Ultrasonic blood flow chart processing method, device and equipment and storage medium

Abstract

The invention discloses an ultrasonic blood flow chart processing method, device and equipment and a storage medium, and is applied to the field of medical treatment.The method comprises the steps that an ultrasonic blood flow chart is obtained; identifying blood vessel boundaries, blood vessel interiors and tissues in the ultrasonic blood flow graph, and marking to obtain a marked graph; determining a first filter corresponding to the blood vessel boundary, a second filter corresponding to the blood vessel interior and a third filter corresponding to the tissue according to the mark graph; filtering the blood vessel boundary by using a first filter; filtering the inside of the blood vessel by using a second filter; filtering the tissue by using a third filter; the filtered ultrasonic blood flow graph is obtained. According to the ultrasonic blood flow image processing method provided by the invention, different optimal filters can be selected to remove clutter signals according to different types of blood vessel interiors, blood vessel boundaries and tissues in the collected ultrasonic blood flow images, so that the purpose that the ultrasonic blood flow image reflects real blood flow is achieved.

Description

Technical Field

[0001] The present application relates to the field of medical processing, and in particular to an ultrasonic blood flow image processing method, device, equipment and storage medium. Background Art

[0002] In the process of forming an ultrasonic blood flow image, ultrasonic color flow imaging technology will generate clutter signals due to tissue movement and it is not easy to remove. The energy of this part of the clutter signal is 60-80dB higher than the energy of the useful blood flow signal. If the clutter signal cannot be effectively removed, the useful blood flow signal will be submerged in the clutter signal and cannot be detected.

[0003] At present, wavelet transform algorithm is usually used to remove clutter signals caused by tissue movement. However, due to the different combined ratios of signal energy reflected by blood flow and tissue movement, if the same filtering method is used to filter out the influence of tissue movement, the clutter signals caused by tissue movement will not be removed cleanly, and the real blood flow signal cannot be obtained well. Summary of the invention

[0004] In view of this, the purpose of the present application is to provide an ultrasonic blood flow image processing method, device, equipment and storage medium, which solves the problem in the prior art that the blood flow signal is not true due to unclean removal of clutter signals.

[0005] In order to solve the above technical problems, the present application provides an ultrasonic blood flow image processing method, comprising:

[0006] Obtain ultrasound blood flow diagram;

[0007] Identifying blood vessel boundaries, blood vessel interiors and tissues in the ultrasonic blood flow map, and marking them to obtain a marked map;

[0008] Determine, according to the label map, a first filter corresponding to the blood vessel boundary, a second filter corresponding to the interior of the blood vessel, and a third filter corresponding to the tissue;

[0009] The first filter is used to filter the blood vessel boundary; the second filter is used to filter the inside of the blood vessel; the third filter is used to filter the tissue; so as to obtain a filtered ultrasonic blood flow map.

[0010] Optionally, the identifying of the blood vessel boundary, the interior of the blood vessel and the tissue in the ultrasonic blood flow map and marking them to obtain a marked map includes:

[0011] Using the grayscale image in the ultrasonic blood flow image to obtain a grayscale image template corresponding to the current frame;

[0012] The grayscale image template is subjected to blood vessel boundary recognition, blood vessel interior recognition and tissue recognition, and is marked to obtain the marked image.

[0013] Optionally, the step of obtaining a grayscale image template corresponding to the current frame by using the grayscale image in the ultrasonic blood flow image includes:

[0014] Get a preset number of adjacent grayscale images;

[0015] Calculating weighted values ​​of adjacent grayscale images of the preset number of frames;

[0016] The weighted value is used as the grayscale image template.

[0017] Optionally, after taking the weighted value as the grayscale image template, the method further includes:

[0018] Performing a filtering operation on the grayscale image template to obtain a filtered grayscale image template;

[0019] Correspondingly, the grayscale image template is subjected to blood vessel boundary recognition, blood vessel interior recognition and tissue recognition, and is marked to obtain the marked image, including:

[0020] The filtered grayscale image template is subjected to blood vessel boundary recognition, blood vessel interior recognition and tissue recognition, and is marked to obtain the marked image.

[0021] Optionally, the performing blood vessel boundary recognition, blood vessel interior recognition and tissue recognition on the filtered grayscale image template and marking to obtain the marked image includes:

[0022] Get the upper and lower thresholds;

[0023] The grayscale value corresponding to each pixel in the filtered grayscale image template is threshold determined and classified and marked according to the upper threshold and the lower threshold, so as to obtain a marked image including the tissue, the blood vessel boundary and the inside of the blood vessel.

[0024] Optionally, after obtaining the labeled image including the tissue, the blood vessel boundary and the interior of the blood vessel, the method further includes:

[0025] A connected region labeling map including the blood vessel boundary region, the blood vessel internal region and the tissue region is obtained by using the connected method;

[0026] The blood vessel boundary region, the blood vessel internal region and the tissue region in the connected region labeling map are respectively judged and corrected to obtain a corrected connected region labeling map;

[0027] Accordingly, the determining, according to the label map, a first filter corresponding to the blood vessel boundary, a second filter corresponding to the interior of the blood vessel, and a third filter corresponding to the tissue includes:

[0028] A first filter corresponding to the blood vessel boundary, a second filter corresponding to the blood vessel interior, and a third filter corresponding to the tissue are determined according to the modified connected region labeling map.

