Method and apparatus for suppressing blood flow noise, ultrasonic device and readable storage medium

Abstract

This invention relates to the field of image processing technology, and discloses a method, apparatus, ultrasound device, and readable storage medium for suppressing blood flow noise. The method includes: acquiring an intravascular ultrasound image to be processed; performing vessel recognition on the intravascular ultrasound image based on a preset vessel recognition model to obtain the vessel region of the intravascular ultrasound image; wherein the preset vessel recognition model is trained based on intravascular ultrasound image samples and vessel region samples; and suppressing blood flow noise in the vessel region to generate a target image. By implementing the technical solution of this invention, noise suppression can be performed on the vessel region, improving the processing speed of noise suppression, thereby enhancing the efficiency of blood flow noise removal from intravascular ultrasound images and facilitating efficient vessel recognition.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and more specifically to a method, apparatus, ultrasound equipment, and readable storage medium for suppressing blood flow noise. Background Technology

[0002] Intravenous ultrasound (IVUS) is a medical imaging technique that combines ultrasound and catheter technology for the diagnosis of coronary artery disease. However, IVUS images often contain speckled noise in the blood vessels, which can cause difficulties in vascular diagnosis and identification.

[0003] To address the aforementioned issues, commonly used methods primarily involve using time-variance maps (TVAs) from two or more frames of a sequence of images to remove speckle noise and suppress blood flow noise in IVUS images. Filtering methods can also be employed to remove blood flow noise from IVUS images. However, these approaches process the IVUS image holistically, making it difficult to target noise within specific vascular regions. This results in low efficiency in removing blood flow noise from IVUS images, impacting vascular diagnosis and identification. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a method, apparatus, ultrasound device, and readable storage medium for suppressing blood flow noise, in order to solve the problem of difficulty in noise processing in vascular areas.

[0005] According to a first aspect, an embodiment of the present invention provides a method for suppressing blood flow noise, comprising: acquiring an intravascular ultrasound image to be processed; performing blood vessel recognition on the intravascular ultrasound image based on a preset blood vessel recognition model to obtain a blood vessel region of the intravascular ultrasound image; wherein the preset blood vessel recognition model is trained based on intravascular ultrasound image samples and blood vessel region samples; and suppressing blood flow noise on the blood vessel region to generate a target image.

[0006] The blood flow noise suppression method provided in this embodiment of the invention identifies the vascular region in an intravascular ultrasound image and suppresses blood flow noise in the identified vascular region. This allows for noise suppression targeting the vascular region, improving the processing speed of noise suppression and thus enhancing the efficiency of blood flow noise removal in intravascular ultrasound images, facilitating efficient vascular identification.

[0007] In conjunction with the first aspect, in the first embodiment of the first aspect, the step of suppressing blood flow noise in the vascular region to generate a target image includes: filtering the intravascular ultrasound image to generate a smooth image; performing noise suppression processing on the vascular region in the smooth image based on a preset suppression threshold to obtain a noise-suppressed image; and fusing the noise-suppressed image with the intravascular ultrasound image to obtain the target image.

[0008] The blood flow noise suppression method provided in this invention involves filtering an intravascular ultrasound image to obtain a smooth image, facilitating noise removal from the intravascular ultrasound image. Then, noise suppression is applied to the vascular region within the smooth image based on a preset suppression threshold. Finally, the noise-suppressed image is fused with the intravascular ultrasound image to obtain the target image. This allows for targeted noise removal of the vascular region, providing a simple and efficient method for suppressing blood flow noise in this area.

[0009] In conjunction with the first embodiment of the first aspect, in the second embodiment of the first aspect, fusing the noise-suppressed image with the intravascular ultrasound image to obtain the target image includes: obtaining a first weight for the intravascular ultrasound image and a second weight for the noise-suppressed image; weighting the intravascular ultrasound image and the noise-suppressed image based on the first weight and the second weight to obtain the target image; wherein the sum of the first weight and the second weight is 1.

