Methods, apparatus, computer equipment and storage media for determining reflux data
By automatically identifying backflow edge contours and connected components, and combining multi-frame image data processing, the problems of low efficiency and insufficient accuracy in backflow data determination in existing technologies are solved, and efficient and accurate automated determination of backflow data is achieved.
Patent Information
- Application Number
- CN202311092367.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-08-28
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2043-08-28
AI Technical Summary
In existing technologies, the determination of reflux data relies on manually drawn images, which leads to low efficiency and inaccurate results, especially when identifying reflux areas and atrial regions, making it difficult to accurately determine the area.
By receiving ultrasound image data, the system automatically identifies the regurgitation edge contour and determines the connected regions. It then calculates the area of the regurgitation region and the atrial region by combining multiple frames of image data. Using noise reduction, edge detection, and contour smoothing techniques, the system achieves automated determination of regurgitation data.
This improves the efficiency of backflow data determination, reduces reliance on human experience, and ensures the accuracy and consistency of backflow data.
Smart Images

Figure CN117333531B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of ultrasound imaging, and more specifically to a method, apparatus, computer equipment, and storage medium for determining backflow data. Background Technology
[0002] Currently, regurgitation data is typically obtained by staff identifying and hand-drawing the regurgitation area and the atrial area where regurgitation occurs on regurgitation images. The regurgitation area and atrial area are then determined based on the hand-drawn regurgitation area and atrial area. This method is highly dependent on the staff's experience, and because the outlines of the regurgitation area and atrial area are not regular, it is difficult to determine the area of the regurgitation area and the atrial area. Often, the final regurgitation data is not accurate enough, and the complicated determination work also makes the staff's efficiency relatively low. Summary of the Invention
[0003] In view of this, embodiments of the present invention provide a method, apparatus, computer device, and storage medium for determining backflow data, in order to solve the problems of slow determination speed, time-consuming and laborious process, and inaccurate backflow data results caused by manually drawing images.
[0004] In a first aspect, embodiments of the present invention provide a method for determining backflow data, including:
[0005] Receive ultrasound image data, wherein the ultrasound image data includes at least multiple frames of initial blood flow image data;
[0006] Determine the target reflux edge contour data corresponding to the first frame of initial blood flow image data, wherein the first frame of initial blood flow image data is any frame of blood flow image data among multiple frames of initial blood flow image data;
[0007] Identify the corresponding connected components based on the target reflux edge contour data, and determine the two-dimensional reflux region corresponding to the initial blood flow image data based on at least some of the connected components;
[0008] The target reflux data is determined based on all two-dimensional reflux regions corresponding to multiple frames of initial blood flow image data. The target reflux data includes at least the target reflux region and the area of the target reflux region.
[0009] The above method involves receiving ultrasound image data, which includes at least multiple frames of initial blood flow image data; determining the target reflux edge contour data corresponding to the first frame of initial blood flow image data, wherein the first frame of initial blood flow image data is any one of the multiple frames of initial blood flow image data; identifying the corresponding connected components based on the target reflux edge contour data; and determining the two-dimensional reflux region corresponding to the initial blood flow image data based on at least some of the connected components; and determining the target reflux data based on all the two-dimensional reflux regions corresponding to the multiple frames of initial blood flow image data, wherein the target reflux data includes at least the target reflux region and its area. By determining the target reflux edge contour data from the received ultrasound images, and then determining the connected components corresponding to the target reflux edge contour data, and determining the reflux data based on at least some of the connected components, automatic determination of reflux data can be achieved, greatly improving work efficiency for staff and avoiding the reliance on personnel experience for manual recording of reflux regions.
[0010] In one optional implementation, the ultrasound image data further includes initial cardiac image data, and the target reflux data further includes a target atrial region and the area of the target atrial region; after determining the target reflux region based on the contours of all two-dimensional reflux regions corresponding to multiple frames of initial blood flow image data, the method further includes:
[0011] Contour recognition processing is performed on the initial cardiac image data to determine the first cardiac contour;
[0012] The first heart contour is completed based on the target reflux region to obtain a closed second heart contour;
[0013] The heart region corresponding to the second heart contour is defined as the target atrial region, and the area of the target atrial region is determined based on all the pixels corresponding to the target atrial region.
[0014] In one optional implementation, determining the target reflux edge contour data corresponding to the initial blood flow image data of the first frame includes:
[0015] The first frame of initial blood flow image data is subjected to a first noise reduction process according to a preset threshold to obtain the first blood flow image data.
[0016] Edge detection is performed on the first blood flow image data through binarization to obtain the initial reflux edge contour data;
[0017] The initial reflux edge contour data is subjected to data filling and first contour smoothing to obtain the target reflux edge contour data.
[0018] By performing the first noise reduction process on the initial blood flow image data of the first frame according to the preset threshold, some noise in the image can be removed, and a relatively rough blood flow region contour can be obtained. Then, edge detection is performed to obtain the initial reflux edge contour processing. After data filling processing and the first contour smoothing processing, a more refined target reflux edge contour data can be obtained.
