Ultrasonic image processing method and device, electronic equipment and storage medium

Abstract

The invention provides an ultrasonic image processing method and device, electronic equipment, a storage medium and a computer product. The ultrasonic image processing method comprises the following steps: acquiring an ultrasonic image containing at least one blood vessel region; for a blood vessel region in the ultrasonic image, image segmentation is carried out on the ultrasonic image to obtain a first segmented image, and the first segmented image comprises the blood vessel region; determining a central pixel of each blood vessel region in the first segmented image; correcting a blood vessel region in the first segmented image based on the central pixel and the ultrasonic image to obtain a second segmented image; and synthesizing the second segmented image and the ultrasonic image to obtain a tissue attenuation image of which the blood vessel region is filtered. According to the scheme, the tissue attenuation image of the blood vessel filtering area can be obtained more accurately, and accurate diagnosis of medical staff is facilitated.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, in particular to an ultrasonic image processing method and device, electronic equipment, storage medium and computer program product. BACKGROUND

[0002] With the development of science and technology, ultrasonic imaging technology is becoming more and more mature. It uses an ultrasonic beam to scan a target object, and obtains an image of an internal organ of the target object by receiving and processing reflected signals. Undoubtedly, ultrasonic imaging will be affected by internal organs and tissues such as blood vessels in the target object.

[0003] When ultrasonic waves propagate in tissues, they will be affected by acoustic attenuation, that is, the energy of the acoustic waves will decrease with the increase of the propagation distance. This characteristic of ultrasonic waves can be used for tissue acoustic attenuation imaging. Its basic principle is to use the different propagation attenuations of ultrasonic waves in different tissues, calculate the corresponding attenuation coefficients by using the frequency method, and display the attenuation coefficients of each part of the tissue by color mapping. Currently, tissue acoustic attenuation imaging is applied in many medical examinations and diagnoses, for example, quantitative measurement of non-alcoholic fatty liver. There are rich blood vessels in the human liver, and when ultrasonic waves encounter blood vessel walls, there will be optical phenomena such as refraction and reflection, and when they encounter blood flow, there will be Doppler frequency shift, which will result in that the tissues and blood vessels in the final ultrasonic image cannot be clearly distinguished, affecting the accuracy of diagnosis.

[0004] In related technologies, the position of the blood vessels is found and filtered out according to the ultrasonic echo signal, but due to the influence of the characteristics of the ultrasonic waves, too many or too few blood vessel regions are easily filtered out, and it is difficult to accurately filter out various blood vessels. SUMMARY

[0005] The present application is proposed in consideration of the above problems.

[0006] According to a first aspect of the present application, an ultrasonic image processing method is provided. The method comprises:

[0007] obtaining an ultrasonic image containing at least one blood vessel region;

[0008] performing image segmentation on the ultrasonic image for the blood vessel region in the ultrasonic image to obtain a first segmentation image, the first segmentation image comprising a blood vessel region;

[0009] determining a center pixel of each blood vessel region in the first segmentation image;

[0010] correcting the blood vessel region in the first segmentation image based on the center pixel and the ultrasonic image to obtain a second segmentation image; and

[0011] The second segmentation image and the ultrasonic image are synthesized to obtain a tissue attenuation image in which a blood vessel region is filtered out.

[0012] The blood vessel region in the first segmentation image is corrected based on the center pixel and the ultrasonic image to obtain a second segmentation image.

[0013] For the center pixel of each blood vessel region in the first segmentation image, a reference pixel is initialized as the center pixel, and an expansion operation is performed in the first segmentation image according to the ultrasonic image until a new reference pixel cannot be determined.

[0014] The expansion operation specifically includes: determining the new reference pixel from a plurality of first pixels based on a pixel value corresponding to the reference pixel position in the ultrasonic image and pixel values corresponding to a plurality of first pixel positions adjacent to the reference pixel position in the ultrasonic image.

[0015] The corrected blood vessel region in the first segmentation image is determined according to positions of all reference pixels, wherein the all reference pixels include the center pixel and the new reference pixel.

[0016] The second segmentation image is determined according to the corrected blood vessel region in the first segmentation image.

[0017] The expansion operation specifically includes: determining the new reference pixel from a plurality of first pixels based on a pixel value corresponding to the reference pixel position in the ultrasonic image and pixel values corresponding to a plurality of first pixel positions adjacent to the reference pixel position in the ultrasonic image.

[0018] An average value of pixel values corresponding to all current reference pixels in the ultrasonic image is determined.

[0019] A first absolute value of a difference between a pixel value corresponding to each first pixel in the ultrasonic image and the average value is determined.

[0020] The new reference pixel is selected from all first pixels according to the first absolute value of the difference between the pixel value corresponding to each first pixel in the ultrasonic image and the average value.

[0021] The new reference pixel is selected from all first pixels according to the first absolute value of the difference between the pixel value corresponding to each first pixel in the ultrasonic image and the average value.

[0022] determining a minimum first absolute value from the first absolute values determined for each of the first pixels respectively, and comparing the minimum first absolute value with a first preset threshold to obtain a comparison result;

[0023] if the comparison result indicates that the minimum first absolute value is less than the first preset threshold, determining the first pixel corresponding to the minimum first absolute value as the new reference pixel.

[0024] Exemplarily, the determining the second segmentation image according to the corrected blood vessel region in the first segmentation image comprises:

[0025] determining the second segmentation image according to the positions of the pixels in the corrected blood vessel region in the first segmentation image, wherein the blood vessel region in the second segmentation image comprises pixels corresponding to the positions of the pixels in the corrected blood vessel region in the first segmentation image.

[0026] Exemplarily, the determining the center pixel of each of the blood vessel regions in the first segmentation image comprises:

[0027] for each of the blood vessel regions in the first segmentation image, determining the center pixel in each of the blood vessel regions according to average coordinates of the positions of the pixels in each of the blood vessel regions respectively.

[0028] Exemplarily, the image segmentation of the ultrasonic image for the blood vessel region in the ultrasonic image to obtain the first segmentation image comprises:

[0029] for the Nth row of pixels of the ultrasonic image, determining a median value of the pixel values of the Nth row of pixels, wherein N is a positive integer less than or equal to the number of rows of the ultrasonic image;

[0030] determining a second absolute value corresponding to each of the pixel values of the Nth row of pixels respectively, and comparing the second absolute value corresponding to each of the pixel values of the Nth row of pixels with a second preset threshold respectively, wherein the second absolute value is an absolute value of the difference between each of the pixel values of the Nth row of pixels and the median value;

[0031] obtaining the first segmentation image according to the second pixels in the ultrasonic image, wherein the second pixels are the pixels in the ultrasonic image corresponding to the second absolute values greater than the second preset threshold, and the positions of the pixels in the blood vessel region in the first segmentation image correspond to the positions of the second pixels in the ultrasonic image.

[0032] Exemplarily, before the determining the center pixel of each of the blood vessel regions in the first segmentation image, the method further comprises:

[0033] determine an area of each blood vessel region in the first segmented image;

[0034] delete the blood vessel region whose determined area is less than the area threshold.

[0035] Exemplarily, before the image segmentation on the ultrasound wave, the method further comprises:

[0036] de-noise the ultrasound wave image to obtain a de-noised ultrasound wave image.

[0037] Exemplarily, before the image segmentation on the ultrasound wave, the method further comprises:

[0038] normalize pixel values corresponding to pixels in the ultrasound wave image to obtain a normalized ultrasound wave image.

