image into the first segmentation model, and use the first segmentation model to acquire a first intermediate image containing the segmentation results of the spine and the intervertebral disc. The first segmentation model is trained based on the first original sample medical image and the first original sample mask image, and the original sample mask image is obtained after the labels of the spine, intervertebral disc, lateral recess and spinal nerve root are marked in the original sample medical image.

[0165] In some embodiments, the target image acquisition module 601 is configured to: input the original medical image into the second segmentation model, and use the second segmentation model to acquire a second intermediate image containing the segmentation results of the lateral recess and the spinal nerve root. The second segmentation model is trained based on the second original sample medical image and the second original sample mask image, the second original sample medical image is a sub-image including the spine and its surrounding area cut out from the first original sample medical image, and the second original sample mask image is a sub-image including the spine and its surrounding area cut out from the second original sample mask image.

[0166] Combination Figure 7 As shown, an embodiment of the present disclosure provides an electronic device 700, and the electronic device 700 includes a processor (processor) 701 and a memory (memory) 702. Optionally, the electronic device 700 may also include a communication interface (Communication Interface) 703 and a bus 704. Among them, the processor 701, the communication interface 703, and the memory 702 can communicate with each other through the bus 704. The communication interface 703 can be used for information transmission. The processor 701 can call the logic instructions in the memory 702 to execute the method for evaluating the compression condition of the spinal nerve root of the above embodiment.

[0167] In addition, the logic instructions in the memory 702 described above may be implemented in the form of software functional units and when sold or used as independent products, may be stored in a computer-readable storage medium.

[0168] The memory 702 is a computer-readable storage medium that can be used to store software programs and computer executable programs, such as program instructions / modules corresponding to the method in the embodiment of the present disclosure. The processor 701 executes the function application and data processing by running the program instructions / modules stored in the memory 702, that is, the method for evaluating the compression condition of the spinal nerve root in the above embodiment is implemented.

[0169] The memory 702 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 702 may include a high-speed random access memory and may also include a non-volatile memory.

[0170] An embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to execute the above-mentioned method for assessing the compression condition of a spinal nerve root.

[0171] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiment of the present disclosure. The aforementioned storage medium may be a non-transient storage medium, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes.

[0172] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent only possible changes. Unless explicitly required, separate components and functions are optional, and the order of operation may vary. The parts and features of some embodiments may be included in or replace the parts and features of other embodiments. Moreover, the words used in this application are only used to describe the embodiments and are not used to limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates, the singular forms of "a", "an" and "the" are intended to include plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of listings containing one or more associated ones. In addition, when used in the present application, the term "comprise" and its variants "comprises" and / or comprising refer to the presence of stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof. In the absence of further restrictions, the elements defined by the sentence "comprising a ..." do not exclude the presence of other identical elements in the process, method or device comprising the elements. In this article, each embodiment may focus on the differences from other embodiments, and the same and similar parts between the various embodiments may refer to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can refer to the description of the method part.

[0173] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. The technicians may use different methods for each specific application to implement the described functions, but such implementations should not be considered to exceed the scope of the embodiments of the present disclosure. The technicians may clearly understand that, for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above may refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0174] In the embodiments disclosed herein, the disclosed methods and products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units can be only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to implement this embodiment. In addition, each functional unit in the embodiment of the present disclosure may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit.

[0175] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A method for evaluating the compression condition of a spinal nerve root, characterized in that: include: The spine, intervertebral disc, lateral recess and spinal nerve root are identified and marked in the original medical image of the patient to obtain a target medical image; Calculate characteristic parameters of the spine, intervertebral disc, lateral recess and spinal nerve root based on the target medical image; Determine whether the spinal nerve roots are at risk of compression based on characteristic parameters of the spine, intervertebral disc, and lateral recess; When there is a risk of compression of the spinal nerve root, the degree of compression of the spinal nerve root is determined based on characteristic parameters of the spinal nerve root.

2. The method for evaluating compression conditions according to claim 1, characterized in that: Determine whether a spinal nerve root is at risk of compression based on characteristic parameters of the spine, intervertebral disc, and lateral recess, including: Determine whether there is a risk of disc herniation based on the characteristic parameters of the spine and intervertebral disc; Based on the characteristic parameters of the lateral recess, determining whether there is a risk of lateral recess stenosis; In cases with risk of disc herniation and / or lateral recess stenosis, the risk of spinal nerve root compression is determined.