[0019] In one optional implementation, the initial blood flow image data of the first frame is subjected to a first noise reduction process based on a threshold determined in real time to obtain the first blood flow image data, including:
[0020] All pixels are determined as the target value sequence based on the absolute value of the value corresponding to each pixel in the first frame of initial blood flow image data;
[0021] The absolute value of the pixel corresponding to the preset percentile in the target numerical sequence is determined as a threshold in real time.
[0022] Remove all pixels with absolute values less than a real-time determined threshold from the initial blood flow image data of the first frame to obtain the first blood flow image data.
[0023] By determining the threshold based on the absolute value of the pixel values and eliminating all pixels with absolute values less than the threshold, the region of velocity overlap in the initial blood flow image data can be eliminated.
[0024] In one optional implementation, edge detection is performed on the first blood flow image data through binarization processing to obtain initial reflux edge contour data, including:
[0025] Based on the first data in the first blood flow image data, determine the relationship between the data values of all points in its eight neighboring regions and the preset values, wherein the first data is any data in the first blood flow image data;
[0026] Based on the relationship between the data values of all points in the eight neighboring regions and the preset values, the first data is binarized to obtain the second blood flow image data.
[0027] The contour data formed by all pixels with a value of 1 in the second blood flow image data is used as the initial reflux region contour data.
[0028] In one optional implementation, the target reflux data is determined based on all two-dimensional reflux regions corresponding to multiple frames of initial blood flow image data, including:
[0029] All two-dimensional reflux regions corresponding to multiple frames of initial blood flow image data are combined to obtain a three-dimensional reflux region;
[0030] The three-dimensional reflux region is subjected to a second contour smoothing process to obtain the updated three-dimensional reflux region;
[0031] Calculate the area of each two-dimensional reflux region in the updated three-dimensional reflux region, and determine the target two-dimensional reflux region with the largest area;
[0032] The target two-dimensional reflux region and its area are defined as the target reflux data.
[0033] In one optional implementation, contour recognition processing is performed on the initial cardiac image data to determine a first cardiac contour, including:
[0034] The initial cardiac image data is subjected to a second noise reduction process to obtain the first cardiac image data;
[0035] Perform a first edge detection process on the first heart image data to obtain the edge of the first heart;
[0036] A second edge detection process is performed on the region formed by the edge of the first heart using a preset matrix template to determine the outline of the first heart.
[0037] In one optional implementation, the first cardiac contour is completed based on the contour of the target reflux region to obtain a closed second cardiac contour, including:
[0038] For each pixel in the region contour corresponding to the target reflux region, determine the normal extension line corresponding to the pixel, wherein the normal extension line starts from the pixel and extends to the first heart contour.
[0039] The target missing pixels are selected based on the length of all normal extension lines. The target missing pixels and all pixels on the first heart contour form a closed second heart contour.
[0040] Specifically, the target missing pixels are selected based on the length of all normal extension lines, including:
[0041] Starting from each pixel in the outline of the target reflux region, extend along the normal of each starting point on the outline of the target reflux region until it touches the outline of the first heart, and obtain the extension line corresponding to each starting point.
[0042] Target missing pixels are selected from the first heart contour based on the length of all extension lines.
[0043] Using the above method, the normal extension line corresponding to each pixel in the target reflux region is determined. The target missing pixels are selected based on the length of the normal extension line. The first heart contour can be completed based on the target missing pixels and the normal extension line to form a closed second heart contour.
[0044] Secondly, embodiments of the present invention provide a device for determining backflow data, comprising:
[0045] A receiving module is used to receive ultrasound image data, wherein the ultrasound image data includes at least multiple frames of initial blood flow image data;
[0046] The first determining module is used to determine the target reflux edge contour data corresponding to the first frame of initial blood flow image data, wherein the first frame of initial blood flow image data is any frame of blood flow image data among multiple frames of initial blood flow image data;
[0047] The identification module is used to identify the corresponding connected components based on the target reflux edge contour data, and to determine the two-dimensional reflux region corresponding to the initial blood flow image data based on at least some of the connected components.
[0048] The second determining module is used to determine the target reflux data based on all two-dimensional reflux regions corresponding to multiple frames of initial blood flow image data. The target reflux data includes at least the target reflux region and the area of the target reflux region.
[0049] Thirdly, embodiments of the present invention provide a computer device, including: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the method for determining reverse flow data as described in the first aspect or any corresponding embodiment.
