Anesthesia site identification method and system based on image navigation technology

Abstract

The invention relates to the technical field of anesthesia site identification, and discloses an anesthesia site identification method and system based on an image navigation technology, and the method comprises the steps: carrying out the digital operation of an original spine image, obtaining a standard spine image, carrying out the comparison operation of the standard spine image through a pre-constructed spine image database, obtaining a plurality of potential anesthesia sites, and carrying out the comparison operation of the plurality of potential anesthesia sites. The optimized spine image is sent to a pre-constructed spine management system, returned spine images returned by a spine diagnosis client are received, the returned spine images are gathered to obtain a plurality of returned spine images, a plurality of calibrated anesthesia sites are obtained based on the plurality of returned spine images, and the calibrated anesthesia sites are used for positioning the spine diagnosis client. And obtaining a target anesthesia site according to the plurality of calibrated anesthesia sites, and completing the identification of the anesthesia site based on the target anesthesia site. Therefore, the accuracy of anesthesia site identification is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of anesthesia site recognition, and in particular to an anesthesia site recognition method, system, electronic device and computer-readable storage medium based on image navigation technology. Background Art

[0002] Identification of anesthesia sites plays an important role in surgery. Correct identification of anesthesia sites can improve the anesthesia effect and the safety of anesthetic drugs, and avoid damage to surrounding tissues and nerves when injecting anesthetic drugs.

[0003] Although the identification of anesthesia sites plays an important role in surgery, since the conditions of each patient are different, the identification of anesthesia sites mostly relies on the doctor's experience. If the most appropriate anesthesia site cannot be determined according to the patient's condition, the patient's safety cannot be guaranteed. Therefore, how to improve the accuracy of anesthesia site identification is an urgent problem to be solved. Summary of the invention

[0004] The present invention provides an anesthesia site recognition method based on image navigation technology, the main purpose of which is to improve the accuracy of anesthesia site recognition.

[0005] To achieve the above object, the present invention provides an anesthesia site identification method based on image navigation technology, comprising:

[0006] receiving an identification instruction of an anesthesia site, and starting a pre-built imaging device and a pre-built spinal fixation device according to the identification instruction;

[0007] Identify the spine of the patient to be anesthetized, use a spinal fixation device to perform a fixation operation on the patient's spine to obtain a fixed spine, and use an image capture device to perform a photographing operation on the fixed spine to obtain an original spinal image;

[0008] Performing digital operation on the original spinal image to obtain a standard spinal image;

[0009] Using a pre-built spine image database to perform a comparison operation on a standard spine image, a plurality of potential anesthesia sites are obtained, wherein the spine image database includes a plurality of reference spine images, and a distance between a potential anesthesia site and another potential anesthesia site is at least 0.5 cm;

[0010] A spinal image coordinate system is constructed in a standard spinal image, a plurality of potential anesthesia coordinates are obtained based on a plurality of potential anesthesia sites, and the plurality of potential anesthesia coordinates are projected into a standard spinal image containing the spinal image coordinate system to obtain an optimized spinal image;

[0011] Sending the optimized spinal image to a pre-built spinal management system, wherein the spinal management system includes a spinal diagnosis client corresponding to each of a plurality of spinal diagnosis experts;

[0012] When the spine management system successfully receives the optimized spine image, the spine management system is used to perform a connection operation on the spine diagnosis client. When the spine management system successfully connects to the spine diagnosis client, the spine management system is used to send the optimized spine image to the spine diagnosis client and receive the returned spine image from the spine diagnosis client.

[0013] Summarizing the returned spinal images to obtain a plurality of returned spinal images, and acquiring a plurality of calibrated anesthesia sites based on the plurality of returned spinal images;

[0014] A target anesthesia site is obtained according to a plurality of calibrated anesthesia sites, and the anesthesia site is identified based on the target anesthesia site.

[0015] Optionally, performing a digitization operation on the original spinal image to obtain a standard spinal image includes:

[0016] Acquire an initial spinal image based on the original spinal image, perform an upsampling operation on the initial spinal image to obtain an updated spinal image, wherein the updated spinal image includes a plurality of updated pixel points;

[0017] Performing a first quantization operation on the updated spine image using a preset initial quantization bit number to obtain a plurality of spine pixel points;

[0018] Acquire a grayscale value set using a plurality of spine pixel points, wherein the grayscale value set includes a plurality of grayscale values, and the grayscale values ​​correspond to the spine pixel points one by one;

[0019] Obtaining a grayscale value variance based on the grayscale value set, wherein the grayscale value variance is a variance of multiple grayscale values ​​in the grayscale value set;

[0020] Comparing the grayscale value variance with a preset grayscale variance threshold;

[0021] If the gray value variance is less than the gray variance threshold, taking multiple spine pixel points as multiple evaluation pixel points, performing a quantization update operation on the initial quantization bit number to obtain an updated quantization bit number;

[0022] Performing a second quantization operation on a plurality of evaluation pixels using the updated quantization bit number to obtain a plurality of target pixels, and performing an encoding operation on the plurality of target pixels to obtain a plurality of encoded pixels;

[0023] A coded spinal image is acquired according to a plurality of coded pixel points, a coded clarity is acquired based on the coded spinal image, and the coded spinal image is optimized using the coded clarity to obtain a standard spinal image.

[0024] Optionally, optimizing the encoded spinal image by using encoding clarity to obtain a standard spinal image includes:

[0025] Compare the encoding clarity with the preset spine clarity threshold;

[0026] If the coding clarity is greater than or equal to the spine clarity threshold, the coded spine image is used as the standard spine image;

[0027] If the encoding clarity is less than the spine clarity threshold, a denoising operation is performed on the encoded spine image to obtain a denoised spine image, and a sharpening operation is performed on the denoised spine image to obtain a standard spine image.

[0028] Optionally, the pre-built spine image database is used to perform a comparison operation on the standard spine image to obtain multiple potential anesthesia sites, including:

[0029] Performing information extraction operations on standard spine images to obtain standard patient information;

[0030] The following operations are performed on each of the multiple reference spine images:

[0031] Acquire reference patient information based on reference spinal images, wherein the number of reference spinal images is the same as the number of reference patient information, and the dimension of the standard patient information is the same as the dimension of the reference patient information, wherein the dimension of the standard patient information and the dimension of the reference patient information both include gender dimension, weight dimension, age dimension, height dimension and spinal posture dimension;

[0032] A reference spine sequence is constructed based on the reference patient information, where the reference spine sequence is as follows:

[0033] J i =[A, B, C, D, E]

[0034] Among them, J i represents the reference spine sequence corresponding to the i-th reference spine image in multiple reference spine images, A represents the gender dimension, B represents the weight dimension, C represents the age dimension, D represents the height dimension, and E represents the spine posture dimension;

[0035] Summarizing the reference spine sequences to obtain multiple reference spine sequences;

[0036] A standard spinal sequence is constructed using standard patient information, a plurality of target spinal sequences are identified from a plurality of reference spinal sequences using the standard spinal sequence, and a plurality of first spinal images are extracted from a spinal image database using the plurality of target spinal sequences, wherein the target spinal sequences correspond to the first spinal images one by one;

[0037] Multiple potential anesthesia sites were identified using multiple first spinal images.

[0038] Optionally, the method of using a plurality of first spinal images to identify a plurality of potential anesthesia sites includes:

[0039] A standard spine contour is obtained according to a standard spine image, and the following operation is performed on each of the multiple first spine images:

[0040] Acquire a first spine contour according to the first spine image, construct a spine similarity formula, calculate a spine similarity value using the spine similarity formula, the first spine contour and the standard spine contour, and obtain multiple spine similarity values;

[0041] Acquire a target spinal image based on multiple spinal similarity values, wherein the target spinal image is a first spinal image corresponding to a maximum spinal similarity value among the multiple spinal similarity values;

[0042] Multiple potential anesthesia sites were obtained based on the target spinal images.

[0043] Optionally, constructing a spine similarity formula includes:

[0044] Performing a vertebral body recognition operation on the standard vertebral contour to obtain a plurality of standard vertebral bodies, and identifying a first vertebral body and a second vertebral body from the plurality of standard vertebral bodies;

[0045] Identify the upper edge of the first vertebra and the lower edge of the second vertebra of the first vertebra and the second vertebra, respectively, draw tangents at the upper edge of the first vertebra and the lower edge of the second vertebra, and obtain the first vertebra tangent and the second vertebra tangent;

[0046] Performing a vertical line drawing operation on the first vertebral body tangent and the second vertebral body tangent respectively to obtain a first vertebral body vertical line and a second vertebral body vertical line, and performing a vertical line extension operation on the first vertebral body vertical line and the second vertebral body vertical line respectively to obtain a first extended vertical line and a second extended vertical line;

[0047] Acquire the spine extension angle according to the first extended perpendicular line and the second extended perpendicular line, perform an angle measurement operation on the spine extension angle, and obtain the spine angle;

[0048] Constructing a standard spine matrix based on the weight dimension, age dimension, height dimension and spine intersection angle;

[0049] Acquire a first intersection angle based on the first spinal image, and summarize the first intersection angles to obtain a plurality of first intersection angles;

[0050] The following operation is performed for each of the multiple first intersection angles:

[0051] Constructing a first spine matrix using the first intersection angle, weight dimension, age dimension and height dimension;

[0052] The spine similarity formula is constructed using the standard spine matrix and the first spine matrix.

