Ultrasonic blood flow image post-processing method, device, equipment and medium
By receiving ultrasound echo signals to generate an ultrasound blood flow map, the current frame and the previous frame sub-parameter map are used for region marking and updating, and noise flicker points are filtered out to improve the clarity of the ultrasound blood flow map and help doctors make accurate diagnoses.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CONTEC MEDICAL SYST
- Filing Date
- 2024-11-14
- Publication Date
- 2026-05-15
AI Technical Summary
Noise flickering points can be present in ultrasound blood flow maps, affecting the accuracy of vascular disease diagnosis.
The initial ultrasound blood flow map of the current frame is generated by receiving ultrasound echo signals. The velocity threshold map is obtained using the sub-parameter maps of the current frame and the previous frame. Region marking and updating are performed, invalid points are filtered out, and the velocity threshold map is modified to filter out noise flickering points.
It effectively removes noise flickering points, improves the clarity of ultrasound blood flow images, and facilitates doctors' observation and diagnosis.
Smart Images
Figure CN122031004A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of medical image processing, in particular to an ultrasound blood flow image post-processing method and device, equipment and medium. BACKGROUND
[0002] As a non-invasive and real-time detection method, the ultrasonic diagnostic equipment is more and more accepted by doctors and patients. Color Doppler imaging has a milestone significance for the ultrasonic diagnostic equipment. The color blood flow is superimposed on the black and white image, which not only has a two-dimensional ultrasound structure image, but also provides the kinetic information of the blood flow, and has a great effect on the diagnosis of vascular diseases.
[0003] After the Doppler signal is demodulated and wall-filtered, it is sent to a blood flow parameter estimator. The estimated speed, energy or variance of three parameters or part is sent to a digital scan converter. Finally, a pseudo-color encoding is performed to obtain a color Doppler image, that is, an ultrasound blood flow image. Due to the existence of speckle noise, low Doppler signal echo intensity, and fewer data points involved in estimation, there will be errors in the estimated blood flow parameter value, which will further cause flickering color isolated points in the tissue and cavities in the blood vessels, and the edges of the blood vessels are not smooth.
[0004] In summary, how to filter out the noise flickering points in the ultrasound blood flow image is a problem to be solved in the field. SUMMARY
[0005] Therefore, the purpose of the present application is to provide an ultrasound blood flow image post-processing method, device, equipment and medium, which can filter out the noise flickering points in the ultrasound blood flow image. The specific scheme is as follows:
[0006] In a first aspect, the present application discloses an ultrasound blood flow image post-processing method, comprising:
[0007] Receiving echo signals returned based on ultrasonic waves of a target part, and generating an initial ultrasound blood flow image of a current frame based on the echo signals; wherein the initial ultrasound blood flow image of the current frame comprises a plurality of current frame sub-parameter images;
[0008] Obtaining an initial velocity threshold image of the current frame according to the current frame sub-parameter image and a previous frame sub-parameter image, and obtaining a connected region image using the initial velocity threshold image of the current frame, and performing region labeling on the connected region image to obtain an initial region label image of the current frame;
[0009] Determining a target parameter value of the initial region label image of the current frame, and screening out invalid points from the initial region label image of the current frame according to the size relationship between the target parameter value and a preset threshold, and updating the label value of the invalid points in the initial region label image of the current frame to obtain a target region label image of the current frame;
[0010] Based on the target region marker map of the current frame, the velocity value in the initial velocity threshold map of the current frame is modified to obtain the target velocity map of the current frame. Then, the initial ultrasound blood flow map of the current frame is processed according to the target velocity map of the current frame to obtain the target ultrasound blood flow map of the current frame.
[0011] Optionally, each current frame sub-parameter map is a current frame velocity map, a current frame energy map, and a current frame variance map, respectively.
[0012] Accordingly, obtaining the initial velocity threshold map of the current frame based on the current frame sub-parameter map and the previous frame sub-parameter map includes:
[0013] Determine the preset velocity threshold, preset energy threshold, and preset variance threshold based on the current frame subparameter map and the previous frame subparameter map;
[0014] The velocity values of the target points in the current frame velocity map are updated to 0, while the velocity values of the non-target points in the current frame velocity map remain unchanged, to obtain the initial velocity threshold map of the current frame.
[0015] Optionally, the velocity value of the target point in the current frame velocity map is less than the preset velocity threshold, or the energy value in the current frame energy map is less than the preset energy threshold, or the variance value in the current frame variance map is greater than the preset variance threshold.
[0016] Optionally, the step of obtaining a connected component map using the initial velocity threshold map of the current frame, and marking the connected component map to obtain an initial region-marked map of the current frame, includes:
[0017] The initial velocity threshold map of the current frame and the target velocity threshold map of the previous frame are binarized respectively to obtain the corresponding template map of the current frame and the template map of the previous frame.
[0018] Traverse the connected regions in the current frame template graph and the previous frame template graph to obtain a connected region graph, and mark the regions in the connected region graph to obtain the initial region marking graph of the current frame and the region marking graph of the previous frame.
[0019] Optionally, determining the target parameter value of the initial region marker map of the current frame and filtering out invalid points from the initial region marker map of the current frame based on the relationship between the target parameter value and a preset threshold includes:
[0020] The previous frame template image is compared with the current frame initial velocity threshold image region by region to find the number of target points with a mark value of 1 at each region position in the previous frame template image, and the target percentage of the number of target points relative to the total number of points in the corresponding region is calculated, and the target percentage is determined as the first target parameter value of the current frame initial region mark image.
