Image processing method and system for puncture needle

By acquiring and processing ultrasound images in real time, and utilizing feature enhancement and neural network segmentation models, the problem of lack of real-time feedback in traditional puncture techniques is solved, enabling precise monitoring and adjustment of the puncture needle position, and improving the accuracy and convenience of puncture operations.

CN118587292BActive Publication Date: 2024-11-05THE FIRST AFFILIATED HOSPITAL OF MEDICAL COLLEGE OF XIAN JIAOTONG UNIV
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202411075357.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-07
Publication Date
2024-11-05
Estimated Expiration
2044-08-07

AI Technical Summary

Technical Problem

Traditional puncture techniques rely on the doctor's experience and lack real-time image or data feedback, making it difficult to guarantee the accuracy of the puncture needle placement and increasing the difficulty of the operation.

Method used

An ultrasound image acquisition module was used to acquire images of the surgical target area in real time during the operation. The position of the puncture needle tip was accurately extracted through feature enhancement and neural network image segmentation model. Wavelet denoising, edge detection and V-Net network optimization were used to train the model.

Benefits of technology

It enables real-time monitoring and adjustment of the needle tip position, improving the accuracy and convenience of puncture procedures.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118587292B_ABST
    Figure CN118587292B_ABST
Patent Text Reader

Abstract

The present invention provides an image processing method and system for a puncture needle, belonging to the field of image processing technology, wherein the method comprises: using an ultrasonic image acquisition module to acquire an ultrasonic image of a surgical target area including a puncture needle in real time during surgery; performing feature enhancement processing on the ultrasonic image to obtain an enhanced ultrasonic image; inputting the enhanced ultrasonic image as a sample into a neural network for training to obtain an image segmentation model; using the image segmentation model to extract the needle tip of the puncture needle; and determining the position of the needle tip of the puncture needle based on the pixel point where the needle tip of the puncture needle is located. The present invention can accurately extract the needle tip position of the puncture needle by using an ultrasonic image acquisition module to acquire an ultrasonic image of the surgical target area in real time during surgery, thereby enabling the doctor to monitor and adjust the position of the needle tip of the puncture needle in real time during the puncture process.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to an image processing method and system for a puncture needle. Background Art

[0002] Traditional puncture technology mainly relies on the doctor's experience and visual judgment to locate the target area and perform the puncture operation. This process is often affected by multiple factors, including but not limited to the variation of the patient's anatomical structure, the depth of the puncture site, the movement of the skin surface, and the doctor's personal skill level; the accuracy of the puncture needle's puncture position directly affects the success rate of the puncture operation. However, most existing puncture needles do not have real-time feedback functions and cannot provide instant image or data feedback during the puncture process, which increases the difficulty of the doctor's operation. Summary of the invention

[0003] To solve the above problems, the present invention aims to provide a puncture needle image processing method and system.

[0004] A puncture needle image processing method, comprising:

[0005] Step 1: Using the ultrasound image acquisition module to acquire ultrasound images of the surgical target area including the puncture needle in real time during the operation;

[0006] Step 2: performing feature enhancement processing on the ultrasonic image to obtain an enhanced ultrasonic image;

[0007] Step 3: Input the enhanced ultrasound image as a sample into the neural network for training to obtain an image segmentation model;

[0008] Step 4: extracting the needle tip of the puncture needle using the image segmentation model;

[0009] Step 5: Based on the pixel point where the puncture needle tip is located, determine the position of the puncture needle tip.

[0010] Preferably, the step 2: performing feature enhancement processing on the ultrasonic image to obtain an enhanced ultrasonic image comprises:

[0011] Step 2.1: using the adjustment coefficient and its corresponding denoising function to denoise the ultrasonic image to obtain an ultrasonic denoised image;

[0012] Step 2.2: Evaluate the ultrasonic denoised image to obtain an evaluation value;

[0013] Step 2.3: when the evaluation value is not within the preset range, the value of the adjustment coefficient is changed and the denoising function is used again to denoise the ultrasonic image until the evaluation value of the ultrasonic denoised image is within the preset range, thereby obtaining a denoised ultrasonic image;

[0014] Step 2.4: performing smoothing processing on the denoised ultrasonic image to obtain a smoothed ultrasonic image;

[0015] Step 2.5: Use an edge detection algorithm to perform feature enhancement processing on the smoothed ultrasound image to obtain an enhanced ultrasound image.

