A method and system for anesthesia puncture positioning based on vision assistance
By continuously collecting multiple ultrasound images in anesthesia puncture and calculating pixel point weights, combined with the weighted mean filtering algorithm to reduce noise, the problem of excessive smoothing of weighted mean filtering is solved, and image clarity and puncture accuracy are improved.
Patent Information
- Application Number
- CN202411171261.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-26
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-08-26
AI Technical Summary
When weighted mean filtering denoising ultrasound images, it may excessively smooth nerves and blood vessels, affecting the accuracy of anesthesia puncture.
By continuously collecting multiple ultrasound images at the same location of the patient and grayscale, each pixel point is calculated based on the grayscale distribution characteristics, grayscale value differences and change trends of pixel points in the filter window of each grayscale image. The weight parameters, weight coefficients and weight factors of the image are reduced by combining the weighted mean filtering algorithm.
It improves the clarity of ultrasound images, accurately retains fine structure and edge information, reduces the impact of noise, and improves the accuracy and safety of anesthesia puncture.
Smart Images

Figure CN118680646B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of image processing, and in particular to a vision-assisted anesthesia puncture positioning method and system. Background Art
[0002] With the rapid development of modern medicine, anesthesiology has moved towards precision and visualization. The emergence of visualized anesthesia technology has provided anesthesiologists with more intuitive and accurate means of operation, greatly improving the accuracy of anesthesia and the safety of patients. Based on visual-assisted anesthesia puncture positioning technology, ultrasound imaging equipment is mainly used to provide anesthesiologists with real-time, high-resolution images of the patient's internal structure. Through these images, doctors can see the specific location, direction and depth of the target nerves, blood vessels or other tissues more clearly, so as to achieve precise positioning and puncture. Under the real-time guidance of ultrasound images, anesthesiologists can accurately place the puncture needle at the target nerve position and inject local anesthetics to complete nerve block; ultrasound image enhancement can more clearly display the anatomical structure of the target area, allowing anesthesiologists to more accurately determine the puncture point. Clear images help reduce puncture errors caused by image blur or noise interference, and improve the accuracy and safety of puncture.
[0003] Weighted mean filtering can be used for denoising ultrasound images. Since noise is usually randomly distributed and its value is greatly different from the surrounding pixel values, weighted mean filtering can weaken the impact of noise to a certain extent. However, in ultrasound images, due to the influence of noise and imaging characteristics, the local statistical characteristics and noise distribution of the image may become complex and uneven, resulting in unreasonable weight distribution. For example, when small structures such as nerves and blood vessels have low contrast with surrounding tissues, they may be regarded as similar areas and over-smoothed, resulting in doctors being unable to accurately observe nerve tissue and blood vessels, affecting the effect of nerve block. Therefore, it is necessary to select appropriate weights for weighted mean filtering to improve the clarity of ultrasound images and avoid excessive smoothing of nerve tissue and blood vessels. Summary of the invention
[0004] The present invention provides a visually assisted anesthesia puncture positioning method and system to solve the existing problem that weighted mean filtering for denoising ultrasound images will over-smooth nerves and blood vessels, which may affect the accuracy of anesthesia puncture.
[0005] The present invention provides a visually assisted anesthesia puncture positioning method and system using the following technical solutions:
[0006] In a first aspect, the present invention provides a method for anesthesia puncture positioning based on vision assistance, the method comprising the following steps:
[0007] Continuously acquiring a plurality of ultrasound images at the same position of the patient and gray-scaling the images to obtain each gray-scale image;
[0008] According to the grayscale distribution characteristics of the pixels in each filtering window of each grayscale image, the weight parameter of each pixel in each filtering window is obtained; according to the grayscale value difference of the pixels at the same position in the filtering windows at the same position in all grayscale images, the weight coefficient of each pixel in each filtering window is obtained; according to the change trend of the grayscale value of the pixels at the same position in the filtering windows at the same position in all grayscale images, the weight factor of each pixel in each filtering window is obtained; according to the weight parameter, weight coefficient and weight factor of each pixel in each filtering window, the weight of each pixel in each filtering window is obtained;
[0009] Combined with the weight of each pixel in each weighted mean filter window, the weighted mean filter algorithm is used to reduce the noise of each grayscale image, and anesthesia puncture is completed based on the grayscale image after noise reduction.
[0010] Furthermore, the method of continuously acquiring multiple ultrasound images at the same position of the patient and graying the images to obtain each grayscale image includes the following specific methods:
[0011] Using an ultrasound imaging device and a probe thereof, continuous ultrasound image acquisition is performed at the same position of the patient. During the acquisition process, parameters such as the position, angle and depth of the probe are kept consistent. A series of ultrasound images at the same anatomical position are acquired. The time interval for acquiring the ultrasound images is a preset time interval M, and the number of acquired ultrasound images is a preset number N of acquired ultrasound images.
[0012] All acquired ultrasound images are grayed out, and the grayed ultrasound images are traversed in the time sequence of acquiring the ultrasound images, and each grayed ultrasound image after the traversal is used as each grayscale image.
