Ultrasonic image enhancement method and system, ultrasonic equipment and storage medium

By filtering and Radon transforming ultrasound images, combined with image fusion technology, the problem of unclear visualization of puncture needles was solved, achieving efficient and accurate puncture imaging.

CN118941477APending Publication Date: 2024-11-12SONOSCAPE MEDICAL CORP
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310513724.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-08
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

In existing ultrasound image enhancement methods, the puncture needle is not clearly visible, which affects the doctor's confidence and the effectiveness of the puncture. Methods based on image segmentation and machine learning have poor accuracy and stability, and are computationally intensive and difficult to guarantee in real time.

Method used

By acquiring the baseline ultrasound image and deflection ultrasound image of the puncture needle, two sets of filters are used for lateral and longitudinal filtering respectively to determine the target area of ​​the puncture needle. Based on this area, the baseline ultrasound image is enhanced, including Radon transform and image fusion.

Benefits of technology

It achieves clear and accurate puncture imaging, with simple image processing logic and low computational load, thus improving puncture imaging efficiency and user experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118941477A_ABST
    Figure CN118941477A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides an ultrasonic image enhancement method and system, ultrasonic equipment and a storage medium. The method comprises the steps that a basic ultrasonic image and a deflection ultrasonic image of a puncture needle are obtained, wherein the deflection ultrasonic image is obtained in a deflection scanning mode relative to the puncture needle; two groups of filters are respectively used for filtering the deflection ultrasonic image to obtain two filtered images, and each group of filters comprises a transverse filter and a longitudinal filter; determining a target area of the puncture needle in the deflection ultrasonic image based on the pixel value of each pixel in the two filtered images; based on the target area, image enhancement processing is conducted on the basic ultrasonic image to obtain an enhanced ultrasonic image, the pixel value of each pixel in the enhanced area of the enhanced ultrasonic image is larger than the pixel value of the pixel at the corresponding position in the basic ultrasonic image, and the enhanced area is the area corresponding to the position of the target area. According to the scheme, clear and accurate puncture imaging can be realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of biomedical imaging technology, and in particular, to an ultrasonic image enhancement method, an ultrasonic image enhancement system, an ultrasonic device and a storage medium. Background Art

[0002] In recent years, various types of biomedical imaging technologies, such as X-ray, computer-assisted tomography (CT), and ultrasound, have been widely used in the auxiliary diagnosis and treatment of human diseases. For example, during the puncture of the patient's lesion, ultrasound imaging technology can present an ultrasound image of the puncture needle, which allows doctors to intuitively view the position and trajectory of the puncture needle.

[0003] In conventional ultrasonic puncture examinations, due to the mirror reflection of the puncture needle on the ultrasonic wave, the puncture needle is not clearly visible in the basic B-mode ultrasonic image obtained during the examination. The doctor cannot clearly and accurately know the position of the puncture needle from the image, which may affect the doctor's confidence in the puncture and the puncture effect.

[0004] In some existing ultrasound image enhancement solutions, puncture needle visualization is enhanced based on image segmentation. This solution has poor accuracy and stability. In other solutions, ultrasound image enhancement is achieved based on machine learning methods. This solution not only requires additional data labeling and training tasks, but also has a large amount of calculation and is difficult to ensure real-time performance. Summary of the invention

[0005] In order to at least partially solve the problems existing in the prior art, according to a first aspect of the present application, a method for enhancing an ultrasonic image is provided, comprising:

[0006] Acquire a basic ultrasound image and a deflected ultrasound image of the puncture needle, wherein the deflected ultrasound image is obtained by using a deflected scanning method relative to the puncture needle;

[0007] filtering the deflected ultrasound image using two sets of filters respectively to obtain two filtered images, wherein each set of filters includes a transverse filter and a longitudinal filter;

[0008] determining a target area of ​​the puncture needle in the deflected ultrasound image based on the pixel value of each pixel in the two filtered images; and

[0009] Based on the target area, image enhancement processing is performed on the basic ultrasound image to obtain an enhanced ultrasound image, wherein the pixel value of each pixel in the enhanced area of ​​the enhanced ultrasound image is greater than the pixel value of the pixel at the corresponding position in the basic ultrasound image, and the enhanced area is the area corresponding to the position of the target area.

[0010] Exemplarily, the deflected ultrasound image is filtered using two sets of filters respectively to obtain two filtered images, including:

[0011] For each set of filters,

[0012] filtering the deflected ultrasonic image using a transverse filter and a longitudinal filter respectively to obtain a transverse filtered image and a longitudinal filtered image;

[0013] Normalizing each pixel of the horizontally filtered image and the vertically filtered image to obtain a first normalized image and a second normalized image; and

[0014] A filtered image is determined based on pixel values ​​of pixels in the first normalized image and the second normalized image, wherein the pixel value of each pixel in the filtered image is equal to the product of pixel values ​​of pixels at corresponding positions of the first normalized image and the second normalized image.

[0015] Exemplarily, the lateral filter is represented as the product of multiple functions of the horizontal coordinate values ​​of the pixel, and the longitudinal filter is represented as the product of multiple functions of the vertical coordinate values ​​of the pixel. The functions of the lateral filters in different groups of filters are expressed the same but with opposite signs, and the functions of the longitudinal filters in different groups of filters are expressed the same but with opposite signs.

[0016] Exemplarily, the transverse filter and the longitudinal filter in the two groups of filters are respectively expressed by the following formulas:

[0017]

[0018]

[0019] Where x and y represent the horizontal and vertical coordinates of the pixel in the deflected ultrasound image, respectively. h1 and f v1 Respectively represent the filter functions of the transverse filter and the longitudinal filter in the first group of filters, f h2 and f v2 They respectively represent the filter functions of the transverse filter and the longitudinal filter in the second group of filters, and σ0, σ1, σ2, and σ3 all represent constants.

[0020] Exemplarily, determining a target area of ​​the puncture needle in the deflected ultrasound image based on the pixel value of each pixel in the two filtered images includes:

[0021] Performing Radon transform on the two filtered images respectively to obtain two Radon images;

[0022] Determine a first pixel in the Radon image based on the pixel values ​​of each pixel in each Radon image, wherein the pixel value of any first pixel is greater than the pixel value of any other pixel in the Radon image except the first pixel;

[0023] Determining a position of a second pixel in the filtered image corresponding to a first pixel in the Radon image; and

[0024] A target area of ​​the puncture needle in the deflected ultrasound image is determined according to the position of the second pixel in the filtered image.

[0025] Exemplarily, normalizing each pixel of the horizontally filtered image and the vertically filtered image respectively includes:

[0026] respectively setting pixel values ​​of negative pixels in the horizontally filtered image and the vertically filtered image to zero to obtain a first zero-set image and a second zero-set image; and

[0027] The pixel values ​​of the pixels in the first zero-set image and the second zero-set image are respectively subjected to maximum and minimum normalization processing to obtain a first normalized image and a second normalized image.

[0028] The two filtered images are subjected to Radon transform respectively to obtain two Radon images, including:

[0029] The pixels whose pixel values ​​in the two filtered images are greater than 0 are subjected to Radon transform to obtain two Radon images.

[0030] Exemplarily, the method further comprises:

[0031] Performing local binary pattern feature extraction on the two filtered images respectively to obtain a feature image of each filtered image; and

[0032] For each feature image of the filtered image, determining a valid feature region of the puncture needle in the feature image;

[0033] Determining a target area of ​​the puncture needle in the deflected ultrasound image according to a position of a second pixel in the filtered image includes:

[0034] Based on the position of the second pixel in the filtered image and the position of the effective feature area in the feature image, a target area of ​​the puncture needle in the deflected ultrasound image is determined.

[0035] Exemplarily, determining a target area of ​​the puncture needle in the deflected ultrasound image based on a position of a second pixel in the filtered image and a position of a valid feature area in the feature image includes:

[0036] For each filtered image, determining a region corresponding to a position of a second pixel in the filtered image as a first region;

[0037] For each filtered image, determining a second region in the filtered image based on a location of a valid feature region in a feature image of the filtered image;

[0038] determining an intersection of the first region and the second region in each filtered image as a needle edge region; and

[0039] Based on the needle edge region in each filtered image, a target region of the puncture needle in the deflected ultrasound image is determined.

[0040] Exemplarily, the method further comprises:

[0041] determining effective image areas of two filtered images based on an effective deflection angle of the puncture needle relative to an ultrasound probe for acquiring a deflected ultrasound image and an effective distance between a needle insertion position of the puncture needle and the ultrasound probe;

[0042] Perform Radon transform on the two filtered images respectively, including:

[0043] Perform a Radon transform on the valid image regions in the two filtered images.

[0044] Exemplarily, based on the target area, the basic ultrasound image is subjected to image enhancement processing, including:

[0045] Based on the target area, the basic ultrasound image and the deflected ultrasound image are fused to use the fused image as an enhanced ultrasound image, wherein the pixel values ​​of pixels at corresponding positions in the enhanced ultrasound image are determined based at least on the pixel values ​​of pixels in the target area.