[0029] Optionally, determining the first filter corresponding to the blood vessel boundary, the second filter corresponding to the blood vessel interior, and the third filter corresponding to the tissue according to the label map includes:

[0030] Acquiring a collection site corresponding to the ultrasonic blood flow image;

[0031] A first filter corresponding to the blood vessel boundary, a second filter corresponding to the blood vessel interior, and a third filter corresponding to the tissue are obtained by matching from a preset filter matching library according to the acquisition site and the labeling image.

[0032] The present application also provides an ultrasonic blood flow image processing device, comprising:

[0033] An acquisition module, used for acquiring an ultrasonic blood flow map;

[0034] An identification and marking module is used to identify the blood vessel boundary, the interior of the blood vessel and the tissue in the ultrasonic blood flow map, and mark them to obtain a marked map;

[0035] A filter determination module, configured to determine, according to the label map, a first filter corresponding to the blood vessel boundary, a second filter corresponding to the interior of the blood vessel, and a third filter corresponding to the tissue;

[0036] The filtering module is used to filter the blood vessel boundary using the first filter; filter the inside of the blood vessel using the second filter; filter the tissue using the third filter; so as to obtain a filtered ultrasonic blood flow map.

[0037] The present application also provides an ultrasonic blood flow image processing device, comprising:

[0038] Memory for storing computer programs;

[0039] The processor is used to execute the computer program to implement the steps of the above-mentioned ultrasonic blood flow image processing method.

[0040] The present application also provides a storage medium, in which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned ultrasonic blood flow image processing method are implemented.

[0041] It can be seen that the ultrasonic blood flow image processing method provided in the present application obtains an ultrasonic blood flow image; identifies the blood vessel boundaries, blood vessel interiors and tissues in the ultrasonic blood flow image, and marks them to obtain a marked image; determines the first filter corresponding to the blood vessel boundary, the second filter corresponding to the blood vessel interior and the third filter corresponding to the tissue according to the marked image; filters the blood vessel boundary using the first filter; filters the blood vessel interior using the second filter; filters the tissue using the third filter; to obtain a filtered ultrasonic blood flow image. The ultrasonic blood flow image processing method provided in the present application can select different optimal filters to remove clutter signals according to different categories in the collected ultrasonic blood flow image: blood vessel interiors, blood vessel boundaries, and tissues, so as to achieve the purpose of the ultrasonic blood flow image reflecting the real blood flow.

[0042] In addition, the present application also provides an ultrasonic blood flow image processing device, equipment and storage medium, which also have the above-mentioned beneficial effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0044] Figure 1 A flowchart of an ultrasonic blood flow image processing method provided in an embodiment of the present application;

[0045] Figure 2 An example diagram of a marking provided in an embodiment of the present application;

[0046] Figure 3 An example diagram of a region connectivity mark provided in an embodiment of the present application;

[0047] Figure 4 An example diagram of a modified connected region labeling provided in an embodiment of the present application;

[0048] Figure 5 An example diagram of a preset filter matching library provided in an embodiment of the present application;

[0049] Figure 6 An example diagram of a process for processing an ultrasonic blood flow image provided in an embodiment of the present application;

[0050] Figure 7 A schematic diagram of the structure of an ultrasonic blood flow image processing device provided in an embodiment of the present application;

[0051] Figure 8 A schematic diagram of the structure of an ultrasonic blood flow image processing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0053] Ultrasonic color blood flow imaging technology can display the two-dimensional blood flow distribution on the section to be tested. It is real-time and non-destructive, and is an important basis for clinical diagnosis of vascular lesions. Ultrasonic color blood flow imaging technology uses an ultrasonic transducer to repeatedly transmit short pulses along a certain scanning line direction. The received ultrasonic echo signal can form a blood flow image after beam synthesis, demodulation filtering, phase extraction and other processes. However, while receiving useful signals, interference signals generated by tissue movement and system noise will also be received. System noise is defined as Gaussian white noise, and corresponding filters can be designed to remove it. However, the clutter interference generated by tissue movement is not easy to remove. The energy of this part of the clutter signal is 60-80dB higher than that of the useful blood flow signal. If the clutter signal cannot be effectively removed, the useful blood flow signal will be submerged in the clutter signal and cannot be detected. Therefore, it is very important to effectively remove this part of the clutter signal.