[0013] Furthermore, the specific method of obtaining the weight parameter of each pixel in each filtering window according to the grayscale distribution characteristics of the pixels in each filtering window of each grayscale image is as follows:
[0014]
[0015] In the formula, Represents the weight parameter of the cth pixel in the xth filter window of the zth grayscale image, Represents the grayscale value of the i-th pixel in the x-th filter window of the z-th grayscale image, Represents the grayscale value of the cth pixel in the xth filter window of the zth grayscale image, Indicates the discrete degree of the grayscale values of all pixels in the row of the c-th pixel in the x-th filter window of the z-th grayscale image, Indicates the discrete degree of the grayscale values of all pixels in the column where the cth pixel in the xth filter window of the zth grayscale image is located in the filter window; this method is used to obtain the weight parameter of each pixel in each filter window.
[0016] Furthermore, the weight coefficient of each pixel in each filtering window is obtained according to the gray value difference of the pixel at the same position in the filtering window at the same position of all gray images, including the specific method of:
[0017]
[0018] In the formula, represents the weight coefficient of the cth pixel in the xth filter window in the zth grayscale image, n represents the side length of the filter window, represents the gray value of the cth pixel in the xth filter window in the jth gray image, represents the gray value of the cth pixel in the xth filter window in the Jth gray image, Represents the grayscale value of the cth pixel in the xth filter window in the Ith grayscale image, and uses the above method to obtain the weight coefficient of each pixel in each filter window.
[0019] Furthermore, the weight factor of each pixel in each filtering window is obtained according to the change trend of the grayscale value of the pixel at the same position in the filtering window at the same position in all grayscale images, including the specific method of:
[0020]
[0021] In the formula, represents the weight factor of the cth pixel in the xth filter window in the zth grayscale image, represents the gray value of the cth pixel in the xth filter window in the kth gray image, represents the gray value of the cth pixel in the xth filter window in the k+1th gray image, N represents the number of gray images, and the weight factor of each pixel in each filter window is obtained according to this method.
[0022] Furthermore, the method of obtaining the weight of each pixel in each filtering window according to the weight parameter, weight coefficient and weight factor of each pixel in each filtering window includes the following specific methods:
[0023]
[0024] In the formula, represents the weight of the cth pixel in the xth filter window in the zth grayscale image, Represents the weight parameter of the cth pixel in the xth filter window of the zth grayscale image, represents the weight coefficient of the cth pixel in the xth filter window in the zth grayscale image, represents the weight factor of the cth pixel in the xth filter window in the zth grayscale image, represents the weight parameter of the K-th pixel in the x-th filter window of the z-th grayscale image, represents the weight coefficient of the K-th pixel in the x-th filter window in the z-th grayscale image, Represents the weight factor of the K-th pixel in the x-th filter window in the z-th grayscale image; the weight of each pixel in each filter window is obtained according to the above method.
[0025] Furthermore, the method of combining the weight of each pixel in each weighted mean filter window, using a weighted mean filter algorithm to reduce the noise of each grayscale image, and completing anesthesia puncture according to the grayscale image after noise reduction includes the following specific methods:
[0026] Combined with the calculated weight of each pixel in each weighted mean filter window of each grayscale image, the weighted mean filter algorithm is used to reduce the noise of each grayscale image to obtain a series of clearer grayscale images. The user completes the anesthesia puncture based on the information in the grayscale image.
[0027] A second aspect of the present invention provides a visually assisted anesthesia puncture positioning system, the system comprising an image acquisition module, a parameter calculation module and an image processing module, wherein:
[0028] An image acquisition module, used for continuously acquiring multiple ultrasound images at the same position of the patient and graying the images to obtain each grayscale image;
[0029] The parameter calculation module is used to obtain the weight parameter of each pixel in each filtering window according to the grayscale distribution characteristics of the pixels in each filtering window of each grayscale image; obtain the weight coefficient of each pixel in each filtering window according to the difference in the grayscale values of the pixels at the same position in the filtering windows at the same position in all grayscale images; obtain the weight factor of each pixel in each filtering window according to the change trend of the grayscale values of the pixels at the same position in the filtering windows at the same position in all grayscale images; obtain the weight of each pixel in each filtering window according to the weight parameter, weight coefficient and weight factor of each pixel in each filtering window;
[0030] The image processing module is used to combine the weight of each pixel in each weighted mean filter window, use the weighted mean filter algorithm to reduce the noise of each grayscale image, and complete the anesthesia puncture based on the grayscale image after noise reduction.
[0031] A third aspect of the present invention is a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of the above-mentioned visual-assisted anesthesia puncture positioning method.
[0032] A fourth aspect of the present invention is a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned visual-assisted anesthesia puncture positioning method when executing the computer program.
