Spine parameter measurement and spinal sagittal imbalance evaluation method and system

Abstract

The invention discloses a spine parameter measurement and spine sagittal imbalance evaluation method, which comprises the following steps of: acquiring a spine original medical image picture of a target to be detected, and preprocessing to obtain a standardized image picture; and sending the standardized image picture into a spine angular point identification model for algorithm identification processing, and determining a cone sequence and coordinate information of cone angular points. And sending the standardized image picture into a cone identification and division model, and dividing cones in the standardized image picture. And performing calculation and analysis according to the obtained coordinate information to obtain spinal sagittal imbalance degree information, so as to comprehensively analyze and evaluate the spinal column. According to the invention, a neural network algorithm based on artificial intelligence is adopted to process a medical image picture, and each image anatomical marker and a cone contour of a spine are accurately identified; compared with manual measurement, the method is high in measurement precision, lower in error rate, short in time consumption, capable of processing data on a large scale and capable of effectively reducing medical cost.

Description

Technical Field

[0001] The present invention belongs to the field of medical imaging, and in particular relates to a method and system for measuring spinal parameters and evaluating spinal sagittal imbalance. Background Art

[0002] The spine is a complex human tissue composed of bones and connective tissue. As the central axis of the human body, it plays an important role in supporting the body, including weight bearing, shock absorption, movement, and protecting bone marrow and nerves. However, when subjected to excessive mechanical stress, various structures of the vertebral body slip, resulting in structural abnormalities. Another type of vertebral slippage is degenerative, which occurs due to aging of various structures of the lumbar spine. This type of vertebral slippage is often accompanied by lumbar spinal stenosis, which often affects the quality of life and requires surgical treatment.

[0003] At present, when judging the sagittal balance of the vertebrae by X-ray, it is necessary to combine three X-rays, namely the lateral position, the hyperextension position and the hyperflexion position, to comprehensively analyze the sagittal balance of the vertebrae by measuring the sagittal displacement and sagittal rotation of the vertebrae. However, the current manual measurement method is difficult to quickly assess the patient's condition, and completing an assessment report requires a lot of time and energy for clinical physicians. Therefore, there is an urgent need for a method that can automatically measure spinal-related parameters and automatically assess the sagittal balance of the vertebrae to improve the work efficiency of physicians. Summary of the invention

[0004] The technical purpose of the present invention is to provide a method and system for measuring spinal parameters and evaluating spinal sagittal imbalance, so as to solve the existing cone sagittal balance problem.

[0005] To solve the above problems, the technical solution of the present invention is:

[0006] A method for measuring spinal parameters and evaluating spinal sagittal imbalance comprises the following steps:

[0007] Obtaining original medical images of the spine of the target to be detected, including at least one lateral image of the spine, at least one image of the spine in hyperextension, and at least one image of the spine in hyperflexion; preprocessing the original medical images of the spine to obtain standardized images;

[0008] The standardized image is sent to a pre-trained spine corner point recognition model, and the standardized image is processed by algorithm recognition to determine the coordinate data of the cone corner points and the order of cones in the standardized image; the standardized image is then sent to a pre-trained vertebral body recognition and segmentation model to segment the cones in the standardized image;

[0009] The obtained coordinate information is used for calculation and analysis to obtain information on the degree of sagittal imbalance of the spine, which is then used to comprehensively analyze and evaluate the spine.

[0010] The preprocessing of the original medical image of the spine specifically includes: adjusting the parameters of one or more combinations of window width, window position, contrast, rotation and brightness of the original medical image of the spine to obtain a standardized image.

[0011] The construction of the spine corner point recognition model and the vertebral body recognition and segmentation model is as follows:

[0012] Acquire image data of the spine as a training image data set, and preprocess the training image data set;

[0013] Marking the preprocessed image data, wherein the marking information includes vertebral position, vertebral sequence and vertebral angle;

[0014] The labeled image data is fed into a convolutional neural network to build a spine corner recognition model;

[0015] The standardized spine model is input into the spine corner recognition model for training to construct a vertebral recognition and segmentation model.