[0021] The region whose first target parameter value is less than the first preset threshold is identified as the first target region, and all points in the first target region are identified as first invalid points.
[0022] Accordingly, updating the marker values of invalid points in the initial region marker map of the current frame to obtain the target region marker map of the current frame includes:
[0023] The mark value of the first invalid point in the initial region mark map of the current frame is updated to 0 to obtain the first target region mark map of the current frame.
[0024] Optionally, determining the target parameter value of the initial region marker map of the current frame and filtering out invalid points from the initial region marker map of the current frame based on the relationship between the target parameter value and a preset threshold includes:
[0025] Each region of the current frame initial region marker map is compared with the current frame initial velocity threshold map to obtain the average value of the absolute velocity of all points in each region, and the average value is determined as the value of each second target parameter of the current frame initial region marker map;
[0026] The region whose second target parameter value is less than the second preset threshold is identified as the second target region, and all points in the second target region are identified as second invalid points.
[0027] Accordingly, updating the marker values of invalid points in the initial region marker map of the current frame to obtain the target region marker map of the current frame includes:
[0028] The mark value of the second invalid point in the initial region mark map of the current frame is updated to 0 to obtain the second target region mark map of the current frame.
[0029] Optionally, determining the target parameter value of the initial region marker map of the current frame and filtering out invalid points from the initial region marker map of the current frame based on the relationship between the target parameter value and a preset threshold includes:
[0030] The size of each region in the initial region marking map of the current frame is determined, and each region size is determined as a third target parameter value of the initial region marking map of the current frame; wherein, the region size is the number of all points in the corresponding region;
[0031] The region whose third target parameter value is less than the third preset threshold is determined as the third target region, and all points in the third target region are determined as third invalid points;
[0032] Accordingly, updating the marker values of invalid points in the initial region marker map of the current frame to obtain the target region marker map of the current frame includes:
[0033] The mark value of the third invalid point in the initial region mark map of the current frame is updated to 0 to obtain the third target region mark map of the current frame.
[0034] Secondly, this application discloses an ultrasound blood flow image post-processing device, comprising:
[0035] The initial blood flow map acquisition module is used to receive the echo signal returned by ultrasound from the target site, and generate the initial ultrasound blood flow map of the current frame based on the echo signal; wherein, the initial ultrasound blood flow map of the current frame includes each current frame sub-parameter map;
[0036] The initial marker map acquisition module is used to obtain the initial velocity threshold map of the current frame based on the current frame sub-parameter map and the previous frame sub-parameter map, and to obtain a connected region map using the current frame initial velocity threshold map, and to mark the connected region map to obtain the initial region marker map of the current frame;
[0037] The target marker map acquisition module is used to determine the target parameter value of the initial region marker map of the current frame, and filter out invalid points from the initial region marker map of the current frame according to the relationship between the target parameter value and a preset threshold, and update the marker value of the invalid points in the initial region marker map of the current frame to obtain the target region marker map of the current frame.
[0038] The target blood flow map acquisition module is used to modify the velocity value in the initial velocity threshold map of the current frame based on the target region marker map of the current frame to obtain the target velocity map of the current frame, and to process the initial ultrasound blood flow map of the current frame according to the target velocity map of the current frame to obtain the target ultrasound blood flow map of the current frame.
[0039] Thirdly, this application discloses an electronic device, including:
[0040] Memory, used to store computer programs;
[0041] A processor is used to execute the computer program to implement the steps of the aforementioned disclosed ultrasound blood flow image post-processing method.
[0042] Fourthly, this application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the steps of the aforementioned disclosed ultrasound blood flow image post-processing method.
[0043] The beneficial effects of this application are as follows: This application receives echo signals from a target location based on ultrasound, and generates an initial ultrasound blood flow map of the current frame based on the echo signals; wherein, the initial ultrasound blood flow map of the current frame includes sub-parameter maps of each current frame; an initial velocity threshold map of the current frame is obtained based on the sub-parameter maps of the current frame and the previous frame, and a connected region map is obtained using the initial velocity threshold map of the current frame, and the connected region map is marked to obtain an initial region marking map of the current frame; a target parameter value of the initial region marking map of the current frame is determined, and invalid points are filtered out from the initial region marking map of the current frame according to the relationship between the target parameter value and a preset threshold, and the marking values of the invalid points in the initial region marking map of the current frame are updated to obtain a target region marking map of the current frame; the velocity values in the initial velocity threshold map of the current frame are modified based on the target region marking map of the current frame to obtain a target velocity map of the current frame, and the initial ultrasound blood flow map of the current frame is processed based on the target velocity map of the current frame to obtain a target ultrasound blood flow map of the current frame. Therefore, this application obtains the initial velocity threshold map of the current frame based on the current frame sub-parameter map and the previous frame sub-parameter map of the initial ultrasound blood flow map of the current frame, and uses the initial velocity threshold map of the current frame to obtain a connected region map. The connected region map is then marked to obtain the initial region marking map of the current frame. Invalid points are filtered out from the initial region marking map of the current frame based on the relationship between the target parameter value and the preset threshold. These invalid points are noise flickering points. Updating the marking value of the invalid points can filter out the noise flickering points. Then, the velocity value in the initial velocity threshold map of the current frame is modified based on the target region marking map of the current frame. The initial ultrasound blood flow map of the current frame is processed according to the obtained target velocity map of the current frame, thus obtaining a target ultrasound blood flow map of the current frame without noise flickering points. Subsequent ultrasound blood flow image display is not affected by noise flickering points, which facilitates the observation of pathological information by doctors and users and facilitates timely diagnosis. Attached Figure Description
[0044] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.