[0039] According to a second aspect of the present application, there is also provided an ultrasound wave image processing apparatus, comprising:

[0040] an image receiving module configured to acquire an ultrasound wave image containing at least one blood vessel region;

[0041] an image segmentation module configured to perform image segmentation on the ultrasound wave image for blood vessel regions in the ultrasound wave image to obtain a first segmented image, the first segmented image comprising blood vessel regions;

[0042] an image determining module configured to determine a center pixel of each blood vessel region in the first segmented image;

[0043] an image correction module configured to correct blood vessel regions in the first segmented image based on the center pixel and the ultrasound wave image to obtain a second segmented image; and

[0044] an image synthesizing module configured to synthesize the second segmented image and the ultrasound wave image to obtain a tissue attenuation image with blood vessel regions filtered out.

[0045] According to a third aspect of the present application, there is also provided an electronic device comprising a processor and a memory, wherein the memory stores computer program instructions which, when executed by the processor, cause the execution of the above-mentioned ultrasound wave image processing method.

[0046] According to a fourth aspect of the present application, there is also provided a storage medium storing program instructions which, when executed, cause the execution of the above-mentioned ultrasound wave image processing method.

[0047] According to the fifth aspect of the present application, there is also provided a computer program product comprising computer program instructions for performing the above-mentioned ultrasound image processing method when executed.

[0048] In the above technical solution, the ultrasound image containing the blood vessel region is subjected to image segmentation, the blood vessel region is corrected according to the center pixel of the blood vessel region in the first segmented image after image segmentation, to obtain a second segmented image, and the second segmented image and the ultrasound image are synthesized, so that a more accurate tissue attenuation image in which the blood vessel region is filtered out can be obtained, which helps medical personnel to make accurate diagnosis.

[0049] The above description is only a summary of the technical solutions of the present application. In order to enable one skilled in the art to better understand the technical means of the present application and to implement the same according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more apparent and easy to understand, the following specific embodiments of the present application are described. BRIEF DESCRIPTION OF DRAWINGS

[0050] The above and other purposes, features and advantages of the present application will become more apparent from the following detailed description of the embodiments of the present application, taken in conjunction with the accompanying drawings. The accompanying drawings are provided to assist in the understanding of the embodiments of the present application, and constitute a part of the specification, together with the embodiments of the present application, to explain the present application, and do not constitute a limitation on the present application. In the drawings, the same reference numerals generally represent the same components or steps.

[0051] Figure 1 A schematic flowchart of an ultrasound image processing method according to one embodiment of the present application is shown;

[0052] Figure 2 A schematic flowchart of obtaining a first segmented image according to one embodiment of the present application is shown;

[0053] Figure 3 A schematic flowchart of obtaining a second segmented image according to one embodiment of the present application is shown;

[0054] Figure 4 A schematic flowchart of an extension operation according to one embodiment of the present application is shown;

[0055] Figure 5 A schematic flowchart of determining a new reference pixel in a first pixel according to a first absolute value according to one embodiment of the present application is shown;

[0056] Figure 6 A schematic flowchart of filtering out a blood vessel region according to one embodiment of the present application is shown;

[0057] Figure 7A schematic flowchart of an ultrasound image processing method according to another embodiment of the present application is shown;

[0058] Figure 8 A schematic block diagram of an ultrasound host according to an embodiment of the present application is shown;

[0059] Figure 9 A schematic block diagram of an ultrasound image processing apparatus according to an embodiment of the present application is shown;

[0060] Figure 10 A schematic block diagram of an electronic device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0061] In order to make the objects, technical solutions and advantages of the present application more clear, the following will describe the example embodiments according to the present application in detail with reference to the drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application described in the present application, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present application.

[0062] In order to at least partially solve the above problems, the present application provides an ultrasound image processing method, which performs image segmentation on an ultrasound image containing a blood vessel region, and corrects a segmented image obtained after the image segmentation, composites the corrected segmented image and the ultrasound image, so as to obtain a more accurate tissue attenuation image with the blood vessel region filtered out.

[0063] Figure 1 A schematic flowchart of an ultrasound image processing method according to an embodiment of the present application is shown. The method can include steps S1100 to S1900.

[0064] In step S1100, an ultrasound image containing at least one blood vessel region is acquired.

[0065] Exemplarily, the ultrasound image can be an RGB image or a grayscale image. The ultrasound image can be a static image or any video frame in a dynamic video. The ultrasound image can be an image of any suitable size and resolution. The ultrasound image can be a raw image directly collected by an ultrasound device or an image after a pre-processing operation on the raw image. The pre-processing operation can include all operations for improving the visual effect of the ultrasound image, increasing the clarity thereof, or highlighting certain features in the image. Exemplarily but not limitatively, the pre-processing operation can include operations such as digitization, geometric transformation, normalization, filtering, etc. on the raw image. The ultrasound image can also be a synthesized image without affecting the subsequent processing of the ultrasound image.

[0066] After imaging of each tissue in the target object, a corresponding region is formed in the ultrasound image, for example, a blood vessel region, an organ tissue region (e.g., a liver tissue region), etc. The blood vessel region is a region that needs to be filtered out in the ultrasound image, and the ultrasound image can include one or more blood vessel regions.

[0067] In step S1300, the ultrasound image is subjected to image segmentation with respect to the blood vessel region in the ultrasound image to obtain a first segmentation image, the first segmentation image including the blood vessel region.

[0068] The ultrasound image can be subjected to image segmentation by a threshold-based segmentation method, a region-based segmentation method, an edge-based segmentation method, a segmentation method based on a specific theory, etc.

[0069] When the ultrasound image is subjected to image segmentation with respect to the blood vessel region in the ultrasound image, the blood vessel region and the non-blood vessel region in the ultrasound image can be segmented as two different objects to highlight the image information of the blood vessel region in the ultrasound image, so that the blood vessel region and the non-blood vessel region in the ultrasound image are more easily distinguished. Therefore, in the first segmentation image, the blood vessel region and the non-blood vessel region are more easily distinguished than in the ultrasound image. For example, in the first segmentation image, the non-blood vessel region can be represented by a region composed of black pixels, and the blood vessel region can be represented by a region composed of white pixels. The black and white colors are only illustrative, and other color pixels can be used to represent the non-blood vessel region or the blood vessel region.

[0070] The pixels in the first segmentation image correspond to the pixel positions in the ultrasound image.

[0071] The first segmentation image can be an image of the same size as the ultrasound image, i.e., the pixels in the first segmentation image can correspond to the pixels in the ultrasound image one by one.

[0072] The first segmented image can also be an image of different size from the ultrasonic image without affecting the result of image processing. When the first segmented image is larger than the ultrasonic image, each pixel in the ultrasonic image can correspond to a plurality of pixels in the first segmented image; when the first segmented image is smaller than the ultrasonic image, each pixel in the first segmented image can correspond to a plurality of pixels in the ultrasonic image.

[0073] Because image segmentation is a process of dividing a digital image into mutually disjoint regions, the first segmented image can also be a matrix composed of 0 and 1, and each element corresponds to a pixel in the ultrasonic image, in the case that the blood vessel region and the non-blood vessel region can be distinguished obviously. For example, in the first segmented image represented by a matrix, the region composed of elements with a value of 0 can represent the blood vessel region in the first segmented image, and the region composed of elements with a value of 1 can represent the non-blood vessel region (organ tissue region) in the first segmented image.

[0074] In step S1500, the center pixel of each blood vessel region in the first segmented image is determined.