[0050] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing computer instructions for causing a computer to execute the method for determining reverse flow data as described in the first aspect or any corresponding embodiment. Attached Figure Description
[0051] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0052] Figure 1 This is a schematic diagram of CFI images superimposed on a two-dimensional ultrasound B-mode image according to some embodiments of the present invention;
[0053] Figure 2 This is a flowchart illustrating a method for determining backflow data according to some embodiments of the present invention;
[0054] Figure 3This is a flowchart illustrating a method for determining a target atrial region according to some embodiments of the present invention;
[0055] Figure 4 This is a schematic diagram of the first heart outline according to some embodiments of the present invention;
[0056] Figure 5 This is a schematic diagram of the heart outline after completion according to some embodiments of the present invention;
[0057] Figure 6 This is a schematic flowchart of a method for determining the second heart contour according to some embodiments of the present invention;
[0058] Figure 7 This is a schematic diagram of a cardiac contour completion method according to some embodiments of the present invention;
[0059] Figure 8 This is a flowchart illustrating a method for determining backflow data according to some embodiments of the present invention;
[0060] Figure 9 This is a structural block diagram of a device for determining backflow data according to an embodiment of the present invention;
[0061] Figure 10 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation
[0062] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0063] To determine reflux data, we typically overlay the obtained color Doppler flow imaging (CFI) images onto a two-dimensional B-mode ultrasound image. The overlaid image is shown below. Figure 1 As shown, brightness represents the magnitude of velocity, and color represents the direction of blood flow. Different color coding methods produce different effects. In this example, red indicates movement towards the probe; green indicates movement away from the probe; green represents turbulence, where forward turbulence is close to yellow, and reverse turbulence is close to dark cyan. Figure 1 (Color not shown).
[0064] It is not difficult to observe that the reflux signal has the following characteristics:
[0065] (1) It often appears in specific periods;
[0066] (2) High brightness and high flow rate;
[0067] (3) Turbulent flow occurs.
[0068] Based on this, in this embodiment of the invention, a method for determining backflow data is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.
[0069] This embodiment provides a method for determining backflow data, which can be used in the aforementioned computer equipment. Figure 2 This is a flowchart of a method for determining reflux data according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps:
[0070] Step S201: Receive ultrasound image data.
[0071] Specifically, the ultrasound image data includes at least multiple frames of initial blood flow image data. The initial cardiac image is a cardiac image scanned by the device; in an optional example, the cardiac image can be a two-dimensional B-mode echocardiogram. The initial blood flow image data is also a blood flow image scanned by the device, such as Doppler color image data. Because blood flow changes significantly at each moment, multiple frames of initial blood flow images can be acquired to ensure that a more accurate reflux area can be obtained subsequently.
[0072] Step S202: Determine the target reflux edge contour data corresponding to the initial blood flow image data of the first frame.
[0073] Specifically, the first frame of initial blood flow image data is any frame of blood flow image data from multiple initial blood flow image data. Edge detection processing is performed on the first frame of blood flow image data to detect the edges of the reflux region corresponding to the first frame of blood flow image data, thereby determining the target reflux edge contour data.
[0074] In an alternative example, an edge detection algorithm can be used to determine the target reflux edge contour data after edge detection processing of the first frame of blood flow image data.
[0075] Step S203: Identify the corresponding connected components based on the target reflux edge contour data, and determine the two-dimensional reflux region corresponding to the initial blood flow image data based on at least some of the connected components.
[0076] Specifically, connected component identification processing is performed on the first blood flow image data. When the identification result is that there is only one connected component, the connected component is taken as the two-dimensional reflux region corresponding to the first blood flow image data. When there are multiple connected components in the identification result, at least one connected component that meets the preset conditions can be taken as the two-dimensional reflux region corresponding to the first blood flow image data, and the contour of the region is obtained, that is, the two-dimensional reflux region corresponding to the initial blood flow image data.
[0077] In an optional example, for instance, an 8-connected template can be used to identify connected components in the first blood flow image data. When multiple connected components exist in the identification result, the area of each connected component is calculated, the two connected components with the largest areas are found, and they are merged. The merged connected component is taken as the two-dimensional reflux region corresponding to the first blood flow image data. This connected component is the approximate location of the identified reflux region. A boundary smoothing operation is performed on the identified region to obtain the two-dimensional reflux region corresponding to the initial blood flow image data.
[0078] Step S204: Determine the target reflux data based on all two-dimensional reflux regions corresponding to the multiple frames of initial blood flow image data. The target reflux data includes at least the target reflux region and the area of the target reflux region.
[0079] Specifically, the area of the target reflux region can be determined based on the pixels in the reflux region contour, and the best reflux region contour can be selected from all the identified two-dimensional reflux region contours as the target reflux region contour.
[0080] In an alternative example, the largest two-dimensional reflux region can be used as the target reflux region.
[0081] The method for determining backflow data proposed in this embodiment of the invention has the following advantages:
[0082] The process involves receiving ultrasound image data, which includes at least multiple frames of initial blood flow image data; determining the target reflux edge contour data corresponding to the first frame of initial blood flow image data, wherein the first frame of initial blood flow image data is any one of the multiple frames of initial blood flow image data; identifying the corresponding connected components based on the target reflux edge contour data; and determining the two-dimensional reflux region corresponding to the initial blood flow image data based on at least some of the connected components; and determining the target reflux data based on all the two-dimensional reflux regions corresponding to the multiple frames of initial blood flow image data, wherein the target reflux data includes at least the target reflux region and its area. By determining the target reflux edge contour data from the received ultrasound images, and then determining the connected components corresponding to the target reflux edge contour data, and determining the reflux data based on at least some of the connected components, automatic determination of reflux data can be achieved, greatly improving work efficiency for staff and avoiding the reliance on personnel experience for manual recording of reflux regions.
