Ultrasonic measurement method and device for inferior vena cava, electronic equipment and storage medium

Abstract

The invention relates to the technical field of medical image processing, and discloses an ultrasonic measurement method and device for an inferior vena cava, electronic equipment and a storage medium, and the method comprises the steps: obtaining the ultrasonic image data of the inferior vena cava at the current moment; based on the characteristics of the inferior vena cava in the ultrasonic image data, positioning the area where the inferior vena cava is located by adopting a voting algorithm; on the basis of the area where the inferior vena cava is located, the simplified active contour model is combined, and pipe wall information of the inferior vena cava is extracted; and calculating parameters of the inferior vena cava in a respiratory cycle based on the tube wall information of the inferior vena cava. According to the method, the number of parameters of the active contour model and the calculation complexity are reduced, the extraction speed of the inferior vena cava wall information is increased, and the inferior vena cava wall information can be conveniently obtained in real time. In addition, according to the inferior vena cava wall information obtained in real time, the parameters of the inferior vena cava in one respiratory cycle can be calculated in real time, the accuracy of calculation of the parameters of the inferior vena cava is effectively improved, and the real-time requirement of inferior vena cava measurement can be met.

Description

Technical Field

[0001] This invention relates to the field of medical image processing technology, specifically to ultrasound measurement methods, devices, electronic equipment, and storage media for the inferior vena cava. Background Technology

[0002] The inferior vena cava (IVC) is the largest vein in the human body and one of the main pathways for venous blood to return to the heart. Its diameter reflects the amount of venous return. Changes in the diameter of the IVC can further reflect the body's blood volume and cardiac workload. In recent years, IVC ultrasound examination has been increasingly used in patients with acute and severe cardiovascular diseases, playing an important role in fluid resuscitation decisions for conditions such as heart failure, cardiogenic shock, and septic shock-related myocardial depression.

[0003] In manual measurement of the inferior vena cava, the operator needs to locate the ultrasound images at the end of inspiration and expiration in B-mode or M-mode ultrasound images based on experience, thus performing the measurement; this is highly dependent on the operator's clinical experience and measurement skills. Moreover, in related technologies, the method of using machine learning for inferior vena cava localization and measurement in the process of automatic measurement places high demands on the machine's computing power, thus failing to meet real-time requirements. Summary of the Invention

[0004] In view of this, the present invention provides an ultrasound measurement method, device, electronic device and storage medium for the inferior vena cava, to solve the technical problems of difficulty in locating the contour of the inferior vena cava and the inability to obtain the parameters of the inferior vena cava in a timely manner during the cycle.

[0005] In a first aspect, the present invention provides an ultrasound measurement method for the inferior vena cava, the method comprising:

[0006] Acquire ultrasound image data of the inferior vena cava at the current moment;

[0007] Based on the features of the inferior vena cava in the ultrasound image data, a voting algorithm is used to locate the region of the inferior vena cava;

[0008] Based on the location of the inferior vena cava, and combined with a simplified active contour model, the wall information of the inferior vena cava is extracted.

[0009] Based on the wall information of the inferior vena cava, the parameters of the inferior vena cava during one respiratory cycle are calculated.

[0010] Beneficial Effects: By acquiring ultrasound image data of the inferior vena cava at the current moment and using a voting algorithm based on the features of the inferior vena cava in the ultrasound image data, the location of the inferior vena cava is located, achieving highly robust localization and making the localization of the inferior vena cava more accurate. After determining the location of the inferior vena cava, a simplified active contour model is used to extract the wall information of the inferior vena cava; this reduces the number of parameters and computational complexity of the active contour model, making it more suitable for extracting the wall information of the inferior vena cava, improving the extraction speed, and facilitating real-time acquisition of the wall information of the inferior vena cava. Furthermore, based on the real-time acquired wall information of the inferior vena cava, the parameters of the inferior vena cava during a respiratory cycle can be calculated in real time, which can effectively improve the accuracy of the inferior vena cava parameter calculation and meet the real-time requirements of inferior vena cava measurement.

[0011] In one optional implementation, the step of locating the region of the inferior vena cava based on the features of the inferior vena cava in the ultrasound image data using a voting algorithm includes:

[0012] Calculate the average grayscale value of each row of pixels in the ultrasound image data;

[0013] Perform one-dimensional Gaussian smoothing on the grayscale mean;

[0014] The Otsu threshold of the ultrasound image data was calculated based on the Otsu method.

[0015] Based on the Otsu threshold and the average gray value of each row of pixels, calculate the valley under each Otsu threshold and use the valley as a candidate region;

[0016] Calculate the feature score of each candidate region, use a voting algorithm to select the candidate region that is most similar to the inferior vena cava, and take the most similar candidate region as the region where the inferior vena cava is located.

[0017] In one optional implementation, the feature score of the candidate region is a weighted sum of the relative position score of the candidate region with the contour of the inferior vena cava at the previous time, the average gray value score of the candidate region, the width score of the candidate region, and the depth score of the candidate region.