[0016] Among them, after the standardized image is processed by algorithm recognition, the coordinate data of several cone corner points are obtained, and the four adjacent vertebral corner points are divided into a group. According to the coordinate data of each group, the upper and lower position relationship of each vertebra can be obtained, thereby determining the order of the vertebrae. At the same time, according to the order of the cones, the two adjacent vertebrae are divided into a group in pairs.

[0017] Among them, the calculation and analysis based on the obtained coordinate information is specifically as follows: two adjacent vertebrae are divided into a group, and the coordinate data of the corner points of the vertebrae in the same group are geometrically calculated in turn. The line segment connected by the two corner points of the lower edge of the upper vertebrae and the line segment connected by the two corner points of the upper edge of the lower vertebrae are calculated to obtain the displacement distance and the rotation angle. When the displacement distance exceeds the normal range value, it is considered to be a sagittal imbalance, otherwise it is normal.

[0018] A system for measuring spinal parameters and evaluating spinal sagittal imbalance is provided, which uses the spinal parameter measurement and spinal sagittal imbalance evaluation method as described above, and comprises:

[0019] The acquisition module is configured to obtain original medical images of the spine of the target to be detected, including at least one lateral image of the spine, at least one image of the spine in hyperextension, and at least one image of the spine in hyperflexion; preprocess the original medical images of the spine to obtain standardized images;

[0020] The parameter measurement module is configured to send the standardized image picture into a pre-trained spine corner point recognition model, perform recognition processing on the standardized image picture, determine the order of cones in the standardized image picture and the coordinate information of the cone corner points; then send the standardized image picture into a pre-trained vertebral body recognition and division model, and divide the cones in the standardized image picture;

[0021] The spinal sagittal imbalance analysis module is configured to perform calculations and analysis based on the obtained coordinate information to obtain information on the degree of spinal sagittal imbalance, thereby comprehensively analyzing and evaluating the spine.

[0022] A computer device includes a memory and a processor. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor executes the above-mentioned spinal parameter measurement and spinal sagittal imbalance assessment method.

[0023] A storage medium storing computer-readable instructions, when the computer-readable instructions are executed by one or more processors, enables the one or more processors to execute the above-mentioned spinal parameter measurement and spinal sagittal imbalance assessment method.

[0024] Due to the adoption of the above technical solution, the present invention has the following advantages and positive effects compared with the prior art:

[0025] The present invention uses a neural network algorithm based on artificial intelligence to process medical images and accurately identify various anatomical landmarks of the spine and the cone contours. Compared with manual measurement, the measurement accuracy is high, the error rate is lower, the time consumption is short, and data can be processed in large quantities, which can effectively reduce medical costs.

[0026] The present invention can effectively improve the popularity of spinal radiological parameter measurement through automatic identification and automatic calculation without any professional requirements or thresholds, and has strong clinical practical significance and promotion significance.

[0027] The parameter measurement can be used to automatically assess the degree of sagittal imbalance of the spine, thus assisting in the clinical assessment of spinal conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the following detailed description of the preferred embodiment.The drawings are only for the purpose of illustrating the preferred embodiments and are not to be construed as limiting the invention.

[0029] Figure 1 The present invention is a flowchart diagram of a method for measuring spinal parameters and evaluating spinal sagittal imbalance. DETAILED DESCRIPTION

[0030] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the specific implementation methods of the present invention will be described below with reference to the accompanying drawings. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings and other implementation methods can be obtained based on these drawings without creative work.

[0031] In order to simplify the drawings, only the parts related to the present invention are schematically shown in each figure, and they do not represent the actual structure of the product. In addition, in order to simplify the drawings and facilitate understanding, in some figures, only one of the parts with the same structure or function is schematically drawn or marked. In this article, "one" not only means "only one", but also means "more than one".

[0032] The following is a further detailed description of a spinal parameter measurement and spinal sagittal imbalance assessment method and system proposed by the present invention in conjunction with the accompanying drawings and specific embodiments. The advantages and features of the present invention will become more apparent from the following description and claims.