[0075] In this step, for each blood vessel region in the first segmented image, the center pixel of the blood vessel region is determined. In other words, each blood vessel region corresponds to a center pixel, and when there are a plurality of blood vessel regions, a plurality of center pixels can be determined. It can be understood that for each blood vessel region, it is a connected region. For the image segmentation step of step S120, there can be a case that the segmentation result is inaccurate. However, the problem of inaccuracy mainly occurs at the junction position of the blood vessel region and other regions. The center pixel of the blood vessel region is located away from the boundary of the blood vessel region, so it is usually in the blood vessel region.

[0076] When the center pixel is determined, the position of the center pixel can be determined to facilitate subsequent operations. The center pixel can be any pixel in the blood vessel region far away from the boundary of the blood vessel region, or can be determined by calculation according to the pixels in the blood vessel region. The center pixel can be determined according to the average coordinates of the pixel positions in each blood vessel region, or can be determined according to the weight of each pixel position, or can be determined according to the median coordinates of all pixel positions, or can be the pixel in the blood vessel region at the center position.

[0077] Specifically, for each blood vessel region in the first segmented image, a center pixel in each blood vessel region can be determined according to average coordinates of pixel positions within each blood vessel region. For each blood vessel region, a first average value of row coordinates of all pixels in the blood vessel region can be calculated to take the first average value as a row coordinate value of the center pixel of the blood vessel region; a second average value of column coordinates of all pixels in the blood vessel region can be calculated to take the second average value as a column coordinate value of the center pixel of the blood vessel region.

[0078] In the technical solution, the center pixel in each blood vessel region is determined according to average coordinates of pixel positions within each blood vessel region. The center pixel thus determined is farther away from the boundary of the blood vessel region, which ensures that the center pixel is a pixel imaged for the blood vessel region, and further ensures the accuracy of the tissue attenuation image obtained based on the center pixel.

[0079] In step S1700, the blood vessel region in the first segmented image is corrected based on the center pixel and the ultrasonic image to obtain a second segmented image.

[0080] As described above, the center pixel is determined to belong to the blood vessel region, and the ultrasonic image includes original image information. The blood vessel region in the first segmented image can be corrected based on both. The correction can include expanding the boundary of the blood vessel region in the first segmented image outward or shrinking the boundary inward. For example, the pixels in the non-blood vessel region can be changed according to the center pixel of the blood vessel region and the ultrasonic image, so that the pixels in the non-blood vessel region are divided into the blood vessel region to increase the blood vessel region in the first segmented image. The pixels in the non-blood vessel region can be changed by directly adjusting the pixel value of the non-blood vessel region. For example, when the blood vessel region in the first segmented image is represented by a white pixel region and the non-blood vessel region is represented by a black pixel region, the black pixel can be directly adjusted to a white pixel to increase the blood vessel region represented by the white pixel. Similarly, the white pixel can be directly adjusted to a black pixel to decrease the blood vessel region represented by the white pixel. An additional image can also be determined according to the center pixel and the ultrasonic image, and the additional image can be merged with the first segmented image to change the pixels in the non-blood vessel region. The additional image can include a corrected blood vessel region. By merging the additional image with the first segmented image, the blood vessel region in the first segmented image can be replaced to correct the blood vessel region in the first segmented image, and the pixels in the non-blood vessel region in the first segmented image can also change. The additional image avoids the information in the ultrasonic image.

[0081] When the correction is performed, the correction can be performed on a single pixel basis or on a plurality of pixel basis.

[0082] When the first segmented image is represented by a matrix, the region composed of elements with a value of 1 represents the non-vascular region, and the region composed of elements with a value of 0 represents the vascular region, the vascular region in the first segmented image can be enlarged by adjusting the element value representing the non-vascular region to 0. Understandably, the vascular region in the first segmented image can also be reduced by adjusting the element value representing the vascular region to 1.

[0083] In step S1900, the second segmented image and the ultrasonic image are synthesized to obtain a tissue attenuation image in which the vascular region is filtered out.

[0084] When the synthesis is performed, the pixels corresponding to the vascular region in the second segmented image can be directly removed in the ultrasonic image, or the pixels can be replaced with a color that is easy to distinguish from the non-vascular region. The color that is easy to distinguish from the non-vascular region may, for example, be the color of the pixels of the vascular region in the first segmented image, so that the corresponding pixels in the ultrasonic image are directly replaced.

[0085] The second segmented image and the ultrasonic image can be synthesized by any relevant image fusion algorithm.

[0086] In the tissue attenuation image, only the pixels of the non-vascular region can be retained, or the vascular region can be retained and the pixel information of the pixels corresponding to the vascular region can be removed, so that only the effective pixels of the non-vascular region exist in the tissue attenuation image. In this way, the contrast between the vascular region and the non-vascular region in the tissue attenuation image can be improved.

[0087] In the above technical solution, the ultrasonic image containing the vascular region is subjected to image segmentation, the vascular region is corrected according to the central pixel of the vascular region in the first segmented image after the image segmentation to obtain the second segmented image, and the second segmented image and the ultrasonic image are synthesized, so that a more accurate tissue attenuation image in which the vascular region is filtered out can be obtained, which is helpful for medical personnel to make accurate diagnosis.

[0088] Figure 2 A schematic flowchart for obtaining the first segmented image according to an embodiment of the present application is shown. As shown in Figure 2 The above step S1300 can include steps S1310 to S1330.

[0089] In step S1310, for the Nth row of pixels of the ultrasonic image, the median value of the pixel values of the Nth row of pixels is determined, where N is a positive integer less than or equal to the number of rows of the ultrasonic image.

[0090] The pixel value can be a gray value, or an RGB value, or the like, without affecting the processing of the ultrasonic image. For the Nth row of pixels of the ultrasonic image, a median value of the pixel values of the row of pixels can be determined. Specifically, the pixel values of the row of pixels can be arranged in descending order, and the pixel value at the middle position of the arranged pixel values is the median value of the pixel values. For example, when N is a positive integer equal to the number of rows of the ultrasonic image, the median value of the pixel values of each row of pixels of the ultrasonic image can be determined, respectively.

[0091] In step S1320, a second absolute value corresponding to each pixel value of the Nth row of pixels is determined, respectively, and the second absolute value and a second preset threshold are compared, respectively, wherein the second absolute value is an absolute value of a difference between each pixel value of the Nth row of pixels and the median value.

[0092] The second absolute value represents a difference between the pixel value of the pixel and the second preset threshold. The greater the second absolute value, the more obvious the difference between the pixel value of the pixel and the median value. It can be understood that in the ultrasonic image, the blood vessel region only accounts for a small part, and most of the regions are other regions except the blood vessel region, so for any row of pixels of the ultrasonic image, the median value of the pixel values thereof can represent the pixel values of the other regions, and the pixel values of the pixels of the blood vessel region are significantly different from the median value. In other words, the more obvious the difference between the pixel value and the median value, the more likely the corresponding pixel is a pixel value of the blood vessel region.

[0093] The second preset threshold can be a threshold determined before the above ultrasonic image processing process, or a threshold determined during the above ultrasonic image processing process. The second preset threshold can be a fixed threshold, or can be adjusted according to the system or manually.

[0094] In step S1330, a first segmentation image is obtained according to the second pixels in the ultrasonic image, wherein the second pixels are pixels in the ultrasonic image whose corresponding second absolute values are greater than the second preset threshold, and the pixel positions of the blood vessel region in the first segmentation image correspond to the positions of the second pixels in the ultrasonic image.

[0095] Because the pixel positions of the blood vessel region in the first segmentation image correspond to the positions of the second pixels in the ultrasonic image, the position of the pixel corresponding to the second pixel in the first segmentation image can be determined according to the position of the second pixel in the ultrasonic image, and the blood vessel region in the first segmentation image can be determined, thereby obtaining the first segmentation image.