[0018] In one optional implementation, the step of extracting the inferior vena cava wall information based on the location of the inferior vena cava and in conjunction with a simplified active contour model includes:

[0019] Based on the location of the inferior vena cava, an initial contour curve of the inferior vena cava is constructed, which is formed by a combination of multiple control points;

[0020] An energy function is constructed based on the initial contour curve of the inferior vena cava;

[0021] The energy function is iteratively updated based on the gradient descent algorithm, and the final contour curve of the inferior vena cava is obtained after the iterative update condition is met.

[0022] The wall information of the inferior vena cava is extracted based on the final contour curve of the inferior vena cava.

[0023] In one optional implementation, the step of iteratively updating the energy function based on the gradient descent algorithm, and obtaining the final contour curve of the inferior vena cava after satisfying the iterative update conditions, includes:

[0024] Based on the current contour curve, ultrasound image data, and preset step size, and combined with Euler's equation and gradient descent algorithm, the position of the control point after iteration is calculated;

[0025] Calculate the iterative energy function based on the control point positions after iteration, and calculate the difference between the current iteration result and the previous iteration result of the energy function;

[0026] Based on the difference between the current iteration result and the previous iteration result of the energy function, it is determined whether to continue iterating and updating the contour curve or terminate the iteration update. When the iteration is terminated, the final contour curve is output.

[0027] In one optional implementation, the inferior vena cava wall information includes upper wall information and lower wall information; the step of calculating the parameters of the inferior vena cava during a respiratory cycle based on the inferior vena cava wall information includes:

[0028] Based on the upper tube wall information and the lower tube wall information, the distance between the upper tube wall and the lower tube wall in each column of the ultrasound image data is calculated to obtain the lumen diameter of all columns in one respiratory cycle.

[0029] Based on the lumen diameter of all columns in the respiratory cycle, parameters of the inferior vena cava are calculated, including at least one of the following: maximum diameter, minimum diameter, collapse index, dilation index, and respiratory variability.

[0030] In one optional implementation, the formula for calculating the collapse index is:

[0031] CI = (D max -D min ) / D max

[0032] The expansion index is calculated using the following formula:

[0033] DI = (D max -D min ) / D min

[0034] The formula for calculating the respiratory variability rate is:

[0035] IVCV=(D max -D min ) / [(D max +D min ) / 2]

[0036] Where CI is the collapse index of the inferior vena cava; DI is the dilation index of the inferior vena cava; IVCV is the respiratory variability of the inferior vena cava; D max D is the maximum diameter of the inferior vena cava; min This is the minimum diameter of the inferior vena cava.

[0037] Secondly, the present invention also provides an ultrasound measuring device for the inferior vena cava, comprising:

[0038] The acquisition module is used to acquire ultrasound image data of the inferior vena cava at the current moment;

[0039] The positioning module is used to locate the region of the inferior vena cava based on the features of the inferior vena cava in the ultrasound image data and by adopting a voting algorithm.

[0040] The contour extraction module is used to extract the wall information of the inferior vena cava based on the location of the inferior vena cava and in combination with a simplified active contour model.

[0041] The calculation module is used to calculate the parameters of the inferior vena cava during a respiratory cycle based on the wall information of the inferior vena cava.

[0042] Thirdly, the present invention also provides an electronic device, comprising: a memory, a processor, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other through the communication bus;

[0043] The memory is used to store at least one executable instruction that causes the processor to perform the above-described ultrasound measurement method for the inferior vena cava.

[0044] Fourthly, the present invention also provides a computer-readable storage medium storing at least one executable instruction that, when executed on an electronic device / ultrasound measuring device for the inferior vena cava, causes the electronic device / ultrasound measuring device for the inferior vena cava to perform the aforementioned ultrasound measuring method for the inferior vena cava.

[0045] The above description is merely an overview of the technical solutions of the embodiments of the present invention. In order to better understand the technical means of the embodiments of the present invention and to implement them in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the embodiments of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0046] 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.

[0047] Figure 1 This is a flowchart illustrating an ultrasound measurement method for the inferior vena cava provided in an embodiment of the present invention.

[0048] Figure 2 This is a flowchart illustrating an ultrasound measurement method for the inferior vena cava according to another embodiment of the present invention;

[0049] Figure 3 This is a schematic diagram of the average grayscale value of each row of pixels in the ultrasound image data provided in the embodiments of the present invention;

[0050] Figure 4 This is a schematic diagram of the mean gray level in the ultrasound image data provided in this embodiment of the invention after one-dimensional Gaussian smoothing;

[0051] Figure 5 This is a schematic diagram of calculating the Otsu threshold in ultrasound image data provided in an embodiment of the present invention;

[0052] Figure 6 This is a schematic diagram of calculating candidate regions in ultrasound image data provided in an embodiment of the present invention;

[0053] Figure 7 A flowchart illustrating an ultrasound measurement method for the inferior vena cava according to another embodiment of the present invention;

[0054] Figure 8 This is a schematic diagram of constructing the initial contour of the inferior vena cava wall in ultrasound image data provided in an embodiment of the present invention;

[0055] Figure 9 This is a schematic diagram of the final contour curve of the inferior vena cava in the ultrasound image data provided in the embodiments of the present invention;