[0054] At present, the method of removing clutter signals generated by tissue movement generally adopts wavelet transform algorithm. However, due to the different combined proportions of the signal energy reflected by blood flow and tissue movement in the detection area of ​​the entire probe, if the same filtering method is used to filter out the influence of tissue movement, the clutter signals generated by tissue movement will not be removed cleanly, and the real blood flow signal cannot be obtained well. This application provides an ultrasonic blood flow image processing method that can solve the problem of unclean clutter processing. For details, please refer to Figure 1 , Figure 1 A flowchart of an ultrasonic blood flow image processing method provided in an embodiment of the present application. The method may include:

[0055] S101: Obtain an ultrasonic blood flow map.

[0056] The execution subject of this embodiment is a terminal. This embodiment does not limit the type of terminal, as long as it can complete the operation of ultrasonic blood flow image processing.

[0057] The image acquisition device of this embodiment acquires images by emitting ultrasonic signals; the image acquisition device may specifically be a color ultrasonic diagnostic instrument; the image acquisition device comprises an ultrasonic probe and a conversion circuit, the image acquisition device uses the ultrasonic probe to emit ultrasonic signals to the human body, and uses the conversion circuit to convert the echo signals received by the ultrasonic probe into electrical signals, the conversion circuit comprises a signal amplification circuit, an A / D conversion circuit and a beam synthesis circuit, and the signals are converted into two signals through the conversion circuit, one of which is a two-dimensional signal for generating a grayscale image signal, and the other is a color blood flow signal, and the color blood flow signal is subjected to autocorrelation calculation to obtain a velocity map signal, an energy map signal and a variance map signal.

[0058] The above-mentioned process of obtaining the velocity map signal, the energy map signal, and the variance map signal by performing autocorrelation calculation on the color blood flow signal may specifically include:

[0059] The color blood flow signal undergoes orthogonal demodulation, impurity filtering and autocorrelation estimation, and then enters a velocity calculator to calculate a velocity map signal, a variance calculator to calculate a variance map signal, and an energy calculator to calculate an energy map signal.

[0060] The image processing device is used to process the signal of the grayscale image, the signal of the velocity image, the signal of the energy image, and the signal of the variance image, and obtain the grayscale image, velocity image, energy image, and variance image accordingly, and send the above-mentioned grayscale image, velocity image, energy image, and variance image to the pseudo-color coding and fusion display module to generate an ultrasonic blood flow image.

[0061] S102: Identify the blood vessel boundary, the interior of the blood vessel and the tissue in the ultrasonic blood flow image, and mark them to obtain a marked image.

[0062] This embodiment does not limit the specific process of obtaining the marking image. For example, the energy image in the ultrasonic blood flow image can be used to mark the blood vessel boundaries, the interior of the blood vessel and the tissue to obtain a marking image; or the grayscale image in the ultrasonic blood flow image can be used to mark the blood vessel boundaries, the interior of the blood vessel and the tissue to obtain a marking image.

[0063] Furthermore, because the grayscale image parameter value is small and the processing process is simple, the above-mentioned identification of the blood vessel boundary, the interior of the blood vessel and the tissue in the ultrasonic blood flow image and marking to obtain the marked image may include the following steps:

[0064] Step 21: using the grayscale image in the ultrasonic blood flow image to obtain a grayscale image template corresponding to the current frame;

[0065] Step 22: Perform blood vessel boundary recognition, blood vessel interior recognition and tissue recognition on the grayscale image template, and mark them to obtain a marked image.

[0066] Grayscale images are displayed frame by frame, and multiple frames of grayscale images can be obtained to determine the grayscale image template corresponding to the current frame; or a single frame of grayscale image can be obtained as the grayscale image template. Among them, obtaining multiple frames of grayscale images to determine the grayscale image template corresponding to the current frame can be to obtain grayscale images of several adjacent frames, and calculate the average value of the grayscale images of the adjacent frames, and use the average value as the grayscale image template; or to obtain grayscale images of several adjacent frames, and calculate the weighted value of the grayscale images of the adjacent frames, and use the weighted value as the grayscale image template.

[0067] Further, in order to improve the accuracy, the grayscale image template corresponding to the current frame obtained by using the grayscale image in the ultrasonic blood flow image may include the following steps:

[0068] Step 31: Obtaining adjacent grayscale images of a preset number of frames;

[0069] Step 32: Calculate the weighted values ​​of adjacent grayscale images of a preset number of frames;

[0070] Step 33: Use the weighted value as a grayscale image template.

[0071] In this embodiment, the weighted values ​​of several adjacent grayscale images are used as grayscale image templates. The number of frames includes but is not limited to 1, 2, or 3. Assuming that N adjacent grayscale images are selected, the formula is as follows:

[0072]

[0073] Among them, G is the grayscale image template, coef i is the weight corresponding to the adjacent grayscale image, G i is the value of the corresponding grayscale image; coef i Can be set independently, N is preferably 4, coef i is 0.25, i∈[1,2,3,4].

[0074] This embodiment does not limit whether to filter the grayscale image template; nor does it limit the specific filtering method.