[0096] In the technical solution, the second absolute value is determined based on the median of the pixel values of each row of pixels, and the second absolute value and the second preset threshold are compared respectively, and the first segmentation image is obtained according to the second pixel. With less calculation cost, a more accurate first segmentation image is obtained.

[0097] Figure 3 A schematic flowchart of obtaining the second segmentation image according to one embodiment of the present application is shown. As shown in Figure 3 The step S1700 can include steps S1710 to S1730.

[0098] In step S1710, for the center pixel of each blood vessel region in the first segmentation image, the expansion operation is performed in the first segmentation image according to the ultrasound image with the center pixel as the initial reference pixel until a new reference pixel cannot be determined, wherein in each expansion operation, the new reference pixel is determined from a plurality of first pixels based on the pixel value corresponding to the position of the reference pixel in the ultrasound image and the pixel values corresponding to a plurality of first pixel positions adjacent to the position of the reference pixel in the ultrasound image.

[0099] In step S1720, the corrected blood vessel region in the first segmentation image is determined according to the positions of all reference pixels, wherein the all reference pixels include the center pixel and the new reference pixel.

[0100] It can be understood that because the first segmentation image is a segmentation image obtained by image segmentation of the ultrasound image, each pixel position in the first segmentation image can correspond to a pixel value in the ultrasound image.

[0101] In the above steps, for each blood vessel region in the first segmentation image, the corresponding pixel value in the ultrasound image is used to correct the blood vessel region to obtain the corrected blood vessel region of the first segmentation image.

[0102] For each blood vessel region in the first segmented image, the following operations can be performed. First, the center pixel position of the blood vessel region in the first ultrasound image is determined, and the determined center pixel position is determined as the initial position for the expansion operation. The center pixel position corresponding to the pixel in the ultrasound image is determined, and the expansion operation is used to determine the new reference pixel based on the current reference pixel, i.e., to expand the current blood vessel region in the first segmented image, which can be performed once or multiple times. When the expansion operation is performed once, but the new reference pixel is not determined, the expansion operation for the current blood vessel region ends. Specifically, each time the expansion operation is performed, the pixel value corresponding to the reference pixel position in the ultrasound image can be determined according to the current reference pixel position in the first segmented image, and the pixel values corresponding to the first pixels at the adjacent positions of the reference pixel in the ultrasound image are determined. The pixel value corresponding to the reference pixel position in the ultrasound image and the pixel values corresponding to the first pixels at the adjacent positions of the reference pixel in the ultrasound image can be respectively subtracted, divided, or processed in other manners to determine the difference between the pixel value corresponding to the reference pixel position in the ultrasound image and the pixel values corresponding to the first pixels at the adjacent positions of the reference pixel in the ultrasound image. When the difference is small, it indicates that the reference pixel and the first pixels at the adjacent positions of the reference pixel both belong to the blood vessel region. In other words, during the expansion operation, when the difference between the pixel value of the determined reference pixel and the pixel value of the first pixel is small, the first pixel can be determined as the new reference pixel of the blood vessel region. When the difference between the two pixel values is large, it indicates that the first pixel does not belong to the blood vessel region, and thus, it cannot be used as the new reference pixel of the blood vessel region. If no new reference pixel is found for all the current reference pixels, the expansion operation for the blood vessel region ends.

[0103] Exemplarily, after all the expansion operations are completed, the pixels in the first segmented image corresponding to the positions of the reference pixels are determined as the pixels in the modified blood vessel region, so that the pixels in the modified blood vessel region in the first segmented image are determined. It can be understood that the modified blood vessel region in the first segmented image can be different from the blood vessel region in the first segmented image before the expansion operation. In other words, according to all the reference pixels in the ultrasound image, the modified blood vessel region in the first segmented image can be determined, so that the first segmented image can be modified.

[0104] Alternatively, after all the expansion operations are completed, the blood vessel region in the second segmented image can be determined according to both the pixels of the blood vessel region in the first segmented image and the reference pixels determined after the expansion operation. In this alternative example, the pixels in the first segmented image corresponding to the positions of the aforementioned two types of pixels are both used as the pixels in the modified blood vessel region.

[0105] At step S1730, the second segmentation image is determined according to the modified blood vessel region in the first segmentation image.

[0106] It can be understood that after all the expansion operations are completed, the non-blood vessel region in the first segmentation image is modified while the blood vessel region in the first segmentation image is modified, and thus the modified non-blood vessel region in the first segmentation image can be obtained.

[0107] After the modified blood vessel region in the first segmentation image is determined, the pixels of the modified blood vessel region in the first segmentation image can be taken as the pixels of the blood vessel region in the second segmentation image, and the pixels of the modified non-blood vessel region in the first segmentation image can be taken as the pixels of the non-blood vessel region in the second segmentation image. In this way, the second segmentation image can be determined. The blood vessel region in the second segmentation image corresponds one-to-one to the modified blood vessel region in the first segmentation image.

[0108] For example, the first segmentation image after all the expansion operations are completed can also be subjected to a processing operation, and then the first segmentation image after the processing operation is taken as the second segmentation image. The processing operation can include a denoising operation, a filtering operation, a pixel transformation operation, and the like, which improves the accuracy of the blood vessel region in the first segmentation image.

[0109] In this alternative example, the step S1730 described above can include determining the second segmentation image according to the positions of the pixels in the modified blood vessel region in the first segmentation image, wherein the blood vessel region in the second segmentation image includes the pixels corresponding to the pixel positions in the modified blood vessel region in the first segmentation image.

[0110] In the process of performing the above steps, all the reference pixels in the first segmentation image can be determined as the pixels of the modified blood vessel region, and then the pixels of the modified blood vessel region in the first segmentation image are taken as the pixels in the blood vessel region in the second segmentation image. It can be understood that for the pixels in this part of pixels that originally belong to the blood vessel region, they can remain unchanged; for the pixels in this part of pixels that originally belong to the non-blood vessel region, the pixel values thereof can be changed so as to belong to the blood vessel region. In the example of the first segmentation image in which the pixel values of the pixels of the blood vessel region are 0 and the pixel values of the pixels of the non-blood vessel region are 1, the pixel values of all the pixels can be set to 0 so that the pixel values of the pixels at the positions of the modified blood vessel region in the first segmentation image are all set to 0. At this time, the first segmentation image after the change can be taken as the second segmentation image, wherein the blood vessel region in the second segmentation image not only includes the pixels with the pixel value set to 0, but also retains the original blood vessel region in the first segmentation image.

[0111] In the scheme of the above alternative example, the pixels in the corrected blood vessel region in all the first segmented images are integrated to determine the pixels in the blood vessel region in the second segmented image. The blood vessel region is increased based on the expansion operation while the blood vessel region before the expansion operation is retained, so that the determined blood vessel region is more accurate, and the accuracy of the second segmented image is ensured.

[0112] In the technical scheme, the reference pixels are determined, the expansion operation is performed in the first segmented image based on the ultrasonic image in a loop, new reference pixels are determined in the first pixels adjacent to the positions of the reference pixels, the corrected blood vessel region in the first segmented image is determined based on the determined reference pixels after the loop expansion operation is completed, and the second segmented image is obtained. The expansion of the blood vessel region is performed in a pixel unit one by one, so that the corrected blood vessel region in the first segmented image can be more accurately determined, and the second segmented image can be more accurately determined based on the corrected blood vessel region in the first segmented image.

[0113] Figure 4 A schematic flowchart of the expansion operation according to one embodiment of the present application is shown. It can be understood that the expansion operation is performed for each blood vessel region in the first segmented image. As shown in Figure 4 The expansion operation can include steps S1711 to S1713.