[0046] Exemplarily, fusing the basic ultrasound image and the deflected ultrasound image includes:

[0047] Determining a mask image of the deflected ultrasound image based on the position of the target area, wherein pixel values ​​of pixels in an area of ​​the mask image corresponding to the position of the target area are greater than pixel values ​​of other pixels in the mask image;

[0048] transforming the deflected ultrasonic image using the mask image to obtain a transformed deflected ultrasonic image, wherein a pixel value of a pixel in the transformed deflected ultrasonic image is equal to a product of a pixel value of a pixel at a corresponding position in the mask image and a pixel value of a pixel at a corresponding position in the deflected ultrasonic image; and

[0049] The transformed deflected ultrasonic image and the basic ultrasonic image are fused to obtain an enhanced ultrasonic image.

[0050] Exemplarily, determining the mask image of the deflected ultrasound image includes determining a pixel value of a pixel in the mask image using the following formula:

[0051]

[0052] Where W(x,y) represents the pixel value of the pixel with coordinates (x,y) in the mask image, θ' represents the complementary angle between the straight line where the puncture needle represented by the target area is located and the x-axis, s' represents the distance between the straight line and the pixel with coordinates (0,0) in the mask image, and σ' represents a constant.

[0053] Exemplarily, the deflected ultrasonic image is obtained by using an ultrasonic phased array acoustic beam deflection scanning method.

[0054] According to another aspect of the present application, an ultrasound device is provided, comprising: an ultrasound probe, a processor and a memory, wherein the ultrasound probe is used to obtain a basic ultrasound image and a deflected ultrasound image of a puncture needle, wherein the deflected ultrasound image is obtained by using a deflected scanning method relative to the puncture needle; and computer program instructions are stored in the memory, and the computer program instructions are used by the processor to execute the above-mentioned ultrasound image enhancement method when the processor is running.

[0055] According to another aspect of the present application, a storage medium is provided, on which program instructions are stored, and the program instructions are used to execute the above-mentioned ultrasound image enhancement method when running.

[0056] According to the above scheme of the embodiment of the present application, two sets of filters are used to perform lateral filtering and longitudinal filtering on the additionally acquired deflected ultrasound image of the puncture needle, respectively, to obtain two filtered images. Then, based on the two filtered images, the target area of ​​the puncture needle in the deflected ultrasound image is determined. Finally, the enhanced processing of the puncture needle in the basic ultrasound image is achieved based on the target area. This scheme can not only achieve clear and accurate puncture imaging; at the same time, the image processing scheme of this scheme has simple execution logic, small amount of calculation, and small computing space consumption. Thereby, the efficiency of puncture imaging can be significantly improved, and the user experience is also good.

[0057] A series of simplified concepts are introduced in the invention content, which will be further described in detail in the detailed description. The content of this application does not mean to attempt to define the key features and essential technical features of the technical solution claimed for protection, nor does it mean to attempt to determine the scope of protection of the technical solution claimed for protection.

[0058] The advantages and features of the present application are described in detail below in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The following drawings of the present application are hereby used as part of the present application for understanding the present application. The drawings show the implementation methods of the present application and their descriptions, and are used to explain the principles of the present application. In the drawings,

[0060] Figure 1 A schematic flow chart showing an ultrasound image enhancement method according to an embodiment of the present application is shown;

[0061] Figure 2a A schematic diagram showing a basic ultrasound image according to an embodiment of the present application;

[0062] Figure 2b A schematic diagram showing a deflected ultrasound image according to an embodiment of the present application;

[0063] Figure 3a and Figure 3b Schematic diagrams respectively showing two filtered images according to one embodiment;

[0064] Figure 4 A schematic diagram showing a direct fusion image of two filtered images according to an embodiment of the present application;

[0065] Figure 5 A schematic diagram showing the principle of ultrasonic puncture according to an embodiment of the present application;

[0066] Figure 6 A schematic flow chart showing an ultrasound image enhancement method according to another embodiment of the present application;

[0067] Figure 7 A schematic block diagram showing an ultrasound image enhancement system according to an embodiment of the present application; and

[0068] Figure 8 A schematic block diagram of an ultrasound device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0069] In the following description, a large amount of details are provided so that the present application can be thoroughly understood. However, it will be appreciated by those skilled in the art that the following description only exemplarily illustrates the preferred embodiments of the present application, and the present application can be implemented without one or more such details. In addition, in order to avoid confusion with the present application, some technical features well known in the art are not described in detail.

[0070] In order to at least partially solve the above technical problems, according to one aspect of the present application, an ultrasonic image enhancement method is provided. The method processes different ultrasonic images obtained by ultrasonic detection to obtain an enhanced ultrasonic image that can accurately and clearly present the location of the puncture needle. The ultrasonic image enhancement method has high accuracy, small calculation amount, high processing efficiency and good real-time performance.

[0071] Figure 1 A schematic flow chart of an ultrasound image enhancement method 100 according to an embodiment of the present application is shown. As shown in the figure, the ultrasound image enhancement method 100 includes step S120, step S140, step S160 and step S180.

[0072] Step S120, acquiring a basic ultrasonic image and a deflected ultrasonic image of the puncture needle, wherein the deflected ultrasonic image is obtained by using a linear array deflection scanning method.

[0073] According to the embodiment of the present application, any suitable ultrasonic device can be used to obtain a basic ultrasonic image and a deflected ultrasonic image of the puncture needle, for example, during a puncture performed by a doctor using a puncture needle. It is understandable that these two images can be different images collected at the same time using the same ultrasonic device. The ultrasonic probe of the ultrasonic device can transmit and receive ultrasonic waves and perform electroacoustic signal conversion under the control of the ultrasonic host. The processor in the ultrasonic host can process the ultrasonic signals reflected from the tissue organs and the puncture needle, respectively generate a basic ultrasonic image and a deflected ultrasonic image of the puncture needle, and display them on the display of the ultrasonic host for the doctor to view. Specifically, when the ultrasonic probe transmits ultrasonic waves of a suitable frequency, it can transmit ultrasonic waves from two different angles in an ultrasonic emission plane. The processor can extract and process the ultrasonic signals of each angle reflected from the tissue organs and the puncture needle, respectively, to obtain a basic ultrasonic image and a deflected ultrasonic image of the puncture needle, respectively. The basic ultrasonic image and the deflected ultrasonic image can be any suitable size, suitable resolution, two-dimensional or three-dimensional black and white image, grayscale image or RGB image.

[0074] The basic ultrasound image can be an ultrasound image obtained by any suitable conventional ultrasound imaging method that can clearly show the tissue status of the puncture site. It can be understood that in order to obtain a good quality basic ultrasound image of tissues and organs, ultrasound waves are usually emitted inward at an angle perpendicular to the human skin. The puncture needle also punctures from the skin surface to the inside of the body. Therefore, based on the conventional scanning method, the emission direction of the ultrasound wave is usually not perpendicular to the puncture needle, so that the ultrasound wave reaching the puncture needle cannot return along the original path, so the returned ultrasound energy is weak. From a macroscopic perspective, the puncture needle can be regarded as a line segment in a limited area, and the receiving area of ​​the ultrasound probe is also limited. Therefore, if the emission direction of the ultrasound wave is not perpendicular to the puncture needle, the ultrasound wave reflected back by the puncture needle may be very limited, so that the imaging of the puncture needle in the obtained basic ultrasound image is extremely unclear. Figure 2a FIG. 1 is a schematic diagram showing a basic ultrasound image according to an embodiment of the present application. Figure 2a As shown in FIG. 1 , in the basic ultrasound image obtained by conventional scanning, the pixel values ​​of the puncture needle and the surrounding tissues are not much different, and the puncture needle is not clearly visible. Therefore, it is necessary to find the position of the puncture needle through additional processing methods and clearly display the position in the image to facilitate the doctor's observation.

[0075] According to an embodiment of the present application, in step S120, in addition to obtaining a basic ultrasound image, a deflected ultrasound image of the puncture needle is also obtained. Exemplarily, the deflected ultrasound image of the puncture needle can be obtained by using any existing or future developed deflection scanning method, including but not limited to a linear array deflection scanning method, a convex array deflection scanning method, and a phased array deflection scanning method. Thus, the deflected ultrasound image can be obtained by scanning the ultrasound at an angle substantially perpendicular to the puncture needle. Specifically, the deflection scanning can be achieved by controlling the delay time of the probe array element emitting the sound beam. In one embodiment, the deflected ultrasound image can be obtained by using the sound beam deflection scanning method of the ultrasonic phased array. For example, the deflection of the array element sound beam can be controlled by a delay device so that the ultrasound beam is similar to reaching the puncture needle vertically from the virtual array element, thereby obtaining a deflected ultrasound image with a more obvious puncture needle development. Alternatively, the purpose of the above-mentioned sound beam deflection scanning can also be achieved by setting the arrangement of the virtual array elements. This method is relatively easy to implement and can quickly obtain a deflected ultrasound image with good quality.

[0076] It can be understood that ultrasonic deflection scanning focuses more on the imaging of the puncture needle. By controlling the ultrasonic probe to emit ultrasonic waves at an angle close to perpendicular to the puncture needle, the ultrasonic waves reaching the puncture needle can be effectively reflected back to the ultrasonic probe, thereby obtaining a deflected ultrasonic image including more puncture needle information. Figure 2b A schematic diagram of a deflected ultrasound image according to an embodiment of the present application is shown. It can be understood that due to the deflection setting of the ultrasound scanning angle relative to the puncture needle, the difference between the pixels of the puncture needle and the pixels of the surrounding tissue in the image is greater, which helps to quickly and accurately obtain the position information of the puncture needle in the image, thereby improving the efficiency and effect of the ultrasound image enhancement of the puncture needle.