[0010] The blood flow noise suppression method provided in this embodiment of the invention facilitates effective data fusion of the noise-suppressed image and the intravascular ultrasound image by setting a first weight for the intravascular ultrasound image and a second weight for the noise-suppressed image, thereby ensuring that the target image can accurately represent vascular information.

[0011] In conjunction with the first aspect, in the third embodiment of the first aspect, acquiring the intravascular ultrasound image to be processed includes: acquiring the original intravascular ultrasound image to be processed; and preprocessing the original intravascular ultrasound image to obtain the preprocessed intravascular ultrasound image.

[0012] In conjunction with the third embodiment of the first aspect, in the fourth embodiment of the first aspect, the preprocessing of the original intravascular ultrasound image to obtain the preprocessed intravascular ultrasound image includes: performing initial filtering on the noise in the original intravascular ultrasound image to obtain a filtered image; performing enhancement processing on the filtered image to obtain an enhanced image; and performing gamma transform processing on the enhanced image to obtain the intravascular ultrasound image.

[0013] The blood flow noise suppression method provided in this embodiment of the invention performs preprocessing operations such as filtering, enhancement, and gamma transformation on the original intravascular ultrasound image to initially filter out noise and improve the accuracy of subsequent blood vessel identification.

[0014] In conjunction with the fourth embodiment of the first aspect, in the fifth embodiment of the first aspect, the step of enhancing the filtered image to obtain an enhanced image includes: dividing the filtered image into blocks to obtain each block image and a grayscale value corresponding to each block image; and enhancing the corresponding block image based on each grayscale value to generate the enhanced image.

[0015] The blood flow noise suppression method provided in this embodiment of the invention divides the filtered image into blocks to determine the grayscale value of each block image, and performs enhancement processing based on the grayscale value to adjust the brightness of the block images, thereby enhancing the features of the block images and making the images clearer.

[0016] In conjunction with the first aspect, in the sixth embodiment of the first aspect, the step of performing vascular identification on the intravascular ultrasound image based on a preset vascular identification model to obtain the vascular region of the intravascular ultrasound image includes: performing vascular segmentation on the intravascular ultrasound image using the preset vascular identification model to obtain vascular segmentation results; and determining the vascular region and non-vascular region of the intravascular ultrasound image based on the vascular segmentation results.

[0017] The blood flow noise suppression method provided in this embodiment of the invention segments the vascular region and the non-vascular region from the intravascular ultrasound image by using a preset vascular recognition model. This facilitates noise suppression of the vascular region, while the non-vascular region is not suppressed, thereby improving the noise suppression efficiency.

[0018] According to a second aspect, embodiments of the present invention provide a blood flow noise suppression device, comprising: an acquisition module for acquiring an intravascular ultrasound image to be processed; a blood vessel recognition module for performing blood vessel recognition on the intravascular ultrasound image based on a preset blood vessel recognition model to obtain a blood vessel region of the intravascular ultrasound image; wherein the preset blood vessel recognition model is trained based on intravascular ultrasound image samples and blood vessel region samples; and a noise suppression module for suppressing blood flow noise in the blood vessel region to generate a target image.

[0019] According to a third aspect, an embodiment of the present invention provides an ultrasound device, including: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the blood flow noise suppression method described in the first aspect or any embodiment of the first aspect.

[0020] According to a fourth aspect, embodiments of the present invention provide a computer-readable storage medium storing computer instructions for causing a computer to perform the blood flow noise suppression method described in the first aspect or any embodiment of the first aspect.