[0045] Figure 1 This is a flowchart of a post-processing method for ultrasound blood flow images disclosed in this application;
[0046] Figure 2 This is a flowchart illustrating the first specific area marker map update method disclosed in this application;
[0047] Figure 3 This is a flowchart illustrating the second specific type of area marker map update disclosed in this application.
[0048] Figure 4 A flowchart for updating the third specific area marker map disclosed in this application;
[0049] Figure 5 This is a schematic diagram of the structure of an ultrasound blood flow image post-processing device disclosed in this application;
[0050] Figure 6 This is a structural diagram of an electronic device disclosed in this application. Detailed Implementation
[0051] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.
[0052] Ultrasound diagnostic equipment, as a non-invasive and real-time detection method, is increasingly accepted by doctors and patients. Color Doppler imaging is a milestone for ultrasound diagnostic equipment. By superimposing color blood flow onto a black and white image, it provides both a two-dimensional ultrasound structural image and dynamic information of blood flow, which plays a significant role in the diagnosis of vascular diseases.
[0053] The Doppler signal, after demodulation and wall filtering, is sent to a blood flow parameter estimator. The estimated velocity, energy, or variance parameters, or some of them, are then fed into a digital scan converter. Finally, pseudo-color encoding is performed to obtain a super-color Doppler image, i.e., an ultrasound blood flow map. Due to the presence of speckle noise, low Doppler signal echo intensity, and a small number of data points involved in the estimation, the estimated blood flow parameter values will have certain errors. This can lead to flickering colored isolated spots in tissues, cavities inside blood vessels, and uneven vessel edges.
[0054] Therefore, this application provides a post-processing scheme for ultrasound blood flow images to filter out noise flickering points in ultrasound blood flow images.
[0055] See Figure 1 As shown in the figure, this application discloses a post-processing method for ultrasound blood flow images, including:
[0056] Step S11: Receive the echo signal returned by ultrasound from the target site, and generate the initial ultrasound blood flow map of the current frame based on the echo signal; wherein, the initial ultrasound blood flow map of the current frame includes sub-parameter maps of each current frame.
[0057] The image acquisition device includes an ultrasound probe and a conversion circuit. The ultrasound probe emits ultrasound waves towards the target area and receives the echo signals returned from the target area based on the ultrasound waves. The conversion circuit can then generate an initial ultrasound blood flow map of the current frame based on the echo signals. For example, the image can be acquired using a color ultrasound diagnostic instrument. The generated initial ultrasound blood flow map of the current frame includes sub-parameter maps of each current frame, namely, the current frame velocity map, the current frame energy map, and the current frame variance map. The specific process is as follows:
[0058] 1) An ultrasound probe is used to emit ultrasound signals to the target area. The echo signals received by the ultrasound probe are converted into electrical signals by a conversion circuit, which includes a signal amplification circuit, an A / D conversion circuit, and a beamforming circuit. The conversion circuit converts the signals into two signals: one is a two-dimensional signal, and the other is a color blood flow signal.
[0059] 2) Two-dimensional signals are used to generate grayscale signals. The color blood flow signals are processed by orthogonal demodulation, impurity filtering, and autocorrelation estimation, and then fed into the velocity calculator, variance calculator, and energy calculator for calculation to obtain velocity map signals, energy map signals, and variance map signals.
[0060] 3) The image processing device sends each signal to the pseudo-color encoding and fusion display module to process the grayscale signal, velocity signal, energy signal, and variance signal to obtain the initial ultrasound blood flow map of the current frame. The initial ultrasound blood flow map of the current frame includes the sub-parameter maps of each current frame, namely the grayscale map, velocity map, energy map, and variance map of the current frame.
[0061] 4) Next, the initial ultrasound blood flow map of the current frame can be displayed using an image display device.
[0062] Step S12: Obtain the initial velocity threshold map of the current frame based on the current frame sub-parameter map and the previous frame sub-parameter map, and use the current frame initial velocity threshold map to obtain a connected region map, and mark the connected region map to obtain the current frame initial region marking map.
[0063] In this embodiment, obtaining the initial velocity threshold map of the current frame based on the current frame sub-parameter map and the previous frame sub-parameter map includes: determining a preset velocity threshold, a preset energy threshold, and a preset variance threshold based on the current frame sub-parameter map and the previous frame sub-parameter map; updating the velocity value of the target point in the current frame velocity map to 0, and keeping the velocity values of the non-target points in the current frame velocity map unchanged, so as to obtain the initial velocity threshold map of the current frame. The preset velocity threshold, preset energy threshold, and preset variance threshold are determined based on the current frame sub-parameter map and the previous frame sub-parameter map. Specifically, the preset velocity threshold, preset energy threshold, and preset variance threshold are determined based on the current frame velocity map and the previous frame energy map, respectively. Based on these preset velocity thresholds and / or preset energy thresholds and / or preset variance thresholds, the velocity values of target points in the current frame velocity map are updated to 0, while the velocity values of non-target points in the current frame velocity map remain unchanged, thus obtaining the initial velocity threshold map Vth for the current frame. During the process of determining the preset velocity threshold, preset energy threshold, and preset variance threshold based on the current frame sub-parameter map and the previous frame sub-parameter map, the probe and examination site must also be considered. Different values will be used depending on the probe and examination site. For example, in carotid artery examination mode, the preset velocity threshold can be set to 18, the preset energy threshold can be set to 50, and the preset variance threshold can be set to 110.