[0077] Step S140: filtering the deflected ultrasonic image using two sets of filters respectively to obtain two filtered images, wherein each set of filters includes a transverse filter and a longitudinal filter.

[0078] For each set of filters, its transverse filter can be any suitable transverse filter, and its longitudinal filter can also be any suitable longitudinal filter. It can be understood that the transverse filter and the longitudinal filter can be used to extract the image features in the transverse and longitudinal directions. Therefore, by filtering the deflected ultrasound image by each set of filters, the edge features of the puncture needle can be clearly displayed in the obtained filtered image.

[0079] The filter operators of the transverse filter and the longitudinal filter can be linear filter operators or nonlinear filter operators. Exemplarily but not restrictively, the filter operators of each group of filters can be various discrete differential operators suitable for image edge detection. For example, the filter operators of the transverse filter and the longitudinal filter can be Sobel's transverse filter operator and longitudinal filter operator. Of course, the filter operators of the transverse filter and the longitudinal filter can also be other forms of filter operators, as long as the images that highlight the different edge features of the puncture needle can be obtained through these two groups of filters.

[0080] According to an embodiment of the present application, the filter operators in the two groups of filters used in this step may be the same or different. Optionally, the function expressions of the lateral filter operators in different groups of filters are the same but opposite in sign, and the function expressions of the longitudinal filter operators in different groups of filters are the same but opposite in sign. That is, in this scheme, the two groups of filters can use filter operators with only different signs to filter the deflected ultrasound images. The two filtered images obtained in this way can highlight the different edges of the puncture needle. For example, the two filtered images can respectively highlight the upper edge features and lower edge features of the puncture needle, or the left edge features and right edge features of the puncture needle. Alternatively, the function expressions of the lateral filter operators in different groups of filters may be different, and the function expressions of the longitudinal filter operators in different groups of filters may also be different. That is, different filter operators can be used to obtain images of the edge features of the puncture needle with different filtering effects.

[0081] In this step, for each set of filters, two filtered images of the same set obtained by filtering the deflected ultrasound image of the puncture needle using the transverse filter and the longitudinal filter respectively can be further processed to obtain a corresponding filtered image. For example, the two filtered images of the same set can be merged into one image as the filtered image by using a suitable fusion and denoising method.

[0082] Step S160, determining the target area of ​​the puncture needle in the deflected ultrasound image based on the pixel value of each pixel in the two filtered images.

[0083] As mentioned above, the edge features of the puncture needle can be identified in each filtered image. For example, in the filtered image, the pixel value of the pixel corresponding to the edge of the puncture needle is greater than the pixel values ​​of other surrounding pixels. Therefore, according to the pixel value of the pixel in each filtered image, various suitable target area determination logics can be used to determine the position area of ​​the puncture needle in the deflected ultrasound image as the target area. In one example, the pixel values ​​of each pixel in the two filtered images can be directly statistically analyzed, and the position area of ​​the puncture needle in the deflected ultrasound image can be determined according to the statistical analysis results. For example, the two filtered images are the upper edge feature map and the lower edge feature map of the puncture needle, respectively. The upper edge area and the lower edge area of ​​the puncture needle can be determined in the two filtered images, and the position corresponding area of ​​the two areas in the deflected ultrasound image can be found. Then, the middle area between the two position corresponding areas is determined as the target area of ​​the puncture needle. In another example, one or more image transformation processing methods can be used to process each filtered image separately to obtain a new processed image, and the target area of ​​the puncture needle in the deflected ultrasound image can be determined based on the pixel values ​​of the pixels in the new processed image. For example, Radon transform can be performed on each filtered image to obtain a Radon image, and the target area of ​​the puncture needle in the deflected ultrasound image can be determined based on the pixels whose pixel values ​​in the Radon image are greater than the first pixel value threshold or the pixels with the highest pixel value order. Alternatively, texture feature extraction such as grayscale co-occurrence matrix extraction and local binary feature extraction can be performed on each filtered image, and the target area of ​​the puncture needle in the deflected ultrasound image can be determined based on the feature extraction results. In other examples, two filtered images can also be merged to obtain a merged image. Then, a method similar to the above two examples can be used to determine the target area in the deflected ultrasound image based on the pixel values ​​of the pixels in the merged image.

[0084] Step S180, based on the target area, the basic ultrasound image is enhanced to obtain an enhanced ultrasound image, wherein the pixel value of each pixel in the enhanced area of ​​the enhanced ultrasound image is greater than the pixel value of the pixel at the corresponding position in the basic ultrasound image, and the enhanced area is the area corresponding to the position of the target area.

[0085] Through the above step S160, the position of the puncture needle in the deflected ultrasonic image can be located. It can be understood that there is a position correspondence between each pixel in the deflected ultrasonic image and each pixel in the basic ultrasonic image. Therefore, the target corresponding area where the puncture needle in the basic ultrasonic image is located can be determined according to the position correspondence of the pixels. Optionally, the pixels in the target corresponding area can be directly enhanced to obtain an enhanced ultrasonic image. For example, the corresponding pixels in the target corresponding area can be directly replaced with the pixels in the target area of ​​the deflected ultrasonic image, and the area formed by the replaced pixels is the enhanced area of ​​the puncture needle in the basic ultrasonic image. Alternatively, the pixel values ​​of the pixels in the target corresponding area can be increased by a fixed pixel value, such as increasing the pixel value of each pixel in the area by 20. Alternatively, the basic ultrasonic image and the deflected ultrasonic image can be fused, and the fused image can be used as an enhanced ultrasonic image. For example, the two images can be weighted fused. Specifically, the fusion weight of each pixel in the target area of ​​the deflected ultrasonic image is, for example, 1, and the fusion weight of other pixels outside the target area of ​​the deflected ultrasonic image can be set to 0; the fusion weight of all pixels in the basic ultrasonic image can be set to 1. Therefore, in the fused image, the pixel value of the pixel in the target area where the puncture needle is located is greater than the pixel value of the pixel at the corresponding position in the basic ultrasound image, and the puncture needle is enhanced.

[0086] According to the above scheme of the embodiment of the present application, two sets of filters are used to perform lateral filtering and longitudinal filtering on the additionally acquired deflected ultrasound image of the puncture needle, respectively, to obtain two filtered images. Then, based on the two filtered images, the target area of ​​the puncture needle in the deflected ultrasound image is determined. Finally, the enhanced processing of the puncture needle in the basic ultrasound image is achieved based on the target area. This scheme can not only achieve clear and accurate puncture imaging; at the same time, the image processing scheme of this scheme has simple execution logic, small amount of calculation, and small computing space consumption. Thereby, the efficiency of puncture imaging can be significantly improved, and the user experience is also good.

[0087] Exemplarily, step S140 filters the deflected ultrasound image using two groups of filters respectively, including: for each group of filters, executing steps S141 to S143.

[0088] Step S141, filtering the deflected ultrasonic image using a transverse filter and a longitudinal filter respectively to obtain a transverse filtered image and a longitudinal filtered image. For example, the deflected ultrasonic image can be filtered using a Sobel transverse filter operator and a longitudinal filter operator respectively, and the obtained transverse filtered image includes the left and right edge features of the puncture needle, and the obtained longitudinal filtered image includes the upper and lower edge features of the puncture needle.

[0089] Step S142, respectively normalize each pixel of the horizontally filtered image and the vertically filtered image to obtain a first normalized image and a second normalized image. Exemplarily and not restrictively, each pixel of the horizontally filtered image and the vertically filtered image may be subjected to a maximum and minimum normalization process. For example, the pixel value of each pixel in the image may be divided by a preset pixel value so that the pixel value of each pixel in the first normalized image and the second normalized image falls within the range of [0, 1]. In this example, for the case where there are negative pixel values ​​in the first normalized image and the second normalized image, the pixel value of the pixel with the negative pixel value may be converted to a value equal to or close to 0 by normalization. Optionally, the pixel value of the pixel with the negative pixel value may be directly set to 0, and the pixel values ​​of other pixels may be converted to a value greater than 0. Alternatively, the pixel value of the pixel with the negative pixel value may be converted to a value close to 0. For example, the pixel values ​​of these pixels may be converted to values ​​within the interval of (0, 0.1) by normalization, and the pixel values ​​of other pixels may be converted to values ​​greater than 0.1.

[0090] Step S143, based on the pixel values ​​of the pixels in the first normalized image and the second normalized image, determine the filtered image. The pixel value of each pixel in the filtered image is equal to the product of the pixel values ​​of the pixels at the corresponding positions of the first normalized image and the second normalized image. For example, the pixel value of the pixel at the pixel position (2, 3) in the first normalized image is 0.6, and the pixel value of the pixel at the pixel position (2, 3) in the second normalized image is 1, then the pixel value of the pixel at the pixel position (2, 3) in the filtered image generated by the two normalized images is 0.6.

[0091] In this scheme, the pixel values ​​of the horizontally filtered image and the vertically filtered image obtained by the same set of filters are normalized, and the two images can be unified under the same pixel standard. The two normalized images are multiplied pixel by pixel, and the filtered image obtained can accurately fuse the two images filtered in different directions. In this way, an effect similar to image convolution can be achieved through simple mathematical operations, and the image processing efficiency can be significantly improved on the basis of ensuring good image processing accuracy.

