Method, device and storage medium for analyzing intervertebral disc space of spinal vertebra

Abstract

The present application relates to a method, device, computer equipment and storage medium for analyzing the intervertebral space of a spinal vertebra. The method comprises: obtaining the spinal segmentation result of an object to be detected; the spinal segmentation result includes at least two adjacent vertebrae; extracting the segmentation result of the two adjacent vertebrae from the spinal segmentation result; calculating the distance between the upper and lower edge contour points of the two adjacent vertebrae based on the segmentation result of the two adjacent vertebrae to obtain a distance value set; obtaining the intervertebral space distance between the two adjacent vertebrae based on the distance value set; comparing the intervertebral space distance between the two adjacent vertebrae with a preset intervertebral space distance threshold, and obtaining the intervertebral space analysis result of the object to be detected based on the comparison result. The use of this method can improve the accuracy of intervertebral space detection results.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a method, device, computer equipment and storage medium for analyzing the intervertebral disc space of a spinal vertebra. Background Art

[0002] With the continuous development of society, people's physical labor has gradually decreased, while mental labor has increased. Therefore, people's corresponding sitting time at work has also greatly increased. People's spinal lesions are becoming more and more common. Therefore, it is particularly important to detect the human spine.

[0003] In the related art, when the human spine is tested, the intervertebral spaces between the vertebrae of the spine are usually measured. The measurement method is usually that the doctor conducts an overall analysis of the spinal images taken of the patient and obtains the intervertebral space test results of the patient's spine based on experience.

[0004] However, the above method has the problem that the intervertebral disc detection result obtained is inaccurate. Summary of the invention

[0005] Based on this, it is necessary to provide a method, device, computer equipment and storage medium for analyzing the intervertebral space of the spinal vertebrae that can improve the accuracy of intervertebral space detection results in response to the above technical problems.

[0006] A method for analyzing intervertebral disc space of a spinal column, the method comprising:

[0007] Acquire a spinal segmentation result of the object to be detected; the spinal segmentation result includes at least two adjacent vertebrae;

[0008] Extract segmentation results of two adjacent vertebrae from the above spine segmentation results;

[0009] According to the segmentation results of the two adjacent vertebrae, the distance between the upper and lower edge contour points of the two adjacent vertebrae is calculated to obtain a distance value set;

[0010] According to the above distance value set, the intervertebral space distance between the above two adjacent vertebrae is obtained;

[0011] The intervertebral space distance between the two adjacent vertebrae is compared with a preset intervertebral space distance threshold, and the intervertebral space analysis result of the object to be detected is obtained according to the comparison result.

[0012] In one embodiment, the spine segmentation result includes a plurality of spine sagittal images, and the step of extracting the segmentation results of two adjacent vertebrae from the spine segmentation result includes:

[0013] According to the above spinal segmentation result, a spinal target sagittal image corresponding to the spinal segmentation result is determined from a plurality of spinal sagittal images;

[0014] The segmentation results of two adjacent vertebrae are extracted from the target sagittal image of the spine.

[0015] In one embodiment, if the two adjacent vertebrae include an upper vertebrae located at the upper part and a lower vertebrae located at the lower part; the distance between the upper and lower edge contour points of the two adjacent vertebrae is calculated based on the segmentation results of the two adjacent vertebrae to obtain a distance value set, including:

[0016] According to the segmentation results of two adjacent vertebrae, the distance images of the two adjacent vertebrae are calculated; wherein each value on the distance image of one vertebrae is used to represent the shortest distance value from each point on the vertebrae to another vertebrae;

[0017] Perform edge extraction on the segmentation results of two adjacent vertebrae to obtain the contour points of the lower edge of the upper vertebrae and the contour points of the upper edge of the lower vertebrae;

[0018] According to the positions of the contour points of the lower edge and the positions of the contour points of the upper edge, a first set of distance values ​​corresponding to the contour points of the lower edge is determined from the distance image of the upper vertebra, and a second set of distance values ​​corresponding to the contour points of the upper edge is determined from the distance image of the lower vertebra.

[0019] In one embodiment, the edge extraction of the segmentation results of two adjacent vertebrae to obtain the contour points of the lower edge of the upper vertebrae and the contour points of the upper edge of the lower vertebrae includes:

[0020] Perform edge extraction on the segmentation results of two adjacent vertebrae to obtain the contour point sets of the upper vertebrae and the lower vertebrae;

[0021] Perform corner point detection on the segmentation results of two adjacent vertebrae to obtain the corner points of the upper vertebrae and the lower vertebrae respectively;

[0022] According to the coordinates of the corner points of the upper vertebra, the contour points of the lower edge of the upper vertebra are determined from the contour point set of the upper vertebra; and according to the coordinates of the corner points of the lower vertebra, the contour points of the upper edge of the lower vertebra are determined from the contour point set of the lower vertebra.

[0023] In one embodiment, obtaining the intervertebral space distance between two adjacent vertebrae according to the distance value set includes:

[0024] Acquire a first maximum distance value from a first distance value set corresponding to the upper vertebral body, and acquire a second maximum distance value from a second distance value set corresponding to the lower vertebral body;

[0025] The first maximum distance value and the second maximum distance value are processed by average calculation to obtain the intervertebral space distance between two adjacent vertebral bodies.

[0026] In one embodiment, comparing the intervertebral disc distance between two adjacent vertebrae with a preset intervertebral disc distance threshold comprises:

[0027] Obtain the size of the spine of the object to be detected;

[0028] The intervertebral disc distance between two adjacent vertebrae is ratioed to the size of the spine, and the obtained ratio is compared with a preset intervertebral disc distance threshold.

[0029] In one embodiment, the intervertebral disc analysis result of the object to be detected obtained according to the comparison result includes:

[0030] If the above ratio is greater than a preset intervertebral space distance threshold, it is determined that the intervertebral space between two adjacent vertebrae is narrow.

[0031] In one embodiment, the method of determining a target spinal sagittal image corresponding to the spinal segmentation result from a plurality of spinal sagittal images according to the spinal segmentation result includes:

[0032] According to the spine segmentation results, the centroid coordinates of two adjacent vertebrae are calculated;

[0033] The centroid coordinates of two adjacent vertebrae are processed by mean calculation, and the spinal sagittal image where the obtained mean coordinates are located is determined as the spinal target sagittal image.