[0075] Furthermore, in order to remove the detection error caused by other factors such as noise, after taking the weighted value as the grayscale image template, the following steps may be further included:

[0076] Performing a filtering operation on the grayscale image template to obtain a filtered grayscale image template;

[0077] Accordingly, the grayscale image template is subjected to vascular boundary recognition, vascular interior recognition and tissue recognition, and is marked to obtain a marked image, including:

[0078] The filtered grayscale image template is subjected to blood vessel boundary recognition, blood vessel interior recognition and tissue recognition, and is marked to obtain a marked image.

[0079] This embodiment uses a two-dimensional smoothing filtering method to filter the grayscale image template to obtain a filtered grayscale image template. The filtering method may be a mean filter; or a median filter; or a Gaussian filter. Assuming that the filter coefficient is an N×N matrix, the smoothing filter formula is as follows:

[0080]

[0081] Among them, coef ij is the weight corresponding to each pixel in the grayscale template G; G_out mn is the gray value corresponding to the pixel at the mth row and nth column; G m+i-N / 2-1,n+j-N / 2-1 It is the location of a grayscale value in the grayscale image template.

[0082] This embodiment does not limit the identification method, for example, it can be a threshold method, or it can also be the Otsu segmentation method, which finds the classification gray value points by calculating the variance between the statistical gray histograms; or it can also be various edge detection methods, which extract the blood vessel edges, tissues and intravascular areas by detecting the blood vessel edges; or it can also be machine learning and other methods.

[0083] Further, in order to improve the efficiency of the identification detection, the above-mentioned blood vessel boundary recognition, blood vessel interior recognition and tissue recognition are performed on the filtered grayscale image template, and the marking is performed to obtain a marked image, which may include the following steps:

[0084] Step 51: Obtain an upper threshold and a lower threshold;

[0085] Step 52: threshold determination is performed on the grayscale value corresponding to each pixel in the filtered grayscale image template according to the upper threshold and the lower threshold, and classification and labeling is performed to obtain a labeling image including tissues, blood vessel boundaries and blood vessel interiors.

[0086] In this embodiment, two thresholds are set: an upper threshold Gth1 and a lower threshold Gth2, and the grayscale value corresponding to each pixel in the filtered grayscale image template is threshold judged and classified and marked to obtain a marked image maskp. The specific formula is:

[0087]

[0088] This embodiment does not limit whether to modify the label map; nor does it limit the specific modification method. This embodiment takes into account that in addition to the blood vessel boundary, there are also bone, fascia and other areas as highlight areas because the value in the grayscale image is greater than the upper threshold Gth1. Through the above classification method, this part will be classified as a blood vessel boundary, so the label map maskp can be further modified.

[0089] Furthermore, in order to improve the recognition accuracy, after obtaining the labeled image including the tissue, the blood vessel boundary and the blood vessel interior, the following steps may be further included:

[0090] Step 61: using a connectivity method to obtain a connected region labeling map including a blood vessel boundary region, a blood vessel internal region, and a tissue region;

[0091] Step 62: respectively judging and correcting the blood vessel boundary region, the blood vessel internal region and the tissue region in the connected region labeling map to obtain a corrected connected region labeling map;

[0092] Correspondingly, S103 determines the first filter corresponding to the blood vessel boundary, the second filter corresponding to the blood vessel interior, and the third filter corresponding to the tissue according to the labeling map, including: determining the first filter corresponding to the blood vessel boundary, the second filter corresponding to the blood vessel interior, and the third filter corresponding to the tissue according to the corrected connected area labeling map.

[0093] This embodiment does not limit the specific connectivity method. For example, eight connected regions may be marked, or four connected regions may be marked.

[0094] Furthermore, in order to better mark the connectivity of the regions, this embodiment marks the eight connected regions on the vascular boundaries, vascular interiors and tissue parts of the grayscale image respectively, and obtains a connected region marking map including the vascular boundary regions, vascular interior regions and tissue regions, and judges and corrects the connected region marking map to obtain a corrected connected region marking map including the vascular boundary regions, vascular interior regions and tissue regions.

[0095] To better understand this section, please refer to Figure 2 , Figure 2 This is a marking example diagram provided in the embodiment of the present application. The blood vessel boundary position detected in the grayscale image in this embodiment is Figure 2 After the area detection, the position marked as 2 in the figure is obtained as follows Figure 3 The five blood vessel boundary connected areas shown are Figure 3 This is an example of a region connection labeling diagram provided in an embodiment of the present application. The connected regions of each category obtained are judged and corrected to obtain a corrected connected region labeling diagram. The correction method of this embodiment is: assuming that there are M vascular boundary regions in total, these regions are judged one by one. If the surrounding area of ​​a certain region does not appear to be judged as the region inside the blood vessel, then the vascular boundary region at this time is redefined as a tissue region, that is, in this embodiment, the vascular boundary region marked as 2 is remarked as 1. Figure 2 As shown, the detected blood vessel boundary is initialized to the region point marked as 2. After region detection, the following is obtained: Figure 3The five connected regions shown in the figure are searched in turn to see whether the area around each blood vessel boundary connected region has the type of area inside the blood vessel. Otherwise, the connected region is removed. Figure 2 and Figure 3 As shown in , there are connected areas inside the blood vessels around the fourth connected area and the fifth connected area, and there are no connected areas inside the blood vessels in other positions. Therefore, the first connected area, the second connected area, and the third connected area at the blood vessel boundary are re-marked as tissue areas, that is, marked as 1. The correction result is as follows Figure 4 As shown, Figure 4 An example diagram of a modified labeled connected area label provided in an embodiment of the present application: the solid oblique line portion is the blood vessel boundary area; the dotted oblique line portion is the blood vessel internal area; and the non-oblique line portion is the tissue area.