[0021] It should be noted that the beneficial effects of the blood flow noise suppression device, electronic device, and computer-readable storage medium provided in the embodiments of the present invention can be found in the description of the corresponding content in the blood flow noise suppression method, and will not be repeated here. Attached Figure Description

[0022] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0023] Figure 1 This is a flowchart of a blood flow noise suppression method according to an embodiment of the present invention;

[0024] Figure 2 This is another flowchart of a blood flow noise suppression method according to an embodiment of the present invention;

[0025] Figure 3 A comparison diagram before and after blood flow noise suppression treatment is shown;

[0026] Figure 4 This is another flowchart of a blood flow noise suppression method according to an embodiment of the present invention;

[0027] Figure 5 The comparison images before and after preprocessing are shown;

[0028] Figure 6 A block diagram of an intravascular ultrasound image is shown;

[0029] Figure 7 A schematic diagram illustrating the grayscale value update of a segmented image is shown.

[0030] Figure 8 A schematic diagram of bilinear interpolation is shown;

[0031] Figure 9 A schematic diagram of blood vessel segmentation is shown;

[0032] Figure 10 This is a structural block diagram of a blood flow noise suppression device according to an embodiment of the present invention;

[0033] Figure 11 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0034] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0035] Existing blood flow noise suppression methods mainly fall into two categories: one category involves removing speckle noise by obtaining a temporal variance map from two or more frames of a sequence of images; this type of method is typically quite complex to implement. The other category directly uses filtering methods such as median filtering, mean filtering, Gaussian filtering, and bilateral filtering for noise removal, but these methods struggle to guarantee effective noise removal. Moreover, the aforementioned methods all perform overall processing on the IVUS image, making it difficult to target noise in specific vascular regions. This results in low efficiency in removing blood flow noise from IVUS images, impacting vascular diagnosis and identification.

[0036] Based on this, the technical solution of the present invention can identify vascular regions, and after identifying the vascular regions, noise suppression processing is performed on the vascular regions, thereby achieving simple and efficient blood flow noise suppression.

[0037] According to an embodiment of the present invention, an embodiment of a method for suppressing blood flow noise is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0038] This embodiment provides a method for suppressing blood flow noise, which can be used in electronic devices in the medical field, such as IVUS devices and other ultrasound imaging equipment. Figure 1 This is a flowchart of a blood flow noise suppression method according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps:

[0039] S11, acquire the intravascular ultrasound image to be processed.

[0040] The ultrasound catheter of the IVUS device is used to perform ultrasound scanning on the target blood vessel to acquire ultrasound images inside the target blood vessel. The corresponding intravascular ultrasound image can be obtained by preprocessing the ultrasound image.

[0041] Specifically, medical staff can determine the target blood vessel for which vascular imaging is needed based on the patient's condition, and then apply the ultrasound catheter of the IVUS device to the target blood vessel to acquire the corresponding intravascular ultrasound image.

[0042] S12, based on the preset blood vessel recognition model, perform blood vessel recognition on the intravascular ultrasound image to obtain the blood vessel region of the intravascular ultrasound image.

[0043] The preset blood vessel recognition model is trained based on intravascular ultrasound image samples and blood vessel region samples.

[0044] A preset vessel recognition model is used to identify vascular regions in intravascular ultrasound images. This preset vessel recognition model is trained using intravascular ultrasound image samples as input and corresponding vascular region samples as output. This preset vessel recognition model can be a deep learning network model, such as the U-net network model, a neural network model, or a machine learning model; no specific limitation is made here.

[0045] A preset blood vessel recognition model is deployed into the IVUS device. When the IVUS device acquires intravascular ultrasound images through the ultrasound catheter, the acquired intravascular ultrasound images can be input into the preset blood vessel recognition model, and the blood vessel region in the current intravascular ultrasound image can be output through the preset blood vessel recognition model.

[0046] S13, suppress blood flow noise in the vascular region and generate the target image.

[0047] After obtaining the vascular region, the intravascular ultrasound image can be divided into vascular and non-vascular regions. At this point, blood flow noise suppression can be performed only on the vascular region of the intravascular ultrasound image, while the non-vascular region remains untreated. Then, the non-vascular region and the blood flow noise-suppressed vascular region are merged to obtain a noise-suppressed image. This noise-suppressed image is then fused with the intravascular ultrasound image to generate the final target image.