[0034] A device for analyzing intervertebral disc space of a spinal column, the device comprising:

[0035] An acquisition module, used for acquiring a spinal segmentation result of the object to be detected; the spinal segmentation result includes at least two adjacent vertebrae;

[0036] An extraction module, used for extracting segmentation results of two adjacent vertebrae from the above spinal column segmentation results;

[0037] A vertebra distance calculation module, used to calculate the distance between the upper and lower edge contour points of the two adjacent vertebrae according to the segmentation results of the two adjacent vertebrae, to obtain a distance value set;

[0038] A module for determining intervertebral space distance, used for obtaining the intervertebral space distance between the two adjacent vertebrae according to the distance value set;

[0039] The analysis module is used to compare the intervertebral space distance between the two adjacent vertebrae with a preset intervertebral space distance threshold, and obtain an intervertebral space analysis result of the object to be detected according to the comparison result.

[0040] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0041] Acquire a spinal segmentation result of the object to be detected; the spinal segmentation result includes at least two adjacent vertebrae;

[0042] Extract segmentation results of two adjacent vertebrae from the above spine segmentation results;

[0043] According to the segmentation results of the two adjacent vertebrae, the distance between the upper and lower edge contour points of the two adjacent vertebrae is calculated to obtain a distance value set;

[0044] According to the above distance value set, the intervertebral space distance between the above two adjacent vertebrae is obtained;

[0045] The intervertebral space distance between the two adjacent vertebrae is compared with a preset intervertebral space distance threshold, and the intervertebral space analysis result of the object to be detected is obtained according to the comparison result.

[0046] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0047] Acquire a spinal segmentation result of the object to be detected; the spinal segmentation result includes at least two adjacent vertebrae;

[0048] Extract segmentation results of two adjacent vertebrae from the above spine segmentation results;

[0049] According to the segmentation results of the two adjacent vertebrae, the distance between the upper and lower edge contour points of the two adjacent vertebrae is calculated to obtain a distance value set;

[0050] According to the above distance value set, the intervertebral space distance between the above two adjacent vertebrae is obtained;

[0051] The intervertebral space distance between the two adjacent vertebrae is compared with a preset intervertebral space distance threshold, and the intervertebral space analysis result of the object to be detected is obtained according to the comparison result.

[0052] The above-mentioned spinal vertebral intervertebral space analysis method, device, computer equipment and storage medium obtain the spinal segmentation result of at least two adjacent vertebrae of the object to be detected, calculate the distance between the upper and lower edge contours of the two adjacent vertebrae according to the segmentation results of the two adjacent vertebrae, obtain the intervertebral space distance between the two adjacent vertebrae, and compare the intervertebral space distance with the intervertebral space distance threshold to obtain the intervertebral space analysis result of the object to be detected. In this method, since the distance between the upper and lower edge contour points of the two adjacent vertebrae can be calculated through the spinal segmentation results of the two adjacent vertebrae, and then the intervertebral space distance between the two vertebrae is obtained, it is not necessary for the doctor to obtain the intervertebral space distance based on experience or measurement. Therefore, this method can save manpower and time, and the intervertebral space distance obtained is also relatively accurate. Further, since the intervertebral space distance can be used to determine the intervertebral space analysis result, and the doctor does not need to obtain the analysis result based on experience, therefore, the intervertebral space analysis result obtained by using this method is also relatively accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 is an internal structure diagram of a computer device in one embodiment;

[0054] Figure 2 A schematic diagram of a flow chart of a method for analyzing intervertebral disc spaces of a spinal vertebra in one embodiment;

[0055] Figure 3 A schematic flow chart of the intervertebral disc space analysis step of a spinal vertebra in another embodiment;

[0056] Figure 4 A schematic flow chart of a method for analyzing intervertebral disc space of a spinal vertebra in another embodiment;

[0057] Figure 4a This is an example diagram of extracting the edge of a vertebra to obtain corner points of the vertebra in another embodiment;

[0058] Figure 5 A schematic flow chart of a method for analyzing intervertebral disc space of a spinal vertebra in another embodiment;

[0059] Figure 6 It is a structural block diagram of a device for analyzing the intervertebral disc space of a spinal vertebra in one embodiment. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0061] At present, when testing the human spine, the intervertebral spaces between the vertebrae of the spine are usually measured. The measurement method is usually that the doctor analyzes the spine images taken by the patient as a whole and obtains the intervertebral space detection results of the patient's spine based on experience. However, the above method is labor-intensive and the intervertebral space detection results obtained are not very accurate. Therefore, the present application provides an intervertebral space analysis method, device, computer equipment and storage medium for the vertebral body of the spine, which can solve the above technical problems.

[0062] The intervertebral disc analysis method provided in the present application can be applied to a scanning system, which can be composed of a scanning device and a computer device connected to each other. The scanning device user scans the object to be detected and sends the obtained scanning data to the computer device for processing. The computer device can be a terminal or a server. Taking the computer device as a terminal as an example, its internal structure diagram can be as follows: Figure 1 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for analyzing the intervertebral space of a spinal vertebra is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0063] Those skilled in the art will understand that Figure 1 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0064] It should be noted that the execution subject of the embodiments of the present application can be a scanning system, or a computer device, and of course it can also be a spinal vertebral intervertebral space analysis device. The following method of the following embodiments of the present application will be described using a computer device as the execution subject.

[0065] In one embodiment, a method for analyzing the intervertebral disc space of a spinal vertebra is provided. This embodiment relates to a specific process of obtaining the intervertebral disc distance between two adjacent vertebrae through the spinal segmentation result of the object to be detected, and then obtaining the intervertebral disc space analysis result of the object to be detected. Figure 2 As shown, the method may include the following steps:

[0066] S202, obtaining a spinal segmentation result of the object to be detected; the spinal segmentation result includes at least two adjacent vertebrae.

[0067] The object to be detected may be a living human or animal body, or a dead human or animal body.

[0068] In addition, the spinal segmentation result here can be obtained by segmenting the original spinal image using a multi-label segmentation model. When training the multi-label segmentation model, it can be obtained by training based on multiple sample spinal images and multiple labels corresponding to each sample spinal image. The multiple labels here refer to setting different labels for different sections on the spine. For example, the vertebrae on the spine can be divided into four sections, namely C1~C7, T1~T12, L1~L5, S1~S9, where C represents the cervical spine, T represents the thoracic spine, L represents the lumbar spine, and S represents the sacral spine. Each label can include the location information of points on different sections. At the same time, when training the multi-label segmentation model, all labels can be selected to be added to the training, or specific sections (such as 12 labels of T1~T12) can be selected, depending on the specific application.

[0069] The specific training process may include: 1) generating a training data set: annotating the images containing the spine with multiple labels by manual annotation, that is, each vertebra has a corresponding annotation value, such as 2 for the cervical vertebra C2, 3 for the cervical vertebra C3, and 8 for the thoracic vertebra T1 (the cervical spine has a total of 7 vertebrae), and pairing the original spine image with the annotation result to form a training data set; 2) constructing a multi-label segmentation model: the input of the model is the original spine image in the above training data set, and the output is a multi-channel segmentation result, where the number of channels depends on the number of labels; 3) training a multi-label image segmentation model: using the training set obtained in step 1) to train the segmentation model constructed in step 2), adjusting and setting the network hyperparameters as needed to achieve the best image segmentation effect and saving the trained network model.