[0064] In this embodiment, the target point is defined as follows: its velocity value in the current frame velocity map is less than the preset velocity threshold, its energy value in the current frame energy map is less than the preset energy threshold, or its variance value in the current frame variance map is greater than the preset variance threshold. The target point is the point whose velocity value needs to be updated. This is achieved by analyzing each point in the current frame velocity map one by one. If the value of the current point in the current frame velocity map is less than the preset velocity threshold, or the value of the corresponding point in the current frame energy map is less than the preset energy threshold, or the value of the corresponding point in the current frame variance map is greater than the preset variance threshold, then the current point is the target point. After analyzing each point individually, all target points can be determined.
[0065] In this embodiment, the step of obtaining a connected component map using the initial velocity threshold map of the current frame and marking the connected component map to obtain the initial region-marked map of the current frame includes: performing binarization processing on the initial velocity threshold map of the current frame and the target velocity threshold map of the previous frame to obtain the corresponding template map of the current frame and the template map of the previous frame; traversing the connected components in the template map of the current frame and the template map of the previous frame to obtain a connected component map, and marking the connected component map to obtain the initial region-marked map of the current frame and the region-marked map of the previous frame. The specific process of obtaining the initial region-marked map of the current frame and the region-marked map of the previous frame is as follows:
[0066] 1) Obtain the current frame template image and the previous frame template image based on the obtained initial velocity threshold image Vth of the current frame and the target velocity threshold image Vth_b of the previous frame. The binarization formula for obtaining the current frame template image is as follows:
[0067] ;
[0068] In the formula, Vth is the initial velocity threshold map of the current frame, abs(Vth) is the absolute value of the initial velocity threshold map of the current frame, and mask is the marker map after binarization, which is the template map of the current frame.
[0069] Accordingly, the specific formula for obtaining the binarization of the previous frame template image is as follows:
[0070] ;
[0071] In the formula, Vth_b is the target velocity threshold map of the previous frame, abs(Vth_b) is the absolute value of the target velocity threshold map of the previous frame, and mask_b is the marker map after binarization, which is the template map of the previous frame.
[0072] 2) Traverse the connected regions in the current frame template map mask and the previous frame template map mask_b, and mark the position of the region to obtain an eight-connected region map. Specifically, you can traverse the eight-connected neighborhoods in mask and mask_b, which is equivalent to traversing eight connected regions with the same value.
[0073] 3) Mark the connected region graph to obtain the initial region marking graph of the current frame and the region marking graph of the previous frame. Specifically, the eight connected neighborhoods obtained from the connected region graph can be marked as 1 or 0, that is, connected regions are marked as 1 and non-connected regions are marked as 0, so as to obtain the initial region marking graph RN of the current frame and the region marking graph RN_b of the previous frame. The initial region marking graph of the current frame and the region marking graph of the previous frame can be used to adjust the blood flow display of the ultrasound blood flow image.
[0074] Step S13: Determine the target parameter value of the initial region marking map of the current frame, and filter out invalid points from the initial region marking map of the current frame according to the relationship between the target parameter value and the preset threshold. Update the marking value of the invalid points in the initial region marking map of the current frame to obtain the target region marking map of the current frame.
[0075] After obtaining the initial region marker map of the current frame, it is also necessary to update the marker values of invalid points in the initial region marker map of the current frame. The update methods of the initial region marker map of the current frame can be divided into a first update method based on the percentage of target points in the region, a second update method based on the average velocity of the region, and a third update method based on the size of the region. It can also include a fourth update method combining the first and second update methods, a fifth update method combining the first and third update methods, a sixth update method combining the second and third update methods, and a seventh update method combining the first, second, and third update methods.
[0076] In a first specific embodiment of the marker map update, determining the target parameter value of the current frame initial region marker map and filtering out invalid points from the current frame initial region marker map based on the relationship between the target parameter value and a preset threshold includes: comparing the previous frame template map and the current frame initial velocity threshold map region by region to find the number of target points with a marker value of 1 at each region position in the previous frame template map, calculating the target percentage of the number of target points relative to the total number of points in the corresponding region, and determining the target percentage as each first target parameter value of the current frame initial region marker map; determining regions where the first target parameter value is less than a first preset threshold as first target regions, and determining all points in the first target regions as first invalid points; correspondingly, updating the marker values of the invalid points in the current frame initial region marker map to obtain the current frame target region marker map includes: updating the marker values of the first invalid points in the current frame initial region marker map to 0 to obtain the first current frame target region marker map. For example Figure 2 The flowchart shown illustrates the first specific method for updating the region map. The process of obtaining the target region map for the current frame based on the first update method using the percentage of target points in the region is as follows:
[0077] 1.1) First, identify the first invalid point:
[0078] 1.1.1) Compare the previous frame template map with the current frame initial velocity threshold map region by region to find the number of target points marked with a value of 1 at each region position in the previous frame template map. Assuming that the current frame initial velocity threshold map RN has a total of m regions, it constitutes... , To record the coordinates of the m-th connected region, the template image mask_b from the previous frame is compared with the initial velocity threshold image Vth from the current frame. The number of points with a value of 1 at each region position in the template image mask_b from the previous frame is found, which gives the number of target points marked with a value of 1 in each region.