[0048] The blood flow noise suppression method provided in this embodiment identifies the vascular region in the intravascular ultrasound image and suppresses blood flow noise in the identified vascular region. This allows for noise suppression targeting the vascular region, improving the processing speed of noise suppression and thus enhancing the efficiency of blood flow noise removal in intravascular ultrasound images, facilitating efficient vascular identification.

[0049] This embodiment provides a method for suppressing blood flow noise, which can be used in electronic devices in the medical field, such as IVUS devices and other ultrasound imaging equipment. Figure 2 This is a flowchart of a blood flow noise suppression method according to an embodiment of the present invention, such as... Figure 2As shown, the process includes the following steps:

[0050] S21, acquire the intravascular ultrasound image to be processed. For detailed explanation, please refer to the relevant descriptions in the above embodiments; they will not be repeated here.

[0051] S22, Based on the preset blood vessel recognition model, perform blood vessel recognition on the intravascular ultrasound image to obtain the blood vessel region of the intravascular ultrasound image.

[0052] The preset blood vessel recognition model is trained based on intravascular ultrasound image samples and blood vessel region samples.

[0053] For detailed explanations, please refer to the relevant descriptions corresponding to the above embodiments, which will not be repeated here.

[0054] S23, suppress blood flow noise in the vascular region to generate the target image.

[0055] Specifically, step S23 above may include:

[0056] S231 filters the intravascular ultrasound image to generate a smooth image.

[0057] Intravascular ultrasound images I in An N*N filter is applied to remove noise points from the intravascular ultrasound image, resulting in a smooth image I. S For example, intravascular ultrasound images I in Perform a 5x5 mean filter to obtain a smoothed image I. S Where N*N is not limited to 5*5, it can also be 3*3, 7*7, 9*9, etc.; the filtering process is not limited to mean filtering, it can also be median filtering, Gaussian filtering, bilateral filtering, etc.

[0058] S232, noise suppression processing is performed on the blood vessel region in the smooth image based on a preset suppression threshold to obtain a noise-suppressed image.

[0059] The preset suppression threshold is a pre-defined suppression threshold, which can be set based on empirical values; for example, the preset suppression threshold can be 25. For smoothed image I... S Blood flow noise suppression processing was performed to obtain noise-suppressed image I. out The specific noise suppression methods are as follows:

[0060] Vascular area;

[0061] I out2 =I in Non-vascular area.

[0062] Output the vascular image corresponding to the vascular region (I) out1Other image outputs I corresponding to non-vascular image regions out2 By merging the images, we can obtain the noise-suppressed image I. out .

[0063] S233, the noise-suppressed image is fused with the intravascular ultrasound image to obtain the target image.

[0064] To preserve the features of intravascular ultrasound images to the greatest extent possible, after obtaining the noise-suppressed image, the noise-suppressed image is weighted and fused with the intravascular ultrasound image to obtain the fused target image.

[0065] Specifically, step S233 above may include:

[0066] (1) Obtain a first weight for intravascular ultrasound images and a second weight for noise-suppressed images.

[0067] (2) The intravascular ultrasound image and the noise-suppressed image are weighted based on the first weight and the second weight to obtain the target image.

[0068] The sum of the first weight and the second weight is 1.

[0069] The first weight is used to characterize the fusion coefficient of the intravascular ultrasound image, and the second weight is used to characterize the fusion coefficient of the noise-suppressed image. The intravascular ultrasound image and the noise-suppressed image are weighted according to the first and second weights to generate the corresponding target image. For example... Figure 3 As shown, the left image is an intravascular ultrasound image, and the right image is the target image after blood flow noise suppression.

[0070] The specific fusion method is as follows:

[0071] I Merge =I in *α+β*I Denoise

[0072] α+β=1

[0073] Among them, I Merge Indicates the fused target image; I in Indicates intravascular ultrasound image; I Denoise α represents the noise-suppressed image; α represents the first weight; β represents the second weight.