[0092] For example, in the above step S140, after obtaining the horizontally filtered image and the vertically filtered image by using step S141, it is also possible to first perform an image multiplication step similar to step S143, and then perform a pixel value normalization processing step similar to step S142. That is, the horizontally filtered image and the vertically filtered image can be firstly multiplied pixel by pixel to obtain a multiplied image, and then the pixel values ​​of each pixel in the multiplied image are normalized to obtain a filtered image. A person skilled in the art can understand the various implementation methods of this solution, which will not be described in detail here.

[0093] Exemplarily, the lateral filter is represented as the product of multiple functions of the horizontal coordinate values ​​of the pixel, and the longitudinal filter is represented as the product of multiple functions of the vertical coordinate values ​​of the pixel. The functions of the lateral filters in different groups of filters are expressed the same but with opposite signs, and the functions of the longitudinal filters in different groups of filters are expressed the same but with opposite signs.

[0094] For example, the operator of the transverse filter includes a function φ1(x) about the horizontal coordinate x of the pixel, and the operator of the longitudinal filter includes a function φ2(y) about the vertical coordinate y of the pixel. The two groups of filters include, for example, a first group of filters and a second group of filters. Among them, the operator of the transverse filter in the first group of filters is, for example, x*φ1(x), and the operator of the longitudinal filter is, for example, -y*φ2(y). The operator of the transverse filter in the second group of filters is, for example, -x*φ1(x), and the operator of the longitudinal filter is, for example, y*φ2(y). By using two groups of filters with the same function expression but opposite signs, the two filtered images obtained respectively can include two opposite edges of the puncture needle. Figure 3a and Figure 3b Schematic diagrams of two filtered images according to one embodiment are shown respectively. For example, Figure 3a The first filter pair of the two sets of filters is used Figure 2b The deflected ultrasound image shown is filtered to obtain the filtered image. Figure 3a As shown, the filtered image may be an edge image including the upper edge of the puncture needle. Figure 3b The second filter pair is used in the two sets of filters. Figure 2b The deflected ultrasound image shown is filtered to obtain the filtered image. Figure 3b As shown, the filtered image may be an edge image including the lower edge of the puncture needle. Figure 4 FIG. 1 is a schematic diagram showing a direct fusion image of two filtered images according to an embodiment of the present application. It can be understood that Figure 3a and Figure 3b The corresponding pixels of Figure 4 In the direct fusion image, the upper edge region and the lower edge region of the puncture needle are two separate regions. At the same time, it can also be determined that the axis of the puncture needle should be located between the two regions. Therefore, the target region of the puncture needle can be further determined between the two regions later.

[0095] The two sets of filters in the above scheme can accurately and effectively separate the edge areas of the puncture needle in two opposite directions through filtering, thereby conveniently and accurately determining the position of the puncture needle, thereby improving the accuracy of ultrasound image enhancement.

[0096] Exemplarily, the transverse filter and the longitudinal filter in the two groups of filters are respectively expressed by the following formulas:

[0097]

[0098]

[0099] Where x and y represent the horizontal and vertical coordinates of the pixel in the deflected ultrasound image, respectively. h1 and f v1 They represent the filter functions of the transverse filter and the longitudinal filter in the first filter group. h2 and f v2 Respectively represent the filter functions of the transverse filter and the longitudinal filter in the second group of filters. σ0, σ1, σ2, σ3 all represent constants. The values ​​of σ0, σ1, σ2, σ3 can be the same, for example, σ0 = σ2, σ1 = σ3. Alternatively, their values ​​can also be different, and appropriate values ​​can be set according to actual image processing requirements.

[0100] It can be understood that the operator of each filter can include the product of the independent variable and the Gaussian function of the independent variable. In the filtered image obtained by filtering through these two sets of filters, not only the edge areas of the puncture needle in two relative directions can be accurately and effectively separated, but also most of the non-needle body areas outside the puncture needle can be effectively excluded. That is, the accuracy and efficiency of the filtering are both high. Therefore, it is helpful to accurately determine the location area of ​​the puncture needle, thereby facilitating the improvement of the accuracy and efficiency of ultrasonic puncture enhancement.

[0101] Exemplarily, step S160 determines the target area of ​​the puncture needle in the deflected ultrasound image based on the pixel value of each pixel in the two filtered images, including steps S161 to S164.

[0102] Step S161, performing Radon transform on the two filtered images respectively to obtain two Radon images.

[0103] As mentioned above, the image of the puncture needle can be roughly regarded as a line segment. As for the Radon transform, each pixel in the image after the Radon transform can represent the corresponding straight line in the image before the Radon transform. Therefore, the Radon transform can be performed on the filtered image, and the position of the puncture needle can be determined based on the pixel values ​​of the pixels in the image after the Radon transform.

[0104] It can be understood that each pixel in the transformed Radon image (hereinafter referred to as Radon pixel for simplicity) corresponds to a straight line on the filtered image, and the pixels falling on the straight line can be called filtered pixels. That is, each Radon pixel corresponds to a filtered pixel. In addition, the pixel value of the Radon pixel is positively correlated with the corresponding filtered pixel. For example, the pixel value of the Radon pixel can be equal to the sum or mean of the pixel values ​​of the corresponding filtered pixels.

[0105] For example, a rectangular coordinate system can be established with the vertex of the upper left corner of the image as the origin, and the positions of the first row of pixels at the upper edge and the first column of pixels at the left edge of the image as the x-axis and y-axis, respectively. The two filtered images are respectively subjected to Radon transform using the following formula:

[0106]

[0107] Among them, θ represents the complementary angle between the straight line where the pixel point at the pixel position (x, y) is located and the x-axis, and s represents the distance between the straight line and the pixel point with coordinates (0, 0) in the image. represents the pixel value of the filtered pixel p0(x, y) at the coordinate (x, y) position on the filtered image p0, I p1 (x, y) represents the pixel value of the filtered pixel p1(x, y) at the coordinate (x, y) position on the filtered image p1, R0(s, θ) and R1(s, θ) represent the pixel values ​​of the Radon pixels corresponding to the filtered pixels p0(x, y) and p1(x, y), respectively, and δ() represents the impulse function. Using the above formula, the two filtered images can be quickly transformed into corresponding Radon images, and in this example, the pixel value of the Radon pixel is equal to the sum of the pixel values ​​of the corresponding filtered pixels.

[0108] Step S162, based on the pixel values ​​of each pixel in each Radon image, determine the first pixel in the Radon image, wherein the pixel value of any first pixel is greater than the pixel value of any other pixel in the Radon image except the first pixel.

[0109] Exemplarily, a pixel with the largest pixel value in the Radon image may be directly determined as the first pixel.

[0110] It can be understood that in the filtered image, the area where the edge of the puncture needle is located is usually an area with a larger pixel value, that is, a relatively bright area, but not necessarily the brightest area. Therefore, alternatively, each Radon pixel in the Radon image can be sorted according to the size of the pixel value, and the Radon pixel whose ranking falls in the first preset percentile can be determined as the first pixel. For example, the Radon pixel ranked in the top 20% can be determined as the first pixel. Of course, the Radon pixel whose pixel value is greater than the second pixel value threshold can also be determined as the first pixel. In other examples, the Radon pixel whose ranking falls in the first preset percentile and is within the valid image area can also be determined as the first pixel.

[0111] Step S163, determining the position of the second pixel in the filtered image corresponding to the first pixel in the Radon image.

[0112] Exemplarily, in this step, the position of the second pixel corresponding to the first pixel in the filtered image can be determined according to the formula s=x·cos(θ)+y·sin(θ). That is, the position coordinates of each determined first pixel can be substituted into the above formula to determine the position of the corresponding straight line in the filtered image, and the position (x, y) of each pixel included in the straight line is the position of the second pixel.

[0113] Step S164, determining the target area of ​​the puncture needle in the deflected ultrasound image according to the position of the second pixel in the filtered image.

[0114] In the aforementioned example of determining that the pixel with the largest pixel value in the Radon image is the first pixel, a straight line is determined in each filtered image. The area in the deflected ultrasonic image corresponding to the middle area between the two straight lines can be determined as the target area. It can be understood that according to the Radon transform, the θ value and the s value of the two straight lines can be determined. The θ value of the straight line in the middle of the two straight lines is the same as the θ value of the two straight lines. The average of the s values ​​of the two straight lines is calculated, which can be used as the s value of the straight line in the middle of the two straight lines. The target area in the deflected ultrasonic image can be determined based on the straight line in the middle.

[0115] Similarly, in the aforementioned example where a plurality of first pixels are determined in the Radon image, the target region in the deflected ultrasound image may also be determined based on the second pixels determined in each filtered image.

[0116] For example, the target area in the deflected ultrasound image may be determined directly according to the area formed by the second pixel in the filtered image, or the target area may be determined comprehensively according to the position of the second pixel in the filtered image and in combination with other image processing results.

[0117] In the above scheme, the target area of ​​the puncture needle in the deflected ultrasound image can be determined according to the pixels with the highest pixel values ​​in the Radon image. This scheme can effectively avoid the misselection and omission of the area where the puncture needle is located, so that the target area where the puncture needle is located can be accurately determined, and the efficiency and accuracy of image enhancement can be improved.

[0118] Exemplarily, step S142 performs normalization processing on each pixel of the horizontally filtered image and the vertically filtered image, respectively, and includes step S142a and step S142b.