[0079] 1.1.2) Calculate the target percentage of the number of target points out of the total number of points in the corresponding area. and target percentage The parameter values of each first target are determined as the initial region marker map of the current frame;
[0080] 1.1.3) Regions with first target parameter values less than the first preset threshold are identified as first target regions, and all points within the first target region are identified as first invalid points. This can be understood as all points within regions where the first target parameter value is not less than the first preset threshold being first valid points. For example, if only the m-th region has a first target parameter value less than the first preset threshold, then only the m-th region is the first target region, and all points within the m-th region are first invalid points. The selection of the first preset threshold Rth typically varies depending on the detection site. For example, in the carotid artery mode of the large blood vessel mode, the value of Rth can be set to 0.9, while in the thyroid mode, it can be set to 0.5.
[0081] 1.2) Next, update the label value of the first invalid point: update the label value of the first invalid point in the initial region label map of the current frame to 0 to obtain the first target region label map RN1 of the current frame. It should be noted that if the label value of the first invalid point is already 0, then there is no need to update it, and the label value of the first valid point does not need to be changed either.
[0082] In a second specific embodiment of the marker map update, determining the target parameter value of the current frame initial region marker map and filtering out invalid points from the current frame initial region marker map based on the relationship between the target parameter value and a preset threshold includes: comparing each region of the current frame initial region marker map with the current frame initial velocity threshold map to obtain the average value of the absolute velocity of all points in each region, and determining the average value as each second target parameter value of the current frame initial region marker map; determining regions where the second target parameter value is less than the second preset threshold as second target regions, and determining all points in the second target regions as second invalid points; correspondingly, updating the marker value of the invalid points in the current frame initial region marker map to obtain the current frame target region marker map includes: updating the marker value of the second invalid points in the current frame initial region marker map to 0 to obtain the second current frame target region marker map. For example Figure 3 The second specific flowchart for updating the region map, shown below, details the process of obtaining the target region map for the current frame using the second update method based on the average region velocity:
[0083] 2.1) First, identify the second invalid point:
[0084] 2.2.1) Compare each region of the current frame initial region marker map RN with the current frame initial velocity threshold map to obtain the average value V_ag of the absolute velocity of all points in each region, and determine the average value V_ag as the second target parameter value of the current frame initial region marker map; assuming that the current frame initial region marker map RN has a total of m regions, compare the current frame initial velocity threshold map Vth with the m regions, calculate the average value V_ag of the absolute velocity of all points in each region, and thus obtain the average value V_ag of the absolute velocity of each region, that is, obtain the second target parameter value of each region;
[0085] 2.2.2) The region whose second target parameter value is less than the second preset threshold is determined as the second target region, and all points in the second target region are determined as second invalid points; the second preset threshold VRth is set. For example, if the average value V_ag of the m-th region is greater than the second preset threshold VRth, then the points in the m-th region are considered as second valid points. If the average value V_ag of the m-th region is less than the second preset threshold VRth, then the points in the m-th region are considered as second invalid points.
[0086] 2.2) Next, update the label value of the second invalid point: update the label value of the second invalid point in the initial region label map of the current frame to 0 to obtain the second target region label map RN2 of the current frame. It should be noted that if the label value of the second invalid point is already 0, then there is no need to update it, and the label value of the second valid point does not need to be changed either.
[0087] In a third specific embodiment of the marker map update, determining the target parameter value of the current frame initial region marker map and filtering out invalid points from the current frame initial region marker map based on the relationship between the target parameter value and a preset threshold includes: determining the region size of each region in the current frame initial region marker map, and determining each region size as a third target parameter value of the current frame initial region marker map; wherein, the region size is the number of all points in the corresponding region; determining regions where the third target parameter value is less than a third preset threshold as third target regions, and determining all points in the third target regions as third invalid points; correspondingly, updating the marker values of the invalid points in the current frame initial region marker map to obtain the current frame target region marker map includes: updating the marker values of the third invalid points in the current frame initial region marker map to 0 to obtain a third current frame target region marker map. For example Figure 4 The flowchart shown below illustrates the third specific method for updating the region map. The process of obtaining the target region map for the current frame based on the third update method using the region size is as follows:
[0088] 3.1) First, identify the third invalid point:
[0089] 3.1.1) Determine the region size SVm of each region in the initial region marking map of the current frame, and set the region size as the third target parameter value of the initial region marking map of the current frame; where the region size is the number of points in the corresponding region; assuming that the initial region marking map RN of the current frame has a total of m sub-regions, calculate the region size SVm of each sub-region, and the region size is the number of points in the region;
[0090] 3.1.2) The region whose third target parameter value is less than the third preset threshold is determined as the third target region, and all points in the third target region are determined as the third invalid points; set the third preset threshold SVth. If the region size SVm of the m-th region is greater than the third preset threshold SVth, then the points in the m-th region are considered as the third valid points. If the region size SVm of the m-th region is less than the third threshold SVth, then the points in the m-th region are considered as the third invalid points.
[0091] 3.2) Next, update the label value of the third invalid point: update the label value of the third invalid point in the initial region label map of the current frame to 0, so as to obtain the third target region label map RN3 of the current frame.
[0092] In the fourth specific embodiment of the marker map update, the fourth update method combines the first update method and the second update method. First, the first updated target region marker map RN4' of the current frame is obtained based on the first update method. Then, the first updated target region marker map RN4' of the current frame is used as the new initial region marker map of the current frame. The fourth target region marker map RN4 of the current frame is obtained based on the second update method so that the velocity value in the initial velocity threshold map of the current frame can be modified based on the fourth target region marker map RN4.