[0033] The beneficial effects of the technical solution of the present invention are as follows: continuously acquiring multiple ultrasound images at the same position of the patient and graying the images is to prevent the ultrasound images from being affected by various factors such as equipment performance, individual differences of patients, operating skills and external environment, resulting in uneven image quality and affecting the noise reduction effect;
[0034] According to the grayscale distribution characteristics of the pixels in each filtering window of each grayscale image, the weight parameter of each pixel in each filtering window is obtained; considering the grayscale distribution characteristics of the pixels in the filtering window, the noise points and the fine tissue pixels are preliminarily judged according to the grayscale distribution characteristics of the fine structures in the ultrasound image;
[0035] According to the gray value difference of the pixel at the same position in the filter window of all gray images, the weight coefficient of each pixel in each filter window is obtained; the dynamic change of the pixel of the body structure is taken into account, and the pixel can be more accurately distinguished as noise or fine tissue through the dynamic change;
[0036] According to the change trend of the grayscale value of the pixel at the same position in the filter window at the same position in all grayscale images, the weight factor of each pixel in each filter window is obtained; the pixel at the edge of the fine tissue is taken into account to avoid the pixel at the edge of the fine tissue being smoothed by the weighted mean filter algorithm due to dynamic fluctuations similar to noise;
[0037] According to the weight parameter, weight coefficient and weight factor of each pixel point in each filter window, the weight of each pixel point in each filter window is obtained; after comprehensive consideration, a more accurate weight of the pixel point in the filter window can be obtained;
[0038] Combined with the weight of each pixel in each weighted mean filter window, the weighted mean filter algorithm is used to reduce the noise of each grayscale image, and anesthesia puncture is completed based on the grayscale image after noise reduction. Using this method to reduce the noise of the image can give smaller weights to pixels with a higher noise probability, and give larger weights to small tissues, edges, and normal tissues. While enhancing the noise reduction effect, the detailed information in the ultrasound image is retained, avoiding errors caused by equipment or imaging rules to a certain extent, making the judgment of the anesthesia puncture position more accurate. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0040] Figure 1 A flowchart of the steps of a visually assisted anesthesia puncture positioning method of the present invention;
[0041] Figure 2 The present invention is a structural block diagram of a vision-assisted anesthesia puncture positioning system. DETAILED DESCRIPTION
[0042] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of a visual-assisted anesthesia puncture positioning method and system proposed by the present invention, its specific implementation method, structure, features and effects, in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.
[0043] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
[0044] The following is a detailed description of a specific scheme of a visually assisted anesthesia puncture positioning method and system provided by the present invention in conjunction with the accompanying drawings.
[0045] See also Figure 1 , which shows the first object of the present invention, a flow chart of a method for anesthesia puncture positioning based on visual assistance, the method comprising the following steps:
[0046] Step S001: Continuously acquire multiple ultrasound images at the same position of the patient and grayscale the images to obtain each grayscale image.
[0047] Traditional ultrasonic image denoising is performed based on a single ultrasonic image. If the processing is performed only based on a single ultrasonic image, the imaging quality of the ultrasonic image is easily affected by multiple factors such as equipment performance, individual differences among patients, operating skills, and external environment, resulting in uneven image quality, which in turn affects the denoising effect of the ultrasonic image. Therefore, this step requires the acquisition of multiple ultrasonic images to improve the accuracy of ultrasonic image denoising, and a preset time interval M is required for acquiring ultrasonic images at fixed time intervals, and a preset number of acquired ultrasonic images N is required. In this embodiment, the preset time interval M=0.02s, and the preset number of acquired ultrasonic images N=10. The preset time interval M and the preset number of acquired ultrasonic images N in other embodiments depend on the specific implementation.
[0048] Specifically, multiple ultrasound images are continuously collected at the same position of the patient and the images are grayed to obtain each gray image. The specific method is as follows:
[0049] Using an ultrasound imaging device and a probe thereof, continuous ultrasound image acquisition is performed at the same position of the patient. During the acquisition process, parameters such as the position, angle and depth of the probe are kept consistent. A series of ultrasound images at the same anatomical position are acquired. The time interval for acquiring the ultrasound images is a preset time interval M, and the number of acquired ultrasound images is a preset number N of acquired ultrasound images.
[0050] All acquired ultrasound images are grayed out, and the grayed ultrasound images are traversed in the time sequence of acquiring the ultrasound images, and each grayed ultrasound image after the traversal is used as each grayscale image.
[0051] In one embodiment of the present invention, a method for acquiring a grayscale image is provided, which specifically includes: when the grayscale images are traversed according to the time sequence of acquiring ultrasound images, the image obtained after the first acquired ultrasound image is grayscaled is used as the first grayscale image, the image obtained after the second acquired ultrasound image is grayscaled is used as the second grayscale image, and so on.
[0052] Step S002: Obtain the weight parameter of each pixel in each filtering window according to the grayscale distribution characteristics of the pixels in each filtering window of each grayscale image; obtain the weight coefficient of each pixel in each filtering window according to the difference in grayscale values of the pixels at the same position in the filtering windows at the same position in all grayscale images; obtain the weight factor of each pixel in each filtering window according to the change trend of the grayscale values of the pixels at the same position in the filtering windows at the same position in all grayscale images; obtain the weight of each pixel in each filtering window according to the weight parameter, weight coefficient and weight factor of each pixel in each filtering window.
[0053] It should be noted that the traditional ultrasound image denoising method used for anesthesia puncture positioning is the weighted mean filtering method, which has a good denoising effect on speckle noise and random noise in ultrasound images. However, due to the influence of noise and imaging characteristics, the similarity measurement may not be accurate enough, resulting in unreasonable weight distribution. When the contrast between fine structures such as nerves and blood vessels in ultrasound images and surrounding tissues is low, they may be regarded as similar areas and over-smoothed, resulting in the doctor's inability to accurately observe the nerve tissue and blood vessels, affecting the effect of nerve block.