[0074] The blood flow noise suppression method provided in this embodiment filters the intravascular ultrasound image to obtain a smooth image, facilitating noise removal. Then, noise suppression is applied to the vascular region within the smooth image based on a preset suppression threshold. The noise-suppressed image is then fused with the intravascular ultrasound image to obtain the target image. This allows for targeted noise removal of the vascular region, providing a simple and efficient way to suppress blood flow noise. By setting a first weight for the intravascular ultrasound image and a second weight for the noise-suppressed image, effective data fusion between the two images is facilitated, ensuring that the target image accurately represents vascular information.

[0075] This embodiment provides a method for suppressing blood flow noise, which can be used in electronic devices in the medical field, such as IVUS devices and other ultrasound imaging equipment. Figure 4 This is a flowchart of a blood flow noise suppression method according to an embodiment of the present invention, such as... Figure 4 As shown, the process includes the following steps:

[0076] S31, acquire the intravascular ultrasound image to be processed.

[0077] Specifically, step S31 above may include:

[0078] S311, acquire the raw intravascular ultrasound image to be processed.

[0079] The original intravascular ultrasound image is the ultrasound image acquired by using an ultrasound catheter of an IVUS device to perform ultrasound scanning on the target blood vessel.

[0080] S312, preprocess the original intravascular ultrasound image to obtain a preprocessed intravascular ultrasound image.

[0081] The original intravascular ultrasound image may be blurred due to the presence of blood flow noise. In order to obtain a clearer intravascular ultrasound image, the original intravascular ultrasound image can be preprocessed to initially filter out the blood flow noise.

[0082] As an optional implementation, step S312 above may include:

[0083] (1) Initial filtering is performed on the noise in the original intravascular ultrasound image to obtain the filtered image.

[0084] The acquired raw intravascular ultrasound image is subjected to M*M filtering to remove noise and obtain a filtered image. For example, a 3*3 Gaussian filter is applied to the raw intravascular ultrasound image.

[0085] Wherein, M*M is not limited to 3*3, it can be 5*5, 7*7, etc., and those skilled in the art can determine it according to actual needs; the filtering process is not limited to Gaussian filtering, it can also be mean filtering, median filtering, etc.

[0086] (2) Enhance the filtered image to obtain the enhanced image.

[0087] The filtered image is then enhanced to increase its brightness and make its features more prominent. For example, the pre-processed image... Figure 5 As shown.

[0088] As an optional implementation, the CLAHE algorithm can be used to enhance the filtered image. Accordingly, step (2) above may include:

[0089] (21) The filtered image is divided into blocks to obtain each block image and the corresponding gray value of each block image.

[0090] (22) Enhance the corresponding image blocks based on each gray value to generate an enhanced image.

[0091] The filtered image is divided into blocks according to a preset block size to obtain multiple block images, and the grayscale values ​​of each block image are extracted. For example, dividing the filtered image into 8*8 blocks will yield images like... Figure 6 The image shown is a segmented image.

[0092] Based on the grayscale values ​​of each image block, a grayscale histogram for each block can be calculated. A grayscale limit value Climit is set for the histogram. Then, the grayscale histograms of each image block are cropped according to the corresponding grayscale limit value Climit. That is, if a grayscale level in the histogram exceeds the grayscale limit value Climit, the grayscale histogram of that grayscale level is cropped, and the total number of pixels cropped across all grayscale levels is counted. The total number of cropped pixels is then evenly distributed among the other uncropped grayscale levels in the grayscale histogram, resulting in a new grayscale histogram for each image block. Figure 7 As shown. Repeat the above cropping steps for the resulting new grayscale histogram until all gray levels of the grayscale histogram do not exceed the grayscale limit value Climit. The resulting grayscale histogram is the final grayscale histogram.

[0093] The cumulative distribution function, or gray-level mapping function, is calculated based on the final gray-level histogram of each image block. Specifically, the formula for determining the gray-level mapping function is as follows:

[0094]

[0095] Where r is the gray level (0-255), H(r) is the gray level histogram of the current gray level r, and N is the total number of pixels in the block image.