[0096] S103: Determine, according to the label map, a first filter corresponding to the blood vessel boundary, a second filter corresponding to the interior of the blood vessel, and a third filter corresponding to the tissue.

[0097] This embodiment does not limit the method for determining the filter. For example, a preset filter matching library can be pre-established, and the corresponding optimal filters can be determined in the preset filter matching library according to the blood vessel boundary, blood vessel interior and tissue in the labeling map. This embodiment does not limit the optimal filter. The filter includes but is not limited to IIR (infinite impulse response filter), FIR (finite length unit impulse response filter) and regression filter. This embodiment does not limit the matching items in the preset filter matching library. For example, the matching items can include the optimal filter and the filter coefficient.

[0098] Furthermore, in order to facilitate the matching and post-processing, the above-mentioned determination of the first filter corresponding to the blood vessel boundary, the second filter corresponding to the blood vessel interior and the third filter corresponding to the tissue according to the label map may include the following steps:

[0099] According to the label map, a first filter and a first coefficient corresponding to the blood vessel boundary, a second filter and a second coefficient corresponding to the interior of the blood vessel, and a third filter and a third coefficient corresponding to the tissue are matched from a preset filter matching library;

[0100] Correspondingly, the first filter, the second filter and the third filter are used to filter the blood vessel boundary, the blood vessel interior and the tissue in the ultrasonic blood flow map respectively to obtain the filtered ultrasonic blood flow map, including:

[0101] The first filter and the first coefficient, the second filter and the second coefficient, and the third filter and the third coefficient are used to filter the blood vessel boundary, the blood vessel interior, and the tissue in the ultrasonic blood flow map to obtain a filtered ultrasonic blood flow map.

[0102] This embodiment does not limit the matching method between the filter and each part of the ultrasound blood flow map. For example, the matching can be performed directly based on the three categories of the inside of the blood vessel, the boundary of the blood vessel, and the tissue in the marker map; or the acquisition site in the ultrasound blood flow map can be considered and the matching can be performed based on the acquisition site and the marker map. This embodiment does not limit the acquisition site in the preset filter matching library. For example, the acquisition site may include: thyroid, heart, carotid artery, superficial, liver, etc. Figure 5 As shown, Figure 5 An example diagram of a preset filter matching library provided in an embodiment of the present application.

[0103] Further, in order to make the matching more detailed and accurate and to take into account more comprehensively, the above-mentioned determination of the first filter corresponding to the blood vessel boundary, the second filter corresponding to the blood vessel interior and the third filter corresponding to the tissue according to the label map may include the following steps:

[0104] Obtaining the collection site corresponding to the ultrasonic blood flow map;

[0105] According to the acquisition site and the marking map, a first filter corresponding to the blood vessel boundary, a second filter corresponding to the inside of the blood vessel, and a third filter corresponding to the tissue are matched from a preset filter matching library.

[0106] This embodiment does not limit the method for determining the best filter. When determining the best filter based on the signature map, the filter can also be determined directly based on the signature map of the current frame; or the filter corresponding to the signature map of the current frame can be determined based on the signature map of the previous frame.

[0107] Furthermore, in order to improve the efficiency of filter determination, the following steps may be specifically included:

[0108] Determine whether the difference between the label image of the current frame and the label image of the previous frame is greater than a difference threshold;

[0109] If yes, determining the first filter, the second filter and the third filter according to the label map of the current frame;

[0110] If not, the first filter, the second filter and the third filter corresponding to the marker image of the previous frame are used as the first filter, the second filter and the third filter of the current frame.

[0111] S104: Filter the blood vessel boundary using the first filter; filter the inside of the blood vessel using the second filter; filter the tissue using the third filter; to obtain a filtered ultrasonic blood flow map.