[0054] It should be further explained that, in general, the grayscale values of noise points in ultrasound images are significantly different from those of normal tissues, and the grayscale value distribution of pixels in fine structures such as nerves and vascular tissues has a certain regularity and trend. Therefore, this step needs to make a preliminary distinction between noise pixels and tissue area pixels in the filter window based on the grayscale distribution characteristics of the pixels in the filter window of the weighted mean filter. Because all pixels in the filter window need to be considered, this step needs to traverse each pixel in each filter window. This embodiment uses a serpentine scanning method to traverse each pixel in each filter window in each grayscale image. In other embodiments, the pixel points in the filter window are traversed. The method depends on the specific implementation situation, and it is necessary to ensure that the traversal method of the pixels in all the filter windows is the same; the size of the filter window determines the smoothness of the ultrasound image, so the size of the filter window is not limited in this embodiment, but it is necessary to ensure that the filter windows of all grayscale images are the same, and it is also necessary to ensure that the scanning order of the filter windows in the grayscale image is the same; all the filter windows in the grayscale image are traversed in the scanning order of the filter windows. In this embodiment, the side length of the filter window is discussed with n=7 pixels, and the scanning order of the filter window is discussed from left to right and from top to bottom. In other embodiments, the side length of the filter window and the scanning order of the filter window depend on the specific implementation situation.
[0055] Specifically, according to the grayscale distribution characteristics of the pixels in each filtering window of each grayscale image, the weight parameter of each pixel in each filtering window is obtained. The specific method is as follows:
[0056]
[0057] In the formula, Represents the weight parameter of the cth pixel in the xth filter window of the zth grayscale image, Represents the grayscale value of the i-th pixel in the x-th filter window of the z-th grayscale image, Represents the grayscale value of the cth pixel in the xth filter window of the zth grayscale image, Indicates the discrete degree of the grayscale values of all pixels in the row of the c-th pixel in the x-th filter window of the z-th grayscale image, Indicates the discrete degree of the grayscale values of all pixels in the column where the cth pixel in the xth filter window of the zth grayscale image is located in the filter window; this method is used to obtain the weight parameter of each pixel in each filter window.
[0058] It should be noted that the denominator is increased by one to avoid the situation where the denominator is zero. The larger the value, the gray value of the cth pixel in the xth filter window of the zth gray image is different from the gray values of other pixels in the same filter window. The greater the probability that the pixel is noise. To avoid the influence of noise on the denoising effect of weighted mean filtering, the smaller the weight of the pixel, the smaller the weight parameter. The smaller it is, the smaller the difference between the grayscale value distribution of all pixels in the row where the c-th pixel in the x-th filter window of the z-th grayscale image is located in the filter window and the grayscale value distribution of all pixels in the column where the c-th pixel in the x-th filter window of the z-th grayscale image is located in the filter window is, the greater the probability that the pixel is noise, the smaller the weight of the pixel, and the smaller the weight parameter, because the distribution of neural tissue and vascular tissue is mostly linear and mesh-like, and the noise distribution is generally random and uniform. Therefore, the greater the difference in the grayscale distribution of rows and columns of a pixel, the greater the probability that the pixel is a small tissue, and a larger weight should be given in the weighted mean filtering denoising process to retain the details of the small tissue as much as possible.
[0059] It should be further explained that, in some cases, noise and tissue structure may show similar characteristics in the image, and the presence of noise may interfere with the accurate identification and analysis of tissue structure, while the dynamic changes of tissue structure may also mask the characteristics of noise. This mutual influence further increases the difficulty of judgment, and the imaging quality of ultrasound images is easily affected by multiple factors such as equipment performance, individual differences of patients, operating skills and external environment, resulting in uneven image quality, which in turn affects the noise reduction effect of ultrasound images; therefore, it is difficult to accurately distinguish between noise and tissue structure with only a single image, and it is impossible to better retain small tissues with severe noise during the noise reduction process, and noise with a similar distribution of pixel grayscale values to that of small structures may be misjudged as small structures.
[0060] Specifically, according to the gray value difference of the pixel at the same position in the filter window of all gray images, the weight coefficient of each pixel in each filter window is obtained. The specific method is as follows:
[0061]
[0062] In the formula, represents the weight coefficient of the cth pixel in the xth filter window in the zth grayscale image, n represents the side length of the filter window, represents the gray value of the cth pixel in the xth filter window in the jth gray image, represents the gray value of the cth pixel in the xth filter window in the Jth gray image, Represents the grayscale value of the cth pixel in the xth filter window in the Ith grayscale image, and uses the above method to obtain the weight coefficient of each pixel in each filter window.
[0063] It should be noted that, since the acquisition of ultrasound images is continuous, and the parameters and image acquisition position remain unchanged during the acquisition process, each ultrasound image is a schematic diagram of the same body position and depth of the patient; the filter windows of the grayscale images are the same and the traversal method is the same, so the filter windows of the same sequence in different grayscale images correspond to the same body position of the patient; the pixel points in the filter windows are traversed in the same way, so the pixel points of the same sequence in the filter windows of the same sequence in different grayscale images correspond to the same body position of the patient; Indicates the discrete degree of the grayscale values of all pixels corresponding to the position of the cth pixel in the xth filter window in the zth grayscale image, in the filter window of the same sequence in all grayscale images; if The larger the value is, the greater the fluctuation of the grayscale value of the pixel at that position in all ultrasound images is, which means that there are more noise pixels among all the pixels at that position, and the pixel at that position should be given a smaller weight, and the weight coefficient of the pixel is smaller; because the pixel value changes of normal tissues not affected by noise in ultrasound images are relatively small; and In order to limit the range of the weight coefficient, the final range of the weight coefficient is 0 to 1, and the standard deviation is dimensionless.
[0064] It should be further explained that there may be some pixels at the edge of fine tissues. Because breathing causes the fine tissues to shift or blood flow causes the grayscale values of pixels to change, the calculated weights of these pixels may be smaller. However, these pixels contain edge information of fine tissues and should be given greater weights to retain this edge information.