[0096] The new grayscale value in the segmented image is obtained by bilinear interpolation using the grayscale mapping function of the surrounding smaller blocks. The interpolation formula is as follows:

[0097]

[0098] Wherein, UL, UR, BL, and BR are the grayscale mapping functions corresponding to the four surrounding image blocks of this pixel (e.g., ...). Figure 8 As shown in the figure, the grayscale mapping function of each image block is defined at its center. d1, d2, d3, and d4 are the distances of the pixel from each grayscale mapping function, i is the original grayscale value of the pixel, and I is the new grayscale value of the pixel.

[0099] Therefore, by dividing the filtered image into blocks to determine the grayscale value of each block, and then performing enhancement processing based on the grayscale value, the brightness of the block image is adjusted, thereby enhancing the features of the block image and making the image clearer.

[0100] (3) Perform gamma transformation on the enhanced image to obtain intravascular ultrasound image.

[0101] The enhanced image obtained after enhancement processing is then subjected to gamma transformation to obtain a more clearly defined intravascular ultrasound image. Specifically, the gamma transformation method is as follows:

[0102]

[0103] Where C represents the grayscale scaling factor, r represents the Gamma transformation value, and I i I represents the normalized grayscale value of the enhanced image. O This represents the grayscale value output after Gamma transformation, i.e., the grayscale value of the intravascular ultrasound image obtained after gamma transformation.

[0104] S32, based on a preset blood vessel recognition model, perform blood vessel recognition on the intravascular ultrasound image to obtain the blood vessel region of the intravascular ultrasound image.

[0105] The preset blood vessel recognition model is trained based on intravascular ultrasound image samples and blood vessel region samples.

[0106] Specifically, step S32 above may include:

[0107] S321, the intravascular ultrasound image is segmented using a preset vascular recognition model to obtain the vascular segmentation result.

[0108] The results of vessel segmentation are used to characterize vessel contours. For example... Figure 9 As shown, an intravascular ultrasound image is input into a preset vascular recognition model. The preset vascular recognition model identifies the location of blood vessels in the intravascular ultrasound image and then outputs the vascular contour, generating vascular segmentation results.

[0109] S322, based on the blood vessel segmentation results, determines the vascular region and non-vascular region in the intravascular ultrasound image.

[0110] Based on the results of vessel segmentation, the vascular region in the intravascular ultrasound image can be determined, and the region excluding the vascular region is the non-vascular region.

[0111] S33, suppress blood flow noise in the vascular region to generate the target image. For detailed explanation, please refer to the relevant descriptions in the above embodiments; they will not be repeated here.

[0112] The blood flow noise suppression method provided in this embodiment performs preprocessing operations such as filtering, enhancement, and gamma transformation on the original intravascular ultrasound image to initially remove noise, thereby improving the accuracy of subsequent vessel identification. A preset vessel identification model segments the vascular and non-vascular regions from the intravascular ultrasound image, facilitating noise suppression of the vascular region while leaving the non-vascular region untreated, thus improving the efficiency of noise suppression.

[0113] This embodiment also provides a blood flow noise suppression device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware implementations, or a combination of software and hardware, are also possible and contemplated.

[0114] This embodiment provides a blood flow noise suppression device, such as... Figure 10 As shown, it includes:

[0115] The acquisition module 41 is used to acquire intravascular ultrasound images to be processed.

[0116] The vessel recognition module 42 is used to perform vessel recognition on intravascular ultrasound images based on a preset vessel recognition model to obtain the vessel region of the intravascular ultrasound image; wherein, the preset vessel recognition model is trained based on intravascular ultrasound image samples and vessel region samples.

[0117] The noise suppression module 43 is used to suppress blood flow noise in the vascular region and generate the target image.

[0118] Optionally, the noise suppression module 43 may include:

[0119] The filtering submodule is used to filter intravascular ultrasound images to generate smooth images.