[0053] Optionally, constructing a spine similarity formula using the standard spine matrix and the first spine matrix includes:

[0054] Among them, the standard spine matrix is ​​shown as follows:

[0055]

[0056] Among them, Z0 represents the standard spine matrix, α represents the spine intersection angle, β represents the weight dimension, γ represents the age dimension, and δ represents the height dimension;

[0057] The spine similarity formula is constructed using the standard spine matrix, the first spine matrix and the preset extreme value coefficient, where the spine similarity formula is as follows:

[0058]

[0059] Among them, S represents the spine similarity formula, Z i represents the first spine matrix corresponding to the i-th first spine image among multiple first spine images, a represents the extreme value coefficient, || || F represents the Frobenius norm.

[0060] Optionally, the projecting of the plurality of potential anesthesia coordinates into a standard spinal image containing a spinal image coordinate system to obtain an optimized spinal image comprises:

[0061] A target spine coordinate system is constructed using a target spine image, and a plurality of potential anesthesia coordinates are used to confirm the potential anesthesia coordinates in the target spine coordinate system to obtain a plurality of potential spine coordinates, wherein the potential spine coordinates correspond one to one to the potential anesthesia coordinates;

[0062] Performing a coordinate extraction operation on each of the multiple potential spine coordinates to obtain multiple extracted spine coordinates;

[0063] Annotating a plurality of extracted spine coordinates to a spine image coordinate system to obtain a plurality of annotated spine coordinates;

[0064] Performing a labeling operation on each of the plurality of labeled spinal coordinates to obtain a plurality of labeled spinal coordinates, wherein the potential spinal coordinates correspond one-to-one to the labeled spinal coordinates;

[0065] The standard spine image containing multiple labeled spine coordinates is recorded as the optimized spine image.

[0066] Optionally, acquiring a target anesthesia site according to a plurality of calibrated anesthesia sites comprises:

[0067] Get the number of online clients of the spine diagnosis client;

[0068] If the number of online clients is greater than or equal to a preset minimum threshold and less than or equal to a preset maximum threshold, repetition rates are calculated for multiple calibrated anesthesia sites to obtain one or more repetition rates;

[0069] Acquire a target anesthesia site based on the one or more repetition rates, wherein the target anesthesia site is a calibrated anesthesia site corresponding to a maximum repetition rate among the one or more repetition rates;

[0070] If the number of online clients is greater than the maximum threshold, the calibrated anesthesia sites corresponding to the returned spinal images are sorted in order from earliest to latest time corresponding to the returned spinal images to obtain a calibrated anesthesia site sequence;

[0071] Based on the maximum threshold, an initial anesthesia site sequence is selected from the calibrated anesthesia site sequence, wherein the initial anesthesia site sequence includes multiple initial anesthesia sites, and the number corresponding to the initial anesthesia sites is equal to the maximum threshold, and the target anesthesia site is obtained based on the initial anesthesia site sequence.

[0072] To achieve the above object, the present invention also provides an anesthesia site recognition system based on image navigation technology, comprising:

[0073] An instruction receiving module, used for receiving an identification instruction of an anesthesia site, and starting a pre-built imaging device and a pre-built spinal fixation device according to the identification instruction;

[0074] Identify the spine of the patient to be anesthetized, use a spinal fixation device to perform a fixation operation on the patient's spine to obtain a fixed spine, and use an image capture device to perform a photographing operation on the fixed spine to obtain an original spinal image;

[0075] A coordinate construction module is used to perform a digitization operation on the original spine image to obtain a standard spine image;

[0076] Using a pre-built spine image database to perform a comparison operation on a standard spine image, a plurality of potential anesthesia sites are obtained, wherein the spine image database includes a plurality of reference spine images, and a distance between a potential anesthesia site and another potential anesthesia site is at least 0.5 cm;

[0077] A system management module is used to construct a spinal image coordinate system in a standard spinal image, obtain a plurality of potential anesthesia coordinates based on a plurality of potential anesthesia sites, and project the plurality of potential anesthesia coordinates into a standard spinal image containing the spinal image coordinate system to obtain an optimized spinal image;

[0078] Sending the optimized spinal image to a pre-built spinal management system, wherein the spinal management system includes a spinal diagnosis client corresponding to each of a plurality of spinal diagnosis experts;

[0079] A site determination module is used to, when the spine management system successfully receives the optimized spine image, use the spine management system to perform a connection operation on the spine diagnosis client, and when the spine management system successfully connects to the spine diagnosis client, use the spine management system to send the optimized spine image to the spine diagnosis client, and receive the returned spine image from the spine diagnosis client;

[0080] Summarizing the returned spinal images to obtain a plurality of returned spinal images, and acquiring a plurality of calibrated anesthesia sites based on the plurality of returned spinal images;

[0081] A target anesthesia site is obtained according to a plurality of calibrated anesthesia sites, and the anesthesia site is identified based on the target anesthesia site.

[0082] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:

[0083] a memory storing at least one instruction; and

[0084] The processor executes the instructions stored in the memory to implement the above-mentioned anesthesia site identification method based on image navigation technology.

[0085] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the above-mentioned anesthesia site identification method based on image navigation technology.

[0086] The present invention is to solve the problems described in the background technology. The embodiment of the present invention identifies the spine of the patient to be anesthetized, and uses a spinal fixation device to perform a fixation operation on the patient's spine to obtain a fixed spine. It can be seen that the present invention takes into account the problem that different patient postures may cause inaccurate detection of the patient's spine. Furthermore, by fixing the patient's spine, the accuracy of detecting the patient's spine can be improved. The original spinal image is digitized to obtain a standard spinal image. It can be seen that the embodiment of the present invention digitizes the original spinal image, which is beneficial to the storage and transmission of the original spinal image. The standard spinal image is compared using a pre-constructed spinal image database to obtain multiple potential anesthesia sites. It can be seen that the embodiment of the present invention uses historical data to obtain a reference spinal image that is highly similar to the standard spinal image, and uses historical experience to quickly and accurately find the anesthesia site, constructs a spinal image coordinate system in the standard spinal image, obtains multiple potential anesthesia coordinates based on multiple potential anesthesia sites, and projects the multiple potential anesthesia coordinates onto the standard spinal image containing the spinal image coordinate system. In the image, an optimized spinal image is obtained. It can be seen that the present invention determines the potential anesthesia site with the help of a coordinate system, ensures the correctness of the potential anesthesia site, and sends the optimized spinal image to the pre-built spinal management system. In this embodiment, the spinal management system is constructed to better manage spinal image data, and can improve the accuracy and timeliness of anesthesia sites when searching for anesthesia sites. The returned spinal images from the spinal diagnosis client are received, and the returned spinal images are summarized to obtain multiple returned spinal images. Based on the multiple returned spinal images, multiple calibrated anesthesia sites are obtained, and the target anesthesia site is obtained according to the multiple calibrated anesthesia sites. The anesthesia site is identified based on the target anesthesia site. It can be seen that in the embodiment of the present invention, each spinal diagnosis client corresponds to a spinal diagnosis expert with professional knowledge. The target anesthesia site is confirmed based on the anesthesia site selected by each spinal diagnosis expert according to the optimized spinal image, and the target anesthesia site is confirmed according to the anesthesia site selected by the spinal diagnosis expert. The confirmed target anesthesia site improves the accuracy of anesthesia site confirmation for patients. Therefore, the main purpose of the present invention is to improve the accuracy of anesthesia site identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0087] Figure 1 A schematic diagram of a flow chart of an anesthesia site identification method based on image navigation technology provided by an embodiment of the present invention;

[0088] Figure 2 An original spinal image of the anesthesia site identification method based on image navigation technology provided by an embodiment of the present invention;

[0089] Figure 3 A reference spinal image of the anesthesia site identification method based on image navigation technology provided by an embodiment of the present invention;

[0090] Figure 4A functional module diagram of an anesthesia site recognition system based on image navigation technology provided by an embodiment of the present invention;

[0091] Figure 5 A schematic diagram of the structure of an electronic device for implementing the anesthesia site identification method based on image navigation technology provided in one embodiment of the present invention.