[0065] Specifically, according to the change trend of the grayscale value of the pixel at the same position in the filtering window at the same position in all grayscale images, the weight factor of each pixel in each filtering window is obtained. The specific method is as follows:
[0066]
[0067] In the formula, represents the weight factor of the cth pixel in the xth filter window in the zth grayscale image, represents the gray value of the cth pixel in the xth filter window in the kth gray image, represents the gray value of the cth pixel in the xth filter window in the k+1th gray image, N represents the number of gray images, and the weight factor of each pixel in each filter window is obtained according to this method.
[0068] It should be noted that the pixel fluctuations at the edge of normal tissue or fine tissue change with breathing, blood, and muscle contraction. The grayscale change trend of these pixels is smoother than that of noise pixels. Therefore, when the grayscale change of pixels at a certain position in the continuously collected ultrasound images is smoother, The smaller it is, the smaller the probability that the change of the pixel at this position is affected by noise. It may be normal contraction or displacement of human tissue, and should be given a larger weight. The larger the weight factor of the pixel at this position.
[0069] It should be further explained that the above method obtains the weight parameters, weight coefficients and weight factors for each pixel point in each filtering window. This step needs to obtain the weight of each pixel point in each filtering window based on the weight parameters, weight coefficients and weight factors of each pixel point in each filtering window.
[0070] Specifically, according to the weight parameter, weight coefficient and weight factor of each pixel in each filtering window, the weight of each pixel in each filtering window is obtained. The specific method is as follows:
[0071]
[0072] In the formula, represents the weight of the cth pixel in the xth filter window in the zth grayscale image, Represents the weight parameter of the cth pixel in the xth filter window of the zth grayscale image, represents the weight coefficient of the cth pixel in the xth filter window in the zth grayscale image, represents the weight factor of the cth pixel in the xth filter window in the zth grayscale image, represents the weight parameter of the K-th pixel in the x-th filter window of the z-th grayscale image, represents the weight coefficient of the K-th pixel in the x-th filter window in the z-th grayscale image, Represents the weight factor of the K-th pixel in the x-th filter window in the z-th grayscale image; the weight of each pixel in each filter window is obtained according to the above method.
[0073] It should be noted that the smaller the weight parameter of a pixel point, the greater the probability that the pixel point is noise, and a smaller weight should be assigned to smooth the pixel point; the smaller the weight coefficient of a pixel point, the more likely it is that the pixels at the location of the pixel point in all ultrasound images are noise pixels, and a smaller weight should be assigned; the smaller the weight factor of a pixel point, the smaller the probability that the grayscale value change of all pixels at the location of the pixel point in all ultrasound images is normal contraction or displacement of human tissue, and a smaller weight should be assigned; therefore, within the filtering window, the smaller the weight parameter of a pixel point, the smaller the weight coefficient, and the smaller the weight factor, the smaller the weight of the pixel point.
[0074] Step S003: combining the weight of each pixel in each weighted mean filter window, using the weighted mean filter algorithm to reduce the noise of each grayscale image, and completing the anesthesia puncture based on the grayscale image after the noise reduction.
[0075] It should be noted that the above method obtains the weight of each pixel in each weighted mean filtering window, and the image needs to be denoised according to the weight of each pixel in the weighted mean filtering window.
[0076] Specifically, the weight of each pixel in each weighted mean filter window is combined, and the weighted mean filter algorithm is used to reduce the noise of each grayscale image, and the anesthesia puncture is completed according to the grayscale image after noise reduction. The specific method is as follows:
[0077] Combined with the calculated weight of each pixel in each weighted mean filter window of each grayscale image, the weighted mean filter algorithm is used to reduce the noise of each grayscale image to obtain a series of clearer grayscale images. The user completes the anesthesia puncture based on the information in the grayscale image.
[0078] See also Figure 2 , which shows the second object of the present invention, a structural block diagram of a visually assisted anesthesia puncture positioning system, the system includes the following modules:
[0079] An image acquisition module, used for continuously acquiring multiple ultrasound images at the same position of the patient and graying the images to obtain each grayscale image;
[0080] The parameter calculation module is used to obtain the weight parameter of each pixel in each filtering window according to the grayscale distribution characteristics of the pixels in each filtering window of each grayscale image; obtain the weight coefficient of each pixel in each filtering window according to the difference in the grayscale values of the pixels at the same position in the filtering windows at the same position in all grayscale images; obtain the weight factor of each pixel in each filtering window according to the change trend of the grayscale values of the pixels at the same position in the filtering windows at the same position in all grayscale images; obtain the weight of each pixel in each filtering window according to the weight parameter, weight coefficient and weight factor of each pixel in each filtering window;
[0081] The image processing module is used to combine the weight of each pixel in each weighted mean filter window, use the weighted mean filter algorithm to reduce the noise of each grayscale image, and complete the anesthesia puncture based on the grayscale image after noise reduction.
[0082] The third object of an embodiment of the present invention is to provide a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned visually-assisted anesthesia puncture positioning method when executing the computer program.
[0083] The fourth objective of an embodiment of the present invention is to provide 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, the steps of the above-mentioned visual-assisted anesthesia puncture positioning method are implemented.