[0070] After obtaining the multi-label segmentation model, the original spinal image of the object to be detected can be input into the trained multi-label segmentation model to obtain the corresponding spinal segmentation result. The spinal segmentation result may include vertebrae in different segments, or may only include vertebrae in one segment, which is the same as the segment label used in model training. For example, the labels on the samples used in training are T1-T12 and C1-C7, then the spinal segmentation result includes the vertebrae of T1-T12 and C1-C7. That is to say, at least two vertebrae included in the spinal segmentation result here may be vertebrae belonging to the same segment, or may be vertebrae belonging to different segments. In addition, the original spinal image may be an image obtained by scanning the object to be detected, or may be an image pre-stored in a database or cloud, etc. Of course, the spinal segmentation result here may also be pre-segmented and stored in a database or cloud, etc., and read by a computer device when needed. The original spinal image and spinal segmentation result here may be CT images, MR images, X-ray images, etc.

[0071] Since the spine segmentation results obtained by the multi-label segmentation model mentioned above may be under-segmented or over-segmented, resulting in inaccurate segmentation results, after obtaining the spine segmentation results mentioned above, the image segmentation (Graph Cut) algorithm, deep learning related algorithms, etc. can be used to optimize the spine segmentation results obtained by the multi-label segmentation model to eliminate edge burrs. The parameters of these algorithms can be adjusted according to actual conditions.

[0072] S204, extracting segmentation results of two adjacent vertebrae from the above spine segmentation results.

[0073] Specifically, after obtaining the spinal segmentation result as described above, the position information of the vertebrae included in the spinal segmentation result can also be obtained. Usually, the spinal segmentation result generally includes two or more adjacent vertebrae. Then, the spinal segmentation result where each vertebrae is located can be extracted from the spinal segmentation result through the position information of each vertebrae, and the spinal segmentation result of two adjacent vertebrae can be obtained. The position information of each vertebrae here can be the position information of each point on each vertebrae.

[0074] S206: Calculate the distance between the upper and lower edge contour points of the two adjacent vertebrae according to the segmentation results of the two adjacent vertebrae to obtain a distance value set.

[0075] In this step, after obtaining the spinal column segmentation results of two adjacent vertebrae, the position information of the contour points of the two adjacent vertebrae can also be obtained, wherein the contour points of each vertebrae include an upper edge contour point and a lower edge contour point.

[0076] Then, after obtaining the upper edge contour point and the lower edge contour point of each vertebra, the distance between the upper and lower edges of the two adjacent vertebrae can be directly calculated by the positions of the upper and lower edge contour points of the two adjacent vertebrae. For example, the distance can be calculated between the two upper edge contour points, or between the two lower edge contour points, or between a lower edge contour point and an upper edge contour point. In short, the distance between the upper and lower edge contour points of the two adjacent vertebrae can be calculated to obtain multiple distance values, which are combined to obtain a distance value set.

[0077] Of course, the distance field correlation algorithm can also be used to calculate the distance images of two adjacent vertebrae. The value of each point on the distance images of the two vertebrae represents the shortest distance from the point to the other vertebrae. After obtaining the upper edge contour point and the lower edge contour point of each vertebrae, the shortest distance between the upper and lower edge contour points of the two vertebrae can be obtained from the distance images of the two vertebrae, that is, multiple distance values ​​can be obtained. These multiple distance values ​​are the distances between the upper and lower edge contour points of the two vertebrae. These multiple distance values ​​are combined to obtain a distance value set.

[0078] Of course, the distance between the upper and lower edge contour points of two adjacent vertebral bodies may also be obtained in other ways, which is not specifically limited in this embodiment.

[0079] S208: Obtain the intervertebral space distance between the two adjacent vertebral bodies according to the distance value set.

[0080] In this step, after obtaining the distance value set between the upper and lower edge contour points of two adjacent vertebrae, all distances in the distance value set may be averaged, and the obtained average value may be used as the intervertebral space distance between the two adjacent vertebrae.

[0081] Of course, a maximum distance value may also be selected from the above distance value set, and the maximum distance value may be used as the intervertebral space distance between the two adjacent vertebral bodies.

[0082] Of course, the distance value set may also include the distance value sets of two adjacent vertebrae (representing the distance between the contour point of one cone and the contour point of another vertebra). Then, a maximum distance value may be selected from the distance value sets of the two vertebrae respectively, and the two maximum distance values ​​may be averaged. The average value obtained here may also be used as the intervertebral distance between the two adjacent vertebrae.

[0083] Of course, other calculation methods are also possible, and this embodiment does not specifically limit this.

[0084] S210, comparing the intervertebral disc distance between the two adjacent vertebrae with a preset intervertebral disc distance threshold, and obtaining an intervertebral disc analysis result of the object to be detected according to the comparison result.

[0085] The preset intervertebral disc distance threshold here can be set according to actual conditions, for example, 3 mm, 5 mm, etc. The intervertebral disc distance threshold here can be a distance threshold determined according to parameters such as age, height, etc. of different individuals, and of course, it can also be a distance threshold directly determined regardless of individuals, and of course, it can also be determined in other ways.

[0086] In this step, the method for obtaining the preset intervertebral space distance threshold may include: 1) obtaining a historical case database, which includes spinal images and image analysis reports of each historical object, wherein the image analysis report of each historical object contains the intervertebral space analysis result corresponding to the historical object (which can be obtained by extracting the image report through semantic analysis and other technologies); 2) performing the above-mentioned spinal segmentation and intervertebral space distance calculation process on the spinal image of each historical object to obtain the intervertebral space distance between any two adjacent vertebrae of each historical object; 3) by correlating the intervertebral space distance of each historical object with the corresponding intervertebral space analysis result, the preset intervertebral space distance threshold can be obtained.

[0087] Specifically, after obtaining the intervertebral space distance between two adjacent vertebrae, the intervertebral space distance can be compared with the intervertebral space distance threshold to obtain a comparison result, for example, the intervertebral space distance is greater than the intervertebral space distance threshold or the intervertebral space distance is not greater than the intervertebral space distance threshold, etc. Then, the intervertebral space of the object to be detected can be analyzed based on the comparison result to obtain an analysis result.

[0088] According to the method of this embodiment, the intervertebral disc distance between any two adjacent vertebrae can be calculated and the intervertebral disc analysis result between any two adjacent vertebrae can be obtained accordingly.