[0092] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0093] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0094] The embodiment of the present application provides an anesthesia site identification method based on image navigation technology. The execution subject of the anesthesia site identification method based on image navigation technology includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the anesthesia site identification method based on image navigation technology can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0095] Reference Figure 1 FIG. 1 is a flow chart of an anesthesia site identification method based on image navigation technology provided by an embodiment of the present invention. In this embodiment, the anesthesia site identification method based on image navigation technology includes:

[0096] S1. Receive an identification instruction of an anesthesia site, and start a pre-built imaging device and a pre-built spinal fixation device according to the identification instruction.

[0097] It should be explained that the anesthesia site refers to an injection point for injecting anesthetic drugs, such as an arm, spine, etc., which can be used as an anesthesia site. In the embodiment of the present invention, the anesthesia site is the patient's spine. In addition, the identification instruction of the anesthesia site is generally initiated by an operator who performs anesthesia on the patient's spine.

[0098] Furthermore, the image capturing device refers to a device that forms a medical image based on the anesthesia site. In the embodiment of the present invention, the image capturing device is a device that images the patient's spine based on the principles of magnetic field and radio frequency pulses in magnetic resonance imaging. Optionally, a nuclear magnetic resonance device is used as the image capturing device. Exemplarily, Xiao Zhang needs to be anesthetized, so the image capturing device is used to capture Xiao Zhang's spine first, thereby generating a spinal image, and then the anesthesia site is determined by the spinal image.

[0099] In addition, the spinal fixation device refers to a device for fixing the patient's spine. In this embodiment, a restraint belt is used to fix the patient's spine to prevent the problem of inaccurate spinal image generation due to different patient postures.

[0100] S2. Identify the spine of the patient to be anesthetized, use a spinal fixation device to fix the patient's spine to obtain a fixed spine, and use an image capture device to capture the fixed spine to obtain an original spinal image.

[0101] It should be explained that the patient spine refers to the spine of the patient to be examined. In order to ensure the accuracy and clarity of the generated spinal image, it is necessary to perform a fixation operation on the patient's spine. The fixation operation refers to an operation to fix the patient's posture. For example, when it is necessary to take a picture of Xiao Zhang's spine, Xiao Zhang's posture can be fixed with a restraint belt, and then the nuclear magnetic resonance equipment can be used to take a picture of Xiao Zhang's spine to obtain the original spinal image. At this time, Xiao Zhang's spine with a fixed posture is the fixed spine.

[0102] Specifically, the magnetic field and radio frequency pulses in the imaging device are activated, and the spine is fixed by the magnetic field and radio frequency pulses to obtain the original spine image. Figure 2 Shown is the original spinal image.

[0103] S3. Perform a digital operation on the original spinal image to obtain a standard spinal image.

[0104] It should be emphasized that the imaging effect of the original spinal image may be poor, so performing digital operations on the original spinal image can improve the imaging quality of the original spinal image, thereby improving the accuracy of identifying the anesthesia site.

[0105] In detail, the digitizing operation is performed on the original spinal image to obtain a standard spinal image, including:

[0106] Acquire an initial spinal image based on the original spinal image, perform an upsampling operation on the initial spinal image to obtain an updated spinal image, wherein the updated spinal image includes a plurality of updated pixel points;

[0107] Performing a first quantization operation on the updated spine image using a preset initial quantization bit number to obtain a plurality of spine pixel points;

[0108] Acquire a grayscale value set using a plurality of spine pixel points, wherein the grayscale value set includes a plurality of grayscale values, and the grayscale values ​​correspond to the spine pixel points one by one;

[0109] Obtaining a grayscale value variance based on the grayscale value set, wherein the grayscale value variance is a variance of multiple grayscale values ​​in the grayscale value set;

[0110] Comparing the grayscale value variance with a preset grayscale variance threshold;

[0111] If the gray value variance is less than the gray variance threshold, taking multiple spine pixel points as multiple evaluation pixel points, performing a quantization update operation on the initial quantization bit number to obtain an updated quantization bit number;

[0112] Performing a second quantization operation on a plurality of evaluation pixels using the updated quantization bit number to obtain a plurality of target pixels, and performing an encoding operation on the plurality of target pixels to obtain a plurality of encoded pixels;

[0113] A coded spinal image is acquired according to a plurality of coded pixel points, a coded clarity is acquired based on the coded spinal image, and the coded spinal image is optimized using the coded clarity to obtain a standard spinal image.

[0114] It should be understood that obtaining the initial spinal image based on the original spinal image means: extracting the original spinal image in the form of pixels as the initial spinal image, wherein each pixel corresponds to a grayscale value. The technology of the upsampling operation is a prior art and will not be repeated here. The purpose of performing the upsampling operation on the initial spinal image is to improve the clarity of the initial spinal image, thereby improving the accuracy of identifying the anesthesia site. The initial quantization bit number refers to the number of levels corresponding to the grayscale level. For example, when 16 grayscale levels are used, the initial quantization bit number is 16. The first quantization operation refers to: converting the grayscale value corresponding to each updated pixel point in a plurality of updated pixels to the initial quantization bit number operation, that is, converting the color corresponding to each pixel point in a plurality of pixels corresponding to the initial spinal image into a more refined color. For example, the grayscale value of the pixel point in the initial spinal image adopts 8 grayscale levels, and the initial quantization bit number is 16. Then, through the first quantization operation, the grayscale value corresponding to the 8 grayscale levels in the initial spinal image can be converted to the grayscale value corresponding to the 16 grayscale levels, thereby improving the accuracy of the updated spinal image representation color.

[0115] It is understandable that the first quantization operation performed on the updated spine image using the initial quantization bit number is: using the grayscale corresponding to the initial quantization bit number to perform grayscale conversion on each pixel in the updated spine image. For example: when a 16-level grayscale is used, the grayscale value corresponding to the pixel representing white in the updated spine image is 16, and the technology of using the grayscale to obtain the grayscale value corresponding to the pixel is a prior art and will not be repeated here.

[0116] Furthermore, the initial sampling frequency is preset because different sampling frequencies have a huge impact on the resolution and clarity of the initial spine image. When the initial spine image obtained using the initial sampling frequency cannot meet the required resolution and clarity, it is necessary to perform a frequency update operation on the initial sampling frequency, adjust the initial sampling frequency to a higher frequency update sampling frequency, and use the updated sampling frequency to perform sampling again to obtain a high-resolution and high-definition updated spine image.

[0117] It is understandable that after the first quantization operation, multiple spinal pixels may still not be able to characterize the state of the patient's spine, so the second quantization operation is performed on multiple evaluation pixels using the updated quantization bit number to obtain multiple target pixels, which can improve the color refinement of the multiple target pixels. The higher the grayscale level corresponding to the initial quantization bit number, the more colors represented, and the updated quantization bit number is higher than the initial quantization bit number.

[0118] It should be understood that when the gray value variance is less than the gray variance threshold, it indicates that the difference between multiple spinal pixels is not obvious enough or cannot characterize the state of the patient's spine. Therefore, it is necessary to obtain multiple target pixels with more obvious features through multiple evaluation pixels.

[0119] The key point is that the encoding operation is an operation of converting the quantized multiple target pixel points into a medical digital imaging and communication format for storage and transmission, wherein the medical digital imaging and communication format refers to a format for storing medical images. The multiple encoded pixel points are stored in the medical digital imaging and communication format, that is, the encoded spinal image is obtained. In this embodiment, in order to prevent the situation where the spinal image is distorted and unclear, thereby affecting the examination results, a second quantization operation is performed on the multiple spinal pixel points by updating the quantization bit number to obtain multiple target pixel points without distortion or with high definition.

[0120] It is understandable that the role of the coded spinal image is to examine Xiao Zhang's spine and obtain relevant spinal information. In order to ensure the accuracy of the examination results, it is necessary to ensure the clarity of the coded spinal image. The clarity of the coded spinal image is calculated. The coded spinal image that meets the clarity requirements is a clear spinal image, and the clear spinal image is the standard spinal image. The coding clarity refers to the signal-to-noise ratio of the coded spinal image. The technology of obtaining coding clarity using coded spinal images is a prior art and will not be repeated here.

[0121] Furthermore, the method of optimizing the encoded spinal image by using the encoding clarity to obtain a standard spinal image includes:

[0122] Compare the encoding clarity with the preset spine clarity threshold;

[0123] If the coding clarity is greater than or equal to the spine clarity threshold, the coded spine image is used as the standard spine image;

[0124] If the encoding clarity is less than the spine clarity threshold, a denoising operation is performed on the encoded spine image to obtain a denoised spine image, and a sharpening operation is performed on the denoised spine image to obtain a standard spine image.