[0083] In one optional implementation, the ultrasound image data further includes initial cardiac image data, and the target reflux data further includes a target atrial region and the area of the target atrial region; after determining the target reflux region based on the contours of all two-dimensional reflux regions corresponding to multiple frames of initial blood flow image data, the method further includes... Figure 3 The steps shown are as follows:
[0084] Step S301: Perform contour recognition processing on the initial heart image data to obtain the first heart contour.
[0085] Specifically, by performing contour recognition processing on the initial heart image, a portion of the heart contour can be obtained, such as... Figure 4 As shown in the outline, the first heart outline has a missing part of the atrial edge, indicating it is not closed. This is because there is blood flow near the junction of the left and right atria, making it difficult to clearly identify the outline during outline recognition. Figure 4 As shown by the dashed line.
[0086] Step S302: Complete the first heart contour according to the target reflux region to obtain a closed second heart contour.
[0087] Specifically, the first heart contour can be completed by calculating the positional relationship between the target reflux region and the first heart contour, and by performing calculations based on the distance between pixels in the target reflux region contour and pixels in the first heart contour. Figure 5 As shown, the target heart region is obtained, and a closed second heart contour is obtained based on the pixels in the target heart region.
[0088] Step S303: Determine the heart region corresponding to the second heart contour as the target atrial region, and determine the area of the target atrial region based on all the pixels corresponding to the target atrial region.
[0089] Specifically, the heart region corresponding to the second heart contour is determined as the target atrial region, and the area of the target atrial region is determined based on all the pixels in the target atrial region.
[0090] In one optional example, the target atrium is typically the left atrium. The area of a pixel is determined by the resolution; the area of a pixel can be determined by the image resolution, and then the area of the target atrium can be determined based on the number of pixels within the target atrium region.
[0091] In one optional implementation, determining the target reflux edge contour data corresponding to the initial blood flow image data of the first frame includes:
[0092] Step a1: Perform a first noise reduction process on the initial blood flow image data of the first frame according to a preset threshold to obtain the first blood flow image data.
[0093] Specifically, the initial blood flow image data of the first frame can be subjected to a first noise reduction process, such as removing some areas with low flow rates based on the pixel value.
[0094] Step a2: The first blood flow image data is binarized to perform edge detection to obtain the initial reflux edge contour data.
[0095] Specifically, binarizing an image according to certain rules can produce finer edges, but these edges still contain many holes and points that cannot be closed.
[0096] Step a3: Perform data filling and first contour smoothing processing on the initial reflux edge contour data to obtain the target reflux edge contour data.
[0097] Specifically, data filling processing can include morphological opening / closing operations. For example, performing a morphological closing operation on the binarized data can fill in some small holes, and then performing a morphological opening operation can smooth the contour and eliminate some small unclosed contours. After this processing, the initial backflow edge contour data with relatively clear edges will be obtained.
[0098] By performing the first noise reduction process on the initial blood flow image data of the first frame according to the preset threshold, some noise in the image can be removed, and a relatively rough blood flow region contour can be obtained. Then, edge detection is performed to obtain the initial reflux edge contour processing. After data filling processing and the first contour smoothing processing, a more refined target reflux edge contour data can be obtained.
[0099] In one optional implementation, the first frame of initial blood flow image data is subjected to a first noise reduction process based on a threshold determined in real time to obtain the first blood flow image data, including the following method steps:
[0100] Step b1: Determine all pixels as the target value sequence based on the absolute value of the numerical value corresponding to each pixel in the initial blood flow image data of the first frame.
[0101] Specifically, based on the absolute value of the data corresponding to each pixel in the initial blood flow image data of the first frame, all pixels are determined as the target value sequence. For example, if the absolute value of pixel a is 3, the absolute value of pixel b is 2, and the absolute value of pixel c is 0, then the target value sequence can be a, b, c or c, b, a. The specific sequence can be determined according to the actual needs, and no further restrictions are imposed here.
[0102] Step b2: Determine the absolute value of the pixel corresponding to the preset percentile in the target numerical sequence as a threshold determined in real time.
[0103] Step b3: Eliminate all pixels in the initial blood flow image data of the first frame that have absolute values less than a threshold determined in real time to obtain the first blood flow image data.
[0104] Specifically, in an optional example, the 80th percentile of the absolute value of each data point in the first frame of blood flow image data can be used as a threshold, and data points with an absolute value less than the threshold can be set to 0. In this way, some areas with low flow velocity can be eliminated. The numerical value of the data represents the flow velocity, and the sign (positive or negative) represents the direction of blood flow.
[0105] In one optional implementation, edge detection is performed on the first blood flow image data through binarization processing to obtain initial reflux edge contour data, including:
[0106] Step c1: Using the first data in the first blood flow image data as a reference, determine the relationship between the data values of all points in its eight neighborhoods and the preset values.