[0033] Example 1

[0034] See also Figure 1 The present embodiment provides a method for measuring spinal parameters and assessing spinal sagittal imbalance, comprising the following steps:

[0035] First, it is necessary to build the corresponding neural network model, namely the spinal corner recognition model and the vertebral recognition and segmentation model. The steps of model construction are as follows: obtain a large amount of image data of the spinal part as a training image data set, and perform preprocessing on the training image data set, including but not limited to window width, window position, contrast enhancement, and image size standardization. Mark the preprocessed image data, and the marking information includes vertebral position, vertebral sequence, and vertebral angle. Send the marked image data to the convolutional neural network to build a spinal corner recognition model. Then input the standardized spinal model into the spinal corner recognition model for training to build a vertebral recognition and segmentation model.

[0036] Then, the original medical image of the spine of the target to be detected is obtained, including at least one lateral image of the spine, at least one hyperextension image of the spine, and at least one hyperflexion image of the spine. The original medical image of the spine is preprocessed, wherein the preprocessing of the original medical image of the spine specifically includes: adjusting the parameters of one or more combinations of window width, window position, contrast, rotation and brightness of the original medical image of the spine to obtain a standardized image.

[0037] Next, the standardized image is sent to the pre-trained spinal corner recognition model, and the standardized image is processed by algorithm recognition to obtain the coordinate data of several cone corners. The four adjacent vertebral corners are divided into a group. According to the coordinate data of each group, the upper and lower position relationship of each vertebra can be obtained, so as to determine the order of the vertebrae. At the same time, according to the order of the cones, the two adjacent vertebrae are divided into a group; the standardized image is sent to the pre-trained vertebral recognition and division model to divide the cones in the standardized image. Finally, the coordinate data of the corners of the same group of vertebrae are calculated in turn, and the line segment connected by the two corners of the lower edge of the upper vertebrae and the line segment connected by the two corners of the upper edge of the lower vertebrae are calculated to obtain the displacement distance and rotation angle between the vertebrae in the same group. When the displacement distance exceeds the normal range, it is considered to be sagittal imbalance, otherwise it is normal. So far, the information on the degree of sagittal imbalance of the spine is obtained, which can be used for comprehensive analysis and evaluation of the spine and assist in clinical evaluation of the spine.

[0038] Example 2

[0039] This embodiment provides a spinal parameter measurement and spinal sagittal imbalance assessment system, which uses the spinal parameter measurement and spinal sagittal imbalance assessment method of embodiment 1, including:

[0040] The acquisition module is used to obtain the original medical image of the spine of the target to be detected, including at least one lateral image of the spine, at least one hyperextension image of the spine, and at least one hyperflexion image of the spine. The original medical image of the spine is preprocessed to obtain a standardized image.

[0041] The parameter measurement module is used to send the standardized image picture into a pre-trained spine corner point recognition model, perform calculation processing on the standardized image picture, determine the order of cones in the standardized image picture and the coordinate information of the cone corner points; then send the standardized image picture into a pre-trained vertebral recognition and division model to divide the cones in the standardized image picture.

[0042] The spinal sagittal imbalance analysis module is used to perform calculations and analysis based on the obtained coordinate information to obtain information on the degree of spinal sagittal imbalance, thereby comprehensively analyzing and evaluating the spine.

[0043] Example 3

[0044] This embodiment provides a computer device, including a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the spinal parameter measurement and spinal sagittal imbalance assessment method as described in Embodiment 1.

[0045] Example 4

[0046] This embodiment provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the spinal parameter measurement and spinal sagittal imbalance assessment method as described in Example 1.

[0047] The embodiments of the present invention are described in detail above in conjunction with the accompanying drawings, but the present invention is not limited to the above embodiments. Even if various changes are made to the present invention, if these changes fall within the scope of the claims of the present invention and their equivalents, they still fall within the protection scope of the present invention.