[0114] In step S1711, the average value of the pixel values corresponding to all the current reference pixels in the ultrasonic image is determined.

[0115] It can be understood that the current all reference pixels are the blood vessel region in the first segmented image, which is subjected to the current expansion operation. At the start of the expansion operation, the current all reference pixels only include one initial reference pixel, that is, the center pixel of each blood vessel region in the first image. The number of the current all reference pixels can increase with the performance of the loop expansion operation.

[0116] In step S1712, the first absolute value of the difference between the pixel value corresponding to each first pixel in the ultrasonic image and the average value is determined.

[0117] The first pixel can be determined according to the current at least part of the reference pixels. It can be understood that the current reference pixels constitute a connected domain at any time. The first pixel can be determined according to the edge pixels in the connected domain. Specifically, for example, the first pixel can be determined according to the current first row and last row of reference pixels and the first reference pixel and the last reference pixel in each current row of reference pixels. Only the pixels adjacent to these reference pixels in the ultrasonic image are determined as the first pixel.

[0118] The first pixel can change as the extension operation is performed in the ultrasound image. For each first pixel, an absolute value of a difference between the first pixel and the average value determined in step S1711 is determined, which is referred to as a first absolute value. The first absolute value represents a difference between the first pixel and the average value, i.e., a difference between the first pixel and the current reference pixel. The greater the first absolute value, the more obvious the difference between the first pixel and the current reference pixel.

[0119] In step S1713, a new reference pixel is selected from the first pixels according to the first absolute values.

[0120] When the first absolute value is small, it indicates that the first pixel is similar to the current reference pixel. A third preset threshold can be preset. The first absolute value is compared with the third preset threshold. If the first absolute value is less than the third preset threshold, the first pixel is considered to be similar to the current reference pixel, and both of them are classified as pixels in the blood vessel region.

[0121] For example, after the new reference pixel is selected from the first pixels, the determined reference pixels change, and the determined reference pixels include the new reference pixel and the initial reference pixel. The extension operation can be performed again to determine a new reference pixel according to the determined reference pixels and the first pixels adjacent to the new reference pixel, until all the extension operations are performed and all the reference pixels are determined.

[0122] In the technical solution, the new reference pixel is determined from the first pixels according to the absolute value of the difference between the pixel value of each first pixel and the average value of the pixel value of the reference pixel. In this solution, the average value changes with the current reference pixel, so that the change of the pixel value of the pixel in the blood vessel region at different positions in the ultrasound image is considered when the new reference pixel is determined, the reference pixel representing the blood vessel region can be determined more accurately, and the second segmentation image can be determined more accurately.

[0123] Figure 5 A schematic flowchart of determining a new reference pixel from the first pixels according to the first absolute value is shown according to an embodiment of the present application. As shown in Figure 5 The step S1713 can include steps S713a and S713b.

[0124] In step S713a, a minimum first absolute value is determined from the first absolute values, and the minimum first absolute value is compared with the first preset threshold to obtain a comparison result.

[0125] As described in the previous step S1712, for each first pixel, the difference between the pixel value of the first pixel and the average value is calculated, and the first absolute value of the difference is calculated. For a blood vessel region, a plurality of first absolute values can be determined. All the first absolute values corresponding to the blood vessel region can be compared to determine the minimum first absolute value. Then, the minimum first absolute value is compared with a first preset threshold. The first preset threshold can be a threshold determined before the ultrasound image processing, or a threshold determined during the ultrasound image processing. The first preset threshold can be a fixed threshold, or can be adjusted according to the system or manually.

[0126] In step S713b, when the comparison result of step S713a indicates that the minimum first absolute value is less than the first preset threshold, the first pixel corresponding to the minimum first absolute value is determined as the new reference pixel.

[0127] It can be understood that the minimum first absolute value can correspond to one first pixel, or can correspond to a plurality of first pixels. When the minimum first absolute value corresponds to only one first pixel, the one first pixel is determined as the new reference pixel in the second expansion operation. When the minimum first absolute value corresponds to a plurality of first pixels, the plurality of first pixels can be simultaneously determined as the new reference pixel.

[0128] When the comparison result indicates that the minimum first absolute value is not less than the first preset threshold, it indicates that the blood vessel region has been completely determined, and the expansion operation can be ended. At this time, the obtained reference pixels constitute a new blood vessel region.

[0129] In the above technical solution, the pixel value closest to the average value is first determined in the first pixel, and then whether the first pixel can be determined as the reference pixel is determined according to the difference between the two. In this way, the accuracy of the determined blood vessel region is guaranteed, and the calculation amount is small.

[0130] As described above, in the above ultrasound image processing method, steps S1500 and S1700 are performed for each blood vessel region in the ultrasound image, so that a second segmentation image containing accurate blood vessel region information is obtained. It can be understood that various noises can exist in the ultrasound image. These noises disturb the identification and segmentation of the blood vessel region. In other words, these noises are not blood vessel regions, but can be mistakenly segmented as blood vessel regions in step S1300. Therefore, before step S1500, the above ultrasound image processing method can further include a step of filtering the blood vessel region.

[0131] Figure 6 A schematic flowchart of filtering the blood vessel region according to an embodiment of the present application is shown. As Figure 6As shown, the step S1500 can be preceded by steps S1410 to S1420.

[0132] In step S1410, the area of each blood vessel region in the first segmented image is determined.

[0133] The number of pixels in each blood vessel region can be determined, and the determined number of pixels in each blood vessel region can be taken as the area of each blood vessel region. Alternatively, the area of each blood vessel region can be determined by area calculation based on the position coordinates of the pixels in each blood vessel region.

[0134] In step S1420, the blood vessel region whose determined area is less than the area threshold value is deleted.

[0135] The area threshold value can be a threshold value determined before the ultrasound image processing or a threshold value determined during the ultrasound image processing. The area threshold value can be a fixed threshold value or adjusted by a system or manually. The area threshold value can be the number of pixels or an area value.

[0136] It can be understood that the noise region usually has a smaller area compared to the real blood vessel region. In the technical solution described above, the small-area noise region that is incorrectly identified can be removed by deleting the blood vessel region whose determined area is less than the area threshold value, which not only avoids the interference of the noise region on the identification of the blood vessel region, but also more accurately determines the blood vessel region and reduces the calculation amount in the subsequent steps.

[0137] Exemplarily, before the ultrasound image is segmented in step S1300 described above, the method further includes step S1210 of denoising the ultrasound image to obtain a denoised ultrasound image. The denoising can be any image denoising method, such as mean filtering, wavelet denoising, median filtering, etc., to reduce the noise in the ultrasound image.

[0138] For example, the ultrasound image can be denoised by median filtering. When the ultrasound image is median filtered, a median filtering kernel can be determined, and then the ultrasound image can be median filtered according to the median filtering kernel to obtain a filtered ultrasound image. The median filtering can remove the fine noise in the ultrasound image.

[0139] In the technical solution described above, the fine noise in the ultrasound image can be removed by denoising the ultrasound image, which reduces the interference of the noise on the processing of the ultrasound image and more accurately determines the blood vessel region.

[0140] Exemplarily, before the image segmentation of the ultrasonic image in the step S1300, the method further includes a step S1220 of normalizing pixel values corresponding to pixels in the ultrasonic image to obtain a normalized ultrasonic image. A maximum pixel value can be determined in the pixel values of the pixels in the ultrasonic image, and the corresponding pixel values are normalized according to the proportion of each pixel value to the maximum pixel value to obtain the normalized ultrasonic image.

[0141] Here, the normalization can be any normalization mode required, such as maximum-minimum normalization, range normalization, logarithmic normalization, etc.