[0125] It should be understood that the role of encoding clarity is to determine the clarity of the encoded spinal image. When the original spinal image is collected, noise that affects the quality and clarity of the original spinal image will be generated. The denoising operation is to ensure the quality and clarity of the original spinal image. Optionally, a Gaussian filter is used to perform a denoising operation on the encoded spinal image. The spinal clarity threshold is the minimum clarity that the encoded spinal image is expected to have. Sharpening operation refers to image sharpening, and the sharpening operation is intended to enhance the edges and details of the denoised spinal image, making the denoised spinal image look clearer and more vivid. Optionally, the Laplace operator is used to sharpen the denoised spinal image to obtain a standard spinal image.

[0126] For example, if the encoding clarity is 30dB, the spine clarity threshold is 35dB. When 30dB and 35dB are compared, if 30dB is less than 35dB, it means that the encoding clarity does not reach the required clarity. At this time, it is necessary to perform denoising and sharpening operations on the encoded spine image to obtain a standard spine image. If the encoding clarity is 36dB, the encoded spine image is used as the standard spine image.

[0127] S4. Use a pre-constructed spinal image database to perform a comparison operation on a standard spinal image to obtain multiple potential anesthesia sites, wherein the spinal image database includes multiple reference spinal images, and the distance between a potential anesthesia site and another potential anesthesia site is at least 0.5 cm.

[0128] It should be understood that the spine image database includes multiple reference spine images, and multiple reference anesthesia sites have been marked in each reference spine image. The distance between potential anesthesia sites is limited to avoid obtaining countless potential anesthesia sites. For example, Figure 3 The following is one of the reference spine images. Figure 3 In the reference spine image, the gray circle is the reference anesthesia site.

[0129] Furthermore, the pre-built spine image database is used to perform a comparison operation on the standard spine image to obtain multiple potential anesthesia sites, including:

[0130] Performing information extraction operations on standard spine images to obtain standard patient information;

[0131] The following operations are performed on each of the multiple reference spine images:

[0132] Acquire reference patient information based on reference spinal images, wherein the number of reference spinal images is the same as the number of reference patient information, and the dimension of the standard patient information is the same as the dimension of the reference patient information, wherein the dimension of the standard patient information and the dimension of the reference patient information both include gender dimension, weight dimension, age dimension, height dimension and spinal posture dimension;

[0133] A reference spine sequence is constructed based on the reference patient information, where the reference spine sequence is as follows:

[0134] J i =[A, B, C, D, E]

[0135] Among them, J i represents the reference spine sequence corresponding to the i-th reference spine image in multiple reference spine images, A represents the gender dimension, B represents the weight dimension, C represents the age dimension, D represents the height dimension, and E represents the spine posture dimension;

[0136] Summarizing the reference spine sequences to obtain multiple reference spine sequences;

[0137] A standard spinal sequence is constructed using standard patient information, a plurality of target spinal sequences are identified from a plurality of reference spinal sequences using the standard spinal sequence, and a plurality of first spinal images are extracted from a spinal image database using the plurality of target spinal sequences, wherein the target spinal sequences correspond to the first spinal images one by one;

[0138] Multiple potential anesthesia sites were identified using multiple first spinal images.

[0139] It is understandable that the standard patient information is the patient information corresponding to the patient of the standard spine image, and the definition of the reference patient information is the same as that of the standard patient information. The standard patient information and the reference patient information are both recorded when the patient's spine is examined, so the standard spine image corresponds to the standard patient information, and each reference spine image corresponds to one patient information. The reference spine sequence contains the reference patient information. The standard spine sequence and the reference spine sequence are constructed in the same way and have the same effect, which will not be repeated here. The gender dimension of the standard patient information is used to screen in the reference spine sequence to narrow the range of the number of reference spine images. Each of the remaining multiple reference spine sequences that meet the requirements is a target spine sequence, and the reference spine image corresponding to each target spine sequence in the multiple target spine sequences is the first spine image. The gender dimension refers to gender, the weight dimension refers to weight, the age dimension refers to the patient's age, the height dimension refers to the patient's height, and the spinal posture dimension is the patient's spine posture. Obviously, after the patient is fixed, the patient's spinal posture dimension is only related to the disease on the patient's spine.

[0140] It should be understood that the purpose of constructing reference spinal sequences and standard spinal sequences is to use the parameter contents corresponding to the reference spinal sequences and standard spinal sequences to perform the first round of screening in the spinal image database, narrow the scope of the spinal image database, and reduce the time required for subsequent searches to improve search efficiency. This is the first round of screening of reference spinal images, which reduces the workload of subsequent screening.

[0141] Importantly, the use of multiple first spinal images to identify multiple potential anesthesia sites includes:

[0142] A standard spine contour is obtained according to a standard spine image, and the following operation is performed on each of the multiple first spine images:

[0143] Acquire a first spine contour according to the first spine image, construct a spine similarity formula, calculate a spine similarity value using the spine similarity formula, the first spine contour and the standard spine contour, and obtain multiple spine similarity values;

[0144] Acquire a target spinal image based on multiple spinal similarity values, wherein the target spinal image is a first spinal image corresponding to a maximum spinal similarity value among the multiple spinal similarity values;

[0145] Multiple potential anesthesia sites were obtained based on the target spinal images.

[0146] The key point is to use the existing edge detection algorithm to extract the spine contour in each first spine image to obtain multiple first spine contours, wherein the method for obtaining the standard spine contour is the same as the multiple first spine contours and can achieve the same effect, which will not be repeated here. A similarity formula is constructed to calculate the standard spine contour and each first spine contour to determine whether the standard spine contour and the first spine contour are similar, and the first spine contour that is most similar to the standard spine contour is the target spine image.

[0147] Exemplarily, there are 5 spinal similarity values, which are 0.6, 0.4, 0.33, 0.91 and 0.9, respectively. Among them, the largest spinal similarity value is 0.91, and the first spinal image corresponding to 0.91 is the target spinal image. The multiple anesthesia sites in the target spinal image are used as multiple potential anesthesia sites. The similarity formula constructed here is the final screening, and the target spinal image is directly screened out from the first spinal image, and the target anesthesia site is obtained based on the potential anesthesia site existing in the target spinal image.

[0148] It can be understood that the spine similarity formula is constructed, including:

[0149] Performing a vertebral body recognition operation on the standard vertebral contour to obtain a plurality of standard vertebral bodies, and identifying a first vertebral body and a second vertebral body from the plurality of standard vertebral bodies;

[0150] Identify the upper edge of the first vertebra and the lower edge of the second vertebra of the first vertebra and the second vertebra, and draw tangents on the upper edge of the first vertebra and the lower edge of the second vertebra to obtain a first vertebra tangent and a second vertebra tangent;

[0151] Performing a vertical line drawing operation on the first vertebral body tangent and the second vertebral body tangent respectively to obtain a first vertebral body vertical line and a second vertebral body vertical line, and performing a vertical line extension operation on the first vertebral body vertical line and the second vertebral body vertical line respectively to obtain a first extended vertical line and a second extended vertical line;

[0152] Acquire the spine extension angle according to the first extended perpendicular line and the second extended perpendicular line, perform an angle measurement operation on the spine extension angle, and obtain the spine angle;

[0153] Constructing a standard spine matrix based on the weight dimension, age dimension, height dimension and spine intersection angle;

[0154] Acquire a first intersection angle based on the first spinal image, and summarize the first intersection angles to obtain a plurality of first intersection angles;

[0155] The following operation is performed for each of the multiple first intersection angles:

[0156] Constructing a first spine matrix using the first intersection angle, weight dimension, age dimension and height dimension;

[0157] The spine similarity formula is constructed using the standard spine matrix and the first spine matrix.

[0158] It should be understood that the standard spine profile and the first spine profile are both composed of multiple spinal vertebrae. Since the inclination of each spinal vertebrae is different, the spinal profile of each spinal vertebrae is also different. In the step of performing the vertebral body recognition operation on the standard spine profile, the vertebral body recognition operation can be performed using an edge detection algorithm. The first spinal vertebrae and the second spinal vertebrae are the spinal vertebrae with the largest inclination and the second largest inclination, respectively, and the first spinal vertebrae is located above the second spinal vertebrae. The inclination refers to the maximum value of the angle between the upper edge or lower edge of the spinal vertebrae and the horizontal line. The weight dimension, age dimension, height dimension and spinal intersection angle are used as elements in the spinal matrix to construct a spinal matrix with a specification of 2×2. The acquisition method of the first intersection angle is the same as the spinal intersection angle, and the construction method of the first spinal matrix is ​​also the same as the standard spinal matrix, and the same effect can be achieved.