[0120] The noise removal submodule is used to perform noise suppression processing on the blood vessel region in the smoothed image based on a preset suppression threshold, so as to obtain a noise-suppressed image.

[0121] The fusion submodule is used to fuse the noise-suppressed image with the intravascular ultrasound image to obtain the target image.

[0122] Optionally, the above-mentioned fusion submodule is specifically used to: obtain a first weight for the intravascular ultrasound image and a second weight for the noise-suppressed image; weight the intravascular ultrasound image and the noise-suppressed image based on the first weight and the second weight to obtain the target image; wherein the sum of the first weight and the second weight is 1.

[0123] Optionally, the acquisition module 41 described above may include:

[0124] The acquisition submodule is used to acquire the raw intravascular ultrasound images to be processed.

[0125] The preprocessing submodule is used to preprocess the original intravascular ultrasound images to obtain preprocessed intravascular ultrasound images.

[0126] Optionally, the preprocessing submodule described above is specifically used to: perform initial filtering on the noise in the original intravascular ultrasound image to obtain a filtered image; perform enhancement processing on the filtered image to obtain an enhanced image; and perform gamma transform processing on the enhanced image to obtain an intravascular ultrasound image.

[0127] Optionally, the preprocessing submodule is further configured to: divide the filtered image into blocks to obtain each block image and the corresponding grayscale value of each block image; and enhance the corresponding block image based on each grayscale value to generate an enhanced image.

[0128] Optionally, the aforementioned blood vessel recognition module 42 may include:

[0129] The segmentation submodule is used to segment intravascular ultrasound images using a preset vascular recognition model to obtain vascular segmentation results.

[0130] The region segmentation submodule is used to determine the vascular and non-vascular regions in intravascular ultrasound images based on the vessel segmentation results.

[0131] In this embodiment, the blood flow noise suppression device is presented in the form of a functional unit. Here, a unit refers to an ASIC circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above-mentioned functions.

[0132] The further functional descriptions of each module and submodule are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0133] The blood flow noise suppression device provided in this embodiment identifies the vascular region in the intravascular ultrasound image and suppresses blood flow noise in the identified vascular region. This allows for noise suppression targeting the vascular region, improving the processing speed of noise suppression and thus enhancing the efficiency of blood flow noise removal in intravascular ultrasound images, facilitating efficient vascular identification.

[0134] This invention also provides an electronic device having the above-described features. Figure 10 The device shown is for suppressing blood flow noise.

[0135] Please see Figure 11 , Figure 11 This is a schematic diagram of the structure of an electronic device provided in an optional embodiment of the present invention, such as... Figure 11 As shown, the electronic device may include: at least one processor 501, such as a central processing unit (CPU), at least one communication interface 503, memory 504, and at least one communication bus 502. The communication bus 502 is used to enable communication between these components. The communication interface 503 may include a display screen or a keyboard; optionally, the communication interface 503 may also include a standard wired interface or a wireless interface. The memory 504 may be high-speed volatile random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Optionally, the memory 504 may also be at least one storage device located remotely from the aforementioned processor 501. The processor 501 may be combined with... Figure 10 The described apparatus has an application program stored in memory 504, and a processor 501 calls the program code stored in memory 504 to perform any of the above method steps.

[0136] The communication bus 502 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The communication bus 502 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 11 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0137] The memory 504 may include volatile memory, such as random-access memory (RAM); the memory may also include non-volatile memory, such as flash memory, hard disk drive (HDD) or solid-state drive (SSD); the memory 504 may also include a combination of the above types of memory.

[0138] The processor 501 can be a central processing unit (CPU), a network processor (NP), or a combination of a CPU and an NP.

[0139] The processor 501 may further include a hardware chip. This hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0140] Optionally, the memory 504 is also used to store program instructions. The processor 501 can invoke the program instructions to implement the blood flow noise suppression method as shown in the above embodiments of this application.

[0141] This invention also provides a non-transitory computer storage medium storing computer-executable instructions that can execute the blood flow noise suppression method in any of the above method embodiments. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium may also include combinations of the above types of memory.