[0119] Step S142a, respectively set the pixel values ​​of the negative pixels in the transverse filtered image and the longitudinal filtered image to zero, to obtain the first zeroed image and the second zeroed image. Step S142b, respectively perform maximum and minimum normalization processing on the pixel values ​​of the pixels in the first zeroed image and the second zeroed image, to obtain the first normalized image and the second normalized image. It can be understood that the pixel values ​​of the pixels in the transverse filtered image and the longitudinal filtered image may be negative values. These pixels are often some pixels outside the puncture needle body. For these pixels, their pixel values ​​can be first set to zero, and then the zeroed images can be normalized. This can avoid invalid calculations and improve the efficiency of image processing.

[0120] Step S161 performs Radon transform on the two filtered images respectively to obtain two Radon images, including: performing Radon transform on the pixels with pixel values ​​greater than 0 in the two filtered images to obtain two Radon images. It can be understood that in the filtered images, most of the pixels with pixel values ​​equal to 0 are not the pixels of the puncture needle. The Radon transform is to determine the target area where the puncture needle is located. Therefore, in the process of Radon transform, there is no need to transform these zero-value pixels. Therefore, in this scheme, the operation object of Radon transform is limited to the pixels with pixel values ​​greater than 0 in the filtered images.

[0121] In this way, while ensuring accurate determination of the target area of ​​the puncture needle, the amount of calculation can be further reduced and the speed of the Radon transform process and subsequent related image processing processes can be improved.

[0122] Exemplarily, the method 100 further includes step S144. In step S144, based on the effective deflection angle of the puncture needle relative to the ultrasound probe for acquiring the deflected ultrasound image and the effective distance between the needle insertion position of the puncture needle and the ultrasound probe, the effective image areas of the two filtered images are determined.

[0123] Step S161 performs Radon transform on the two filtered images respectively, including: performing Radon transform on the effective image areas in the two filtered images.

[0124] Figure 5A schematic diagram showing the principle of ultrasonic puncture according to an embodiment of the present application is shown. As shown in the figure, in order to ensure that the ultrasonic probe can effectively detect the puncture needle, the needle insertion position of the puncture needle and the deflection angle of the puncture needle relative to the ultrasonic probe can be parameter-restricted according to preset requirements. For example, the effective deflection angle α of the puncture needle relative to the ultrasonic probe can be parameter-restricted according to the hardware and software characteristics of the ultrasonic probe. Optionally, it can be limited to 10°≤α≤50°. The effective distance d between the needle insertion position of the puncture needle and the nearest side of the ultrasonic probe can also be limited, for example, 20mm≤d≤30mm. Thus, in step S144, the effective image area of ​​the two filtered images can be determined based on these restrictive parameters. That is, the image area in which the needle insertion position in the filtered image meets the range limited by the effective distance and the needle insertion angle meets the range limited by the effective deflection angle can be determined as the effective image area. Furthermore, in the process of Radon transformation, only the effective image area in the two filtered images is subjected to Radon transformation.

[0125] In this way, under the premise of ensuring accurate determination of the target area of ​​the puncture needle, redundant calculations can be further avoided, the amount of calculations can be reduced, and the calculation space can be saved, thereby further improving the speed of image processing.

[0126] It can be understood that, although the above description describes different restriction conditions of the operation object of Radon transform respectively: 1) pixels with pixel values ​​greater than 0 in the filtered image; 2) pixels in the effective image area in the filtered image. However, these two restriction conditions are not mutually exclusive and can coexist in one embodiment. That is, in this embodiment, Radon transform is performed only on pixels that meet the above two conditions. Thus, the image processing speed is accelerated to a greater extent, and the real-time performance of ultrasound image enhancement is ensured.

[0127] Exemplarily, the method 100 further includes step S151 and step S152. Step S151, performing local binary pattern (LBP) feature extraction on the two filtered images respectively to obtain a feature image of each filtered image. Step S152, for the feature image of each filtered image, determining the effective feature area of ​​the puncture needle in the feature image.

[0128] The LBP image detection operator can be used to detect the local texture direction in each filtered image. Specifically, each filtered image can be subjected to LBP feature extraction to obtain an LBP feature image, i.e., an LBP feature spectrum. It can be understood that in the LBP feature image of each filtered image, the pixel value of each pixel is equal to the LBP feature value of the pixel at that position in the filtered image, and the size of the LBP feature value reflects the distribution mode of each pixel within the neighborhood range centered on the pixel. As mentioned above, in order to ensure that the ultrasonic probe can effectively detect the puncture needle, the deflection angle α of the puncture needle relative to the ultrasonic probe can be parameter-restricted according to preset requirements, such as limiting 10°≤α≤50°. Then, in the acquired ultrasonic image of the puncture needle, the distribution of the pixels of the puncture needle must also conform to the restriction law of the deflection angle. Specifically, there are straight lines in the ultrasonic image whose distribution conforms to the above-mentioned angle restriction range. Therefore, the image area whose distribution of pixels within the neighborhood range conforms to the above-mentioned restriction law can be screened out according to the size of the LBP feature value of each pixel. For example, each filtered image is divided into 7*7 image blocks, and the LBP feature value of the central pixel in each image block is determined to obtain an LBP feature map. Then, according to the pixel value of the pixel in the LBP feature map, it can be judged whether the distribution of pixels (or texture direction) in each image block meets the preset requirements. For example, when the deflection angle of the puncture needle relative to the ultrasound probe is limited to the angle interval [10°, 50°], the LBP feature value of the pixel in the puncture needle area should fall within the preset pixel value interval [p1, p2]. Then, in step S152, the image area formed by the pixels whose pixel values ​​in the LBP feature map are within the preset pixel value interval [p1, p2] can be screened out as a valid feature area.

[0129] Step S163, determining the target area of ​​the puncture needle in the deflected ultrasound image according to the position of the second pixel in the filtered image, includes: determining the target area of ​​the puncture needle in the deflected ultrasound image based on the position of the second pixel in the filtered image and the position of the effective feature area in the feature image. In this step, the result of Radon transform and the result of LBP feature extraction can be combined to determine the target area in the deflected ultrasound image. Specifically, the area formed by the second pixel in the filtered image and the effective feature area determined by LBP feature extraction can be comprehensively considered, and a variety of appropriate area determination logics can be used to determine the target area where the puncture needle is located.

[0130] In this scheme, the LBP feature extraction method can be used to assist in determining the position of the puncture needle. Thus, the results of Radon transform and LBP feature extraction can be combined to accurately determine the target area where the puncture needle is located, effectively improving the accuracy of puncture needle detection, and thus improving the accuracy of ultrasound image enhancement.

[0131] Exemplarily, the step of determining the target area of ​​the puncture needle in the deflected ultrasound image based on the position of the second pixel in the filtered image and the position of the effective feature area in the feature image includes the following steps S163a to S163d.

[0132] Step S163a, for each filtered image, the area corresponding to the position of the second pixel in the filtered image is determined as the first area. That is, in each filtered image, each second pixel on the straight line corresponding to the first pixel in the Radon image is found, and the area formed by these pixels is determined as the first area. As mentioned above, the first pixel is a pixel with a larger pixel value in the Radon image. It can be understood that in this step, the area where the second pixel with a larger pixel value in the filtered image is located is determined as the first area, that is, the first area is an area with higher brightness in each filtered image. Thus, the brighter areas in the two filtered images are determined respectively. In particular, if the number of first pixels determined in the aforementioned step S162 is 1, the first area on each filtered image determined in this step is a straight line area. In this way, a first area can be found in each of the two filtered images based on the results of the Radon transform.

[0133] Step S163b, for each filtered image, based on the position of the effective feature region in the feature image of the filtered image, determine the second region in the filtered image. Find the region corresponding to the position of the effective feature region on its feature image determined in step S151 on each filtered image as the second region of the filtered image. In this way, in the two filtered images, the corresponding second region can be found according to the result of LBP feature extraction.

[0134] Step S163c, determining the intersection of the first region and the second region in each filtered image as the needle edge region. That is, for each filtered image, the region screening result of the Radon transform and the region screening result of the LBP feature extraction can be combined to determine a screening region that meets both requirements as the needle edge region in each filtered image. Figure 3a and Figure 3b , Figure 3a The filtered images in the figure respectively identify the approximate area including the upper edge of the puncture needle, Figure 3b The approximate area of ​​the lower edge of the puncture needle can be marked. In this step, the approximate area of ​​the lower edge of the puncture needle can be accurately determined. Figure 3a The upper edge area of ​​the puncture needle and Figure 3b For example, each needle edge region may correspond to a similar straight line region.

[0135] Step S163d, based on the needle edge regions in the two filtered images, determine the target region of the puncture needle in the deflected ultrasound image. Figure 4 After the needle edge regions of the upper edge and the lower edge of the puncture needle are determined by the two filtered images, the position corresponding regions of the two needle edge regions can be determined in the deflected ultrasound image. Optionally, the region between the two needle edge regions can be determined as the target region of the puncture needle. For example, the center straight line of the two needle edge regions can be determined as the axis of the puncture needle. Then, based on the distance between the two needle edge regions, the target region is determined with the axis as the center line.