[0112] The ultrasonic blood flow map provided by the embodiment of the present application is applied; the blood vessel boundaries, blood vessel interiors and tissues in the ultrasonic blood flow map are identified and marked to obtain a marked map; the first filter corresponding to the blood vessel boundaries, the second filter corresponding to the blood vessel interior and the third filter corresponding to the tissue are determined according to the marked map; the blood vessel boundaries are filtered using the first filter; the blood vessel interior is filtered using the second filter; the tissue is filtered using the third filter; to obtain a filtered ultrasonic blood flow map. The ultrasonic blood flow map processing method provided in the present application can select different optimal filters to remove clutter signals according to different categories in the collected ultrasonic blood flow image: blood vessel interiors, blood vessel boundaries and tissues, so as to achieve the purpose of the ultrasonic blood flow map reflecting the real blood flow. Furthermore, the efficiency can be improved by using grayscale images to identify, classify and mark various parts; and the weighted values ​​of adjacent grayscale images of a preset number of frames are used as grayscale image templates to improve accuracy; and the grayscale image templates are smoothed and filtered to remove detection errors caused by noise and other factors; and the threshold method is used for classification and recognition to improve detection efficiency; and the marking image is corrected to improve recognition accuracy; and the acquisition site of the ultrasonic blood flow image is obtained, and the acquisition site and the marking image are matched with the corresponding optimal filter from a preset filter matching library to make the filtering more accurate.

[0113] To make this application easier to understand, please refer to Figure 6 , Figure 6 An example flow chart of an ultrasonic blood flow image processing provided in an embodiment of the present application may specifically include: pre-classifying the interior of blood vessels, blood vessel boundaries and tissues in a grayscale image in an ultrasonic blood flow image to obtain a labeling image, correcting each part of the labeling image to obtain a corrected connected area labeling image; judging the difference between the corrected connected area labeling image of the previous frame and the corrected connected area labeling image of the current frame, and if the difference is greater than a preset threshold, matching the corrected connected area labeling image of the current frame with a database to determine a filter and a filter coefficient; if the difference is not greater than a preset threshold, using the filter and filter coefficient corresponding to the corrected connected area labeling image of the previous frame as the filter and filter coefficient corresponding to the corrected connected area labeling image of the current frame, filtering the ultrasonic blood flow image using the filter and filter coefficient, and outputting the filtered result.

[0114] The ultrasonic blood flow image processing device provided in the embodiment of the present application is introduced below. The ultrasonic blood flow image processing device described below and the ultrasonic blood flow image processing method described above can be referenced to each other.

[0115] Please refer to Figure 7 , Figure 7 A schematic diagram of the structure of an ultrasonic blood flow image processing device provided in an embodiment of the present application may include:

[0116] An acquisition module 100 is used to acquire an ultrasonic blood flow map;

[0117] The identification and marking module 200 is used to identify the blood vessel boundary, the interior of the blood vessel and the tissue in the ultrasonic blood flow map, and mark them to obtain a marked map;

[0118] A filter determination module 300, configured to determine, according to the label map, a first filter corresponding to the blood vessel boundary, a second filter corresponding to the interior of the blood vessel, and a third filter corresponding to the tissue;

[0119] The filtering module 400 is used to filter the blood vessel boundary using the first filter; filter the inside of the blood vessel using the second filter; filter the tissue using the third filter; so as to obtain a filtered ultrasonic blood flow map.

[0120] Based on the above embodiment, the identification mark module 200 may include:

[0121] A grayscale image template acquisition unit, used to acquire a grayscale image template corresponding to a current frame using the grayscale image in the ultrasonic blood flow image;

[0122] The identification and marking unit is used to perform blood vessel boundary recognition, blood vessel interior recognition and tissue recognition on the grayscale image template, and mark the grayscale image template to obtain the marked image.

[0123] Based on the above embodiment, the grayscale image template acquisition unit may include:

[0124] An acquisition subunit, used for acquiring adjacent grayscale images of a preset number of frames;

[0125] A calculation subunit, used for calculating weighted values ​​of adjacent grayscale images of the preset number of frames;

[0126] The grayscale image template subunit is used to use the weighted value as the grayscale image template.

[0127] Based on the above embodiment, the ultrasonic blood flow image processing device may further include:

[0128] A filtering module, configured to perform a filtering operation on the grayscale image template after taking the weighted value as the grayscale image template to obtain a filtered grayscale image template;

[0129] Accordingly, the identification marking unit may include:

[0130] The post-filtering identification and marking subunit is used to perform blood vessel boundary recognition, blood vessel interior recognition and tissue recognition on the filtered grayscale image template, and mark the template to obtain the marked image.

[0131] Based on the above embodiment, the post-filtering identification mark subunit may include:

[0132] A threshold acquisition subunit, used to acquire an upper threshold and a lower threshold;

[0133] The threshold determination subunit performs threshold determination and classification marking on the grayscale value corresponding to each pixel in the filtered grayscale image template according to the upper threshold and the lower threshold, and obtains a marked image including the tissue, the blood vessel boundary and the inside of the blood vessel.

[0134] Based on the above embodiment, the ultrasonic blood flow image processing device may further include:

[0135] A connected region module, used for obtaining a connected region label map including a vascular boundary region, a vascular interior region and a tissue region by using a connectivity method after obtaining the label map including the tissue, the vascular boundary and the interior of the vascular;

[0136] A judgment and correction module, used for judging and correcting the blood vessel boundary area, the blood vessel internal area and the tissue area in the connected area labeling map respectively, to obtain a corrected connected area labeling map;

[0137] Accordingly, the filter determination module 300 may include:

[0138] The modified filter determination unit is used to determine a first filter corresponding to the blood vessel boundary, a second filter corresponding to the blood vessel interior, and a third filter corresponding to the tissue according to the modified connected region labeling map.