Claims

1. A method for measuring spinal parameters and assessing spinal sagittal imbalance, characterized in that: The steps include: Obtaining original medical images of the spine of the target to be detected, including at least one lateral image of the spine, at least one image of the spine in hyperextension, and at least one image of the spine in hyperflexion; preprocessing the original medical images of the spine to obtain standardized images; The standardized image is sent to a pre-trained spine corner point recognition model, and the standardized image is processed by algorithm recognition to determine the coordinate data of the cone corner points and the order of cones in the standardized image; the standardized image is then sent to a pre-trained vertebral body recognition and segmentation model to segment the cones in the standardized image; The obtained coordinate information is used for calculation and analysis to obtain information on the degree of sagittal imbalance of the spine, which is then used to comprehensively analyze and evaluate the spine.

2. The method for measuring spinal parameters and assessing spinal sagittal imbalance according to claim 1, characterized in that: The preprocessing of the original medical image of the spine specifically includes: adjusting the parameters of one or more combinations of window width, window position, contrast, rotation and brightness of the original medical image of the spine to obtain a standardized image.

3. The method for measuring spinal parameters and assessing spinal sagittal imbalance according to claim 1, characterized in that: The construction of the spine corner point recognition model and the vertebral body recognition and segmentation model is as follows: Acquire image data of the spine as a training image data set, and preprocess the training image data set; Marking the preprocessed image data, wherein the marking information includes vertebral position, vertebral sequence and vertebral angle; The labeled image data is sent to a convolutional neural network to construct the spine corner point recognition model; The standardized spine model is input into the spine corner point recognition model for training to construct the vertebral body recognition and segmentation model.

4. The method for measuring spinal parameters and assessing spinal sagittal imbalance according to claim 1, characterized in that: After the standardized image is processed by algorithm recognition, the coordinate data of several cone corner points are obtained, and the four adjacent vertebral corner points are divided into a group. The upper and lower position relationship of each vertebra can be obtained based on the coordinate data of each group, thereby determining the order of the vertebrae. At the same time, according to the order of the cones, two adjacent vertebrae are divided into a group in pairs.

5. The method for measuring spinal parameters and assessing spinal sagittal imbalance according to claim 4, characterized in that: The calculation and analysis based on the obtained coordinate information are as follows: two adjacent vertebrae are divided into a group, and the coordinate data of the corner points of the vertebrae in the same group are geometrically calculated in turn. The line segment connected by the two corner points of the lower edge of the upper vertebrae and the line segment connected by the two corner points of the upper edge of the lower vertebrae are calculated to obtain the displacement distance and rotation angle. When the displacement distance exceeds the normal range, it is considered to be a sagittal imbalance, otherwise it is normal.

6. A system for measuring spinal parameters and evaluating spinal sagittal imbalance, using the spinal parameter measurement and spinal sagittal imbalance evaluation method according to any one of claims 1 to 5, characterized in that: include: The acquisition module is configured to obtain original medical images of the spine of the target to be detected, including at least one lateral image of the spine, at least one image of the spine in hyperextension, and at least one image of the spine in hyperflexion; preprocess the original medical images of the spine to obtain standardized images; The parameter measurement module is configured to send the standardized image picture into a pre-trained spine corner point recognition model, perform recognition processing on the standardized image picture, determine the order of cones in the standardized image picture and the coordinate information of the cone corner points; then send the standardized image picture into a pre-trained vertebral body recognition and division model, and divide the cones in the standardized image picture; The spinal sagittal imbalance analysis module is configured to perform calculations and analysis based on the obtained coordinate information to obtain information on the degree of spinal sagittal imbalance, thereby comprehensively analyzing and evaluating the spine.

7. A computer device, characterized in that: It comprises a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the spinal parameter measurement and spinal sagittal imbalance assessment method as described in any one of claims 1 to 5.

8. A storage medium storing computer-readable instructions, characterized in that: When the computer-readable instructions are executed by one or more processors, the one or more processors execute the method for measuring spinal parameters and assessing spinal sagittal imbalance as described in any one of claims 1 to 5.

Images