[0136] In the above scheme, first, in each filtered image, the effective area of ​​the puncture needle determined by Radon transform and the effective area of ​​the puncture needle determined by LBP feature extraction are comprehensively used to determine the needle edge area on each filtered image. Then, the target area of ​​the puncture needle is determined based on the needle edge areas on the two filtered images. The target area determined by this method is more accurate, and the calculation logic is simple, the calculation amount is small, and the accuracy and efficiency of image processing are good. Therefore, the accuracy and real-time performance of ultrasonic image enhancement are guaranteed.

[0137] Exemplarily, step S180 performs image enhancement processing on the basic ultrasound image based on the target region, including step S181. In step S181, based on the target region, the basic ultrasound image and the deflected ultrasound image are fused to use the fused image as the enhanced ultrasound image. The pixel values ​​of the pixels at the corresponding positions in the enhanced ultrasound image are determined based at least on the pixel values ​​of the pixels in the target region.

[0138] Any suitable image fusion method can be used to fuse at least the pixels of the target area in the deflected ultrasonic image with the pixels of the corresponding position in the basic ultrasonic image to obtain an enhanced ultrasonic image. For example, a weighted fusion method or a maximum value-based fusion method can be used to achieve image fusion in this step. Taking the weighted fusion method as an example, the fusion weights of each pixel in the two ultrasonic images can be set as needed. Exemplarily, the fusion weights of the pixels in the target area in the deflected ultrasonic image can be set to 1, and the fusion weights of other pixels can be set to 0. The fusion weights of the pixels corresponding to the target area in the basic ultrasonic image can be set to any value between 0 and 1, and the fusion weights of other pixels can be set to 1.

[0139] In the above scheme, the basic ultrasound image can be enhanced quickly by the image fusion method. In the fused enhanced ultrasound image, not only the tissues and organs are displayed clearly, but also the enhanced display effect of the puncture needle is clear and realistic.

[0140] Exemplarily, step S181 fuses the basic ultrasound image and the deflected ultrasound image, including steps S181a to S181c.

[0141] Step S181a, based on the position of the target area, determine the mask image of the deflected ultrasonic image. The pixel values ​​of the pixels in the area corresponding to the position of the target area in the mask image are greater than the pixel values ​​of other pixels in the mask image. Step S181b, transform the deflected ultrasonic image using the mask image to obtain a transformed deflected ultrasonic image. The pixel value of the pixel in the transformed deflected ultrasonic image is equal to the product of the pixel value of the pixel at the corresponding position in the mask image and the pixel value of the pixel at the corresponding position in the deflected ultrasonic image. Step S181c, fuse the transformed deflected ultrasonic image and the basic ultrasonic image to obtain an enhanced ultrasonic image.

[0142] Exemplarily, step S181 may fuse the basic ultrasonic image and the deflected ultrasonic image according to the following fusion formula:

[0143] I 增强 (x, y) = Fusion(I 偏转 (x, y)*I 掩膜 (x,y),I 基础 (x, y)

[0144] Among them, I 增强 (x, y) represents the pixel in the fused enhanced ultrasound image, I 偏转 (x, y) represents the position corresponding to the pixel in the deflected ultrasound image, I 掩膜 (x, y) represents the position corresponding to the pixel in the mask image of the deflected ultrasound image, I 基础 (x, y) represents the position corresponding to the pixel in the base ultrasound image.

[0145] Exemplarily, the area in the mask image corresponding to the position of the target area can be referred to as the third area, and the other areas outside the third area on the mask image can be referred to as the fourth area. In a specific example, the pixel value of the pixel in the third area can be set to 1, and the pixel value of the pixel in the fourth area can be set to 0. Alternatively, the pixel value of the pixel in the third area can also be set to a fixed value between 0 and 1. The pixel values ​​of each pixel of the deflected ultrasonic image and its mask image can be multiplied point by point to obtain the transformed ultrasonic image. In the embodiment in which the pixel value of the pixel in the third area of ​​the mask image is set to 1 and the pixel value of the pixel in the fourth area is set to 0, the pixel value of the pixel in the target area of ​​the transformed deflected ultrasonic image remains unchanged, while the pixel value of the pixel in the non-target area is 0. In this example, the pixels in the non-target area of ​​the deflected ultrasonic image may not participate in the fusion. In this way, compared with the basic ultrasonic image, in the enhanced ultrasonic image, the pixel value of the area where the puncture needle is located is increased, so that it can be enhanced, and the other areas outside the puncture needle can be kept unchanged or brightened as a whole.

[0146] In the above scheme, the imaging effects of the tissue and the puncture needle in the enhanced ultrasound image can be better, and the transition of pixels in each area is more natural.

[0147] Exemplarily, in the above rectangular coordinate system, step S181a of determining the mask image of the deflected ultrasound image includes determining the pixel value of the pixel in the mask image using the following formula:

[0148]

[0149] Where W(x,y) represents the pixel value of the pixel with coordinates (x,y) in the mask image, θ' represents the complementary angle between the straight line where the puncture needle represented by the target area is located and the x-axis, s' represents the distance between the straight line and the pixel with coordinates (0,0) in the mask image, and σ' represents a constant.

[0150] Substituting the coordinates of each pixel in the mask image into the above formula, the pixel value of each pixel can be obtained. It can be understood that in the mask image, the pixel value of each pixel corresponding to the straight line position where the target area in the deflected ultrasound image is located is equal to 1, and as the distance between the pixel and the straight line increases, the pixel value of the pixel gradually decreases, and the value range is (0,1).

[0151] In the above scheme, the fusion weight of each pixel in the deflected ultrasonic image may also show a trend of gradually weakening from the center of the puncture needle area to the outside, so that the fusion effect of the deflected ultrasonic image and the basic ultrasonic image is more natural and the visual effect of image enhancement is better.

[0152] Figure 6 FIG. 2 is a schematic flow chart of an ultrasonic image enhancement method according to another embodiment of the present application. Figure 6As shown, in the process of the doctor using the puncture needle to puncture the tissue, the ultrasound device can be used to emit ultrasound from different angles to obtain the basic ultrasound image and the deflected ultrasound image of the puncture needle. For example, the ultrasound phased array technology can be used to control the sound beam of the probe array element to emit ultrasound at an angle substantially perpendicular to the puncture needle, thereby obtaining a deflected ultrasound image with more obvious imaging of the puncture needle. The obtained deflected ultrasound image is input into two groups of filters respectively to obtain two filtered images. Specifically, for each group of filters, the deflected ultrasound image can be filtered transversely and longitudinally respectively to obtain a transverse filtered image and a longitudinal filtered image. And the negative pixels in the transverse filtered image and the longitudinal filtered image are set to zero and then normalized to obtain a first normalized image and a second normalized image. Then, the first normalized image and the second normalized image are multiplied pixel by pixel to obtain a filtered image. Exemplarily, the transverse filter is expressed as the product of multiple functions of the horizontal coordinate values ​​of the pixels, and the longitudinal filter is expressed as the product of multiple functions of the vertical coordinate values ​​of the pixels. The functions of the transverse filters in different groups of filters are expressed in the same way but with opposite signs, and the functions of the longitudinal filters in different groups of filters are expressed in the same way but with opposite signs. Next, based on the effective deflection angle of the puncture needle relative to the ultrasound probe and the effective distance between the needle insertion position of the puncture needle and the ultrasound probe, the effective image areas of the two filtered images are determined. Based on the effective image area, the non-zero pixels of the two filtered images located in the effective image area are subjected to a restrictive Radon transform to obtain two Radon images. The pixel values ​​of all pixels of each Radon image are sorted according to size. The pixel with the highest pixel value in each Radon image is determined as the first pixel. In each filtered image, the second pixel corresponding to each first pixel is determined, and the area formed by these second pixels is determined as the first area. In addition, each filtered image is subjected to LBP image feature extraction to obtain a feature image, and the effective feature area in the feature image is determined according to the feature image. For example, according to the size of the LBP feature value of each pixel in the feature image, the image area whose distribution of pixels in the neighborhood range conforms to the effective deflection angle of the puncture needle is screened out. The area corresponding to the position of the effective feature area in each filtered image can be determined as the second area. For each filtered image, the needle edge area of ​​the puncture needle in the image is obtained by obtaining the intersection area of ​​the first area and the second area. Then, the position corresponding areas of the two needle edge areas can be determined in the deflected ultrasonic image, and the target area of ​​the puncture needle can be determined based on the two position corresponding areas. Furthermore, according to the position of the target area in the deflected ultrasonic image, the mask image of the deflected ultrasonic image is determined. In the mask image, the pixel value of the pixel corresponding to the pixel position of the target area is, for example, 1, and the pixel value of other pixels is, for example, 0. The mask image and the deflected ultrasonic image are multiplied pixel by pixel to obtain the transformed deflected ultrasonic image.Finally, the deflected ultrasound image and the basic ultrasound image are fused by a method such as weighted fusion to obtain an enhanced ultrasound image. In the enhanced ultrasound image, the pixel value of each pixel in the area corresponding to the target area is greater than the pixel value of the pixel at the corresponding position in the basic ultrasound image. Thus, on the one hand, the enhancement of the puncture needle in the ultrasound image is achieved at a faster speed; on the other hand, the ultrasound enhanced image not only clearly displays the tissues and organs, but also the puncture needle is more clearly and accurately displayed.

[0153] According to another aspect of the present application, an ultrasound image enhancement system is also provided. Figure 7 A schematic block diagram of an ultrasound image enhancement system 700 according to an embodiment of the present application is shown. As shown in the figure, the system 700 includes an acquisition module 710, a filtering module 720, a determination module 730 and a processing module 740.