[0107] Specifically, the first data is any one of the data in the first blood flow image data.
[0108] Based on the relationship between the data values of all points in the eight neighboring regions and the preset values, the first data is binarized to obtain the second blood flow image data.
[0109] The contour data formed by all pixels with a value of 1 in the second blood flow image data is used as the initial reflux region contour data.
[0110] Specifically, the first blood flow data is any one of the data in the second blood flow image data. If the first data is positive, all data in its eight neighborhoods are traversed. The eight neighborhoods refer to the data at the top, bottom, left, right, and the four diagonal corners of the first data (top left, bottom left, top right, and bottom right). If all data in the eight neighborhoods are greater than or equal to 0, the first data is marked as 0. If the first data is negative, the values of the data in the eight neighborhoods are also judged. If all data in the eight neighborhoods are less than or equal to 0, the first data is set to 0. In other cases, the first blood flow data is set to 1. The second blood flow image data is obtained in this way. Then, the contour data formed by all pixels with a pixel value of 1 is used as the initial reflux region contour data.
[0111] It's important to note that before traversing, each edge of the second blood flow image data can be expanded outwards by two rows and padded with zeros. This ensures that every data point in the second blood flow image data has an eight-neighborhood value. The purpose of this is to set the data at the edge of non-reflux regions to 0, thus allowing the identification of reflux region contours based on non-zero values. This is because if all values in the eight-neighborhood of a positive value are greater than or equal to 0, it indicates that the data has the same properties as its surrounding data, meaning it is not located at an edge. The same principle applies to negative values.
[0112] In one optional implementation, the target reflux data is determined based on all two-dimensional reflux regions corresponding to multiple frames of initial blood flow image data, including the following method steps:
[0113] Step a1: Combine all two-dimensional reflux regions corresponding to multiple frames of initial blood flow image data to obtain a three-dimensional reflux region.
[0114] Specifically, the two-dimensional reflux region contours identified from each frame of initial blood flow image data are summarized to obtain a three-dimensional reflux region contour.
[0115] Step a2: Perform a second contour smoothing process on the three-dimensional reflux region to obtain the updated three-dimensional reflux region.
[0116] Specifically, a boundary smoothing operation can be performed on the three-dimensional reflux region contour to obtain the final three-dimensional reflux region contour.
[0117] Step a3: Calculate the area of each two-dimensional reflux region in the updated three-dimensional reflux region, and determine the target two-dimensional reflux region with the largest area.
[0118] Step a4: Determine the target two-dimensional reflux region and its area as the target reflux data.
[0119] Specifically, based on the smoothed 3D reflux region contour, the area of the 2D reflux region contour in each frame of the 3D reflux region contour is calculated. The 2D reflux region with the largest area is taken as the target 2D reflux region, and its area is recorded. Similarly, the area of the target reflux region can also be determined based on the number of pixels in the region. In an optional implementation, contour recognition processing is performed on the initial cardiac image data to determine the first cardiac contour, including the following method steps:
[0120] Step b1: Perform a second noise reduction process on the initial cardiac image data to obtain the first cardiac image data.
[0121] Specifically, for example, filtering and smoothing can be used to denoise the initial heart image, and a second denoising process can be performed on the initial heart image data to obtain the first heart image data.
[0122] b2, perform first edge detection processing on the first heart image data to obtain the edge of the first heart.
[0123] Specifically, edge detection algorithms such as differential edge detection algorithms can be used to perform edge detection processing on the first heart image data to obtain the first heart image.
[0124] b3. Use a preset matrix template to perform a second edge detection process on the region formed by the edge of the first heart to determine the outline of the first heart.
[0125] Specifically, an edge detection operation can be performed on the first heart image data using a preset matrix template. When the pixel value of the pixels contained in the preset matrix template meets the preset conditions, the pixel value of the pixel at the center point of the preset matrix template is set to 1; or, when the pixel value of the pixels contained in the preset matrix template does not meet the preset conditions, the pixel value of the pixel at the center point of the preset matrix template is set to 0. Then, the contour formed by the pixels with a pixel value of 1 is used as the contour of the first heart.
[0126] In an optional example, the preset matrix template can be a 3*3 template. The image is traversed using this template. If there are 5 or more pixels with a value of 1 within the 3*3 template range, the pixel is set to 1. Otherwise, the pixel is set to 0. The outline formed by the pixels with a value of 1 is then used as the first heart outline.
[0127] The above method can yield a more refined edge.
[0128] In one alternative implementation, the first cardiac contour is completed based on the target reflux region contour to obtain a closed second cardiac contour, including, for example... Figure 6 The steps shown are as follows:
[0129] Step S601: For each pixel in the region contour corresponding to the target reflux region, determine the normal extension line corresponding to the pixel.