[0139] Based on the above embodiment, the filter determination module 300 may include:

[0140] A collection part acquisition unit, used for acquiring the collection part corresponding to the ultrasonic blood flow image;

[0141] The filter matching unit is used to match the first filter corresponding to the blood vessel boundary, the second filter corresponding to the blood vessel interior and the third filter corresponding to the tissue from a preset filter matching library according to the acquisition site and the labeling map.

[0142] The embodiment of the present application provides an ultrasonic blood flow image processing device, which is used to obtain an ultrasonic blood flow image through an acquisition module 100; an identification and marking module 200 is used to identify the blood vessel boundaries, blood vessel interiors and tissues in the ultrasonic blood flow image, and mark them to obtain a marking image; a filter determination module 300 is used to determine the first filter corresponding to the blood vessel boundary, the second filter corresponding to the blood vessel interior and the third filter corresponding to the tissue according to the marking image; a filtering module 400 is used to filter the blood vessel boundary using the first filter; filter the blood vessel interior using the second filter; filter the tissue using the third filter to obtain a filtered ultrasonic blood flow image. The ultrasonic blood flow image processing method provided in the present application can select different optimal filters to remove clutter signals according to different categories in the collected ultrasonic blood flow image: blood vessel interior, blood vessel boundary, and tissue, so as to achieve the purpose of the ultrasonic blood flow image reflecting the real blood flow. Furthermore, the efficiency can be improved by using grayscale images to identify, classify and mark various parts; and the weighted values ​​of adjacent grayscale images of a preset number of frames are used as grayscale image templates to improve accuracy; and the grayscale image templates are smoothed and filtered to remove detection errors caused by noise and other factors; and the threshold method is used for classification and recognition to improve detection efficiency; and the marking image is corrected to improve recognition accuracy; and the acquisition site of the ultrasonic blood flow image is obtained, and the acquisition site and the marking image are matched with the corresponding optimal filter from a preset filter matching library to make the filtering more accurate.

[0143] The ultrasonic blood flow image processing device provided in the embodiment of the present application is introduced below. The ultrasonic blood flow image processing device described below and the ultrasonic blood flow image processing method described above can refer to each other.

[0144] Please refer to Figure 8 , Figure 8 A schematic diagram of the structure of an ultrasonic blood flow image processing device provided in an embodiment of the present application may include:

[0145] A memory 10, used for storing computer programs;

[0146] The processor 20 is used to execute a computer program to implement the above-mentioned ultrasonic blood flow image processing method.

[0147] The memory 10 , the processor 20 , and the communication interface 31 all communicate with each other via the communication bus 32 .

[0148] In the embodiment of the present application, the memory 10 is used to store one or more programs, and the program may include a program code, and the program code includes a computer operation instruction. In the embodiment of the present application, the memory 10 may store a program for implementing the following functions:

[0149] Obtain ultrasound blood flow diagram;

[0150] Identify the blood vessel boundaries, blood vessel interior and tissue in the ultrasound blood flow map, and mark them to obtain a marked map;

[0151] Determine, according to the label map, a first filter corresponding to the blood vessel boundary, a second filter corresponding to the interior of the blood vessel, and a third filter corresponding to the tissue;

[0152] The first filter is used to filter the blood vessel boundary; the second filter is used to filter the inside of the blood vessel; the third filter is used to filter the tissue; so as to obtain a filtered ultrasonic blood flow map.

[0153] In a possible implementation, the memory 10 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function, etc.; the data storage area may store data created during use.

[0154] In addition, the memory 10 may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include an NVRAM. The memory stores an operating system and operating instructions, executable modules or data structures, or a subset thereof, or an extended set thereof, wherein the operating instructions may include various operating instructions for implementing various operations. The operating system may include various system programs for implementing various basic tasks and processing hardware-based tasks.

[0155] The processor 20 may be a central processing unit (CPU), an application specific integrated circuit, a digital signal processor, a field programmable gate array or other programmable logic device, a microprocessor or any conventional processor, etc. The processor 20 may call a program stored in the memory 10 .

[0156] The communication interface 31 may be an interface of a communication module, and is used to connect to other devices or systems.

[0157] Of course, it should be noted that Figure 8 The structure shown does not constitute a limitation on the ultrasonic blood flow image processing device in the embodiment of the present application. In actual applications, the ultrasonic blood flow image processing device may include Figure 8 More or fewer components than shown, or combinations of certain components.

[0158] The storage medium provided in the embodiment of the present application is introduced below. The storage medium described below and the ultrasonic blood flow image processing method described above can be referenced to each other.

[0159] The present application also provides a storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned ultrasonic blood flow image processing method are implemented.