[0154] The acquisition module 710 is used to acquire a basic ultrasonic image and a deflected ultrasonic image of the puncture needle, wherein the deflected ultrasonic image is obtained by using a deflected scanning method relative to the puncture needle.

[0155] The filtering module 720 is configured to filter the deflected ultrasound image using two sets of filters respectively to obtain two filtered images, wherein each set of filters includes a transverse filter and a longitudinal filter.

[0156] The determination module 730 is used to determine the target area of ​​the puncture needle in the deflected ultrasound image based on the pixel value of each pixel in the two filtered images.

[0157] The processing module 740 is used to perform image enhancement processing on the basic ultrasound image based on the target area to obtain an enhanced ultrasound image, wherein the pixel value of each pixel in the enhanced area of ​​the enhanced ultrasound image is greater than the pixel value of the pixel at the corresponding position in the basic ultrasound image, and the enhanced area is the area corresponding to the position of the target area.

[0158] Exemplarily, the filtering module 720 includes a filtering unit, a normalization unit, and an image determination unit. The filtering unit is used to filter the deflected ultrasound image using a transverse filter and a longitudinal filter for each set of filters, respectively, to obtain a transverse filtered image and a longitudinal filtered image. The normalization unit is used to normalize each pixel of the transverse filtered image and the longitudinal filtered image for each set of filters, respectively, to obtain a first normalized image and a second normalized image. The image determination unit is used to determine a filtered image for each set of filters based on the pixel values ​​of the pixels in the first normalized image and the second normalized image, wherein the pixel value of each pixel in the filtered image is equal to the product of the pixel values ​​of the pixels at the corresponding positions of the first normalized image and the second normalized image.

[0159] Exemplarily, the lateral filter utilized by the filtering unit is expressed as the product of multiple functions of the horizontal coordinate values ​​of the pixel, and the longitudinal filter is expressed as the product of multiple functions of the vertical coordinate values ​​of the pixel. The functions of the lateral filters in different groups of filters are expressed the same but with opposite signs, and the functions of the longitudinal filters in different groups of filters are expressed the same but with opposite signs.

[0160] Exemplarily, the transverse filter and the longitudinal filter in the two groups of filters used by the filtering unit are respectively expressed by the following formulas:

[0161]

[0162]

[0163] Where x and y represent the horizontal and vertical coordinates of the pixel in the deflected ultrasound image, respectively. h1 and f v1 Respectively represent the filter functions of the transverse filter and the longitudinal filter in the first group of filters, f h2 and f v2 They respectively represent the filter functions of the transverse filter and the longitudinal filter in the second group of filters, and σ0, σ1, σ2, and σ3 all represent constants.

[0164] Exemplarily, the determination module 730 includes a Radon transform unit, a Radon image processing unit, a position determination unit, and a target area determination unit. The Radon transform unit is used to perform Radon transform on the two filtered images respectively to obtain two Radon images. The Radon image processing unit is used to determine the first pixel in the Radon image based on the pixel value of each pixel in each Radon image, wherein the pixel value of any first pixel is greater than the pixel value of any other pixel other than the first pixel in the Radon image. The position determination unit is used to determine the position of the second pixel corresponding to the first pixel in the Radon image in the filtered image. The target area determination unit is used to determine the target area of ​​the puncture needle in the deflected ultrasound image according to the position of the second pixel in the filtered image.

[0165] Exemplarily, the normalization unit includes a first normalization subunit and a second normalization subunit. The first normalization subunit is used to set the pixel values ​​of negative pixels in the horizontally filtered image and the vertically filtered image to zero, respectively, to obtain a first zeroed image and a second zeroed image. The second normalization subunit is used to perform maximum and minimum normalization processing on the pixel values ​​of the pixels in the first zeroed image and the second zeroed image, respectively, to obtain a first normalized image and a second normalized image. The Radon transform unit is specifically used to perform Radon transform on pixels whose pixel values ​​in the two filtered images are greater than 0, to obtain two Radon images.

[0166] Exemplarily, the system 700 further includes a feature extraction module and a region determination module. The feature extraction module is used to perform local binary pattern feature extraction on the two filtered images respectively to obtain a feature image of each filtered image. The region determination module is used to determine the effective feature region of the puncture needle in the feature image for each filtered image. The target region determination unit is specifically used to determine the target region of the puncture needle in the deflected ultrasound image based on the position of the second pixel in the filtered image and the position of the effective feature region in the feature image.

[0167] Exemplarily, the target region determination unit includes a first region determination subunit, a second region determination subunit, a needle edge region determination subunit and a target region determination subunit. The first region determination subunit is used to determine, for each filtered image, a region corresponding to a position of a second pixel in the filtered image as a first region. The second region determination subunit is used to determine, for each filtered image, a second region in the filtered image based on a position of a valid feature region in a feature image of the filtered image. The needle edge region determination subunit is used to determine an intersection of the first region and the second region in each filtered image as a needle edge region. The target region determination subunit is used to determine a target region of the puncture needle in a deflected ultrasound image based on the needle edge region in each filtered image.

[0168] Exemplarily, the system 700 further includes an effective image area determination module, which is used to determine the effective image areas of the two filtered images based on the effective deflection angle of the puncture needle relative to the ultrasound probe used to obtain the deflected ultrasound image and the effective distance between the needle insertion position of the puncture needle and the ultrasound probe. The Radon transform unit is specifically used to perform Radon transform on the effective image areas in the two filtered images.

[0169] Exemplarily, the processing module 740 includes a first processing unit. The first processing unit is used to fuse the basic ultrasound image and the deflected ultrasound image based on the target area to use the fused image as the enhanced ultrasound image, wherein the pixel value of the pixel at the corresponding position in the enhanced ultrasound image is determined based on at least the pixel value of the pixel in the target area.

[0170] Exemplarily, the first processing unit includes a mask image determination subunit, an image transformation subunit, and a fusion subunit. The mask image determination subunit is used to determine the mask image of the deflected ultrasonic image based on the position of the target area, wherein the pixel value of the pixel in the area corresponding to the position of the target area in the mask image is greater than the pixel value of other pixels in the mask image. The image transformation subunit is used to transform the deflected ultrasonic image using the mask image to obtain a transformed deflected ultrasonic image, wherein the pixel value of the pixel in the transformed deflected ultrasonic image is equal to the product of the pixel value of the pixel at the corresponding position in the mask image and the pixel value of the pixel at the corresponding position in the deflected ultrasonic image. The fusion subunit is used to fuse the transformed deflected ultrasonic image with the basic ultrasonic image to obtain an enhanced ultrasonic image.

[0171] Exemplarily, the mask image determination subunit determines the pixel value of a pixel in the mask image using the following formula:

[0172]

[0173] Where W(x,y) represents the pixel value of the pixel with coordinates (x,y) in the mask image, θ' represents the complementary angle between the straight line where the puncture needle represented by the target area is located and the x-axis, s' represents the distance between the straight line and the pixel with coordinates (0,0) in the mask image, and σ' represents a constant.

[0174] Exemplarily, the deflected ultrasonic image is obtained by using an ultrasonic phased array acoustic beam deflection scanning method.

[0175] According to another aspect of the present application, an ultrasonic device is also provided. Figure 8 A schematic block diagram of an ultrasound device 800 according to an embodiment of the present application is shown. As shown in the figure, the ultrasound device 800 includes an ultrasound probe 810, a processor 820 and a memory 830. The ultrasound probe 810 is used to obtain a basic ultrasound image and a deflected ultrasound image of a puncture needle, wherein the deflected ultrasound image is obtained by using a deflection scanning method relative to the puncture needle. The memory 830 stores computer program instructions, which are used by the processor 820 to execute the above-mentioned ultrasound image enhancement method 100 when executed.

[0176] According to a fourth aspect of the present application, a storage medium is also provided. Program instructions are stored on the storage medium, and the program instructions are used to execute the above-mentioned ultrasound image enhancement method 100 when running. The storage medium may include, for example, an erasable programmable read-only memory (EPROM), a portable read-only memory (CD-ROM), a USB memory, or any combination of the above storage media. The storage medium may be any combination of one or more computer-readable storage media.

[0177] A person skilled in the art may understand the specific implementation scheme and beneficial effects of the ultrasonic image enhancement system, ultrasonic device and storage medium by reading the above description of the ultrasonic image enhancement method, which will not be described in detail here for the sake of brevity.

[0178] Although example embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above example embodiments are merely exemplary and are not intended to limit the scope of the present application to this. Those of ordinary skill in the art may make various changes and modifications therein without departing from the scope and spirit of the present application. All these changes and modifications are intended to be included within the scope of the present application as required by the appended claims.

[0179] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0180] Similarly, it should be understood that in order to streamline the present application and help understand one or more of the various inventive aspects, in the description of the exemplary embodiments of the present application, the various features of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. However, the method of the present application should not be interpreted as reflecting the following intention: the claimed application requires more features than the features clearly stated in each claim. More specifically, as reflected in the corresponding claims, the inventive point is that the corresponding technical problem can be solved with features less than all the features of a single disclosed embodiment. Therefore, the claims following the specific embodiment are hereby explicitly incorporated into the specific embodiment, wherein each claim itself serves as a separate embodiment of the present application.