[0159] Exemplarily, the first vertebral body with the largest inclination and the second vertebral body with the second largest inclination are found in the standard vertebral contour. The upper edge of the first vertebral body refers to the upper edge of the first vertebral body, and the lower edge of the second vertebral body refers to the lower edge of the second vertebral body. Because the first vertebral body is located above the second vertebral body, tangents can be made at the upper edge of the first vertebral body and the lower edge of the second vertebral body to obtain the first vertebral body tangent and the second vertebral body tangent. Draw a vertical line perpendicular to the first vertebral body tangent and the second vertebral body tangent respectively to obtain the first vertebral body vertical line and the second vertebral body vertical line. Because the first vertebral body and the second vertebral body both have an inclination angle, the first vertebral body vertical line and the second vertebral body vertical line are extended and intersected at one point. The angle formed by this intersection point, the first vertebral body vertical line and the second vertebral body vertical line is the vertebral extension intersection angle, and the vertebral intersection angle of the vertebral extension intersection angle is measured.

[0160] The key point is that the spine similarity formula constructed by using the standard spine matrix and the first spine matrix includes:

[0161] Among them, the standard spine matrix is ​​shown as follows:

[0162]

[0163] Among them, Z0 represents the standard spine matrix, α represents the spine intersection angle, β represents the weight dimension, γ represents the age dimension, and δ represents the height dimension;

[0164] The spine similarity formula is constructed using the standard spine matrix, the first spine matrix and the preset extreme value coefficient, where the spine similarity formula is as follows:

[0165]

[0166] Among them, S represents the spine similarity formula, Z i represents the first spine matrix corresponding to the i-th first spine image among multiple first spine images, a represents the extreme value coefficient, || || F represents the Frobenius norm.

[0167] It should be explained that the purpose of setting the extreme value coefficient a is to avoid the situation where the denominator is zero, and 0<a<1. The Frobenius norm is a norm specifically used to measure the difference between two matrices. The spine similarity formula calculates the spine similarity value between the standard spine contour and each first spine contour, and judges whether the standard spine contour is similar to each first spine contour based on the spine similarity value. According to the formula, the closer the obtained extreme value similarity value is to 1, the more similar the standard spine contour is to the first spine contour, and vice versa.

[0168] S5. Construct a spinal image coordinate system in the standard spinal image, obtain multiple potential anesthesia coordinates based on multiple potential anesthesia sites, and project the multiple potential anesthesia coordinates into the standard spinal image containing the spinal image coordinate system to obtain an optimized spinal image.

[0169] It can be understood that the spinal image coordinate system is a two-dimensional coordinate system constructed in the standard spinal image. Among them, in the standard spinal image, there are 5 lumbar vertebrae, and the order from top to bottom is the first lumbar vertebra, the second lumbar vertebra... and the fifth lumbar vertebra. Optionally, the intersection of the lower edge and the left edge of the fifth lumbar vertebra is used as the origin, the direction from the bottom to the top of the spine is the Y-axis, and the direction perpendicular to the Y-axis is the X-axis. The potential anesthesia coordinates are the coordinates of the potential anesthesia site. Establishing a spinal image coordinate system facilitates the comparison of anesthesia sites, so as to quickly and accurately find the coordinates of the potential anesthesia site. Optimizing the spinal image refers to projecting the potential anesthesia coordinates into the spinal image coordinate system to obtain a standard spinal image.

[0170] For example, a first spinal image highly similar to a standard spinal image has been found in the spinal image database, and the first spinal image has potential anesthesia sites numbered 1, 2, and 3. The coordinates of the three potential anesthesia sites are 1 (1, 2), 2 (2, 2), and 3 (3, 3), respectively, where 1 represents the number of the potential anesthesia site, and (1, 2) represents the coordinates of potential anesthesia site 1. The coordinates of the three potential anesthesia sites are found in the spinal image coordinate system and marked in the form of circles, and the positions of the circles are the positions of the potential anesthesia sites.

[0171] Furthermore, the projecting of the plurality of potential anesthesia coordinates into a standard spinal image containing a spinal image coordinate system to obtain an optimized spinal image includes:

[0172] A target spine coordinate system is constructed using a target spine image, and a plurality of potential anesthesia coordinates are used to confirm the potential anesthesia coordinates in the target spine coordinate system to obtain a plurality of potential spine coordinates, wherein the potential spine coordinates correspond one to one to the potential anesthesia coordinates;

[0173] Performing a coordinate extraction operation on each of the multiple potential spine coordinates to obtain multiple extracted spine coordinates;

[0174] Annotating a plurality of extracted spine coordinates to a spine image coordinate system to obtain a plurality of annotated spine coordinates;

[0175] Performing a labeling operation on each of the plurality of labeled spinal coordinates to obtain a plurality of labeled spinal coordinates, wherein the potential spinal coordinates correspond one-to-one to the labeled spinal coordinates;

[0176] The standard spine image containing multiple labeled spine coordinates is recorded as the optimized spine image.

[0177] It should be understood that the method for constructing the target spinal coordinate system is the same as that of the spinal image coordinate system, which will not be repeated here. There are multiple potential anesthesia sites in the target spinal coordinate system. The corresponding coordinates, that is, the potential spinal coordinates, are found in the target spinal coordinate system. Each potential spinal coordinate is used to find the corresponding position in the spinal image coordinate system, and marked to obtain multiple marked spinal coordinates. In order to distinguish multiple marked spinal coordinates, the marked spinal coordinates are randomly numbered in the order of 1, 2, 3, 4... to obtain multiple numbered spinal coordinates. A standard spinal image containing multiple numbered spinal coordinates is an optimized spinal image.

[0178] Exemplarily, the target spinal coordinate system has three potential anesthesia sites, and the potential spinal coordinates of the three potential anesthesia sites are confirmed to be (1, 1), (2, 2) and (3, 3), respectively. The coordinates (1, 1), (2, 2) and (3, 3) are found in the spinal image coordinate system, respectively, and are marked in the form of points. The three marked spinal coordinates are numbered, where 1 is (1, 1), 2 is (2, 2) and 3 is (3, 3). The marked spinal coordinates after numbering are the labeled spinal coordinates, and the standard spinal images including 1 (1, 1), 2 (2, 2) and 3 (3, 3) are optimized spinal images.

[0179] S6. Send the optimized spinal image to a pre-built spinal management system, wherein the spinal management system includes a spinal diagnosis client corresponding to each of a plurality of spinal diagnosis experts.

[0180] It should be explained that the spine management system refers to a system that classifies and manages optimized spine images and multiple reference spine images. The spine management system can transmit optimized spine images that require anesthesia site confirmation to the spine diagnosis client. The spine diagnosis expert refers to an expert who has spinal medical knowledge and anesthesia injection experience. The spine diagnosis client refers to the client used by the spine diagnosis expert to access and understand the optimized spine images. It should be noted that each spine diagnosis expert corresponds to only one spine diagnosis client.

[0181] S7. When the spinal management system successfully receives the optimized spinal image, the spinal management system is used to perform a connection operation on the spinal diagnosis client. When the spinal management system successfully connects to the spinal diagnosis client, the spinal management system is used to send the optimized spinal image to the spinal diagnosis client, receive the returned spinal image from the spinal diagnosis client, aggregate the returned spinal images, obtain multiple returned spinal images, and obtain multiple calibrated anesthesia sites based on the multiple returned spinal images.

[0182] It can be understood that the marked anesthesia site refers to the anesthesia site selected and marked by a spinal anesthesia expert from multiple potential anesthesia sites.

[0183] Exemplarily, an optimized spinal image with potential anesthesia sites numbered 1, 2, and 3 is transmitted through a spinal management system to a spinal diagnosis client corresponding to a spinal anesthesia expert. After receiving the optimized spinal image, the spinal anesthesia expert selects No. 2 from the three potential anesthesia sites and marks No. 2. The spinal anesthesia expert transmits the optimized spinal image with the marked potential anesthesia sites back to the spinal management system. At this time, the optimized spinal image is the returned spinal image, and the marked potential anesthesia point No. 2 is the calibrated anesthesia site.

[0184] S8. Acquire a target anesthesia site according to a plurality of calibrated anesthesia sites, and complete identification of the anesthesia site based on the target anesthesia site.

[0185] It should be understood that the target anesthesia site refers to the injection point where the anesthetic drug is ultimately injected.