[0084] In this embodiment, multiple ultrasound images are continuously collected at the same position of the patient and the images are grayed to prevent the ultrasound images from being affected by various factors such as equipment performance, individual differences of patients, operation skills, and external environment, resulting in uneven image quality and affecting the noise reduction effect;
[0085] According to the grayscale distribution characteristics of the pixels in each filtering window of each grayscale image, the weight parameter of each pixel in each filtering window is obtained; considering the grayscale distribution characteristics of the pixels in the filtering window, the noise points and the fine tissue pixels are preliminarily judged according to the grayscale distribution characteristics of the fine structures in the ultrasound image;
[0086] According to the gray value difference of the pixel at the same position in the filter window of all gray images, the weight coefficient of each pixel in each filter window is obtained; the dynamic change of the pixel of the body structure is taken into account, and the pixel can be more accurately distinguished as noise or fine tissue through the dynamic change;
[0087] According to the change trend of the grayscale value of the pixel at the same position in the filter window at the same position in all grayscale images, the weight factor of each pixel in each filter window is obtained; the pixel at the edge of the fine tissue is taken into account to avoid the pixel at the edge of the fine tissue being smoothed by the weighted mean filter algorithm due to dynamic fluctuations similar to noise;
[0088] According to the weight parameter, weight coefficient and weight factor of each pixel point in each filter window, the weight of each pixel point in each filter window is obtained; after comprehensive consideration, a more accurate weight of the pixel point in the filter window can be obtained;
[0089] Combined with the weight of each pixel in each weighted mean filter window, the weighted mean filter algorithm is used to reduce the noise of each grayscale image, and anesthesia puncture is completed based on the grayscale image after noise reduction. Using this method to reduce the noise of the image can give smaller weights to pixels with a higher noise probability, and give larger weights to small tissues, edges, and normal tissues. While enhancing the noise reduction effect, the detailed information in the ultrasound image is retained, avoiding errors caused by equipment or imaging rules to a certain extent, making the judgment of the anesthesia puncture position more accurate.
[0090] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0091] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0092] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0093] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0094] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.
Claims
1. A computer-readable storage medium storing a computer program, It is characterized in that When the computer program is executed by a processor, the steps of a visually assisted anesthesia puncture positioning method are implemented, and the method comprises the following steps: Continuously acquiring a plurality of ultrasound images at the same position of the patient and gray-scaling the images to obtain each gray-scale image; The method of continuously acquiring multiple ultrasound images at the same position of the patient and graying the images to obtain each grayscale image includes: Using an ultrasound imaging device and a probe thereof, continuous ultrasound image acquisition is performed at the same position of the patient. During the acquisition process, the position, angle and depth parameters of the probe are kept consistent. A series of ultrasound images at the same anatomical position are acquired. The time interval for acquiring the ultrasound images is a preset time interval M, and the number of acquired ultrasound images is a preset number N of acquired ultrasound images. Grayscale all acquired ultrasound images, and traverse the grayscale ultrasound images according to the time sequence of acquiring the ultrasound images, and use each grayscale ultrasound image after traversal as each grayscale image; According to the grayscale distribution characteristics of the pixels in each filtering window of each grayscale image, a weight parameter of each pixel in each filtering window is obtained; The specific method of obtaining the weight parameter of each pixel in each filtering window according to the grayscale distribution characteristics of the pixel points in each filtering window of each grayscale image includes: In the formula, Represents the weight parameter of the cth pixel in the xth filter window of the zth grayscale image, Represents the grayscale value of the i-th pixel in the x-th filter window of the z-th grayscale image, Represents the grayscale value of the cth pixel in the xth filter window of the zth grayscale image, Indicates the discrete degree of the grayscale values of all pixels in the row of the c-th pixel in the x-th filter window of the z-th grayscale image, Indicates the discrete degree of the grayscale values of all pixels in the column where the c-th pixel in the x-th filter window of the z-th grayscale image is located in the filter window; this method is used to obtain the weight parameter of each pixel in each filter window; According to the gray value difference of the pixel at the same position in the filter window at the same position of all gray images, the weight coefficient of each pixel in each filter window is obtained; The specific method of obtaining the weight coefficient of each pixel in each filtering window according to the grayscale value difference of the pixel at the same position in the filtering window at the same position of all grayscale images is as follows: In the formula, represents the weight coefficient of the cth pixel in the xth filter window in the zth grayscale image, n represents the side length of the filter window, represents the gray value of the cth pixel in the xth filter window in the jth gray image, represents the gray value of the cth pixel in the xth filter window in the Jth gray image, Represents the gray value of the cth pixel in the xth filter window in the Ith gray image, and uses the above method to obtain the weight coefficient of each pixel in each filter window; According to the change trend of the grayscale value of the pixel at the same position in the filtering window at the same position in all grayscale images, the weight factor of each pixel in each filtering window is obtained; The specific method of obtaining the weight factor of each pixel in each filtering window according to the change trend of the grayscale value of the pixel at the same position in the filtering window at the same position in all grayscale images includes: In the formula, represents the weight factor of the cth pixel in the xth filter window in the zth grayscale image, represents the gray value of the cth pixel in the xth filter window in the kth gray image, represents the gray value of the cth pixel in the xth filter window in the k+1th gray image, N represents the number of gray images, and the weight factor of each pixel in each filter window is obtained according to this method; Obtain the weight of each pixel in each filtering window according to the weight parameter, weight coefficient and weight factor of each pixel in each filtering window; The specific method of obtaining the weight of each pixel in each filtering window according to the weight parameter, weight coefficient and weight factor of each pixel in each filtering window is as follows: In the formula, represents the weight of the cth pixel in the xth filter window in the zth grayscale image, Represents the weight parameter of the cth pixel in the xth filter window of the zth grayscale image, represents the weight coefficient of the cth pixel in the xth filter window in the zth grayscale image, represents the weight factor of the cth pixel in the xth filter window in the zth grayscale image, represents the weight parameter of the K-th pixel in the x-th filter window of the z-th grayscale image, represents the weight coefficient of the K-th pixel in the x-th filter window in the z-th grayscale image, Represents the weight factor of the K-th pixel in the x-th filter window in the z-th grayscale image; obtain the weight of each pixel in each filter window according to the above method; Combining the weight of each pixel in each weighted mean filter window, the weighted mean filter algorithm is used to reduce the noise of each grayscale image, and anesthesia puncture is completed based on the grayscale image after noise reduction; The method of combining the weight of each pixel in each weighted mean filter window, using the weighted mean filter algorithm to reduce the noise of each grayscale image, and completing the anesthesia puncture according to the grayscale image after the noise reduction includes the following specific methods: Combined with the calculated weight of each pixel in each weighted mean filter window of each grayscale image, the weighted mean filter algorithm is used to reduce the noise of each grayscale image to obtain a series of clearer grayscale images. The user completes the anesthesia puncture based on the information in the grayscale image.
2. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, a method for positioning anesthesia puncture based on visual assistance is implemented, and the method comprises the following steps: Continuously acquiring a plurality of ultrasound images at the same position of the patient and gray-scaling the images to obtain each gray-scale image; The method of continuously acquiring multiple ultrasound images at the same position of the patient and graying the images to obtain each grayscale image includes: Using an ultrasound imaging device and a probe thereof, continuous ultrasound image acquisition is performed at the same position of the patient. During the acquisition process, the position, angle and depth parameters of the probe are kept consistent. A series of ultrasound images at the same anatomical position are acquired. The time interval for acquiring the ultrasound images is a preset time interval M, and the number of acquired ultrasound images is a preset number N of acquired ultrasound images. Grayscale all acquired ultrasound images, and traverse the grayscale ultrasound images according to the time sequence of acquiring the ultrasound images, and use each grayscale ultrasound image after traversal as each grayscale image; According to the grayscale distribution characteristics of the pixels in each filtering window of each grayscale image, a weight parameter of each pixel in each filtering window is obtained; The specific method of obtaining the weight parameter of each pixel in each filtering window according to the grayscale distribution characteristics of the pixel points in each filtering window of each grayscale image includes: In the formula, Represents the weight parameter of the cth pixel in the xth filter window of the zth grayscale image, Represents the grayscale value of the i-th pixel in the x-th filter window of the z-th grayscale image, Represents the grayscale value of the cth pixel in the xth filter window of the zth grayscale image, Indicates the discrete degree of the grayscale values of all pixels in the row of the c-th pixel in the x-th filter window of the z-th grayscale image, Indicates the discrete degree of the grayscale values of all pixels in the column where the c-th pixel in the x-th filter window of the z-th grayscale image is located in the filter window; this method is used to obtain the weight parameter of each pixel in each filter window; According to the gray value difference of the pixel at the same position in the filter window at the same position of all gray images, the weight coefficient of each pixel in each filter window is obtained; The specific method of obtaining the weight coefficient of each pixel in each filtering window according to the grayscale value difference of the pixel at the same position in the filtering window at the same position of all grayscale images is as follows: In the formula, represents the weight coefficient of the cth pixel in the xth filter window in the zth grayscale image, n represents the side length of the filter window, represents the gray value of the cth pixel in the xth filter window in the jth gray image, represents the gray value of the cth pixel in the xth filter window in the Jth gray image, Represents the gray value of the cth pixel in the xth filter window in the Ith gray image, and uses the above method to obtain the weight coefficient of each pixel in each filter window; According to the change trend of the grayscale value of the pixel at the same position in the filtering window at the same position in all grayscale images, the weight factor of each pixel in each filtering window is obtained; The specific method of obtaining the weight factor of each pixel in each filtering window according to the change trend of the grayscale value of the pixel at the same position in the filtering window at the same position in all grayscale images includes: In the formula, represents the weight factor of the cth pixel in the xth filter window in the zth grayscale image, represents the gray value of the cth pixel in the xth filter window in the kth gray image, represents the gray value of the cth pixel in the xth filter window in the k+1th gray image, N represents the number of gray images, and the weight factor of each pixel in each filter window is obtained according to this method; Obtain the weight of each pixel in each filtering window according to the weight parameter, weight coefficient and weight factor of each pixel in each filtering window; The specific method of obtaining the weight of each pixel in each filtering window according to the weight parameter, weight coefficient and weight factor of each pixel in each filtering window is as follows: In the formula, represents the weight of the cth pixel in the xth filter window in the zth grayscale image, Represents the weight parameter of the cth pixel in the xth filter window of the zth grayscale image, represents the weight coefficient of the cth pixel in the xth filter window in the zth grayscale image, represents the weight factor of the cth pixel in the xth filter window in the zth grayscale image, represents the weight parameter of the K-th pixel in the x-th filter window of the z-th grayscale image, represents the weight coefficient of the K-th pixel in the x-th filter window in the z-th grayscale image, Represents the weight factor of the K-th pixel in the x-th filter window in the z-th grayscale image; obtain the weight of each pixel in each filter window according to the above method; Combining the weight of each pixel in each weighted mean filter window, the weighted mean filter algorithm is used to reduce the noise of each grayscale image, and anesthesia puncture is completed based on the grayscale image after noise reduction; The method of combining the weight of each pixel in each weighted mean filter window, using the weighted mean filter algorithm to reduce the noise of each grayscale image, and completing the anesthesia puncture according to the grayscale image after the noise reduction includes the following specific methods: Combined with the calculated weight of each pixel in each weighted mean filter window of each grayscale image, the weighted mean filter algorithm is used to reduce the noise of each grayscale image to obtain a series of clearer grayscale images. The user completes the anesthesia puncture based on the information in the grayscale image.