[0089] In the above-mentioned intervertebral disc analysis method of the spinal vertebra, by obtaining the spinal segmentation result of at least two adjacent vertebrae of the object to be detected, the distance between the upper and lower edge contours of the two adjacent vertebrae is calculated according to the segmentation result of the two adjacent vertebrae, the intervertebral disc distance between the two adjacent vertebrae is obtained, and the intervertebral disc distance and the intervertebral disc distance threshold are compared to obtain the intervertebral disc analysis result of the object to be detected. In this method, since the distance between the upper and lower edge contour points of the two adjacent vertebrae can be calculated by the spinal segmentation results of the two adjacent vertebrae, and then the intervertebral disc distance between the two vertebrae is obtained, it is not necessary for the doctor to obtain the intervertebral disc distance based on experience or measurement, so the method can save manpower and time, and the intervertebral disc distance obtained is also more accurate. Further, since the intervertebral disc distance can be used to determine the intervertebral disc analysis result, and the doctor does not need to obtain the analysis result based on experience, the intervertebral disc analysis result obtained by the method is also more accurate.

[0090] In another embodiment, another method for analyzing the intervertebral disc of a spinal vertebra is provided. This embodiment relates to the specific process of extracting the segmentation results of two adjacent vertebrae from the multiple spinal sagittal images when the spinal segmentation results include multiple spinal sagittal images. Figure 3 As shown, the above S204 may include the following steps:

[0091] S302: According to the above spinal column segmentation result, a spinal column target sagittal image corresponding to the spinal column segmentation result is determined from a plurality of spinal column sagittal images.

[0092] In this embodiment, the spinal segmentation result includes multiple spinal sagittal images, i.e., spinal images in the sagittal plane. The spinal target sagittal image may be a spinal mid-sagittal image, which is one of the multiple spinal sagittal images. In general, in order to reduce the complexity of the calculation process and the amount of calculation, the vertebral segmentation result can usually be obtained on the spinal mid-sagittal image, and the subsequent intervertebral distance calculation can be performed.

[0093] Then we need to first obtain the mid-sagittal image of the spine. When obtaining it, we can optionally calculate the centroid coordinates of two adjacent vertebrae based on the spine segmentation result; perform mean operation on the centroid coordinates of the two adjacent vertebrae, and determine the sagittal image of the spine where the mean coordinates are obtained as the target sagittal image of the spine.

[0094] That is to say, after obtaining the spinal segmentation result, which includes the position coordinates of each point on the adjacent vertebrae, the center of gravity of each vertebrae can be calculated through the position coordinates of each point on each vertebrae to obtain the center of gravity coordinates of each vertebrae, and the center of gravity coordinates of each adjacent vertebrae can be obtained. Then, the center of gravity coordinates of the two adjacent vertebrae are directly averaged or weighted averaged to obtain a mean coordinate, and the spinal sagittal image where the mean coordinate is located is used as the spinal mid-sagittal image, that is, the spinal target sagittal image.

[0095] Of course, the centroid coordinates, center point coordinates, etc. of two adjacent vertebrae may also be calculated, and the target sagittal image of the spine may be determined by taking the average of the centroid coordinates, center point coordinates, etc. of two adjacent vertebrae.

[0096] S304, extracting segmentation results of two adjacent vertebrae from the target spinal column sagittal image.

[0097] Specifically, after determining a spinal target sagittal image from a plurality of spinal sagittal images, which generally can be a two-dimensional image, two adjacent vertebrae can be extracted from the spinal target sagittal image, i.e., the segmentation result of the two adjacent vertebrae can be obtained.

[0098] In this embodiment, based on the spinal segmentation results, a target spinal sagittal image can be determined from multiple spinal sagittal images, and the segmentation results of two adjacent vertebrae can be extracted from the target spinal sagittal image for subsequent intervertebral space distance calculation. In this way, it is not necessary to use all spinal sagittal images to calculate the intervertebral space distance, and the amount of calculation is small, so the time for intervertebral space distance calculation can be saved, thereby improving the efficiency of intervertebral space analysis of spinal vertebrae.

[0099] In another embodiment, another method for analyzing the intervertebral space of a spinal vertebra is provided. The above mentioned calculation of the distance between the upper and lower edge contour points of two adjacent vertebrae, if the two adjacent vertebrae include an upper vertebrae located in the upper part and a lower vertebrae located in the lower part, then how to calculate the specific process of the distance between the upper vertebrae and the lower vertebrae. Based on the above embodiment, Figure 4 As shown, the above S206 may include the following steps:

[0100] S402, calculating the distance images of the two adjacent vertebrae according to the segmentation results of the two adjacent vertebrae; wherein each value on the distance image of a vertebrae is used to represent the shortest distance value from each point on the vertebrae to another vertebrae.

[0101] In this step, a distance field correlation algorithm may be used to calculate the distance images of the upper vertebra and the lower vertebra. The value of each point on the distance images of the two vertebrae represents the shortest distance from the point to the other vertebra.

[0102] The specific calculation process is as follows: the shortest distance value from each point on the upper vertebra to the lower vertebra can be calculated, and the shortest distance value of each point on the upper vertebra is used as the value of the point. All points on the upper vertebra are calculated in this way to obtain the shortest distance value of each point, that is, to obtain the distance image corresponding to the upper vertebra. Of course, in this way, the shortest distance value from each point on the lower vertebra to the upper vertebra can also be calculated to obtain the distance image corresponding to the lower vertebra.

[0103] S404: performing edge extraction on the segmentation results of two adjacent vertebrae to obtain contour points of the lower edge of the upper vertebrae and contour points of the upper edge of the lower vertebrae.

[0104] In this step, when calculating the contour points of the upper and lower vertebrae, optionally, edge extraction can be performed on the segmentation results of the two adjacent vertebrae to obtain respective contour point sets of the upper vertebrae and the lower vertebrae; corner point detection can be performed on the segmentation results of the two adjacent vertebrae to obtain respective corner points of the upper vertebrae and the lower vertebrae; the contour points of the lower edge of the upper vertebrae are determined from the contour point set of the upper vertebrae based on the coordinates of the corner points of the upper vertebrae; and the contour points of the upper edge of the lower vertebrae are determined from the contour point set of the lower vertebrae based on the coordinates of the corner points of the lower vertebrae.