[0186] The key point is that obtaining the target anesthesia site according to the multiple calibrated anesthesia sites includes:

[0187] Get the number of online clients of the spine diagnosis client;

[0188] If the number of online clients is greater than or equal to a preset minimum threshold and less than or equal to a preset maximum threshold, repetition rates are calculated for multiple calibrated anesthesia sites to obtain one or more repetition rates;

[0189] Acquire a target anesthesia site based on the one or more repetition rates, wherein the target anesthesia site is a calibrated anesthesia site corresponding to a maximum repetition rate among the one or more repetition rates;

[0190] If the number of online clients is greater than the maximum threshold, the calibrated anesthesia sites corresponding to the returned spinal images are sorted in order from earliest to latest time corresponding to the returned spinal images to obtain a calibrated anesthesia site sequence;

[0191] Based on the maximum threshold, an initial anesthesia site sequence is selected from the calibrated anesthesia site sequence, wherein the initial anesthesia site sequence includes multiple initial anesthesia sites, and the number corresponding to the initial anesthesia sites is equal to the maximum threshold, and the target anesthesia site is obtained based on the initial anesthesia site sequence.

[0192] It is understandable that the number of online clients is the number of spinal diagnosis clients that can successfully connect to the spinal management system. The number filtering threshold is set because each spinal anesthesia expert only selects one calibrated anesthesia site. To ensure that the optimal target anesthesia site can be obtained, the target anesthesia site cannot be obtained between the calibrated anesthesia sites calibrated by less than 2 spinal anesthesia experts, in case the selection of the target anesthesia site is not the optimal solution, where 2 is the minimum threshold in the number filtering threshold. If the number of calibrated anesthesia sites is too large, the subsequent calculation of the calibrated anesthesia site will be more complicated, thereby reducing the efficiency of the entire anesthesia site identification. The calibrated anesthesia site calibrated by the spinal anesthesia expert is selected according to the maximum threshold, and the selection judgment standard is: according to the maximum threshold and the time of returning the returned spinal image, the returned spinal image is selected as the returned spinal image for screening the target anesthesia site, wherein the returned spinal image for screening the target anesthesia site includes the calibrated anesthesia site. The calibrated anesthesia site with the highest repetition rate is selected as the target anesthesia site among multiple repetition rates, wherein the repetition rate is calculated by the number of times each calibrated anesthesia site is selected among multiple calibrated anesthesia sites.

[0193] The key point is that the minimum threshold is 2 and the maximum threshold is 10. When the number of returned spinal images exceeds 10, the times of the returned spinal images are 10:00, 10:01, 10:03, 10:04, 10:05, 10:07, 10:09, 10:10, 10:11, 10:16, 10:17, 10:18 and 10:20, respectively. The calibrated anesthesia sites in the times and the corresponding returned spinal images are used to construct a calibrated anesthesia site sequence. According to the chronological order, the first 10 calibrated anesthesia sites corresponding to the first 10 times in the calibrated anesthesia site sequence are selected as the initial anesthesia site sequence, that is, the calibrated anesthesia sites corresponding to 10:00, 10:01, 10:03, 10:04, 10:05, 10:07, 10:09, 10:10, 10:11 and 10:16. Finally, the target anesthesia site is confirmed using the same steps as the number of online clients is greater than or equal to the minimum threshold and less than or equal to the maximum threshold.

[0194] For example, there are 5 spinal anesthesia experts who send back 5 spinal images, each of which includes a calibrated anesthesia site. There are 5 calibrated anesthesia sites in total. The repetition rate of the 5 calibrated anesthesia sites is calculated, No. 1 is 10%, No. 2 is 60%, No. 3 is 10%, No. 4 is 12%, and No. 5 is 8%. The calibrated anesthesia site No. 2 with the highest repetition rate is selected as the target anesthesia site. When the number of calibrated anesthesia exceeds the maximum threshold, where the maximum threshold is 10, the first 10 are taken as calibrated anesthesia sites according to the value of the maximum threshold of 10, and the subsequent process is the same as when the number of calibrated anesthesia is between the minimum threshold and the maximum threshold and can achieve the same effect.

[0195] The present invention is to solve the problems described in the background technology. The embodiment of the present invention identifies the spine of the patient to be anesthetized, and uses a spinal fixation device to perform a fixation operation on the patient's spine to obtain a fixed spine. It can be seen that the present invention takes into account the problem that different patient postures may cause inaccurate detection of the patient's spine. Furthermore, by fixing the patient's spine, the accuracy of detecting the patient's spine can be improved. The original spinal image is digitized to obtain a standard spinal image. It can be seen that the embodiment of the present invention digitizes the original spinal image, which is beneficial to the storage and transmission of the original spinal image. The standard spinal image is compared using a pre-constructed spinal image database to obtain multiple potential anesthesia sites. It can be seen that the embodiment of the present invention uses historical data to obtain a reference spinal image that is highly similar to the standard spinal image, and uses historical experience to quickly and accurately find the anesthesia site, constructs a spinal image coordinate system in the standard spinal image, obtains multiple potential anesthesia coordinates based on multiple potential anesthesia sites, and projects the multiple potential anesthesia coordinates onto the standard spinal image containing the spinal image coordinate system. In the image, an optimized spinal image is obtained. It can be seen that the present invention determines the potential anesthesia site with the help of a coordinate system, ensures the correctness of the potential anesthesia site, and sends the optimized spinal image to the pre-built spinal management system. In this embodiment, the spinal management system is constructed to better manage spinal image data, and can improve the accuracy and timeliness of anesthesia sites when searching for anesthesia sites. The returned spinal images from the spinal diagnosis client are received, and the returned spinal images are summarized to obtain multiple returned spinal images. Based on the multiple returned spinal images, multiple calibrated anesthesia sites are obtained, and the target anesthesia site is obtained according to the multiple calibrated anesthesia sites. The anesthesia site is identified based on the target anesthesia site. It can be seen that in the embodiment of the present invention, each spinal diagnosis client corresponds to a spinal diagnosis expert with professional knowledge. The target anesthesia site is confirmed based on the anesthesia site selected by each spinal diagnosis expert according to the optimized spinal image, and the target anesthesia site is confirmed according to the anesthesia site selected by the spinal diagnosis expert. The confirmed target anesthesia site improves the accuracy of anesthesia site confirmation for patients. Therefore, the main purpose of the present invention is to improve the accuracy of anesthesia site identification.

[0196] like Figure 4 , which is a functional module diagram of an anesthesia site recognition system based on image navigation technology provided by an embodiment of the present invention.

[0197] The anesthesia site recognition system 100 based on image navigation technology of the present invention can be installed in an electronic device. According to the functions to be implemented, the anesthesia site recognition system 100 based on image navigation technology can include an instruction receiving module 101, a coordinate construction module 102, a system management module 103 and a site determination module 104. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0198] The instruction receiving module 101 is used to receive an identification instruction of an anesthesia site, and start a pre-built imaging device and a pre-built spinal fixation device according to the identification instruction;

[0199] Identify the spine of the patient to be anesthetized, use a spinal fixation device to perform a fixation operation on the patient's spine to obtain a fixed spine, and use an image capture device to perform a photographing operation on the fixed spine to obtain an original spinal image;

[0200] The coordinate construction module 102 is used to perform a digitization operation on the original spine image to obtain a standard spine image;

[0201] Using a pre-built spine image database to perform a comparison operation on a standard spine image, a plurality of potential anesthesia sites are obtained, wherein the spine image database includes a plurality of reference spine images, and a distance between a potential anesthesia site and another potential anesthesia site is at least 0.5 cm;

[0202] The system management module 103 is used to construct a spinal image coordinate system in the standard spinal image, obtain a plurality of potential anesthesia coordinates based on a plurality of potential anesthesia sites, and project the plurality of potential anesthesia coordinates into the standard spinal image containing the spinal image coordinate system to obtain an optimized spinal image;

[0203] Sending the optimized spinal image to a pre-built spinal management system, wherein the spinal management system includes a spinal diagnosis client corresponding to each of a plurality of spinal diagnosis experts;

[0204] The site determination module 104 is used to, when the spine management system successfully receives the optimized spine image, use the spine management system to perform a connection operation on the spine diagnosis client, and when the spine management system successfully connects to the spine diagnosis client, use the spine management system to send the optimized spine image to the spine diagnosis client, and receive the returned spine image from the spine diagnosis client;

[0205] Summarizing the returned spinal images to obtain a plurality of returned spinal images, and acquiring a plurality of calibrated anesthesia sites based on the plurality of returned spinal images;

[0206] A target anesthesia site is obtained according to a plurality of calibrated anesthesia sites, and the anesthesia site is identified based on the target anesthesia site.