[0016] Preferably, the step 2.1: using the adjustment coefficient and its corresponding denoising function to denoise the ultrasonic image to obtain an ultrasonic denoised image comprises:

[0017] The ultrasonic image is decomposed using a wavelet basis function, and when the decomposed wavelet coefficient is greater than or equal to a threshold, the formula is used:

[0018]

[0019] Threshold processing is performed on the wavelet coefficients to obtain denoised wavelet coefficients; wherein, For the i wavelet coefficients, After denoising, i wavelet coefficients, is the adjustment coefficient, is the threshold value.

[0020] Preferably, in step 2.1, it also includes:

[0021] When the decomposed wavelet coefficients When , use the formula:

[0022]

[0023] Threshold processing is performed on the wavelet coefficients to obtain denoised wavelet coefficients; wherein, ,and , , , represents the median value, is the adjustment coefficient, represents the length of the ultrasound image, Indicates the width of the ultrasound image;

[0024] When the decomposed wavelet coefficients , the corresponding wavelet coefficients are set to 0.

[0025] Preferably, the step 2.2: evaluating the ultrasonic denoised image to obtain an evaluation value comprises:

[0026] The evaluation value of the corresponding ultrasonic denoised image is obtained based on the information difference between the ultrasonic denoised image and the original ultrasonic image; wherein the evaluation value calculation formula is:

[0027]

[0028] in, represents the information content of the ultrasonic denoised image, Represents the amount of information of the original ultrasound image, represents the pixel value of the i-th pixel, represents the probability and occurrence of all pixel gray levels on the ultrasonic denoised image, represents the pixel mean of the ultrasonic denoised image, Represents the probability and occurrence of all pixel gray levels on the original ultrasound image, Represents the pixel mean of the original ultrasound image.

[0029] Preferably, the step 2.4: performing smoothing processing on the denoised ultrasonic image to obtain a smoothed ultrasonic image comprises:

[0030] The maximum and minimum values ​​of the pixels on the denoised ultrasonic image are obtained, and the denoised ultrasonic image is smoothed based on the maximum and minimum values ​​to obtain a smoothed ultrasonic image; wherein the smoothing formula of the ultrasonic image is:

[0031]

[0032] in, represents the smoothed ultrasound image, represents the denoised ultrasound image, Indicates the minimum value of the pixel on the denoised ultrasound image. Indicates the maximum value of the pixel on the denoised ultrasound image. Represents the minimum value of the pixel on the smoothed ultrasound image, Indicates the maximum value of the pixel on the smoothed ultrasound image.

[0033] Preferably, the step 3: inputting the enhanced ultrasound image as a sample into a neural network for training to obtain an image segmentation model comprises:

[0034] Step 3.1: Input the enhanced ultrasound image as a sample into the V-Net network;

[0035] Step 3.2: Use the loss function to optimize the V-Net network and obtain the image segmentation model; the loss function in the training process is:

[0036]

[0037] in, represents the predicted probability of the V-Net network that the i-th pixel belongs to the puncture needle tip, represents the true label of the i-th pixel.

[0038] The present invention also provides an image processing system for a puncture needle, comprising:

[0039] Ultrasonic image acquisition module, used for real-time acquisition of ultrasonic images of the surgical target area including the puncture needle during the operation;

[0040] A feature enhancement module, used for performing feature enhancement processing on the ultrasonic image to obtain an enhanced ultrasonic image;

[0041] A training module, used for inputting the enhanced ultrasound image as a sample into a neural network for training to obtain an image segmentation model;

[0042] A needle extraction module, used to extract the needle of the puncture needle using the image segmentation model;

[0043] The needle positioning module is used to determine the position of the puncture needle tip based on the pixel point where the puncture needle tip is located.

[0044] The present invention also provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and wherein the computer program, when executed by the processor, implements the steps in the above-mentioned method for image processing of a puncture needle.

[0045] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps in the above-mentioned method for image processing of a puncture needle when executed by a processor.

[0046] The beneficial effect of the image processing method and system for a puncture needle provided by the present invention is that, compared with the prior art, the present invention can accurately extract the needle tip position of the puncture needle by utilizing an ultrasonic image acquisition module to acquire ultrasonic images of the surgical target area during surgery in real time, thereby enabling the doctor to monitor and adjust the position of the puncture needle tip in real time during the puncture process.