[0105] For details, see Figure 4a As shown, edge extraction-related algorithms can be used to extract edges from the segmentation results of the upper vertebra and the lower vertebra. The edge extraction-related algorithms can be edge algorithms of the Sobel operator, Canny algorithms, etc. Through edge extraction, the contour points of the upper vertebra and the contour points of the lower vertebra can be obtained. The contour points of the upper vertebra and the contour points of the lower vertebra can be combined to obtain the contour point set of the upper vertebra and the contour point set of the lower vertebra. Then, the coordinates of the corner points on the circumscribed rectangular box of each vertebra can be obtained by calculating the circumscribed rectangular box of each vertebra (for example, Figure 4a Then, for the upper cone, the coordinates of the four corner points on the rectangular box of the upper vertebra can be compared with the coordinates of each contour point on the upper vertebra to obtain the coordinates of the four contour points closest to the four corner points. The coordinates of these four contour points are the coordinates of the four corner points of the upper vertebra.

[0106] Afterwards, the coordinates of the two corner points located at the lower edge of the upper vertebra can be obtained from the coordinates of the four corner points of the upper vertebra. Then, from the contour point set corresponding to the upper vertebra, the contour points between the coordinates of the two corner points located at the lower edge of the upper vertebra are obtained, and these contour points are the contour points of the lower edge of the upper vertebra.

[0107] Similarly, the contour points of the upper edge of the lower vertebral body can also be obtained from the contour point set of the lower vertebral body in this way.

[0108] S406, according to the positions of the contour points of the lower edge and the positions of the contour points of the upper edge, determine a first distance value set corresponding to the contour points of the lower edge from the distance image of the upper vertebra, and determine a second distance value set corresponding to the contour points of the upper edge from the distance image of the lower vertebra.

[0109] In this step, after determining the contour points of the lower edge of the upper vertebra, the distance values ​​at the positions of these contour points can be found from the distance image of the upper vertebra according to the positions of the contour points of the lower edge of the upper vertebra, that is, multiple distance values ​​are obtained, all of which are recorded as the first distance values, and the combination is the first distance value set.

[0110] Similarly, after determining the contour points of the upper edge of the lower vertebra, the distance values ​​at the positions of the contour points on the upper edge of the lower vertebra can be found from the distance image of the lower vertebra according to the positions of the contour points on the upper edge of the lower vertebra, that is, multiple distance values ​​are obtained, all of which are recorded as second distance values, and the combination is a second distance value set.

[0111] Accordingly, after obtaining the first distance value set and the second distance value set, the intervertebral space distance between the upper vertebral body and the lower vertebral body can be calculated accordingly. That is, optionally, the above S208 may include the following steps:

[0112] A first maximum distance value is obtained from a first distance value set corresponding to the upper vertebral body, and a second maximum distance value is obtained from a second distance value set corresponding to the lower vertebral body; the first maximum distance value and the second maximum distance value are averaged to obtain the intervertebral space distance between two adjacent vertebral bodies.

[0113] Specifically, the maximum first distance value can be obtained from the first distance value set, the maximum second distance value can be obtained from the second distance value set, and the maximum first distance value and the maximum second distance value can be averaged, and the average value obtained can be used as the intervertebral disc distance between the two vertebrae. In this way, the process of calculating the intervertebral disc distance is relatively simple, the calculated intervertebral disc distance is also more representative, and relatively more accurate.

[0114] In this embodiment, the respective distance images can be calculated based on the segmentation results of the two adjacent vertebrae, and the lower edge contour points of the upper vertebrae and the upper edge contour points of the lower vertebrae can be obtained by edge extraction of the segmentation results, and the distance value set can be obtained through the respective distance images and contour points of the two vertebrae. Here, the distance values ​​corresponding to the respective edge contour points are obtained through the distance images of the two vertebrae, and the calculation method is refined, which can facilitate the calculation of the distance values ​​of the respective contour points of the two vertebrae, ensuring the feasibility of the calculation process; at the same time, the calculated distance values ​​of the two adjacent vertebrae are also relatively accurate, so that the intervertebral distance between the vertebrae calculated by the distance value later is also relatively accurate.

[0115] In another embodiment, another method for analyzing the intervertebral space of a spinal vertebra is provided. This embodiment relates to a specific process of comparing the intervertebral space distance of two vertebrae with the intervertebral space threshold and obtaining the intervertebral space analysis result according to the comparison result. Figure 5 As shown, the comparison of the intervertebral space distance between the two adjacent vertebral bodies with a preset intervertebral space distance threshold in S210 may include the following steps:

[0116] S502, obtaining the size of the spine of the object to be detected.

[0117] In this step, the spinal size of the object to be tested can be the size of the entire spine or the size of a section of the spine. For example, if the intervertebral disc analysis is of the cervical segment, then the spinal size here can be the size of the cervical segment of the object to be tested.

[0118] S504: Ratio the intervertebral space distance between two adjacent vertebrae to the size of the spine, and compare the obtained ratio with a preset intervertebral space distance threshold.

[0119] In this step, the intervertebral disc distance threshold calculated in S210 and the spinal column size of the corresponding historical object may be ratioed, and the obtained ratio is used as the intervertebral disc distance threshold preset here.

[0120] Afterwards, the intervertebral disc distance of the object to be detected can be ratioed with the corresponding spinal column size to obtain the ratio of the object to be detected, and then the ratio of the object to be detected can be compared with the intervertebral disc distance threshold here to obtain a comparison result.

[0121] After the comparison result is obtained, the intervertebral space can be analyzed accordingly. Optionally, obtaining the intervertebral space analysis result of the object to be detected according to the comparison result in S210 may include the following steps S506:

[0122] S506: If the ratio is greater than a preset intervertebral space distance threshold, it is determined that the intervertebral space between two adjacent vertebrae is narrow.

[0123] That is to say, if the comparison result shows that the ratio of the object to be detected is greater than the intervertebral space distance threshold, then it can be considered that the intervertebral space of the two adjacent vertebrae of the object to be detected is narrow. If the comparison result shows that the ratio of the object to be detected is not greater than the intervertebral space distance threshold, then it can be considered that the intervertebral space of the two adjacent vertebrae of the object to be detected is not narrow.

[0124] In this embodiment, the spinal column size of the subject to be detected and the calculated intervertebral disc distance can be ratioed, and the ratio can be compared with the intervertebral disc distance threshold. If the ratio is greater than the preset intervertebral disc distance threshold, the intervertebral disc between two adjacent vertebrae is determined to be narrow. In this way, the difference in spinal column sizes of different individuals can be comprehensively considered, and the intervertebral disc comparison error caused by the difference in spinal column sizes of different individuals can be avoided, so that the intervertebral disc analysis result of the subject to be detected obtained by comparing the results is more in line with the actual situation and more accurate.

[0125] In order to explain the technical solution of the present application in more detail, the technical solution of the present application is explained in detail below in conjunction with a more specific embodiment. The method may include the following steps:

[0126] S1, obtaining a spinal segmentation result of a subject to be detected; the spinal segmentation result includes at least two adjacent vertebrae.

[0127] S2: Calculate the centroid coordinates of two adjacent vertebrae based on the spine segmentation results.