[0142] In the technical solution, the normalization of the ultrasonic image can accelerate the processing speed of the system for the ultrasonic image, and improve the efficiency of determining the blood vessel region in the ultrasonic image.

[0143] Alternatively, other numerical conversion methods other than normalization can also be used to perform noise reduction operation on the ultrasonic image, such as Z-score standardization, etc.

[0144] Exemplarily, the above steps can be implemented by an artificial intelligence model. The type and architecture of the artificial intelligence model are not limited here.

[0145] Figure 7 A schematic flowchart of an ultrasonic image processing method according to another embodiment of the present application is shown.

[0146] As Figure 7 shown, a frame of ultrasonic image can be obtained by an ultrasonic host, and the ultrasonic image can be represented by a matrix of M rows and N columns, which corresponds to the scanning range of acoustic attenuation imaging. The ultrasonic image can be analyzed and processed to determine the blood vessel region therein. First, the ultrasonic image can be normalized and small noise in the ultrasonic image can be removed by median filtering. For the ultrasonic image, the maximum value max(Image) of the pixel values of all pixels in the ultrasonic image can be found, and based on the maximum value of the pixel values, the normalized result NormImage = Image / max(Image) is output, where Image represents the pixel value of the pixel. The output normalized result NormImage is subjected to median filtering. Assuming that the median filtering kernel is MedCor, the output result of the median filtering is represented by a matrix MedImage, and it can be understood that MedImage represents the ultrasonic image after median filtering.

[0147] Afterwards, threshold judgment can be made on the pixel values of all pixels in MedImage to obtain a first segmentation image by image segmentation. It can be understood that the first segmentation image can be represented by a matrix MaskSignal. The median value of the elements of each row of MedImage is obtained, where the median value is the median of the element values of each row of elements, to obtain a corresponding vector Med (a total of M elements). All elements in MaskSignal are initialized to 1, and the corresponding element is set to 0 according to the absolute value of the difference between the numerical value of each element in each row and the median value. When the absolute value of the difference between the numerical value of an element in a row and the median value is greater than a second preset threshold T, the element can be set to 0. Subsequently, MaskSignal can be further processed to become a second segmentation image VasMask that can accurately locate the blood vessel region.

[0148] Small-range noise blocks in MaskSignal can be filtered out. All elements in MaskSignal are traversed, and when a current element is 1 and the element to the right or below is 0, an element with a value of 0 is used as a starting element, and all elements with a value of 0 connected to the element are found by deep recursion, and the coordinates of these elements are recorded. When the number of these elements is less than an area threshold MinArea, all these elements are set to 1, and if it is greater than MinArea, the center element coordinates of these elements are found and recorded as the center pixel of the blood vessel region in the first segmentation image. The function of the above deep search can be used to search for elements that meet the conditions connected to the target position, and store the corresponding coordinates of the elements in the variable Points. The stored elements correspond to the pixels in the blood vessel region, and the number of elements stored in Points is used to determine whether to filter out the corresponding region. If the region is not filtered out, the center pixel of the region is calculated and its position coordinates are stored in the matrix PointsForExpend as input data for subsequent neighborhood mean blood vessel subtraction operation.

[0149] After the above steps, the result MaskSignal filtered out by small-range noise points and the center element set matrix PointsForExpend can be obtained. Subsequently, the second segmentation image VasMask can be calculated by combining the results of the median filtering MedImage and the two sets of input.

[0150] Assuming that the position coordinate stored in PointsForExpend read is (x, y), the coordinate is stored in the set matrix VasPoints for recording the position coordinates of the reference pixels. Four elements adjacent to (x, y) are (x-1, y), (x+1, y), (x, y-1), and (x, y+1), which are stored in the set matrix VasPointsBackup. A mean threshold MeanMin (a first preset threshold) is set. The average value of the gray scale values of all coordinates in VasPoints corresponding to the pixels (reference pixels) in MedImage is calculated as VasPointsGray. For all coordinates in the set matrix VasPointsBackup, the gray scale values of the corresponding pixels (first pixels) in MedImage are obtained, and the value closest to VasPointsGray and the corresponding coordinate are found. If the absolute value of the difference between the value and VasPointsGray (a first absolute difference) is less than MeanMin, the corresponding coordinate is stored in the matrix VasPoints as a new reference pixel, and the above process is repeated until no new reference pixel is generated. Finally, for the input coordinate (x, y), the extended coordinate result VasPoints can be obtained, and the extended coordinate result VasPoints corresponds to the pixel position of the blood vessel region in the second segmented image.

[0151] The above operation is repeated for all coordinates in PointsForExpend, that is, the extended operation is performed in a loop to obtain the coordinate set of all pixel positions of the blood vessel region. The pixel values of the corresponding positions in MaskSignal can be set to zero, that is, the output VasMask.

[0152] The median filter core MedCor, the second preset threshold T, the area threshold MinArea, and the first preset threshold MeanMin are set to appropriate default values. Through the above ultrasonic image processing method, a VasMask for blood vessel removal can be obtained. The ultrasonic image is superimposed with the VasMask to obtain a tissue attenuation image with the blood vessels filtered out.

[0153] Before the above ultrasonic image processing method is executed to output the tissue attenuation image, it can be determined whether to use an adaptive algorithm. When it is determined to use the adaptive algorithm, first, the attenuation value determined by the user is obtained, and the related parameters are set according to the range in which the attenuation value is located. Then, the above ultrasonic image processing method is executed using the set related parameters to filter out the blood vessels in the ultrasonic image and output the tissue attenuation image with the blood vessel region filtered out. The attenuation value range can be divided into three levels. Table 1 shows the relationship between the attenuation value and the parameter setting.

[0154] Table 1

[0155]

[0156] In Table 1, "3×3", "5×5", and "7×7" represent the sizes of different median filter kernels. T1, T2, and T3 represent the second preset thresholds corresponding to different attenuation ranges, MinArea1, MinArea2, and MinArea3 represent the area thresholds corresponding to different attenuation ranges, and MeanMin1, MeanMin2, and MeanMin3 represent the first preset thresholds corresponding to different attenuation ranges. When it is determined that the adaptive algorithm is not used, the tissue attenuation image after filtering out blood vessels can be directly output.

[0157] Figure 8 A schematic block diagram of an ultrasound host according to an embodiment of the present invention is shown. Figure 8 As shown, the ultrasound host can acquire ultrasound images containing at least one vascular region, and obtain a tissue attenuation image with the vascular region filtered out according to the aforementioned ultrasound image processing method. The ultrasound host may include an image display area that can display the ultrasound image containing at least one vascular region. The ultrasound host may be equipped with an input device, such as a button, mouse, keyboard, or touchscreen. The user can use the input device to activate the aforementioned ultrasound image processing method and input an attenuation value. Figure 8 The touchscreen shown can display options for triggering the aforementioned ultrasonic image processing procedure, such as... Figure 8 The "Adaptive Vascular Filtration" option is shown. Figure 8 The "Adaptive Vascular Filtering" option shown can also be other control components displayed on the touchscreen to prompt the user to activate the aforementioned ultrasound image processing method. The ultrasound host may also include hardware that, when operated by the user, can activate the aforementioned ultrasound image processing method. This hardware structure can be a control component such as a button or knob, or it can be the aforementioned input device.

[0158] Figure 9 A schematic block diagram of an ultrasonic image processing apparatus 800 according to an embodiment of the present invention is shown. Figure 9 As shown, the ultrasonic image processing device 800 includes an image receiving module 810, an image segmentation module 830, an image determination module 850, an image correction module 870, and an image synthesis module 890.