[0142] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for suppressing blood flow noise, characterized in that, include: Acquire intravascular ultrasound images to be processed; The intravascular ultrasound image is used to identify blood vessels based on a preset blood vessel recognition model to obtain the blood vessel region of the intravascular ultrasound image; wherein, the preset blood vessel recognition model is trained based on intravascular ultrasound image samples and blood vessel region samples; The method for suppressing blood flow noise in the vascular region to generate a target image includes: filtering the intravascular ultrasound image to generate a smooth image; performing noise suppression processing on the vascular region in the smooth image based on a preset suppression threshold to obtain the vascular image output corresponding to the vascular region and the image output corresponding to the non-vascular image region; merging the vascular image output corresponding to the vascular region and the image output corresponding to the non-vascular image region to obtain a noise-suppressed image; and fusing the noise-suppressed image with the intravascular ultrasound image to obtain the target image.

2. The method according to claim 1, characterized in that, The step of fusing the noise-suppressed image with the intravascular ultrasound image to obtain the target image includes: Obtain a first weight for the intravascular ultrasound image and a second weight for the noise-suppressed image; The target image is obtained by weighting the intravascular ultrasound image and the noise-suppressed image based on the first weight and the second weight; Wherein, the sum of the first weight and the second weight is 1.

3. The method according to claim 1, characterized in that, The acquisition of the intravascular ultrasound image to be processed includes: Acquire the raw intravascular ultrasound image to be processed; The original intravascular ultrasound image is preprocessed to obtain the preprocessed intravascular ultrasound image.

4. The method according to claim 3, characterized in that, The preprocessing of the original intravascular ultrasound image to obtain the preprocessed intravascular ultrasound image includes: The noise in the original intravascular ultrasound image is initially filtered to obtain a filtered image; The filtered image is enhanced to obtain an enhanced image; The enhanced image is subjected to gamma transformation to obtain the intravascular ultrasound image.

5. The method according to claim 4, characterized in that, The enhancement process for the filtered image to obtain the enhanced image includes: The filtered image is divided into blocks to obtain each block image and the corresponding grayscale value of each block image; The corresponding image blocks are enhanced based on their respective grayscale values ​​to generate the enhanced image.

6. The method according to claim 1, characterized in that, The step of performing vascular identification on the intravascular ultrasound image based on a preset vascular identification model to obtain the vascular region of the intravascular ultrasound image includes: The blood vessel segmentation result is obtained by segmenting the intravascular ultrasound image using the preset blood vessel recognition model. Based on the blood vessel segmentation results, the vascular region and non-vascular region of the intravascular ultrasound image are determined.

7. A blood flow noise suppression device, characterized in that, include: The acquisition module is used to acquire intravascular ultrasound images to be processed; A blood vessel recognition module is used to perform blood vessel recognition on the intravascular ultrasound image based on a preset blood vessel recognition model to obtain the blood vessel region of the intravascular ultrasound image; wherein, the preset blood vessel recognition model is trained based on intravascular ultrasound image samples and blood vessel region samples; A noise suppression module is used to suppress blood flow noise in the vascular region and generate a target image; The noise suppression module includes: a filtering submodule for filtering the intravascular ultrasound image to generate a smooth image; a noise removal submodule for performing noise suppression processing on the vascular region in the smooth image based on a preset suppression threshold, obtaining the vascular image output corresponding to the vascular region and the image output corresponding to the non-vascular image region, and merging the vascular image output corresponding to the vascular region and the image output corresponding to the non-vascular image region to obtain a noise-suppressed image; and a fusion submodule for fusing the noise-suppressed image with the intravascular ultrasound image to obtain the target image.

8. An ultrasonic device, characterized in that, include: A memory and a processor are communicatively connected, the memory storing computer instructions, and the processor executing the computer instructions to perform the blood flow noise suppression method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to perform the blood flow noise suppression method according to any one of claims 1-6.

Images