[0047] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0049] Figure 1 A flow chart of an image processing method for a puncture needle provided in an embodiment of the present invention is shown;

[0050] Figure 2 A schematic diagram of an image processing system for a puncture needle provided in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0051] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0052] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0053] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0054] See also Figure 1 , a puncture needle image processing method, comprising:

[0055] Step 1: Using the ultrasound image acquisition module to acquire ultrasound images of the surgical target area including the puncture needle in real time during the operation;

[0056] Step 2: performing feature enhancement processing on the ultrasonic image to obtain an enhanced ultrasonic image;

[0057] Furthermore, the step 2 comprises:

[0058] Step 2.1: using the adjustment coefficient and its corresponding denoising function to denoise the ultrasonic image to obtain an ultrasonic denoised image;

[0059] In step 2.1, the present invention uses a wavelet basis function to decompose the ultrasound image, and when the decomposed wavelet coefficient is greater than or equal to a threshold, the formula is used:

[0060]

[0061] Threshold processing is performed on the wavelet coefficients to obtain denoised wavelet coefficients; wherein, For the i wavelet coefficients, After denoising, i wavelet coefficients, is the adjustment coefficient, is the threshold value.

[0062] When the decomposed wavelet coefficients When , use the formula:

[0063]

[0064] Threshold processing is performed on the wavelet coefficients to obtain denoised wavelet coefficients; wherein, ,and , , , represents the median value, is the adjustment coefficient, which is an empirical coefficient and generally takes a value between 0 and 1. represents the length of the ultrasound image, Indicates the width of the ultrasound image;

[0065] When the decomposed wavelet coefficients , the corresponding wavelet coefficients are set to 0.

[0066] Step 2.2: Evaluate the ultrasonic denoised image to obtain an evaluation value;

[0067] In step 2.2, the present invention can use the information difference between the ultrasonic denoised image and the original ultrasonic image to obtain the evaluation value of the corresponding ultrasonic denoised image; the information difference can quantitatively represent the processing effect of the denoising algorithm on the image, and by comparing the information difference between the original ultrasonic image and the denoised image, the pros and cons of the denoising effect can be more specifically understood; wherein, the evaluation value calculation formula is:

[0068]

[0069] in, represents the information content of the ultrasonic denoised image, Represents the amount of information of the original ultrasound image, represents the pixel value of the i-th pixel, represents the probability and occurrence of all pixel gray levels on the ultrasonic denoised image, represents the pixel mean of the ultrasonic denoised image, Represents the probability and occurrence of all pixel gray levels on the original ultrasound image, Represents the pixel mean of the original ultrasound image.

[0070] The present invention repeatedly adjusts the coefficient value and re-performs the denoising process, and can determine the evaluation value based on the image information amount, so as to more accurately evaluate the denoising effect of the image, thereby making the final ultrasound image quality more ideal.

[0071] Step 2.3: when the evaluation value is not within the preset range, the value of the adjustment coefficient is changed and the denoising function is used again to denoise the ultrasonic image until the evaluation value of the ultrasonic denoised image is within the preset range, thereby obtaining a denoised ultrasonic image;

[0072] Step 2.4: performing smoothing processing on the denoised ultrasonic image to obtain a smoothed ultrasonic image;

[0073] Among them, step 2.4 includes:

[0074] The maximum and minimum values ​​of the pixels on the denoised ultrasonic image are obtained, and the denoised ultrasonic image is smoothed based on the maximum and minimum values ​​to obtain a smoothed ultrasonic image; wherein the smoothing formula of the ultrasonic image is:

[0075]

[0076] in, represents the smoothed ultrasound image, represents the denoised ultrasound image, Indicates the minimum value of the pixel on the denoised ultrasound image. Indicates the maximum value of the pixel on the denoised ultrasound image. Represents the minimum value of the pixel on the smoothed ultrasound image, Indicates the maximum value of the pixel on the smoothed ultrasound image.

[0077] The present invention can increase the contrast of the image by adjusting the range of the gray value of the ultrasonic image, so that the details in the image are more clearly visible.

[0078] Step 2.5: Use an edge detection algorithm to perform feature enhancement processing on the smoothed ultrasound image to obtain an enhanced ultrasound image.

[0079] Step 3: Input the enhanced ultrasound image as a sample into the neural network for training to obtain an image segmentation model;

[0080] Furthermore, the step 3 comprises:

[0081] Step 3.1: Input the enhanced ultrasound image as a sample into the V-Net network;

[0082] Step 3.2: Use the loss function to optimize the V-Net network and obtain the image segmentation model; the loss function in the training process is:

[0083]

[0084] in, represents the predicted probability of the V-Net network that the i-th pixel belongs to the puncture needle tip, represents the true label of the i-th pixel.