3. A visually assisted anesthesia puncture positioning system, It is characterized in that The system includes the following modules: An image acquisition module, used for continuously acquiring multiple ultrasound images at the same position of the patient and graying the images to obtain each grayscale image; The method of continuously acquiring multiple ultrasound images at the same position of the patient and graying the images to obtain each grayscale image includes: Using an ultrasound imaging device and a probe thereof, continuous ultrasound image acquisition is performed at the same position of the patient. During the acquisition process, the position, angle and depth parameters of the probe are kept consistent. A series of ultrasound images at the same anatomical position are acquired. The time interval for acquiring the ultrasound images is a preset time interval M, and the number of acquired ultrasound images is a preset number N of acquired ultrasound images. Grayscale all acquired ultrasound images, and traverse the grayscale ultrasound images according to the time sequence of acquiring the ultrasound images, and use each grayscale ultrasound image after traversal as each grayscale image; A parameter calculation module is used to obtain a weight parameter of each pixel in each filtering window according to the grayscale distribution characteristics of the pixels in each filtering window of each grayscale image; The specific method of obtaining the weight parameter of each pixel in each filtering window according to the grayscale distribution characteristics of the pixel points in each filtering window of each grayscale image includes: In the formula, Represents the weight parameter of the cth pixel in the xth filter window of the zth grayscale image, Represents the grayscale value of the i-th pixel in the x-th filter window of the z-th grayscale image, Represents the grayscale value of the cth pixel in the xth filter window of the zth grayscale image, Indicates the discrete degree of the grayscale values of all pixels in the row of the c-th pixel in the x-th filter window of the z-th grayscale image, Indicates the discrete degree of the grayscale values of all pixels in the column where the c-th pixel in the x-th filter window of the z-th grayscale image is located in the filter window; this method is used to obtain the weight parameter of each pixel in each filter window; According to the gray value difference of the pixel at the same position in the filter window at the same position of all gray images, the weight coefficient of each pixel in each filter window is obtained; The specific method of obtaining the weight coefficient of each pixel in each filtering window according to the grayscale value difference of the pixel at the same position in the filtering window at the same position of all grayscale images is as follows: In the formula, represents the weight coefficient of the cth pixel in the xth filter window in the zth grayscale image, n represents the side length of the filter window, represents the gray value of the cth pixel in the xth filter window in the jth gray image, represents the gray value of the cth pixel in the xth filter window in the Jth gray image, Represents the gray value of the cth pixel in the xth filter window in the Ith gray image, and uses the above method to obtain the weight coefficient of each pixel in each filter window; According to the change trend of the grayscale value of the pixel at the same position in the filtering window at the same position in all grayscale images, the weight factor of each pixel in each filtering window is obtained; The specific method of obtaining the weight factor of each pixel in each filtering window according to the change trend of the grayscale value of the pixel at the same position in the filtering window at the same position in all grayscale images includes: In the formula, represents the weight factor of the cth pixel in the xth filter window in the zth grayscale image, represents the gray value of the cth pixel in the xth filter window in the kth gray image, represents the gray value of the cth pixel in the xth filter window in the k+1th gray image, N represents the number of gray images, and the weight factor of each pixel in each filter window is obtained according to this method; Obtain the weight of each pixel in each filtering window according to the weight parameter, weight coefficient and weight factor of each pixel in each filtering window; The specific method of obtaining the weight of each pixel in each filtering window according to the weight parameter, weight coefficient and weight factor of each pixel in each filtering window is as follows: In the formula, represents the weight of the cth pixel in the xth filter window in the zth grayscale image, Represents the weight parameter of the cth pixel in the xth filter window of the zth grayscale image, represents the weight coefficient of the cth pixel in the xth filter window in the zth grayscale image, represents the weight factor of the cth pixel in the xth filter window in the zth grayscale image, represents the weight parameter of the K-th pixel in the x-th filter window of the z-th grayscale image, represents the weight coefficient of the K-th pixel in the x-th filter window in the z-th grayscale image, Represents the weight factor of the K-th pixel in the x-th filter window in the z-th grayscale image; obtain the weight of each pixel in each filter window according to the above method; An image processing module is used to combine the weight of each pixel in each weighted mean filter window, use a weighted mean filter algorithm to reduce the noise of each grayscale image, and complete anesthesia puncture based on the grayscale image after noise reduction; The method of combining the weight of each pixel in each weighted mean filter window, using the weighted mean filter algorithm to reduce the noise of each grayscale image, and completing the anesthesia puncture according to the grayscale image after the noise reduction includes the following specific methods: Combined with the calculated weight of each pixel in each weighted mean filter window of each grayscale image, the weighted mean filter algorithm is used to reduce the noise of each grayscale image to obtain a series of clearer grayscale images. The user completes the anesthesia puncture based on the information in the grayscale image.