[0093] In the fifth specific embodiment of the marker map update, the fifth update method combines the first update method and the third update method. First, the second updated target region marker map RN5' of the current frame is obtained based on the first update method. Then, the second updated target region marker map RN4' of the current frame is used as the new initial region marker map of the current frame. The fifth target region marker map RN5 of the current frame is obtained based on the third update method so that the velocity value in the initial velocity threshold map of the current frame can be modified based on the fifth target region marker map RN5.
[0094] In the sixth specific embodiment of the marker map update, the sixth update method combines the second update method and the third update method. First, the target region marker map RN6' of the current frame after the third update is obtained based on the second update method. Then, the target region marker map RN6' of the current frame after the third update is used as the new initial region marker map of the current frame. The sixth target region marker map RN6 of the current frame is obtained based on the third update method so that the velocity value in the initial velocity threshold map of the current frame can be modified based on the sixth target region marker map RN6.
[0095] In the seventh specific embodiment of the marker map update, the seventh update method combines the first update method, the second update method, and the third update method. First, the fourth updated target region marker map RN7'' of the current frame is obtained based on the first update method. Then, the fourth updated target region marker map RN7'' of the current frame is used as the new initial region marker map of the current frame. The fifth updated target region marker map RN7' of the current frame is obtained based on the second update method and used as the new initial region marker map of the current frame. Then, the seventh target region marker map RN7 of the current frame is obtained based on the third update method so that the velocity value in the initial velocity threshold map of the current frame can be modified based on the seventh target region marker map RN7.
[0096] Understandably, the fourth, fifth, sixth, and seventh update methods are more accurate in identifying invalid points compared to the first, second, and third update methods.
[0097] Step S14: Modify the velocity value in the initial velocity threshold map of the current frame based on the target region marker map of the current frame to obtain the target velocity map of the current frame, and process the initial ultrasound blood flow map of the current frame according to the target velocity map of the current frame to obtain the target ultrasound blood flow map of the current frame.
[0098] The velocity values in the initial velocity threshold map of the current frame are modified based on the target region marker map of the current frame to obtain the target velocity map of the current frame. Then, the initial ultrasound blood flow map of the current frame is processed according to the target velocity map of the current frame to obtain the target ultrasound blood flow map of the current frame after filtering out noise and flickering points. Specifically, modifying the velocity values in the initial velocity threshold map of the current frame based on the target region marker map of the current frame involves finding the position where the point is 0 in the target region marker map of the current frame (RN1 or RN2 or RN3 or RN4 or RN5 or RN6 or RN7), and modifying the corresponding point in the initial velocity threshold map of the current frame to 0, thereby obtaining a new target velocity map of the current frame, and then generating an ultrasound blood flow image. This makes it easier for doctors to observe the ultrasound blood flow image, accurately grasp user information, and facilitate timely diagnosis.
[0099] The beneficial effects of this application are as follows: This application receives echo signals from a target location based on ultrasound, and generates an initial ultrasound blood flow map of the current frame based on the echo signals; wherein, the initial ultrasound blood flow map of the current frame includes sub-parameter maps of each current frame; an initial velocity threshold map of the current frame is obtained based on the sub-parameter maps of the current frame and the previous frame, and a connected region map is obtained using the initial velocity threshold map of the current frame, and the connected region map is marked to obtain an initial region marking map of the current frame; a target parameter value of the initial region marking map of the current frame is determined, and invalid points are filtered out from the initial region marking map of the current frame according to the relationship between the target parameter value and a preset threshold, and the marking values of the invalid points in the initial region marking map of the current frame are updated to obtain a target region marking map of the current frame; the velocity values in the initial velocity threshold map of the current frame are modified based on the target region marking map of the current frame to obtain a target velocity map of the current frame, and the initial ultrasound blood flow map of the current frame is processed based on the target velocity map of the current frame to obtain a target ultrasound blood flow map of the current frame. Therefore, this application obtains the initial velocity threshold map of the current frame based on the current frame sub-parameter map and the previous frame sub-parameter map of the initial ultrasound blood flow map of the current frame, and uses the initial velocity threshold map of the current frame to obtain a connected region map. The connected region map is then marked to obtain the initial region marking map of the current frame. Invalid points are filtered out from the initial region marking map of the current frame based on the relationship between the target parameter value and the preset threshold. These invalid points are noise flickering points. Updating the marking value of the invalid points can filter out the noise flickering points. Then, the velocity value in the initial velocity threshold map of the current frame is modified based on the target region marking map of the current frame. The initial ultrasound blood flow map of the current frame is processed according to the obtained target velocity map of the current frame, thus obtaining a target ultrasound blood flow map of the current frame without noise flickering points. Subsequent ultrasound blood flow image display is not affected by noise flickering points, which facilitates the observation of pathological information by doctors and users and facilitates timely diagnosis.
[0100] See Figure 5 As shown in the figure, this application discloses an ultrasound blood flow image post-processing device, including:
[0101] The initial blood flow map acquisition module 11 is used to receive the echo signal returned by ultrasound from the target site, and generate the current frame initial ultrasound blood flow map based on the echo signal; wherein, the current frame initial ultrasound blood flow map includes each current frame sub-parameter map;
[0102] The initial marker map acquisition module 12 is used to acquire the initial velocity threshold map of the current frame based on the current frame sub-parameter map and the previous frame sub-parameter map, and to acquire the connected region map using the current frame initial velocity threshold map, and to perform region marking on the connected region map to obtain the initial region marker map of the current frame;
[0103] The target marker map acquisition module 13 is used to determine the target parameter value of the initial region marker map of the current frame, and filter out invalid points from the initial region marker map of the current frame according to the size relationship between the target parameter value and the preset threshold, and update the marker value of the invalid points in the initial region marker map of the current frame to obtain the target region marker map of the current frame.