[0207] In detail, each module in the anesthesia site recognition system 100 based on image navigation technology in the embodiment of the present invention is used in the same manner as described above. Figure 1 The anesthesia site identification method based on image navigation technology described in the invention is the same technical means and can produce the same technical effect, so it will not be repeated here.

[0208] like Figure 5 FIG. 1 is a schematic diagram of the structure of an electronic device for implementing an anesthesia site recognition method based on image navigation technology provided by an embodiment of the present invention.

[0209] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as an anesthesia site recognition method program based on image navigation technology.

[0210] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 can also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 11 also includes an internal storage unit of the electronic device 1 and an external storage device. The memory 11 can not only be used to store application software and various types of data installed in the electronic device 1, such as the code of the anesthesia site recognition method program based on image navigation technology, but also can be used to temporarily store data that has been output or is to be output.

[0211] The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory 11 (such as anesthesia site recognition method programs based on image navigation technology, etc.), and calls data stored in the memory 11 to execute various functions of the electronic device 1 and process data.

[0212] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 may be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0213] Figure 5 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 5 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0214] For example, although not shown, the electronic device 1 may also include a power source (such as a battery) for supplying power to each component. Preferably, the power source may be logically connected to the at least one processor 10 through a power management system, so that the power management system can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators. The electronic device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0215] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0216] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0217] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0218] The anesthesia site identification method program based on image navigation technology stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve:

[0219] receiving an identification instruction of an anesthesia site, and starting a pre-built imaging device and a pre-built spinal fixation device according to the identification instruction;

[0220] Identify the spine of the patient to be anesthetized, use a spinal fixation device to perform a fixation operation on the patient's spine to obtain a fixed spine, and use an image capture device to perform a photographing operation on the fixed spine to obtain an original spinal image;

[0221] Performing digital operation on the original spinal image to obtain a standard spinal image;

[0222] Using a pre-built spine image database to perform a comparison operation on a standard spine image, a plurality of potential anesthesia sites are obtained, wherein the spine image database includes a plurality of reference spine images, and a distance between a potential anesthesia site and another potential anesthesia site is at least 0.5 cm;

[0223] A spinal image coordinate system is constructed in a standard spinal image, a plurality of potential anesthesia coordinates are obtained based on a plurality of potential anesthesia sites, and the plurality of potential anesthesia coordinates are projected into a standard spinal image containing the spinal image coordinate system to obtain an optimized spinal image;

[0224] Sending the optimized spinal image to a pre-built spinal management system, wherein the spinal management system includes a spinal diagnosis client corresponding to each of a plurality of spinal diagnosis experts;

[0225] When the spine management system successfully receives the optimized spine image, the spine management system is used to perform a connection operation on the spine diagnosis client. When the spine management system successfully connects to the spine diagnosis client, the spine management system is used to send the optimized spine image to the spine diagnosis client and receive the returned spine image from the spine diagnosis client.

[0226] Summarizing the returned spinal images to obtain a plurality of returned spinal images, and acquiring a plurality of calibrated anesthesia sites based on the plurality of returned spinal images;

[0227] A target anesthesia site is obtained according to a plurality of calibrated anesthesia sites, and the anesthesia site is identified based on the target anesthesia site.

[0228] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figures 1 to 5 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0229] Furthermore, if the module / unit integrated in the electronic device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or system that can carry the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0230] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement:

[0231] receiving an identification instruction of an anesthesia site, and starting a pre-built imaging device and a pre-built spinal fixation device according to the identification instruction;

[0232] Identify the spine of the patient to be anesthetized, use a spinal fixation device to perform a fixation operation on the patient's spine to obtain a fixed spine, and use an image capture device to perform a photographing operation on the fixed spine to obtain an original spinal image;

[0233] Performing digital operation on the original spinal image to obtain a standard spinal image;

[0234] Using a pre-built spine image database to perform a comparison operation on a standard spine image, a plurality of potential anesthesia sites are obtained, wherein the spine image database includes a plurality of reference spine images, and a distance between a potential anesthesia site and another potential anesthesia site is at least 0.5 cm;

[0235] A spinal image coordinate system is constructed in a standard spinal image, a plurality of potential anesthesia coordinates are obtained based on a plurality of potential anesthesia sites, and the plurality of potential anesthesia coordinates are projected into a standard spinal image containing the spinal image coordinate system to obtain an optimized spinal image;

[0236] Sending the optimized spinal image to a pre-built spinal management system, wherein the spinal management system includes a spinal diagnosis client corresponding to each of a plurality of spinal diagnosis experts;

[0237] When the spine management system successfully receives the optimized spine image, the spine management system is used to perform a connection operation on the spine diagnosis client. When the spine management system successfully connects to the spine diagnosis client, the spine management system is used to send the optimized spine image to the spine diagnosis client and receive the returned spine image from the spine diagnosis client.

[0238] Summarizing the returned spinal images to obtain a plurality of returned spinal images, and acquiring a plurality of calibrated anesthesia sites based on the plurality of returned spinal images;

[0239] A target anesthesia site is obtained according to a plurality of calibrated anesthesia sites, and the anesthesia site is identified based on the target anesthesia site.

[0240] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only illustrative, and actual implementation may have other division methods.

[0241] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0242] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0243] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0244] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or systems stated in a system claim can also be implemented by one unit or system through software or hardware. Secondary words are used to indicate names, but not to indicate any particular order.

[0245] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for identifying anesthesia sites based on image navigation technology, characterized in that: The method comprises: receiving an identification instruction of an anesthesia site, and starting a pre-built imaging device and a pre-built spinal fixation device according to the identification instruction; Identify the spine of the patient to be anesthetized, use a spinal fixation device to perform a fixation operation on the patient's spine to obtain a fixed spine, and use an image capture device to perform a photographing operation on the fixed spine to obtain an original spinal image; Performing digital operation on the original spinal image to obtain a standard spinal image; Using a pre-built spine image database to perform a comparison operation on a standard spine image, a plurality of potential anesthesia sites are obtained, wherein the spine image database includes a plurality of reference spine images, and a distance between a potential anesthesia site and another potential anesthesia site is at least 0.5 cm; A spinal image coordinate system is constructed in a standard spinal image, a plurality of potential anesthesia coordinates are obtained based on a plurality of potential anesthesia sites, and the plurality of potential anesthesia coordinates are projected into a standard spinal image containing the spinal image coordinate system to obtain an optimized spinal image; Sending the optimized spinal image to a pre-built spinal management system, wherein the spinal management system includes a spinal diagnosis client corresponding to each of a plurality of spinal diagnosis experts; When the spine management system successfully receives the optimized spine image, the spine management system is used to perform a connection operation on the spine diagnosis client. When the spine management system successfully connects to the spine diagnosis client, the spine management system is used to send the optimized spine image to the spine diagnosis client and receive the returned spine image from the spine diagnosis client. Summarizing the returned spinal images to obtain a plurality of returned spinal images, and acquiring a plurality of calibrated anesthesia sites based on the plurality of returned spinal images; A target anesthesia site is obtained according to a plurality of calibrated anesthesia sites, and the anesthesia site is identified based on the target anesthesia site.

2. The anesthesia site identification method based on image navigation technology according to claim 1, characterized in that: The step of performing a digitization operation on the original spinal image to obtain a standard spinal image includes: Acquire an initial spinal image based on the original spinal image, perform an upsampling operation on the initial spinal image to obtain an updated spinal image, wherein the updated spinal image includes a plurality of updated pixel points; Performing a first quantization operation on the updated spine image using a preset initial quantization bit number to obtain a plurality of spine pixel points; Acquire a grayscale value set using a plurality of spine pixel points, wherein the grayscale value set includes a plurality of grayscale values, and the grayscale values ​​correspond to the spine pixel points one by one; Obtaining a grayscale value variance based on the grayscale value set, wherein the grayscale value variance is a variance of multiple grayscale values ​​in the grayscale value set; Comparing the grayscale value variance with a preset grayscale variance threshold; If the gray value variance is less than the gray variance threshold, taking multiple spine pixel points as multiple evaluation pixel points, performing a quantization update operation on the initial quantization bit number to obtain an updated quantization bit number; Performing a second quantization operation on a plurality of evaluation pixels using the updated quantization bit number to obtain a plurality of target pixels, and performing an encoding operation on the plurality of target pixels to obtain a plurality of encoded pixels; A coded spinal image is acquired according to a plurality of coded pixel points, a coded clarity is acquired based on the coded spinal image, and the coded spinal image is optimized using the coded clarity to obtain a standard spinal image.