[0159] Image receiving module 810 is used to acquire ultrasound images containing at least one vascular region.

[0160] The image segmentation module 830 is configured to perform image segmentation on the ultrasonic image to obtain a first segmentation image, the first segmentation image comprising the blood vessel region.

[0161] The image determination module 850 is configured to determine a center pixel of each blood vessel region in the first segmentation image.

[0162] The image correction module 870 is configured to correct the blood vessel region in the first segmentation image based on the center pixel and the ultrasonic image to obtain a second segmentation image.

[0163] The image synthesis module 890 is configured to synthesize the second segmentation image and the ultrasonic image to obtain a tissue attenuation image in which the blood vessel region is filtered out.

[0164] Exemplarily, the image correction module 870 comprises a first correction submodule, a second correction submodule and a third correction submodule. The first correction submodule is configured to, for the center pixel of each blood vessel region in the first segmentation image, perform an expansion operation in the first segmentation image with the center pixel as an initial reference pixel, until a new reference pixel cannot be determined, wherein the expansion operation is specifically: determining the new reference pixel from a plurality of first pixels based on a pixel value corresponding to a position of the reference pixel in the ultrasonic image and pixel values corresponding to a plurality of first pixel positions adjacent to the position of the reference pixel in the ultrasonic image. The second correction submodule is configured to determine a corrected blood vessel region in the first segmentation image according to positions of all reference pixels, wherein the all reference pixels comprise the center pixel and the new reference pixel. The third correction submodule is configured to determine the second segmentation image according to the corrected blood vessel region in the first segmentation image.

[0165] Exemplarily, the image determination module 850 comprises a mean value determination submodule, a difference value determination submodule and a first determination submodule. The mean value determination submodule is configured to determine a mean value of pixel values corresponding to all reference pixels in the ultrasonic image. The difference value determination submodule is configured to determine a first absolute value of a difference between a pixel value corresponding to each first pixel in the ultrasonic image and the mean value. The first determination submodule is configured to select the new reference pixel from the plurality of first pixels according to the first absolute value.

[0166] Exemplarily, the image determination module 850 can further comprise a first numerical value comparison submodule and a second determination submodule. The numerical value comparison submodule is configured to determine a smallest first absolute value from the first absolute values, and compare the smallest first absolute value with a first preset threshold to obtain a comparison result. The second determination submodule is configured to, if the comparison result indicates that the smallest first absolute value is smaller than the first preset threshold, determine the first pixel corresponding to the smallest first absolute value as the new reference pixel.

[0167] Exemplarily, the image correction module 870 can further include a fourth correction sub-module. The fourth correction sub-module is configured to determine a second segmented image according to the positions of the pixels in the corrected blood vessel region in the first segmented image, wherein the blood vessel region in the second segmented image comprises the pixels corresponding to the positions of the pixels in the corrected blood vessel region in the first segmented image.

[0168] Exemplarily, the image correction module 870 can further include a center pixel determination sub-module. The center pixel determination sub-module is configured to determine, for each blood vessel region in the first segmented image, a center pixel in the blood vessel region according to average coordinates of the positions of the pixels in the blood vessel region.

[0169] Exemplarily, the image segmentation module 830 can include a median value determination sub-module, a second value comparison sub-module, and an image segmentation sub-module. The median value determination sub-module is configured to determine a median value of the pixel values of the Nth row of pixels in the ultrasonic image, wherein N is a positive integer less than or equal to the number of rows of the ultrasonic image. The second value comparison sub-module is configured to determine a second absolute value corresponding to each pixel value of the Nth row of pixels respectively, and compare the second absolute value and a second preset threshold value respectively, wherein the second absolute value is the absolute value of the difference between each pixel value of the Nth row of pixels and the median value. The image segmentation sub-module is configured to obtain a first segmented image according to the second pixels in the ultrasonic image, wherein the second pixels are the pixels in the ultrasonic image corresponding to the second absolute values greater than the second preset threshold value, and the positions of the pixels in the blood vessel region in the first segmented image correspond to the positions of the second pixels in the ultrasonic image.

[0170] Exemplarily, the ultrasonic image processing apparatus 800 can further include an area determination module. The area determination module can include an area determination sub-module and an area comparison sub-module. The area determination sub-module is configured to determine the area of each blood vessel region in the first segmented image before the ultrasonic image is segmented. The area comparison sub-module is configured to delete the blood vessel region with an area less than an area threshold value.

[0171] Exemplarily, the ultrasonic image processing apparatus 800 can further include a noise reduction module. The noise reduction module is configured to reduce the noise of the ultrasonic image to obtain a noise-reduced ultrasonic image before the ultrasonic image is segmented.

[0172] Exemplarily, the ultrasonic image processing apparatus 800 can further include a normalization module. The normalization module is configured to normalize the pixel values corresponding to the pixels in the ultrasonic image to obtain a normalized ultrasonic image before the ultrasonic image is segmented.

[0173] According to another aspect of the present application, an electronic device is also provided. Figure 10 A schematic block diagram of an electronic device 900 according to an embodiment of the present application is shown. As shown in FIG. 9, the electronic device 900 can include an ultrasonic image processing apparatus 910 and a display 920.Figure 10 As shown, the electronic device 900 includes a processor 910 and a memory 920, wherein the memory 920 stores computer program instructions, and the computer program instructions are used to execute the ultrasonic image processing method as described above when executed by the processor 910.

[0174] In addition, according to another aspect of the present application, there is also provided a storage medium, on which program instructions are stored, and the program instructions, when executed by a computer or a processor, cause the computer or the processor to perform the corresponding steps of the ultrasonic image processing method of the embodiments of the present application, and are used to implement the corresponding modules in the ultrasonic image processing apparatus according to the embodiments of the present application. The storage medium may, for example, include a memory card of a smart phone, a storage component of a tablet computer, a hard disk of a personal computer, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disc read-only memory (CD-ROM), a USB memory, or any combination of the above storage media. The computer-readable storage medium can be any combination of one or more computer-readable storage media.

[0175] According to another aspect of the present application, there is also provided a computer program product, including computer program instructions, which, when executed, are used to execute the ultrasonic image processing method described above.

[0176] Those skilled in the art can understand the specific implementation and advantages of the ultrasonic image processing apparatus, the electronic device, the storage medium and the computer program product by reading the above specific description of the ultrasonic image processing method, and for brevity, will not be repeated here.

[0177] Although the example embodiments have been described herein with reference to the accompanying drawings, it is to be understood that the example embodiments are merely exemplary and are not intended to limit the scope of the present application. Those skilled in the art can make various changes and modifications without departing from the scope and spirit of the present application. All such changes and modifications are intended to be included within the scope of the present application as claimed in the appended claims.

[0178] Those skilled in the art can realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be realized in electronic hardware, or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0179] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the above-described device embodiments are merely illustrative, and the division of the units is merely a logical function division. In actual implementation, another division manner can be used, for example, a plurality of units or components can be combined or integrated into another device, or some features can be omitted or not executed.

[0180] In the specification provided herein, a large number of specific details are described. However, it can be understood that the embodiments of the present application can be practiced without these specific details. In some examples, well-known methods, structures and techniques are not described in detail in order not to obscure the understanding of the present specification.

[0181] Similarly, it should be appreciated that, in the description of the exemplary embodiments of the present application, various features of the present application are sometimes grouped together in a single embodiment, figure, or description of a related aspect. This is done for the purpose of clarity in understanding the present application. However, it should be understood that the method of the present application is not limited in this manner. In accordance with the application, features from different embodiments can be combined to make or implement a different embodiment of the present application. Therefore, the following claims are hereby expressly intended to include all possible combinations of the features described herein.