[0181] It will be understood by those skilled in the art that, except for mutually exclusive features, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this specification may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature that provides the same, equivalent or similar purpose.

[0182] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present application and form different embodiments. For example, in the claims, any one of the claimed embodiments can be used in any combination.

[0183] It should be noted that the above embodiments illustrate the present application rather than limit the present application, and that those skilled in the art may design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets should not be constructed as a limitation to the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of multiple such elements. The present application may be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In a unit claim that lists several devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names.

[0184] The above is only a specific implementation or description of a specific implementation of the present application, and the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. The protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for enhancing an ultrasonic image, It is characterized in that include: Acquiring a basic ultrasonic image and a deflected ultrasonic image of the puncture needle, wherein the deflected ultrasonic image is obtained by using a deflected scanning method relative to the puncture needle; filtering the deflected ultrasound image using two sets of filters respectively to obtain two filtered images, wherein each set of filters includes a transverse filter and a longitudinal filter; determining a target area of ​​the puncture needle in the deflected ultrasound image based on a pixel value of each pixel in the two filtered images; as well as Based on the target area, image enhancement processing is performed on the basic ultrasonic image to obtain an enhanced ultrasonic image, wherein a pixel value of each pixel in an enhanced area of ​​the enhanced ultrasonic image is greater than a pixel value of a pixel at a corresponding position in the basic ultrasonic image, and the enhanced area is an area corresponding to the position of the target area.

2. The ultrasonic image enhancement method according to claim 1, It is characterized in that The filtering the deflected ultrasonic image using two sets of filters respectively to obtain two filtered images includes: For each set of filters, filtering the deflected ultrasonic image using a transverse filter and a longitudinal filter respectively to obtain a transverse filtered image and a longitudinal filtered image; Normalizing each pixel of the horizontally filtered image and the vertically filtered image to obtain a first normalized image and a second normalized image; and The filtered image is determined based on pixel values ​​of pixels in the first normalized image and the second normalized image, wherein the pixel value of each pixel in the filtered image is equal to the product of pixel values ​​of pixels at corresponding positions of the first normalized image and the second normalized image.

3. The ultrasonic image enhancement method according to claim 1 or 2, It is characterized in that The transverse filter is expressed as the product of multiple functions of the horizontal coordinate values ​​of the pixel, and the longitudinal filter is expressed as the product of multiple functions of the vertical coordinate values ​​of the pixel. The functions of the transverse filters in different groups of filters are expressed the same but with opposite signs, and the functions of the longitudinal filters in different groups of filters are expressed the same but with opposite signs.

4. The ultrasonic image enhancement method according to claim 3, It is characterized in that The transverse filter and the longitudinal filter in the two groups of filters are respectively expressed by the following formulas: Wherein, x and y represent the horizontal and vertical coordinates of the pixel in the deflected ultrasonic image, respectively, and f h1 and f v1 Respectively represent the filter functions of the transverse filter and the longitudinal filter in the first group of filters, f h2 and f v2 Respectively represent the filter functions of the transverse filter and the longitudinal filter in the second group of filters, σ 0 , σ 1 , σ 2 , σ 3 All represent constants.

5. The ultrasonic image enhancement method according to claim 1 or 2, It is characterized in that The step of determining a target area of ​​the puncture needle in the deflected ultrasound image based on the pixel value of each pixel in the two filtered images comprises: Performing Radon transform on the two filtered images respectively to obtain two Radon images; Determine a first pixel in each Radon image based on the pixel values ​​of each pixel in the Radon image, wherein the pixel value of any first pixel is greater than the pixel value of any other pixel in the Radon image except the first pixel; Determining a position of a second pixel in the filtered image corresponding to the first pixel in the Radon image; and A target area of ​​the puncture needle in the deflected ultrasound image is determined according to the position of the second pixel in the filtered image.

6. The ultrasonic image enhancement method according to claim 5 as recited in claim 2, It is characterized in that The normalizing of each pixel of the horizontally filtered image and the vertically filtered image respectively comprises: respectively setting pixel values ​​of negative pixels in the horizontally filtered image and the vertically filtered image to zero, to obtain a first zero-set image and a second zero-set image; and Respectively performing maximum and minimum normalization processing on the pixel values ​​of the pixels in the first zero-set image and the second zero-set image to obtain the first normalized image and the second normalized image, and respectively performing Radon transform on the two filtered images to obtain two Radon images, including: Performing Radon transform on pixels whose pixel values ​​are greater than 0 in the two filtered images to obtain the two Radon images.

7. The ultrasonic image enhancement method according to claim 5, It is characterized in that The method further comprises: Performing local binary pattern feature extraction on the two filtered images respectively to obtain a feature image of each filtered image; and For each feature image of the filtered image, determining a valid feature area of ​​the puncture needle in the feature image; Determining a target area of ​​the puncture needle in the deflected ultrasound image according to the position of the second pixel in the filtered image includes: A target area of ​​the puncture needle in the deflected ultrasound image is determined based on the position of the second pixel in the filtered image and the position of the effective feature area in the feature image.

8. The ultrasonic image enhancement method according to claim 7, It is characterized in that The determining the target area of ​​the puncture needle in the deflected ultrasound image based on the position of the second pixel in the filtered image and the position of the effective feature area in the feature image comprises: For each filtered image, determining a region corresponding to the position of the second pixel in the filtered image as a first region; For each filtered image, determining a second region in the filtered image based on a location of a valid feature region in a feature image of the filtered image; determining an intersection of the first region and the second region in each filtered image as a needle edge region; and Based on the needle edge region in each filtered image, a target region of the puncture needle in the deflected ultrasound image is determined.

9. The ultrasonic image enhancement method according to claim 5, It is characterized in that The method further comprises: determining effective image areas of the two filtered images based on an effective deflection angle of the puncture needle relative to an ultrasonic probe used to acquire the deflected ultrasonic image and an effective distance between a needle insertion position of the puncture needle and the ultrasonic probe; The performing Radon transform on the two filtered images respectively comprises: A Radon transform is performed on the valid image region in the two filtered images.

10. The ultrasonic image enhancement method according to claim 1 or 2, It is characterized in that The performing image enhancement processing on the basic ultrasound image based on the target area includes: Based on the target area, the basic ultrasonic image and the deflected ultrasonic image are fused to use the fused image as the enhanced ultrasonic image, wherein the pixel values ​​of the pixels at corresponding positions in the enhanced ultrasonic image are determined at least based on the pixel values ​​of the pixels in the target area.

11. The ultrasonic image enhancement method according to claim 10, It is characterized in that The fusing of the basic ultrasonic image and the deflected ultrasonic image comprises: determining a mask image of the deflected ultrasound image based on the position of the target area, wherein pixel values ​​of pixels in an area of ​​the mask image corresponding to the position of the target area are greater than pixel values ​​of other pixels in the mask image; transforming the deflected ultrasonic image using the mask image to obtain a transformed deflected ultrasonic image, wherein a pixel value of a pixel in the transformed deflected ultrasonic image is equal to a product of a pixel value of a pixel at a corresponding position in the mask image and a pixel value of a pixel at a corresponding position in the deflected ultrasonic image; and The transformed deflected ultrasonic image and the basic ultrasonic image are fused to obtain the enhanced ultrasonic image.

12. The ultrasonic image enhancement method according to claim 11, It is characterized in that Determining the mask image of the deflected ultrasound image includes determining the pixel value of a pixel in the mask image using the following formula: Wherein, W(x,y) represents the pixel value of the pixel point with coordinates (x,y) in the mask image, θ' represents the complementary angle between the straight line where the puncture needle represented by the target area is located and the x-axis, s' represents the distance between the straight line and the pixel point with coordinates (0,0) in the mask image, and σ' represents a constant.

13. The ultrasonic image enhancement method according to claim 1 or 2, It is characterized in that The deflected ultrasonic image is obtained by using an ultrasonic phased array sound beam deflection scanning method.

14. An ultrasound image enhancement system, It is characterized in that include: An acquisition module, used for acquiring a basic ultrasonic image and a deflected ultrasonic image of the puncture needle, wherein the deflected ultrasonic image is obtained by using a deflected scanning method relative to the puncture needle; A filtering module, configured to filter the deflected ultrasonic image using two sets of filters respectively to obtain two filtered images, wherein each set of filters includes a transverse filter and a longitudinal filter; a determination module, configured to determine a target area of ​​the puncture needle in the deflected ultrasound image based on a pixel value of each pixel in the two filtered images; as well as A processing module is used to perform image enhancement processing on the basic ultrasonic image based on the target area to obtain an enhanced ultrasonic image, wherein the pixel value of each pixel in the enhanced area of ​​the enhanced ultrasonic image is greater than the pixel value of the pixel at the corresponding position in the basic ultrasonic image, and the enhanced area is an area corresponding to the position of the target area.

15. An ultrasonic device, It is characterized in that include: Ultrasound probe, processor and memory, The ultrasonic probe is used to obtain a basic ultrasonic image and a deflected ultrasonic image of the puncture needle, wherein the deflected ultrasonic image is obtained by using a deflected scanning method relative to the puncture needle; The memory stores computer program instructions, which are used by the processor to execute the ultrasound image enhancement method according to any one of claims 1 to 13 when executed. 16 . A storage medium having program instructions stored thereon, wherein the program instructions are used to execute the ultrasound image enhancement method according to claim 1 when run.