3. The anesthesia site identification method based on image navigation technology according to claim 2, characterized in that: The step of optimizing the encoded spine image by using the encoding clarity to obtain a standard spine image includes: Compare the encoding clarity with the preset spine clarity threshold; If the coding clarity is greater than or equal to the spine clarity threshold, the coded spine image is used as the standard spine image; If the encoding clarity is less than the spine clarity threshold, a denoising operation is performed on the encoded spine image to obtain a denoised spine image, and a sharpening operation is performed on the denoised spine image to obtain a standard spine image.

4. The anesthesia site identification method based on image navigation technology according to claim 3, characterized in that: The pre-built spine image database is used to perform a comparison operation on the standard spine image to obtain multiple potential anesthesia sites, including: Performing information extraction operations on standard spine images to obtain standard patient information; The following operations are performed on each of the multiple reference spine images: Acquire reference patient information based on reference spinal images, wherein the number of reference spinal images is the same as the number of reference patient information, and the dimension of the standard patient information is the same as the dimension of the reference patient information, wherein the dimension of the standard patient information and the dimension of the reference patient information both include gender dimension, weight dimension, age dimension, height dimension and spinal posture dimension; A reference spine sequence is constructed based on the reference patient information, where the reference spine sequence is as follows: J i =[A、B、C、D、E] Among them, J i represents the reference spine sequence corresponding to the i-th reference spine image in multiple reference spine images, A represents the gender dimension, B represents the weight dimension, C represents the age dimension, D represents the height dimension, and E represents the spine posture dimension; Summarizing the reference spine sequences to obtain multiple reference spine sequences; A standard spinal sequence is constructed using standard patient information, a plurality of target spinal sequences are identified from a plurality of reference spinal sequences using the standard spinal sequence, and a plurality of first spinal images are extracted from a spinal image database using the plurality of target spinal sequences, wherein the target spinal sequences correspond to the first spinal images one by one; Multiple potential anesthesia sites were identified using multiple first spinal images.

5. The anesthesia site identification method based on image navigation technology according to claim 4, characterized in that: The method of using a plurality of first spinal images to identify a plurality of potential anesthesia sites includes: A standard spine contour is obtained according to a standard spine image, and the following operation is performed on each of the multiple first spine images: Acquire a first spine contour according to the first spine image, construct a spine similarity formula, calculate a spine similarity value using the spine similarity formula, the first spine contour and the standard spine contour, and obtain multiple spine similarity values; Acquire a target spinal image based on multiple spinal similarity values, wherein the target spinal image is a first spinal image corresponding to a maximum spinal similarity value among the multiple spinal similarity values; Multiple potential anesthesia sites were obtained based on the target spinal images.

6. The anesthesia site identification method based on image navigation technology according to claim 5, characterized in that: The constructing of the spine similarity formula includes: Performing a vertebral body recognition operation on the standard vertebral contour to obtain a plurality of standard vertebral bodies, and identifying a first vertebral body and a second vertebral body from the plurality of standard vertebral bodies; Identify the upper edge of the first vertebra and the lower edge of the second vertebra of the first vertebra and the second vertebra, and draw tangents on the upper edge of the first vertebra and the lower edge of the second vertebra to obtain a first vertebra tangent and a second vertebra tangent; Performing a vertical line drawing operation on the first vertebral body tangent and the second vertebral body tangent respectively to obtain a first vertebral body vertical line and a second vertebral body vertical line, and performing a vertical line extension operation on the first vertebral body vertical line and the second vertebral body vertical line respectively to obtain a first extended vertical line and a second extended vertical line; Acquire the spine extension angle according to the first extended perpendicular line and the second extended perpendicular line, perform an angle measurement operation on the spine extension angle, and obtain the spine angle; Constructing a standard spine matrix based on the weight dimension, age dimension, height dimension and spine intersection angle; Acquire a first intersection angle based on the first spinal image, and summarize the first intersection angles to obtain a plurality of first intersection angles; The following operation is performed for each of the multiple first intersection angles: Constructing a first spine matrix using the first intersection angle, weight dimension, age dimension and height dimension; The spine similarity formula is constructed using the standard spine matrix and the first spine matrix.

7. The anesthesia site identification method based on image navigation technology according to claim 6, characterized in that: The spine similarity formula is constructed by using the standard spine matrix and the first spine matrix, include: Among them, the standard spine matrix is ​​shown as follows: Among them, Z0 represents the standard spine matrix, α represents the spine intersection angle, β represents the weight dimension, γ represents the age dimension, and δ represents the height dimension; The spine similarity formula is constructed using the standard spine matrix, the first spine matrix and the preset extreme value coefficient, where the spine similarity formula is as follows: Among them, S represents the spine similarity formula, Z i represents the first spine matrix corresponding to the i-th first spine image among multiple first spine images, a represents the extreme value coefficient, || || F represents the Frobenius norm.

8. The anesthesia site identification method based on image navigation technology according to claim 7, characterized in that: The method of projecting a plurality of potential anesthesia coordinates into a standard spinal image containing a spinal image coordinate system to obtain an optimized spinal image includes: A target spine coordinate system is constructed using a target spine image, and a plurality of potential anesthesia coordinates are used to confirm the potential anesthesia coordinates in the target spine coordinate system to obtain a plurality of potential spine coordinates, wherein the potential spine coordinates correspond one to one to the potential anesthesia coordinates; Performing a coordinate extraction operation on each of the multiple potential spine coordinates to obtain multiple extracted spine coordinates; Annotating a plurality of extracted spine coordinates to a spine image coordinate system to obtain a plurality of annotated spine coordinates; Performing a labeling operation on each of the multiple labeled spinal coordinates to obtain multiple labeled spinal coordinates, wherein the potential spinal coordinates correspond to the labeled spinal coordinates one by one; The standard spine image containing multiple labeled spine coordinates is recorded as the optimized spine image.

9. The anesthesia site identification method based on image navigation technology according to claim 8, characterized in that: The step of obtaining a target anesthesia site according to a plurality of calibrated anesthesia sites includes: Get the number of online clients of the spine diagnosis client; If the number of online clients is greater than or equal to a preset minimum threshold and less than or equal to a preset maximum threshold, repetition rates are calculated for multiple calibrated anesthesia sites to obtain one or more repetition rates; Acquire a target anesthesia site based on the one or more repetition rates, wherein the target anesthesia site is a calibrated anesthesia site corresponding to a maximum repetition rate among the one or more repetition rates; If the number of online clients is greater than the maximum threshold, the calibrated anesthesia sites corresponding to the returned spinal images are sorted in order from earliest to latest time corresponding to the returned spinal images to obtain a calibrated anesthesia site sequence; Based on the maximum threshold, an initial anesthesia site sequence is selected from the calibrated anesthesia site sequence, wherein the initial anesthesia site sequence includes multiple initial anesthesia sites, and the number corresponding to the initial anesthesia sites is equal to the maximum threshold, and the target anesthesia site is obtained based on the initial anesthesia site sequence.

10. An anesthesia site recognition system based on image navigation technology, characterized in that: The system comprises: An instruction receiving module, used for receiving an identification instruction of an anesthesia site, and starting a pre-built imaging device and a pre-built spinal fixation device according to the identification instruction; Identify the spine of the patient to be anesthetized, use a spinal fixation device to perform a fixation operation on the patient's spine to obtain a fixed spine, and use an image capture device to perform a photographing operation on the fixed spine to obtain an original spinal image; A coordinate construction module is used to perform a digitization operation on the original spine image to obtain a standard spine image; Using a pre-built spine image database to perform a comparison operation on a standard spine image, a plurality of potential anesthesia sites are obtained, wherein the spine image database includes a plurality of reference spine images, and a distance between a potential anesthesia site and another potential anesthesia site is at least 0.5 cm; A system management module is used to construct a spinal image coordinate system in a standard spinal image, obtain a plurality of potential anesthesia coordinates based on a plurality of potential anesthesia sites, and project the plurality of potential anesthesia coordinates into a standard spinal image containing the spinal image coordinate system to obtain an optimized spinal image; Sending the optimized spinal image to a pre-built spinal management system, wherein the spinal management system includes a spinal diagnosis client corresponding to each of a plurality of spinal diagnosis experts; A site determination module is used to, when the spine management system successfully receives the optimized spine image, use the spine management system to perform a connection operation on the spine diagnosis client, and when the spine management system successfully connects to the spine diagnosis client, use the spine management system to send the optimized spine image to the spine diagnosis client, and receive the returned spine image from the spine diagnosis client; Summarizing the returned spinal images to obtain a plurality of returned spinal images, and acquiring a plurality of calibrated anesthesia sites based on the plurality of returned spinal images; A target anesthesia site is obtained according to a plurality of calibrated anesthesia sites, and the anesthesia site is identified based on the target anesthesia site.

Images