[0104] The target blood flow map acquisition module 14 is used to modify the velocity value in the initial velocity threshold map of the current frame based on the target region marker map of the current frame to obtain the target velocity map of the current frame, and to process the initial ultrasound blood flow map of the current frame according to the target velocity map of the current frame to obtain the target ultrasound blood flow map of the current frame.
[0105] The beneficial effects of this application are as follows: This application receives echo signals from a target location based on ultrasound, and generates an initial ultrasound blood flow map of the current frame based on the echo signals; wherein, the initial ultrasound blood flow map of the current frame includes sub-parameter maps of each current frame; an initial velocity threshold map of the current frame is obtained based on the sub-parameter maps of the current frame and the previous frame, and a connected region map is obtained using the initial velocity threshold map of the current frame, and the connected region map is marked to obtain an initial region marking map of the current frame; a target parameter value of the initial region marking map of the current frame is determined, and invalid points are filtered out from the initial region marking map of the current frame according to the relationship between the target parameter value and a preset threshold, and the marking values of the invalid points in the initial region marking map of the current frame are updated to obtain a target region marking map of the current frame; the velocity values in the initial velocity threshold map of the current frame are modified based on the target region marking map of the current frame to obtain a target velocity map of the current frame, and the initial ultrasound blood flow map of the current frame is processed based on the target velocity map of the current frame to obtain a target ultrasound blood flow map of the current frame. Therefore, this application obtains the initial velocity threshold map of the current frame based on the current frame sub-parameter map and the previous frame sub-parameter map of the initial ultrasound blood flow map of the current frame, and uses the initial velocity threshold map of the current frame to obtain a connected region map. The connected region map is then marked to obtain the initial region marking map of the current frame. Invalid points are filtered out from the initial region marking map of the current frame based on the relationship between the target parameter value and the preset threshold. These invalid points are noise flickering points. Updating the marking value of the invalid points can filter out the noise flickering points. Then, the velocity value in the initial velocity threshold map of the current frame is modified based on the target region marking map of the current frame. The initial ultrasound blood flow map of the current frame is processed according to the obtained target velocity map of the current frame, thus obtaining a target ultrasound blood flow map of the current frame without noise flickering points. Subsequent ultrasound blood flow image display is not affected by noise flickering points, which facilitates the observation of pathological information by doctors and users and facilitates timely diagnosis.
[0106] Furthermore, embodiments of this application also provide an electronic device.Figure 6 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content of the diagram should not be construed as limiting the scope of this application.
[0107] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Specifically, it may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the ultrasound blood flow image post-processing method performed by the electronic device disclosed in any of the foregoing embodiments.
[0108] In this embodiment, the power supply 23 is used to provide operating voltage for various hardware devices on the electronic device; the communication interface 24 can create a data transmission channel between the electronic device and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.
[0109] The processor 21 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 21 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 21 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.
[0110] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or optical disk, etc. The resources stored on it include operating system 221, computer program 222 and data 223, etc., and the storage method can be temporary storage or permanent storage.
[0111] The operating system 221 manages and controls the various hardware devices and computer programs 222 on the electronic device to enable the processor 21 to perform calculations and processing on the massive amounts of data 223 in the memory 22. The operating system can be Windows, Unix, Linux, etc. The computer program 222, in addition to including a computer program capable of performing the ultrasound blood flow image post-processing method disclosed in any of the foregoing embodiments, may further include computer programs capable of performing other specific tasks. The data 223 may include data received by the electronic device from external devices, as well as data collected by its own input / output interface 25.
[0112] Furthermore, this application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the aforementioned disclosed ultrasound blood flow image post-processing method. Specific steps of this method can be found in the corresponding content disclosed in the foregoing embodiments, and will not be repeated here.
[0113] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.
[0114] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented 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 this application. The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly in hardware, software modules executed by a processor, or a combination of both. The software module may be located in random access memory (RAM), memory, read-only memory (ROM), electrically programmable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), register, hard disk, removable disk, CD-ROM (Compact Disc Read-Only Memory), or any other form of storage medium known in the art.
[0115] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0116] The present invention provides a detailed description of an ultrasound blood flow image post-processing method, apparatus, device, and medium. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.
Claims
1. A method for post-processing ultrasound blood flow images, characterized in that, include: The system receives echo signals from the target site based on ultrasound waves and generates an initial ultrasound blood flow map for the current frame based on the echo signals; wherein, the initial ultrasound blood flow map for the current frame includes sub-parameter maps for each current frame. The initial velocity threshold map of the current frame is obtained based on the current frame sub-parameter map and the previous frame sub-parameter map, and the connected component map is obtained using the current frame initial velocity threshold map. The connected component map is then marked to obtain the current frame initial region marking map. Determine the target parameter value of the initial region marking map of the current frame, and filter out invalid points from the initial region marking map of the current frame according to the relationship between the target parameter value and a preset threshold. Update the marking value of the invalid points in the initial region marking map of the current frame to obtain the target region marking map of the current frame. Based on the target region marker map of the current frame, the velocity value in the initial velocity threshold map of the current frame is modified to obtain the target velocity map of the current frame. Then, the initial ultrasound blood flow map of the current frame is processed according to the target velocity map of the current frame to obtain the target ultrasound blood flow map of the current frame.