[0128] S3, performing mean calculation processing on the centroid coordinates of two adjacent vertebrae, and determining the spinal sagittal image where the obtained mean coordinates are located as the spinal target sagittal image.

[0129] S4, calculating the distance images of the two adjacent vertebrae according to the segmentation results of the two adjacent vertebrae; wherein each value on the distance image of a vertebrae is used to represent the shortest distance value from each point on the vertebrae to another vertebrae.

[0130] S5, performing edge extraction on the segmentation results of two adjacent vertebrae to obtain respective contour point sets of the upper vertebrae and the lower vertebrae.

[0131] S6, performing corner point detection on the segmentation results of two adjacent vertebrae to obtain respective corner points of the upper vertebrae and the lower vertebrae.

[0132] S7, determining the contour points of the lower edge of the upper vertebra from the contour point set of the upper vertebra according to the coordinates of the corner points of the upper vertebra; and determining the contour points of the upper edge of the lower vertebra from the contour point set of the lower vertebra according to the coordinates of the corner points of the lower vertebra.

[0133] S8, according to the positions of the contour points of the lower edge and the positions of the contour points of the upper edge, determine a first set of distance values ​​corresponding to the contour points of the lower edge from the distance image of the upper vertebra, and determine a second set of distance values ​​corresponding to the contour points of the upper edge from the distance image of the lower vertebra.

[0134] S9, obtaining a first maximum distance value from a first distance value set corresponding to the upper vertebral body, and obtaining a second maximum distance value from a second distance value set corresponding to the lower vertebral body.

[0135] S10, performing mean operation processing on the first maximum distance value and the second maximum distance value to obtain the intervertebral space distance between two adjacent vertebral bodies.

[0136] S11, obtaining the size of the spine of the object to be detected, making a ratio between the intervertebral space distance between two adjacent vertebrae and the size of the spine, and comparing the obtained ratio with a preset intervertebral space distance threshold.

[0137] S12: If the ratio is greater than a preset intervertebral space distance threshold, it is determined that the intervertebral space between two adjacent vertebrae is narrow.

[0138] It should be understood that although Figure 2-5 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2-5 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0139] In one embodiment, Figure 6 As shown, a device for analyzing the intervertebral space of a spinal vertebra is provided, comprising: an acquisition module 10, an extraction module 11, a vertebral distance calculation module 12, an intervertebral space distance determination module 13 and an analysis module 14, wherein:

[0140] An acquisition module 10 is used to acquire a spinal segmentation result of the object to be detected; the spinal segmentation result includes at least two adjacent vertebrae;

[0141] An extraction module 11 is used to extract segmentation results of two adjacent vertebrae from the above spine segmentation results;

[0142] A vertebra distance calculation module 12 is used to calculate the distance between the upper and lower edge contour points of the two adjacent vertebrae according to the segmentation results of the two adjacent vertebrae to obtain a distance value set;

[0143] The intervertebral space distance determination module 13 is used to obtain the intervertebral space distance between the two adjacent vertebrae according to the distance value set;

[0144] The analysis module 14 is used to compare the intervertebral disc distance between the two adjacent vertebrae with a preset intervertebral disc distance threshold, and obtain an intervertebral disc analysis result of the object to be detected according to the comparison result.

[0145] The specific definition of the intervertebral disc analysis device for the spinal vertebrae can be found in the above-mentioned definition of the intervertebral disc analysis method for the spinal vertebrae, which will not be repeated here.

[0146] In another embodiment, another spinal vertebral intervertebral space analysis device is provided. Based on the above embodiment, the spinal segmentation result includes a plurality of spinal sagittal images, and the extraction module 11 may include a target sagittal determination unit and an extraction unit, wherein:

[0147] A target sagittal determination unit is used to determine a target sagittal image of the spine corresponding to the spine segmentation result from a plurality of spine sagittal images according to the spine segmentation result;

[0148] The extraction unit is used to extract the segmentation results of two adjacent vertebrae from the target sagittal image of the spine.

[0149] Optionally, the target sagittal position determination unit may include a barycenter coordinate calculation subunit and a target sagittal position determination subunit, wherein:

[0150] A barycentric coordinate calculation subunit is used to calculate the barycentric coordinates of two adjacent vertebrae according to the spine segmentation result;

[0151] The target sagittal position determination subunit is used to perform mean calculation processing on the centroid coordinates of two adjacent vertebrae, and determine the spinal sagittal position image where the obtained mean coordinates are located as the spinal target sagittal position image.

[0152] In another embodiment, another spinal vertebral intervertebral space analysis device is provided. Based on the above embodiment, when the two adjacent vertebrae include an upper vertebrae located at the upper part and a lower vertebrae located at the lower part, the vertebrae distance calculation module 12 may include a vertebrae distance image calculation unit, an edge extraction unit and a distance value set determination unit, wherein:

[0153] A vertebral distance image calculation unit is used to calculate the distance images of two adjacent vertebrae according to the segmentation results of the two adjacent vertebrae; wherein each value on the distance image of a vertebrae is used to represent the shortest distance value from each point on the vertebrae to another vertebrae;

[0154] An edge extraction unit is used to extract edges from the segmentation results of two adjacent vertebrae to obtain contour points of the lower edge of the upper vertebrae and contour points of the upper edge of the lower vertebrae;

[0155] A distance value set determination unit is used to determine a first distance value set corresponding to the contour points of the lower edge from the distance image of the upper vertebra according to the positions of the contour points of the lower edge and the positions of the contour points of the upper edge, and to determine a second distance value set corresponding to the contour points of the upper edge from the distance image of the lower vertebra.

[0156] Optionally, the edge extraction unit may include an edge extraction subunit, a corner point detection subunit and a contour point determination subunit, wherein:

[0157] The edge extraction subunit is used to extract the edges of the segmentation results of two adjacent vertebrae to obtain the contour point sets of the upper vertebrae and the lower vertebrae respectively;

[0158] A corner point detection subunit is used to perform corner point detection on the segmentation results of two adjacent vertebrae to obtain the corner points of the upper vertebrae and the lower vertebrae respectively;

[0159] The contour point determination subunit is used to determine the contour points of the lower edge of the upper vertebra from the contour point set of the upper vertebra according to the coordinates of the corner points of the upper vertebra; and to determine the contour points of the upper edge of the lower vertebra from the contour point set of the lower vertebra according to the coordinates of the corner points of the lower vertebra.