[0182] Those of skill in the art will understand that, in addition to the features described herein, all of the features of the specification (including the accompanying claims, abstract and drawings), and all of the steps or elements of any method or device so described, can be combined in any combination by those of skill in the art. Each feature disclosed in the specification (including the accompanying claims, abstract and drawings), can be replaced by alternative features that serve the same, equivalent or similar purpose, unless expressly stated otherwise.

[0183] In addition, those of skill in the art will appreciate that the features of the different embodiments described herein can be combined in any combination, that the features of the different embodiments are meant to be within the scope of the present application and form different embodiments of the present application. For example, in the claims, any of the claimed embodiments can be used in any combination.

[0184] The various component embodiments of the present application can be implemented in hardware, or as software modules running in one or more processors, or combinations thereof. Those skilled in the art will appreciate that some or all of the functions of some of the modules in the ultrasound image processing apparatus according to the embodiments of the present application can be implemented in practice using a microprocessor or a digital signal processor (DSP). The present application can also be implemented as a program (for example, a computer program and a computer program product) for executing some or all of the methods described herein. Such a program implementing the present application can be stored on a computer-readable medium, or can be in the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or in any other form.

[0185] It should be noted that the above-mentioned embodiments illustrate rather than limit the application, and that one skilled in the art will be able to design many alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word 'comprising' does not exclude the presence of elements or steps other than those listed in a claim. The word 'a' or 'an' preceding an element does not exclude the presence of a plurality of such elements. The application can be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In a unitary claim, several of the devices, apparatuses or means, if any, can be implemented by one and the same item of hardware. The use of the words 'first','second' and 'third', etc. do not imply any order but rather are used for identification purposes only. The word 'plurality' does not imply a specific number of elements.

[0186] The above description is only specific embodiments or specific implementations of the present application, and the protection scope of the present application is not limited thereto. Any skilled person in the art can easily think of changes or replacements within the technical range disclosed by the present application, and all of them should be covered within the protection scope of the present application. The protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An ultrasonic image processing method, characterized in that, The method includes: Acquire ultrasound images containing at least one vascular region; For the blood vessel region in the ultrasound image, the ultrasound image is segmented to obtain a first segmented image, the first segmented image including the blood vessel region; Determine the center pixel of each of the blood vessel regions in the first segmented image; Based on the center pixel and the ultrasound image, the blood vessel region in the first segmented image is corrected to obtain a second segmented image; and The second segmented image and the ultrasound image are combined to obtain a tissue attenuation image with the vascular region filtered out.

2. The method according to claim 1, characterized in that, The step of correcting the blood vessel region in the first segmented image based on the center pixel and the ultrasound image to obtain the second segmented image includes: For the center pixel of each blood vessel region in the first segmented image, the expansion operation is performed cyclically in the first segmented image based on the ultrasound image, using the center pixel as the initial reference pixel, until a new reference pixel cannot be determined. Specifically, the expansion operation involves determining a new reference pixel among several first pixels based on the pixel value corresponding to the reference pixel position in the ultrasonic image and the pixel values ​​corresponding to several first pixel positions adjacent to the reference pixel position in the ultrasonic image. Based on the positions of all reference pixels, the corrected blood vessel region in the first segmented image is determined, wherein all reference pixels include the center pixel and the new reference pixel; The second segmented image is determined based on the corrected blood vessel region in the first segmented image.

3. The method according to claim 2, characterized in that, The step of determining the new reference pixel from among the plurality of first pixels based on the pixel value corresponding to the reference pixel position in the ultrasonic image and the pixel values ​​corresponding to a plurality of first pixel positions adjacent to the reference pixel position in the ultrasonic image includes: Determine the average value of the pixel values ​​corresponding to all the current reference pixels in the ultrasonic image; Determine a first absolute value of the difference between the pixel value corresponding to each first pixel in the ultrasonic image and the average value; Based on the first absolute value, the new reference pixel is selected from all the first pixels.

4. The method according to claim 3, characterized in that, The step of selecting the new reference pixel from all the first pixels based on the first absolute value includes: Determine the smallest first absolute value among the first absolute values, and compare the smallest first absolute value with a first preset threshold to obtain a comparison result; If the comparison result indicates that the smallest first absolute value is less than the first preset threshold, then the first pixel corresponding to the smallest first absolute value is determined as the new reference pixel.

5. The method according to claim 2, characterized in that, Determining the second segmented image based on the corrected blood vessel region in the first segmented image includes: The second segmented image is determined based on the position of pixels in the corrected blood vessel region in the first segmented image, wherein the blood vessel region in the second segmented image includes pixels corresponding to the pixel positions in the corrected blood vessel region in the first segmented image.

6. The method according to claim 1, characterized in that, Determining the center pixel of each blood vessel region in the first segmented image includes: For each blood vessel region in the first segmented image, the center pixel in each blood vessel region is determined based on the average coordinates of the pixel positions within each blood vessel region.

7. The method according to any one of claims 1 to 6, characterized in that, The step of segmenting the ultrasound image for the vascular region in the ultrasound image to obtain a first segmented image includes: For the Nth row of pixels in the ultrasound image, determine the median pixel value of the Nth row of pixels, where N is a positive integer less than or equal to the number of rows in the ultrasound image; Determine the second absolute value corresponding to each pixel value of the Nth row of pixels, and compare the second absolute value with the second preset threshold, wherein the second absolute value is the absolute value of the difference between each pixel value of the Nth row of pixels and the median value; The first segmented image is obtained based on the second pixel in the ultrasound image, wherein the second pixel is a pixel in the ultrasound image whose corresponding second absolute value is greater than the second preset threshold, and the pixel position of the blood vessel region in the first segmented image corresponds to the position of the second pixel in the ultrasound image.

8. The method according to any one of claims 1 to 6, characterized in that, Before determining the center pixel of each blood vessel region in the first segmented image, the method further includes: Determine the area of ​​each blood vessel region in the first segmented image; Delete the identified blood vessel regions whose area is smaller than the area threshold.

9. The method according to any one of claims 1 to 6, characterized in that, Before performing image segmentation on the ultrasound waves, the method further includes: The ultrasonic image is denoised to obtain a denoised ultrasonic image.

10. The method according to any one of claims 1 to 6, characterized in that, Before performing image segmentation on the ultrasound waves, the method further includes: The pixel values ​​corresponding to the pixels in the ultrasonic image are normalized to obtain a normalized ultrasonic image.

11. An ultrasonic image processing device, characterized in that, include: Image receiving module, used to acquire ultrasound images containing at least one vascular region; An image segmentation module is used to segment the ultrasound image for the blood vessel region in the ultrasound image to obtain a first segmented image, wherein the first segmented image includes the blood vessel region. An image determination module is used to determine the center pixel of each blood vessel region in the first segmented image; An image correction module is used to correct the blood vessel region in the first segmented image based on the center pixel and the ultrasound image to obtain a second segmented image. as well as An image synthesis module is used to synthesize the second segmented image and the ultrasound image to obtain a tissue attenuation image with the vascular region filtered out.

12. An electronic device comprising a processor and a memory, characterized in that, The memory stores computer program instructions, which, when executed by the processor, are used to perform the ultrasonic image processing method as described in any one of claims 1 to 10.

13. A storage medium on which program instructions are stored, characterized in that, The program instructions, when executed, are used to perform the ultrasonic image processing method as described in any one of claims 1 to 10.

14. A computer program product comprising computer program instructions, characterized in that, The computer program instructions, when executed, are used to perform the ultrasonic image processing method as described in any one of claims 1 to 10.

Images