[0085] The present invention can not only reduce the influence of noise and other interference factors by enhancing ultrasonic images, but also improve the accuracy of image feature extraction and prediction by the V-Net network, thereby enhancing the robustness of the network.

[0086] Step 4: extracting the needle tip of the puncture needle using the image segmentation model;

[0087] Step 5: Based on the pixel point where the puncture needle tip is located, determine the position of the puncture needle tip.

[0088] The present invention uses an ultrasonic image acquisition module to acquire ultrasonic images of the surgical target area in real time during the operation, and can accurately extract the needle tip position of the puncture needle, so that the doctor can monitor and adjust the needle tip position of the puncture needle in real time during the puncture process.

[0089] See also Figure 2 The present invention also provides an image processing system for a puncture needle, comprising:

[0090] Ultrasonic image acquisition module, used for real-time acquisition of ultrasonic images of the surgical target area including the puncture needle during the operation;

[0091] A feature enhancement module, used for performing feature enhancement processing on the ultrasonic image to obtain an enhanced ultrasonic image;

[0092] A training module, used for inputting the enhanced ultrasound image as a sample into a neural network for training to obtain an image segmentation model;

[0093] A needle extraction module, used to extract the needle of the puncture needle using the image segmentation model;

[0094] The needle positioning module is used to determine the position of the puncture needle tip based on the pixel point where the puncture needle tip is located.

[0095] Compared with the prior art, the beneficial effects of the image processing system for a puncture needle provided by the present invention are the same as the beneficial effects of the image processing method for a puncture needle described in the above technical solution, and will not be described in detail here.

[0096] The present invention also provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and wherein the computer program, when executed by the processor, implements the steps in the above-mentioned method for processing an image of a puncture needle. Compared with the prior art, the beneficial effects of the electronic device provided by the present invention are the same as the beneficial effects of the method for processing an image of a puncture needle described in the above-mentioned technical solution, and are not described in detail herein.

[0097] The present invention also provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps in the above-mentioned method for processing an image of a puncture needle are implemented. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present invention are the same as the beneficial effects of the method for processing an image of a puncture needle described in the above-mentioned technical solution, and are not elaborated herein.

[0098] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technical solution that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for processing an image of a puncture needle, characterized in that: include: Step 1: Using the ultrasound image acquisition module to acquire ultrasound images of the surgical target area including the puncture needle in real time during the operation; Step 2: performing feature enhancement processing on the ultrasonic image to obtain an enhanced ultrasonic image; The step 2: performing feature enhancement processing on the ultrasonic image to obtain an enhanced ultrasonic image, comprises: Step 2.1: using the adjustment coefficient and its corresponding denoising function to denoise the ultrasonic image to obtain an ultrasonic denoised image; Step 2.2: Evaluate the ultrasonic denoised image to obtain an evaluation value; Step 2.3: when the evaluation value is not within the preset range, the value of the adjustment coefficient is changed and the denoising function is used again to denoise the ultrasonic image until the evaluation value of the ultrasonic denoised image is within the preset range, thereby obtaining a denoised ultrasonic image; Step 2.4: performing smoothing processing on the denoised ultrasonic image to obtain a smoothed ultrasonic image; Step 2.5: Use an edge detection algorithm to perform feature enhancement processing on the smoothed ultrasound image to obtain an enhanced ultrasound image; Step 3: Input the enhanced ultrasound image as a sample into the neural network for training to obtain an image segmentation model; Step 4: extracting the needle tip of the puncture needle using the image segmentation model; Step 5: Determine the position of the puncture needle tip based on the pixel point where the puncture needle tip is located; The step 2.1: using the adjustment coefficient and its corresponding denoising function to denoise the ultrasonic image to obtain an ultrasonic denoised image, comprises: The ultrasonic image is decomposed using a wavelet basis function, and when the decomposed wavelet coefficient is greater than or equal to a threshold, the formula is used: Threshold processing is performed on the wavelet coefficients to obtain denoised wavelet coefficients; wherein, w i is the i-th wavelet coefficient, is the i-th wavelet coefficient after denoising, k is the adjustment coefficient, and T is the threshold; When the decomposed wavelet coefficient T0≤|w i When |≤T, use the formula: Threshold processing is performed on the wavelet coefficients to obtain denoised wavelet coefficients; wherein T0=εT, and 0<ε<1, σ=median(|w|) / 0.6745, where median(·) represents the median value, d represents the adjustment coefficient, M represents the length of the ultrasound image, and N represents the width of the ultrasound image; When the decomposed wavelet coefficient |w i When |<T0, the corresponding wavelet coefficient is set to 0.