[0160] Optionally, the intervertebral space distance determination module 13 may include a maximum value acquisition unit and an intervertebral space distance calculation unit, wherein:

[0161] a maximum value acquisition unit, configured to acquire a first maximum distance value from a first distance value set corresponding to the upper vertebral body, and to acquire a second maximum distance value from a second distance value set corresponding to the lower vertebral body;

[0162] The intervertebral space distance calculation unit is used to perform mean operation processing on the first maximum distance value and the second maximum distance value to obtain the intervertebral space distance between two adjacent vertebrae.

[0163] In another embodiment, another device for analyzing the intervertebral disc space of a spinal vertebra is provided. Based on the above embodiment, the analysis module 14 may include: a spinal dimension acquisition unit and a comparison unit, wherein:

[0164] A spine size acquisition unit, used to acquire the spine size of the object to be detected;

[0165] The comparison unit is used to make a ratio between the intervertebral space distance between two adjacent vertebrae and the size of the spine, and compare the obtained ratio with a preset intervertebral space distance threshold.

[0166] Optionally, the analysis module 14 may include an analysis result determination unit, which is used to determine that the intervertebral space between two adjacent vertebrae is narrow when the ratio is greater than a preset intervertebral space distance threshold.

[0167] The specific definition of the intervertebral space analysis device of the spinal vertebrae can be found in the definition of the intervertebral space analysis method of the spinal vertebrae mentioned above, which will not be repeated here. Each module in the above-mentioned intervertebral space analysis device of the spinal vertebrae can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

[0168] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0169] Acquire a spinal segmentation result of the object to be detected; the spinal segmentation result includes at least two adjacent vertebrae;

[0170] Extract segmentation results of two adjacent vertebrae from the above spine segmentation results;

[0171] According to the segmentation results of the two adjacent vertebrae, the distance between the upper and lower edge contour points of the two adjacent vertebrae is calculated to obtain a distance value set;

[0172] According to the above distance value set, the intervertebral space distance between the above two adjacent vertebrae is obtained;

[0173] The intervertebral space distance between the two adjacent vertebrae is compared with a preset intervertebral space distance threshold, and the intervertebral space analysis result of the object to be detected is obtained according to the comparison result.

[0174] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0175] According to the above spinal segmentation results, a spinal target sagittal image corresponding to the spinal segmentation result is determined from a plurality of spinal sagittal images; and segmentation results of two adjacent vertebrae are extracted from the spinal target sagittal image.

[0176] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0177] According to the segmentation results of two adjacent vertebrae, the distance images of the two adjacent vertebrae are calculated; wherein each value on the distance image of one vertebra is used to characterize the shortest distance value from each point on the vertebra to another vertebra; the segmentation results of the two adjacent vertebrae are subjected to edge extraction to obtain the contour points of the lower edge of the upper vertebra and the contour points of the upper edge of the lower vertebra; according to the positions of the contour points of the lower edge and the positions of the contour points of the upper edge, a first distance value set corresponding to the contour points of the lower edge is determined from the distance image of the upper vertebra, and a second distance value set corresponding to the contour points of the upper edge is determined from the distance image of the lower vertebra.

[0178] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0179] Perform edge extraction on the segmentation results of two adjacent vertebrae to obtain respective contour point sets of the upper vertebrae and the lower vertebrae; perform corner point detection on the segmentation results of two adjacent vertebrae to obtain respective corner points of the upper vertebrae and the lower vertebrae; determine the contour points of the lower edge of the upper vertebrae from the contour point set of the upper vertebrae based on the coordinates of the corner points of the upper vertebrae; and determine the contour points of the upper edge of the lower vertebrae from the contour point set of the lower vertebrae based on the coordinates of the corner points of the lower vertebrae.

[0180] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0181] A first maximum distance value is obtained from a first distance value set corresponding to the upper vertebral body, and a second maximum distance value is obtained from a second distance value set corresponding to the lower vertebral body; the first maximum distance value and the second maximum distance value are averaged to obtain the intervertebral space distance between two adjacent vertebral bodies.

[0182] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0183] The spinal column size of the object to be detected is obtained; the intervertebral space distance between two adjacent vertebrae is ratioed to the spinal column size, and the obtained ratio is compared with a preset intervertebral space distance threshold.

[0184] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0185] If the above ratio is greater than a preset intervertebral space distance threshold, it is determined that the intervertebral space between two adjacent vertebrae is narrow.

[0186] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0187] According to the spinal segmentation result, the centroid coordinates of two adjacent vertebrae are calculated; the centroid coordinates of the two adjacent vertebrae are averaged, and the spinal sagittal image where the obtained mean coordinates are located is determined as the spinal target sagittal image.

[0188] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0189] Acquire a spinal segmentation result of the object to be detected; the spinal segmentation result includes at least two adjacent vertebrae;

[0190] Extract segmentation results of two adjacent vertebrae from the above spine segmentation results;

[0191] According to the segmentation results of the two adjacent vertebrae, the distance between the upper and lower edge contour points of the two adjacent vertebrae is calculated to obtain a distance value set;

[0192] According to the above distance value set, the intervertebral space distance between the above two adjacent vertebrae is obtained;

[0193] The intervertebral space distance between the two adjacent vertebrae is compared with a preset intervertebral space distance threshold, and the intervertebral space analysis result of the object to be detected is obtained according to the comparison result.

[0194] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0195] According to the above spinal segmentation results, a spinal target sagittal image corresponding to the spinal segmentation result is determined from a plurality of spinal sagittal images; and segmentation results of two adjacent vertebrae are extracted from the spinal target sagittal image.

[0196] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0197] According to the segmentation results of two adjacent vertebrae, the distance images of the two adjacent vertebrae are calculated; wherein each value on the distance image of one vertebra is used to characterize the shortest distance value from each point on the vertebra to another vertebra; the segmentation results of the two adjacent vertebrae are subjected to edge extraction to obtain the contour points of the lower edge of the upper vertebra and the contour points of the upper edge of the lower vertebra; according to the positions of the contour points of the lower edge and the positions of the contour points of the upper edge, a first distance value set corresponding to the contour points of the lower edge is determined from the distance image of the upper vertebra, and a second distance value set corresponding to the contour points of the upper edge is determined from the distance image of the lower vertebra.

[0198] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0199] Perform edge extraction on the segmentation results of two adjacent vertebrae to obtain respective contour point sets of the upper vertebrae and the lower vertebrae; perform corner point detection on the segmentation results of two adjacent vertebrae to obtain respective corner points of the upper vertebrae and the lower vertebrae; determine the contour points of the lower edge of the upper vertebrae from the contour point set of the upper vertebrae based on the coordinates of the corner points of the upper vertebrae; and determine the contour points of the upper edge of the lower vertebrae from the contour point set of the lower vertebrae based on the coordinates of the corner points of the lower vertebrae.