2. The ultrasound blood flow image post-processing method according to claim 1, characterized in that, The sub-parameter maps of each current frame are the current frame velocity map, the current frame energy map, and the current frame variance map, respectively. Accordingly, obtaining the initial velocity threshold map of the current frame based on the current frame sub-parameter map and the previous frame sub-parameter map includes: Determine the preset velocity threshold, preset energy threshold, and preset variance threshold based on the current frame subparameter map and the previous frame subparameter map; The velocity values of the target points in the current frame velocity map are updated to 0, while the velocity values of the non-target points in the current frame velocity map remain unchanged, to obtain the initial velocity threshold map of the current frame.
3. The ultrasound blood flow image post-processing method according to claim 2, characterized in that, The target point's velocity value in the current frame velocity graph is less than the preset velocity threshold, or its energy value in the current frame energy graph is less than the preset energy threshold, or its variance value in the current frame variance graph is greater than the preset variance threshold.
4. The ultrasound blood flow image post-processing method according to claim 2, characterized in that, The step of obtaining a connected component map using the initial velocity threshold map of the current frame, and marking the connected component map to obtain an initial region-marked map of the current frame, includes: The initial velocity threshold map of the current frame and the target velocity threshold map of the previous frame are binarized respectively to obtain the corresponding template map of the current frame and the template map of the previous frame. Traverse the connected regions in the current frame template graph and the previous frame template graph to obtain a connected region graph, and mark the regions in the connected region graph to obtain the initial region marking graph of the current frame and the region marking graph of the previous frame.
5. The ultrasound blood flow image post-processing method according to claim 4, characterized in that, The step of determining the target parameter value of the initial region marker map of the current frame and filtering out invalid points from the initial region marker map of the current frame based on the relationship between the target parameter value and a preset threshold includes: The previous frame template image is compared with the current frame initial velocity threshold image region by region to find the number of target points with a mark value of 1 at each region position in the previous frame template image, and the target percentage of the number of target points relative to the total number of points in the corresponding region is calculated, and the target percentage is determined as the first target parameter value of the current frame initial region mark image. The region whose first target parameter value is less than the first preset threshold is identified as the first target region, and all points in the first target region are identified as first invalid points. Accordingly, updating the marker values of invalid points in the initial region marker map of the current frame to obtain the target region marker map of the current frame includes: The mark value of the first invalid point in the initial region mark map of the current frame is updated to 0 to obtain the first target region mark map of the current frame.
6. The ultrasound blood flow image post-processing method according to claim 4, characterized in that, The step of determining the target parameter value of the initial region marker map of the current frame and filtering out invalid points from the initial region marker map of the current frame based on the relationship between the target parameter value and a preset threshold includes: Each region of the current frame initial region marker map is compared with the current frame initial velocity threshold map to obtain the average value of the absolute velocity of all points in each region, and the average value is determined as the value of each second target parameter of the current frame initial region marker map; The region whose second target parameter value is less than the second preset threshold is identified as the second target region, and all points in the second target region are identified as second invalid points. Accordingly, updating the marker values of invalid points in the initial region marker map of the current frame to obtain the target region marker map of the current frame includes: The mark value of the second invalid point in the initial region mark map of the current frame is updated to 0 to obtain the second target region mark map of the current frame.
7. The ultrasound blood flow image post-processing method according to claim 4, characterized in that, The step of determining the target parameter value of the initial region marker map of the current frame and filtering out invalid points from the initial region marker map of the current frame based on the relationship between the target parameter value and a preset threshold includes: The size of each region in the initial region marking map of the current frame is determined, and each region size is determined as a third target parameter value of the initial region marking map of the current frame; wherein, the region size is the number of all points in the corresponding region; The region whose third target parameter value is less than the third preset threshold is determined as the third target region, and all points in the third target region are determined as third invalid points; Accordingly, updating the marker values of invalid points in the initial region marker map of the current frame to obtain the target region marker map of the current frame includes: The mark value of the third invalid point in the initial region mark map of the current frame is updated to 0 to obtain the third target region mark map of the current frame.
8. A post-processing device for ultrasound blood flow images, characterized in that, include: The initial blood flow map acquisition module is used to receive the echo signal returned by ultrasound from the target site, and generate the initial ultrasound blood flow map of the current frame based on the echo signal; wherein, the initial ultrasound blood flow map of the current frame includes each current frame sub-parameter map; The initial marker map acquisition module is used to obtain the initial velocity threshold map of the current frame based on the current frame sub-parameter map and the previous frame sub-parameter map, and to obtain a connected region map using the current frame initial velocity threshold map, and to mark the connected region map to obtain the initial region marker map of the current frame; The target marker map acquisition module is used to determine the target parameter value of the initial region marker map of the current frame, and filter out invalid points from the initial region marker map of the current frame according to the relationship between the target parameter value and a preset threshold, and update the marker value of the invalid points in the initial region marker map of the current frame to obtain the target region marker map of the current frame. The target blood flow map acquisition module is used to modify the velocity value in the initial velocity threshold map of the current frame based on the target region marker map of the current frame to obtain the target velocity map of the current frame, and to process the initial ultrasound blood flow map of the current frame according to the target velocity map of the current frame to obtain the target ultrasound blood flow map of the current frame.
9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the steps of the ultrasound blood flow image post-processing method as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, Used to store a computer program; wherein, when executed by a processor, the computer program implements the steps of the ultrasound blood flow image post-processing method as described in any one of claims 1 to 7.