[0130] Specifically, the normal extension line starts from a pixel and extends to the first heart contour. It can be like this: Figure 7 As shown, each pixel in the outline of the target reflux region is taken as the starting point, and the normal of the outline of the target reflux region is extended along the starting point, which is the normal extension line corresponding to each pixel.
[0131] Step S602: Select the target missing pixels based on the length of all normal extension lines. The target missing pixels and all pixels on the first heart contour form a closed second heart contour.
[0132] Specifically, the target missing pixels are selected based on the length of all normal extension lines, including:
[0133] Starting from each pixel in the outline of the target reflux region, extend along the normal of each starting point on the outline of the target reflux region until it touches the outline of the first heart, and obtain the extension line corresponding to each starting point.
[0134] Target missing pixels are selected from the first heart contour based on the length of all extension lines.
[0135] Specifically, the normal extension line of each pixel stops when it touches the first heart contour. As a result, in the missing portion of the first heart contour, the extension line will be significantly longer than in the unmissing portion, causing a sharp abrupt change in gradient. The point where the extension line length changes abruptly is identified; this point is the starting point of the missing portion of the first heart contour, which is also the junction of the left and right atria. Figure 7 As shown, this point is taken as the target missing pixel.
[0136] A pixel 5 pixels away from the first target pixel can be selected as the target slope pixel. The missing target pixel and the target slope pixel are connected by a straight line, and the slope of this line is the extension slope. Starting from the missing target pixel, the extension is performed along the direction corresponding to the extension slope to complete the first heart contour, i.e., the closed second heart contour.
[0137] In an optional example, after obtaining the second heart contour, connected component recognition processing can be performed on the second heart contour. For example, an eight-connected template can be used to perform connected component recognition processing on the second heart contour to obtain the recognition result. When the recognition result includes multiple connected components, the connected component containing the target reflux region is taken as the target heart region. In this way, it can be guaranteed that the connected component is the atrial region where reflux occurs. Then, further data analysis can be performed based on the data of the atrial region where reflux occurs and the target reflux data.
[0138] To make the method described in this application clearer, this application also provides a specific embodiment, such as in... Figure 8 As shown, this method can be loaded into the relevant device as software. When it is necessary to determine reflux data, the automatic reflux data determination function can be activated, and then the maximum frame of the reflux bundle can be automatically located and the reflux bundle can be automatically recorded to calculate the reflux region area. Then, the left atrium can be automatically recorded and the left atrial area can be calculated. The reflux data is determined based on the ratio of the reflux region area to the left atrial area.
[0139] This embodiment also provides a device for determining backflow data, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.
[0140] This embodiment provides a device for determining reflux data, such as... Figure 9 As shown, it includes: a receiving module 901, a first determining module 902, an identification module 903, and a second determining module 904;
[0141] The receiving module 901 is used to receive ultrasound image data, wherein the ultrasound image data includes at least multiple frames of initial blood flow image data;
[0142] The first determining module 902 is used to determine the target reflux edge contour data corresponding to the first frame of initial blood flow image data, wherein the first frame of initial blood flow image data is any frame of blood flow image data among multiple frames of initial blood flow image data;
[0143] The identification module 903 is used to identify the corresponding connected components based on the target reflux edge contour data, and to determine the two-dimensional reflux region corresponding to the initial blood flow image data based on at least some of the connected components.
[0144] The second determining module 904 is used to determine the target reflux data based on all two-dimensional reflux regions corresponding to multiple frames of initial blood flow image data. The target reflux data includes at least the target reflux region and the area of the target reflux region.
[0145] In one optional embodiment, the device further includes: a contour recognition module 905, a completion module 906, and a third determination module 907;
[0146] The contour recognition module 905 is used to perform contour recognition processing on the initial cardiac image data to determine the first cardiac contour.
[0147] The completion module 906 is used to complete the first heart contour based on the target reflux region to obtain a closed second heart contour.
[0148] The third determining module 907 is used to determine the heart region corresponding to the second heart contour as the target atrial region, and to determine the area of the target atrial region based on all the pixels corresponding to the target atrial region.
[0149] In one optional implementation, the first determining module 902 includes:
[0150] The first noise reduction processing unit is used to perform first noise reduction processing on the first frame of initial blood flow image data according to a preset threshold to obtain the first blood flow image data.
[0151] An edge detection unit is used to perform edge detection on the first blood flow image data through binarization processing to obtain initial reflux edge contour data;
[0152] The data filling and first contour smoothing processing unit is used to perform data filling processing and first contour smoothing processing on the initial backflow edge contour data to obtain the target backflow edge contour data.
[0153] In one optional implementation, the first noise reduction processing unit includes:
[0154] The first determining subunit determines all pixels as the target value sequence based on the absolute value of the value corresponding to each pixel in the initial blood flow image data of the first frame; the absolute value of the value of the pixel corresponding to the preset percentile in the target value sequence is a threshold determined in real time.
[0155] The elimination subunit is used to eliminate all pixels in the initial blood flow image data of the first frame whose absolute values are less than a threshold determined in real time, so as to obtain the first blood flow image data.