3. The method for evaluating compression conditions according to claim 2, characterized in that: The characteristic parameters of the spine include the longest diameter of each spinal segment in the sagittal image, and the characteristic parameters of the intervertebral disc include the longest diameter of each intervertebral disc segment in the sagittal image; Based on the characteristic parameters of the spine and intervertebral disc, the risk of intervertebral disc herniation is determined, including: For each intervertebral disc segment, the longest diameter ratio of the intervertebral disc segment in the sagittal image to the longest diameter of its adjacent vertebral segment in the sagittal image was calculated; When the longest diameter ratio of each intervertebral disc segment in the sagittal image to the longest diameter of its adjacent vertebral segment in the sagittal image is greater than the length-to-diameter ratio threshold, it is determined that there is a risk of intervertebral disc herniation; When the longest diameter ratio of any intervertebral disc segment in the sagittal image to the longest diameter of its adjacent vertebral segment in the sagittal image is not greater than the aspect ratio threshold, it is determined that there is no risk of intervertebral disc herniation.

4. The method for evaluating compression conditions according to claim 2, characterized in that: The characteristic parameters of the lateral recess include the diameter of the lateral recess on each side in the sagittal image; Based on the characteristic parameters of the lateral recess, the risk of lateral recess stenosis is determined, including: For each side of the lateral recess, the diameter of the lateral recess in the sagittal image was compared with the first diameter threshold; When the diameter of any lateral recess in the sagittal image is smaller than the first diameter threshold, it is determined that there is a risk of lateral recess stenosis; When the diameter of each recess in the sagittal image is not less than the first diameter threshold, it is determined that there is no risk of lateral recess stenosis.

5. The method for evaluating a compression condition according to any one of claims 1 to 4, characterized in that: The characteristic parameters of the spinal nerve root include the effective diameter of the spinal nerve root lumen and the ratio of the maximum diameter of the lumen to the minimum diameter of the lumen. The degree of compression ranges from 0 to 3, where 0 is the lowest and 3 is the highest. The degree of compression of the spinal nerve root is determined based on the characteristic parameters of the spinal nerve root, including: comparing the effective diameter of the spinal nerve root lumen to a second diameter threshold; When the effective diameter of the spinal nerve root lumen is greater than the second diameter threshold, determining that the compression degree of the spinal nerve root is the highest level; When the effective diameter of the spinal nerve root lumen is not greater than the second diameter threshold, the compression degree of the spinal nerve root is determined based on the comparison result of the diameter ratio of the spinal nerve root and the corresponding ratio threshold.

6. The method according to any one of claims 1 to 4, characterized in that The spine, intervertebral disc, lateral recess and spinal nerve roots are identified and marked in the original medical image of the patient to obtain the target medical image, including: Acquire a first intermediate image including segmentation results of the spine and the intervertebral disc based on the original medical image; Acquire a second intermediate image including segmentation results of the lateral recess and spinal nerve roots based on the original medical image; Acquire a third intermediate image containing a classification result of the spine based on the original medical image; acquiring a fourth intermediate image including a classification result of the intervertebral disc based on the original medical image; The first intermediate image, the second intermediate image, the third intermediate image and the fourth intermediate image are combined to obtain a target medical image.

7. The method according to claim 6, characterized in that Acquiring a first intermediate image including segmentation results of the spine and the intervertebral disc based on the original medical image, comprising: Inputting the original medical image into a first segmentation model, and using the first segmentation model to obtain a first intermediate image including segmentation results of the spine and the intervertebral disc; The first segmentation model is trained based on the first original sample medical image and the first original sample mask image, and the original sample mask image is obtained after marking the labels of the spine, intervertebral disc, lateral recess and spinal nerve root in the original sample medical image.

8. The method according to claim 7, characterized in that A second intermediate image including segmentation results of the lateral recess and the spinal nerve root is obtained based on the original medical image, including: Inputting the original medical image into a second segmentation model, and using the second segmentation model to obtain a second intermediate image including segmentation results of the lateral recess and the spinal nerve root; The second segmentation model is trained based on the second original sample medical image and the second original sample mask image, the second original sample medical image is a sub-image including the spine and its surrounding area cropped from the first original sample medical image, and the second original sample mask image is a sub-image including the spine and its surrounding area cropped from the second original sample mask image.

9. A device for evaluating the compression condition of a spinal nerve root, characterized in that: include: A target image acquisition module is configured to identify and mark the spine, intervertebral disc, lateral recess and spinal nerve root in the original medical image of the patient to obtain a target medical image; a feature parameter calculation module configured to calculate feature parameters of the spine, intervertebral disc, lateral recess and spinal nerve root based on the target medical image; A compression risk determination module, configured to determine whether a spinal nerve root is at risk of compression based on characteristic parameters of the spine, intervertebral disc, and lateral recess; The compression degree determination module is configured to determine the compression degree of the spinal nerve root based on the characteristic parameters of the spinal nerve root when there is a risk of compression of the spinal nerve root.

10. An electronic device comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to execute the method for assessing the compression condition of a spinal nerve root according to any one of claims 1 to 8 when running the program instructions.

Images