[0200] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0201] A first maximum distance value is obtained from a first distance value set corresponding to the upper vertebral body, and a second maximum distance value is obtained from a second distance value set corresponding to the lower vertebral body; the first maximum distance value and the second maximum distance value are averaged to obtain the intervertebral space distance between two adjacent vertebral bodies.

[0202] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0203] The spinal column size of the object to be detected is obtained; the intervertebral space distance between two adjacent vertebrae is ratioed to the spinal column size, and the obtained ratio is compared with a preset intervertebral space distance threshold.

[0204] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0205] If the above ratio is greater than a preset intervertebral space distance threshold, it is determined that the intervertebral space between two adjacent vertebrae is narrow.

[0206] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0207] According to the spinal segmentation result, the centroid coordinates of two adjacent vertebrae are calculated; the centroid coordinates of the two adjacent vertebrae are averaged, and the spinal sagittal image where the obtained mean coordinates are located is determined as the spinal target sagittal image.

[0208] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0209] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0210] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for analyzing the intervertebral disc space of a spinal column, characterized in that: The method comprises: Acquire a spinal segmentation result of the object to be detected; the spinal segmentation result includes at least two adjacent vertebrae; Extracting the segmentation results of the two adjacent vertebrae from the spine segmentation results; According to the segmentation results of the two adjacent vertebrae, the distance between the upper and lower edge contour points of the two adjacent vertebrae is calculated to obtain a distance value set; the distance value set includes the shortest distance between the upper and lower edge contour points of the two adjacent vertebrae; If the two adjacent vertebrae include an upper vertebrae located at the top and a lower vertebrae located at the bottom; the distance between the upper and lower edge contour points of the two adjacent vertebrae is calculated according to the segmentation results of the two adjacent vertebrae to obtain a distance value set, including: A distance field correlation algorithm is used to calculate the shortest distance values ​​from each point on the upper vertebra to the lower vertebra to obtain a distance image corresponding to the upper vertebra, and the shortest distance values ​​from each point on the lower vertebra to the upper vertebra to obtain a distance image corresponding to the lower vertebra; wherein each value on the distance image of one vertebra is used to characterize the shortest distance value from each point on the vertebra to another vertebra; Performing edge extraction on the segmentation results of the two adjacent vertebrae to obtain contour points of the lower edge of the upper vertebrae and contour points of the upper edge of the lower vertebrae; According to the position of the contour point of the lower edge, a plurality of first distance values ​​at the position of the contour point of the lower edge are determined from the distance image of the upper vertebral body, and the plurality of first distance values ​​are combined to obtain a first distance value set corresponding to the contour point of the lower edge; and, according to the position of the contour point of the upper edge, a plurality of second distance values ​​at the position of the contour point of the upper edge are determined from the distance image of the lower vertebral body, and the plurality of second distance values ​​are combined to obtain a second distance value set corresponding to the contour point of the upper edge; The step of performing edge extraction on the segmentation results of the two adjacent vertebrae to obtain contour points of the lower edge of the upper vertebrae and contour points of the upper edge of the lower vertebrae includes: Performing edge extraction on the segmentation results of the two adjacent vertebrae to obtain respective contour point sets of the upper vertebrae and the lower vertebrae; Performing corner point detection on the segmentation results of the two adjacent vertebrae to obtain respective corner points of the upper vertebrae and the lower vertebrae; Determine the contour points of the lower edge of the upper vertebra from the contour point set of the upper vertebra according to the coordinates of the corner points of the upper vertebra; and determine the contour points of the upper edge of the lower vertebra from the contour point set of the lower vertebra according to the coordinates of the corner points of the lower vertebra; Obtaining the intervertebral space distance between the two adjacent vertebrae according to the distance value set; The intervertebral space distance between the two adjacent vertebrae is compared with a preset intervertebral space distance threshold, and the intervertebral space analysis result of the object to be detected is obtained according to the comparison result.

2. The method according to claim 1, characterized in that The spinal column segmentation result includes a plurality of spinal column sagittal images, and extracting the segmentation results of the two adjacent vertebrae from the spinal column segmentation result includes: According to the spinal column segmentation result, determining a spinal column target sagittal image corresponding to the spinal column segmentation result from the multiple spinal column sagittal images; The segmentation results of the two adjacent vertebrae are extracted from the target spinal column sagittal image.

3. The method according to claim 1 or 2, characterized in that: The method for calculating the distance image comprises: According to the segmentation results of the two adjacent vertebrae, respective distance images of the two adjacent vertebrae are calculated.

4. The method according to claim 3, characterized in that The step of performing edge extraction on the segmentation results of the two adjacent vertebrae to obtain contour points of the lower edge of the upper vertebrae and contour points of the upper edge of the lower vertebrae includes: Performing edge extraction on the segmentation results of the two adjacent vertebrae to obtain respective contour point sets of the upper vertebrae and the lower vertebrae; Performing corner point detection on the segmentation results of the two adjacent vertebrae to obtain respective corner points of the upper vertebrae and the lower vertebrae; According to the coordinates of the corner points of the upper vertebra, the contour points of the lower edge of the upper vertebra are determined from the contour point set of the upper vertebra; and according to the coordinates of the corner points of the lower vertebra, the contour points of the upper edge of the lower vertebra are determined from the contour point set of the lower vertebra.

5. The method according to claim 3, characterized in that: The step of obtaining the intervertebral space distance between the two adjacent vertebrae according to the distance value set includes: Acquire a first maximum distance value from a first distance value set corresponding to the upper vertebral body, and acquire a second maximum distance value from a second distance value set corresponding to the lower vertebral body; The first maximum distance value and the second maximum distance value are processed by average calculation to obtain the intervertebral space distance between the two adjacent vertebral bodies.

6. The method according to claim 1, characterized in that The step of comparing the intervertebral space distance between the two adjacent vertebrae with a preset intervertebral space distance threshold comprises: Obtaining the size of the spine of the object to be detected; The intervertebral disc distance between the two adjacent vertebrae is ratioed to the size of the spine, and the obtained ratio is compared with the preset intervertebral disc distance threshold.

7. The method according to claim 6, characterized in that The step of obtaining the intervertebral disc analysis result of the object to be detected according to the comparison result includes: If the ratio is greater than the preset intervertebral space distance threshold, it is determined that the intervertebral space between the two adjacent vertebral bodies is narrow.

8. The method according to claim 2, characterized in that: Determining, according to the spinal column segmentation result, from the plurality of spinal column sagittal images, a spinal column target sagittal image corresponding to the spinal column segmentation result, comprises: Calculating the centroid coordinates of the two adjacent vertebrae according to the spine segmentation result; The centroid coordinates of the two adjacent vertebrae are processed by mean calculation, and the spinal sagittal image where the obtained mean coordinates are located is determined as the spinal target sagittal image.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images