[0156] In one alternative implementation, the edge detection unit includes:
[0157] The second determining subunit is used to determine the relationship between the data values of all points in its eight neighborhoods and preset values based on the first data in the first blood flow image data, wherein the first data is any data in the first blood flow image data;
[0158] The binarization processing subunit is used to perform binarization processing on the first data according to the relationship between the data values of all points in the eight neighborhoods and the preset values to obtain the second blood flow image data; and to use the contour data composed of all pixels with a pixel value of 1 in the second blood flow image data as the initial reflux region contour data.
[0159] In one optional implementation, the second determining module 904 includes:
[0160] The combination unit is used to combine all two-dimensional reflux regions corresponding to multiple frames of initial blood flow image data to obtain a three-dimensional reflux region.
[0161] The second contour smoothing unit is used to perform second contour smoothing on the three-dimensional reflux region to obtain the updated three-dimensional reflux region.
[0162] The calculation unit is used to calculate the area of each two-dimensional reflux region in the updated three-dimensional reflux region and determine the target two-dimensional reflux region with the largest area.
[0163] The first determining unit is used to determine the target two-dimensional reflux region and the area of the target two-dimensional reflux region as target reflux data.
[0164] In one alternative implementation, the contour recognition module 905 includes:
[0165] The second noise reduction processing unit is used to perform a second noise reduction process on the initial cardiac image data to obtain the first cardiac image data.
[0166] The first edge detection processing unit is used to perform first edge detection processing on the first heart image data to obtain the edge of the first heart;
[0167] The second edge detection processing unit is used to perform second edge detection processing on the region formed by the edge of the first heart using a preset matrix template to determine the outline of the first heart.
[0168] In one alternative implementation, the completion module 906 includes:
[0169] The second determining unit is used to determine the normal extension line corresponding to each pixel in the region contour corresponding to the target reflux region, wherein the normal extension line starts from the pixel and extends to the first heart contour.
[0170] The filtering unit is used to filter out the target missing pixels based on the length of all normal extension lines. The target missing pixels and all pixels on the first heart contour form a closed second heart contour.
[0171] The filtering unit includes:
[0172] The extension subunit is used to extend along the normal of each starting point on the contour of the target reflux region, starting from each pixel in the contour of the target reflux region, until it touches the first heart contour, and obtain the extension line corresponding to each starting point.
[0173] The filtering sub-unit is used to filter out target missing pixels from the first heart contour based on the length of all extension lines.
[0174] In this embodiment, the device for determining the backflow data is presented in the form of a functional unit. Here, a unit refers to an ASIC circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above-mentioned functions.
[0175] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.
[0176] This invention also provides a computer device having the above-described features. Figure 9 The device shown is for determining the reflux data.
[0177] Please see Figure 10 , Figure 10 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 10 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 10 Take a processor 10 as an example.
[0178] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.
[0179] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.
[0180] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device as shown by a landing page for an app. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, which can be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
[0181] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.
[0182] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.
[0183] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.
[0184] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.
Claims
1. A method for determining reflux data, characterized in that, The method includes: Receive ultrasound image data, wherein the ultrasound image data includes at least multiple frames of initial blood flow image data; Determine the target reflux edge contour data corresponding to the initial blood flow image data of the first frame, wherein the initial blood flow image data of the first frame is any one frame of blood flow image data among the multiple frames of initial blood flow image data; Identify the corresponding connected components based on the target reflux edge contour data, and determine the two-dimensional reflux region corresponding to the initial blood flow image data based on at least a portion of the connected components; Target reflux data is determined based on all the two-dimensional reflux regions corresponding to the initial blood flow image data of multiple frames, and the target reflux data includes at least the target reflux region and the area of the target reflux region; The ultrasound image data also includes initial cardiac image data, and the target reflux data also includes a target atrial region and the area of the target atrial region; after determining the target reflux region based on all the two-dimensional reflux regions corresponding to multiple frames of the initial blood flow image data, the method further includes: The initial cardiac image data is subjected to contour recognition processing to determine the first cardiac contour; The first heart contour is completed based on the target reflux region to obtain a closed second heart contour; The heart region corresponding to the second heart contour is determined as the target atrial region, and the area of the target atrial region is determined according to all the pixels corresponding to the target atrial region. The step of completing the first heart contour based on the target reflux region to obtain a closed second heart contour includes: For each pixel in the region contour corresponding to the target reflux region, determine the normal extension line corresponding to the pixel, wherein the normal extension line starts from the pixel and extends to the first heart contour. Target missing pixels are selected based on the length of all said normal extension lines, and the target missing pixels and all pixels on the first heart contour form a closed second heart contour. The step of filtering out target missing pixels based on the lengths of all the normal extension lines includes: Starting from each pixel in the target reflux region contour, extend along the normal of each starting point on the target reflux region contour until it touches the first heart contour, and obtain the extension line corresponding to each starting point. Target missing pixels are selected from the first heart contour based on the length of all the extended lines.