2. The image processing method for a puncture needle according to claim 1, characterized in that: The step 2.2: evaluating the ultrasonic denoised image to obtain an evaluation value, comprises: The evaluation value of the corresponding ultrasonic denoised image is obtained based on the information difference between the ultrasonic denoised image and the original ultrasonic image; wherein the evaluation value calculation formula is: Where Q represents the information content of the ultrasonic denoised image, P represents the information content of the original ultrasonic image, and f i represents the pixel value of the i-th pixel, h(q) represents the probability and total grayscale of all pixels on the ultrasonic denoised image, μ1(k) represents the pixel mean of the ultrasonic denoised image, h(p) represents the probability and total grayscale of all pixels on the original ultrasonic image, and μ2(k) represents the pixel mean of the original ultrasonic image.

3. The image processing method for a puncture needle according to claim 2, characterized in that: The step 2.4: performing smoothing processing on the denoised ultrasonic image to obtain a smoothed ultrasonic image, comprises: The maximum and minimum values ​​of the pixels on the denoised ultrasonic image are obtained, and the denoised ultrasonic image is smoothed based on the maximum and minimum values ​​to obtain a smoothed ultrasonic image; wherein the smoothing formula of the ultrasonic image is: Among them, g(x,y) represents the smoothed ultrasound image, f(x,y) represents the denoised ultrasound image, and f min represents the minimum value of the pixel on the denoised ultrasound image, f max Indicates the maximum value of the pixel on the denoised ultrasound image, g min represents the minimum value of the pixel on the smoothed ultrasound image, g max Indicates the maximum value of the pixel on the smoothed ultrasound image.

4. The image processing method for a puncture needle according to claim 3, characterized in that: The step 3: inputting the enhanced ultrasound image as a sample into a neural network for training to obtain an image segmentation model, including: Step 3.1: Input the enhanced ultrasound image as a sample into the V-Net network; Step 3.2: Use the loss function to optimize the V-Net network and obtain the image segmentation model; the loss function in the training process is: Among them, p i represents the predicted probability of the V-Net network that the i-th pixel belongs to the puncture needle, y i represents the true label of the i-th pixel.

5. A puncture needle image processing system, characterized in that: include: Ultrasonic image acquisition module, used for real-time acquisition of ultrasonic images of the surgical target area including the puncture needle during the operation; A feature enhancement module, used for performing feature enhancement processing on the ultrasonic image to obtain an enhanced ultrasonic image, comprising: Using the adjustment coefficient and its corresponding denoising function to denoise the ultrasonic image to obtain an ultrasonic denoised image includes: The ultrasonic image is decomposed using a wavelet basis function, and when the decomposed wavelet coefficient is greater than or equal to a threshold, the formula is used: Threshold processing is performed on the wavelet coefficients to obtain denoised wavelet coefficients; wherein, w i is the i-th wavelet coefficient, is the i-th wavelet coefficient after denoising, k is the adjustment coefficient, and T is the threshold; When the decomposed wavelet coefficient T0≤|w i When |≤T, use the formula: Threshold processing is performed on the wavelet coefficients to obtain denoised wavelet coefficients; wherein T0=εT, and 0<ε<1, σ=median(w) / 0.6745, median(·) represents the median value, d represents the adjustment coefficient, M represents the length of the ultrasound image, and N represents the width of the ultrasound image; When the decomposed wavelet coefficient |w i |<T0, the corresponding wavelet coefficient is set to 0; A training module, used for inputting the enhanced ultrasound image as a sample into a neural network for training to obtain an image segmentation model; A needle extraction module, used to extract the needle of the puncture needle using the image segmentation model; The needle positioning module is used to determine the position of the puncture needle tip based on the pixel point where the puncture needle tip is located.

6. An electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, wherein: When the computer program is executed by the processor, the steps of the image processing method for a puncture needle according to any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the image processing method for a puncture needle according to any one of claims 1 to 4 are implemented.

Citation Information

Patent Citations

  • Continuous min-cut-based ultrasonic image segmentation method

    CN108717699A

  • Puncture needle enhanced display method and device in ultrasonic puncture

    CN111476790A

  • Puncture needle recognition method, system and equipment containing puncture needle ultrasonic blood vessel image

    CN113362294A

  • Puncture needle ultrasound image segmentation method, device and system

    CN116152266A

  • Ultrasonic image enhancement method and system based on mixed learning

    CN117391997A