[0160] The computer storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0161] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0162] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0163] Finally, it should be noted that, in this article, relationships such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variations are intended to cover non-exclusive inclusion, so that a process, method, article or device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0164] The above is a detailed introduction to the ultrasonic blood flow image processing method, device, equipment and storage medium provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for processing an ultrasonic blood flow image, characterized in that: include: Obtain ultrasound blood flow diagram; Identifying blood vessel boundaries, blood vessel interiors and tissues in the ultrasonic blood flow map, and marking them to obtain a marked map; Determine, according to the label map, a first filter corresponding to the blood vessel boundary, a second filter corresponding to the interior of the blood vessel, and a third filter corresponding to the tissue; The first filter is used to filter the blood vessel boundary; the second filter is used to filter the inside of the blood vessel; the third filter is used to filter the tissue; so as to obtain a filtered ultrasonic blood flow map.

2. The ultrasonic blood flow image processing method according to claim 1, characterized in that: The identifying of the blood vessel boundary, the interior of the blood vessel and the tissue in the ultrasonic blood flow map and marking them to obtain a marked map includes: Using the grayscale image in the ultrasonic blood flow image to obtain a grayscale image template corresponding to the current frame; The grayscale image template is subjected to blood vessel boundary recognition, blood vessel interior recognition and tissue recognition, and is marked to obtain the marked image.

3. The ultrasonic blood flow image processing method according to claim 2, characterized in that: The step of obtaining a grayscale image template corresponding to the current frame by using the grayscale image in the ultrasonic blood flow image includes: Get a preset number of adjacent grayscale images; Calculating weighted values ​​of adjacent grayscale images of the preset number of frames; The weighted value is used as the grayscale image template.

4. The ultrasonic blood flow image processing method according to claim 3, characterized in that: After taking the weighted value as the grayscale image template, the method further includes: Performing a filtering operation on the grayscale image template to obtain a filtered grayscale image template; Correspondingly, the grayscale image template is subjected to blood vessel boundary recognition, blood vessel interior recognition and tissue recognition, and is marked to obtain the marked image, including: The filtered grayscale image template is subjected to blood vessel boundary recognition, blood vessel interior recognition and tissue recognition, and is marked to obtain the marked image.

5. The ultrasonic blood flow image processing method according to claim 4, characterized in that: The step of performing blood vessel boundary recognition, blood vessel interior recognition and tissue recognition on the filtered grayscale image template and marking the template to obtain the marked image includes: Get the upper and lower thresholds; The grayscale value corresponding to each pixel in the filtered grayscale image template is threshold determined and classified and marked according to the upper threshold and the lower threshold, so as to obtain a marked image including the tissue, the blood vessel boundary and the inside of the blood vessel.

6. The ultrasonic blood flow processing method according to claim 5, characterized in that: After obtaining the labeled image including the tissue, the blood vessel boundary and the interior of the blood vessel, the method further includes: A connected region labeling map including the blood vessel boundary region, the blood vessel internal region and the tissue region is obtained by using the connected method; The blood vessel boundary region, the blood vessel internal region and the tissue region in the connected region labeling map are respectively judged and corrected to obtain a corrected connected region labeling map; Accordingly, the determining, according to the label map, a first filter corresponding to the blood vessel boundary, a second filter corresponding to the interior of the blood vessel, and a third filter corresponding to the tissue includes: A first filter corresponding to the blood vessel boundary, a second filter corresponding to the blood vessel interior, and a third filter corresponding to the tissue are determined according to the modified connected region labeling map.

7. The ultrasonic blood flow processing method according to claim 1, characterized in that: The step of determining the first filter corresponding to the blood vessel boundary, the second filter corresponding to the blood vessel interior, and the third filter corresponding to the tissue according to the label map includes: Acquiring a collection site corresponding to the ultrasonic blood flow image; According to the acquisition site and the label map, a first filter corresponding to the blood vessel boundary, a second filter corresponding to the blood vessel interior, and a third filter corresponding to the tissue are matched from a preset filter matching library.

8. An ultrasonic blood flow image processing device, characterized in that: include: An acquisition module, used for acquiring an ultrasonic blood flow map; An identification and marking module is used to identify the blood vessel boundary, the interior of the blood vessel and the tissue in the ultrasonic blood flow map, and mark them to obtain a marked map; A filter determination module, configured to determine, according to the label map, a first filter corresponding to the blood vessel boundary, a second filter corresponding to the interior of the blood vessel, and a third filter corresponding to the tissue; The filtering module is used to filter the blood vessel boundary using the first filter; filter the inside of the blood vessel using the second filter; filter the tissue using the third filter; so as to obtain a filtered ultrasonic blood flow map.

9. An ultrasonic blood flow image processing device, characterized in that: include: Memory for storing computer programs; A processor is used to execute the computer program to implement the steps of the ultrasonic blood flow image processing method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the ultrasonic blood flow image processing method according to any one of claims 1 to 7 are implemented.

Images