2. The method for determining reflux data according to claim 1, characterized in that, Determining the target reflux edge contour data corresponding to the initial blood flow image data of the first frame includes: The initial blood flow image data of the first frame is subjected to a first noise reduction process according to a preset threshold to obtain the first blood flow image data; Edge detection is performed on the first blood flow image data through binarization to obtain initial reflux edge contour data; The initial backflow edge contour data is subjected to data filling processing and first contour smoothing processing to obtain the target backflow edge contour data.
3. The method for determining reflux data according to claim 2, characterized in that, The initial blood flow image data of the first frame is subjected to a first noise reduction process based on a threshold determined in real time to obtain the first blood flow image data, including: Based on the absolute value of the numerical value corresponding to each pixel in the initial blood flow image data of the first frame, all the pixels are determined as the target numerical sequence; The absolute value of the pixel corresponding to the preset percentile in the target numerical sequence is determined as a threshold in real time. Eliminate all pixels in the initial blood flow image data of the first frame that have absolute values less than the threshold determined in real time to obtain the first blood flow image data.
4. The method for determining reflux data according to claim 2, characterized in that, The step of performing edge detection on the first blood flow image data through binarization processing to obtain initial reflux edge contour data includes: Based on the first data in the first blood flow image data, determine the relationship between the data values of all points in its eight neighboring regions and the preset values, wherein the first data is any data in the first blood flow image data; Based on the relationship between the data values of all points in the eight neighboring regions and the preset values, the first data is binarized to obtain the second blood flow image data. The contour data formed by all pixels with a value of 1 in the second blood flow image data is used as the initial reflux region contour data.
5. The method for determining reflux data according to any one of claims 1-4, characterized in that, The step of determining the target reflux data based on all the two-dimensional reflux regions corresponding to the multiple frames of the initial blood flow image data includes: The two-dimensional reflux regions corresponding to the initial blood flow image data of multiple frames are combined to obtain the three-dimensional reflux region; The three-dimensional reflux region is subjected to a second contour smoothing process to obtain an updated three-dimensional reflux region; Calculate the area of each of the two-dimensional reflux regions in the updated three-dimensional reflux region, and determine the target two-dimensional reflux region with the largest area; The target two-dimensional reflux region and its area are defined as the target reflux data.
6. The method for determining reflux data according to claim 1, characterized in that, The step of performing contour recognition processing on the initial cardiac image data to determine the first cardiac contour includes: The initial cardiac image data is subjected to a second noise reduction process to obtain the first cardiac image data; Perform a first edge detection process on the first heart image data to obtain the first heart edge; A second edge detection process is performed on the region formed by the edge of the first heart using a preset matrix template to determine the outline of the first heart.
7. A device for determining reflux data, characterized in that, The device includes: A receiving module is used to receive ultrasound image data, wherein the ultrasound image data includes at least multiple frames of initial blood flow image data; The first determining module is used to determine the target reflux edge contour data corresponding to the initial blood flow image data of the first frame, wherein the initial blood flow image data of the first frame is any one frame of blood flow image data among multiple frames of initial blood flow image data; The identification module is used to identify the corresponding connected components based on the target reflux edge contour data, and to determine the two-dimensional reflux region corresponding to the initial blood flow image data based on at least a portion of the connected components. The second determining module is used to determine target reflux data based on all the two-dimensional reflux regions corresponding to the initial blood flow image data of multiple frames, wherein the target reflux data includes at least the target reflux region and the area of the target reflux region; The ultrasound image data also includes initial cardiac image data, and the target reflux data also includes a target atrial region and the area of the target atrial region; after determining the target reflux region based on all the two-dimensional reflux regions corresponding to multiple frames of the initial blood flow image data, the method further includes: The initial cardiac image data is subjected to contour recognition processing to determine the first cardiac contour; The first heart contour is completed based on the target reflux region to obtain a closed second heart contour; The heart region corresponding to the second heart contour is determined as the target atrial region, and the area of the target atrial region is determined according to all the pixels corresponding to the target atrial region. The step of completing the first heart contour based on the target reflux region to obtain a closed second heart contour includes: For each pixel in the region contour corresponding to the target reflux region, determine the normal extension line corresponding to the pixel, wherein the normal extension line starts from the pixel and extends to the first heart contour. Target missing pixels are selected based on the length of all said normal extension lines, and the target missing pixels and all pixels on the first heart contour form a closed second heart contour. The step of filtering out target missing pixels based on the lengths of all the normal extension lines includes: Starting from each pixel in the target reflux region contour, extend along the normal of each starting point on the target reflux region contour until it touches the first heart contour, and obtain the extension line corresponding to each starting point. Target missing pixels are selected from the first heart contour based on the length of all the extended lines.
8. A computer device, characterized in that, include: A memory and a processor are communicatively connected, the memory storing computer instructions, and the processor executing the computer instructions to perform the method for determining reverse flow data as described in any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to perform the method for determining the reverse flow data according to any one of claims 1 to 6.
Citation Information
Patent Citations
Backflow monitoring method and system
CN115956952A