[0056] Figure 10 A flowchart illustrating an ultrasound measurement method for the inferior vena cava according to another embodiment of the present invention;

[0057] Figure 11 This is a schematic diagram of the contour curve of the inferior vena cava after one respiratory cycle in the ultrasound image data provided in the embodiments of the present invention;

[0058] Figure 12 This is a schematic diagram of the structure of an ultrasound measuring device for the inferior vena cava provided in an embodiment of the present invention;

[0059] Figure 13 This is a schematic diagram of the structure of an embodiment of the electronic device provided in this invention. Detailed Implementation

[0060] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0061] The following describes a specific embodiment of an ultrasound measurement method for the inferior vena cava according to the present invention. Figure 1 This is a flowchart illustrating an ultrasound measurement method for the inferior vena cava according to an embodiment of the present invention. This specification provides the method operation steps as shown in the embodiments or flowcharts, but based on conventional or non-inventive labor, more or fewer operation steps may be included. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only execution order. In actual system or server products, the method can be executed sequentially according to the embodiments or drawings, or in parallel (e.g., in a parallel processor or multi-threaded processing environment). Specifically, as shown... Figure 1 As shown, the method may include the following steps:

[0062] Step S100: Obtain ultrasound image data of the inferior vena cava at the current moment.

[0063] In step S100, by selecting a convex array probe or a phased array probe, the probe is moved downwards along the contour of the liver between the right midclavicular line and the costal arch until the location where the inferior vena cava connects to the right atrium is found. Using the M mode of the ultrasound imaging device, the sampling line is placed at the measurement point and perpendicular to the long axis of the inferior vena cava, thereby performing an image scan of the inferior vena cava. After the automatic measurement of the inferior vena cava is activated, the ultrasound imaging device emits ultrasound waves and receives reflected waves, generating real-time ultrasound image data of the inferior vena cava based on the information of the reflected waves for subsequent analysis and processing.

[0064] Following step S100, preprocessing of the ultrasound image data is also included. This specifically includes image denoising, histogram equalization, image smoothing, and image sharpening to obtain higher-quality ultrasound image data, providing a good foundation for subsequent inferior vena cava analysis and processing based on ultrasound image data.

[0065] Step S200: Based on the characteristics of the inferior vena cava in the ultrasound image data, a voting algorithm is used to locate the region of the inferior vena cava.

[0066] In step S200, the inferior vena cava has unique characteristics in ultrasound images, such as a specific range of gray values, shape, texture, and width. A voting algorithm is used to traverse each depth region in the ultrasound image data and evaluate each depth region to determine its likelihood of belonging to the inferior vena cava. For each depth region that matches the characteristics of the inferior vena cava, a vote is taken, and each depth region can obtain a different score. By statistically analyzing all the scores, the depth region with the highest score is ultimately selected as the depth region where the inferior vena cava is located in the ultrasound image data.

[0067] Step S300: Based on the location of the inferior vena cava, and combined with the simplified active contour model, extract the wall information of the inferior vena cava.

[0068] In step S300, the active contour model can represent the contour of the inferior vena cava as a deformable curve by defining an energy function. The curve converges to the boundary of the inferior vena cava by minimizing the energy function. Simplifying and improving the original active contour model to suit the characteristics of the inferior vena cava reduces the number of parameters and computational complexity, making it more suitable for extracting information about the inferior vena cava wall. After determining the location of the inferior vena cava, this region is used as input, and the simplified active contour model is used to extract the contour within that region. The active contour model continuously adjusts the position and shape of the curve based on grayscale changes and edge information in the ultrasound image data, ultimately converging to the location of the inferior vena cava wall, thereby extracting the inferior vena cava wall information.

[0069] Step S400: Calculate the parameters of the inferior vena cava during one respiratory cycle based on the wall information of the inferior vena cava.

[0070] In step S400, it is necessary to continuously monitor and record ultrasound image data and corresponding vessel wall information of the inferior vena cava throughout a complete respiratory cycle. A respiratory cycle includes inspiration and expiration, and the morphology and size of the inferior vena cava undergo periodic changes during inspiration and expiration. Based on the inferior vena cava vessel wall information recorded within a respiratory cycle, various parameters of the inferior vena cava can be calculated, such as the collapse index, dilation index, diameter, and respiratory variability. For example, by comparing the vessel wall information of the inferior vena cava at the end of inspiration and expiration, and calculating according to the formulas for the collapse index and dilation index, the functional changes of the inferior vena cava during respiration can be reflected, thus providing important evidence for clinical assessment of the patient's blood volume status and right ventricular function.

[0071] The ultrasound measurement method for the inferior vena cava provided by this invention acquires ultrasound image data of the inferior vena cava at the current moment and, based on the characteristics of the inferior vena cava in the ultrasound image data, uses a voting algorithm to locate the region of the inferior vena cava, thereby achieving highly robust localization of the inferior vena cava and making the localization more accurate. After determining the location of the inferior vena cava, a simplified active contour model is used to extract the wall information of the inferior vena cava; this reduces the number of parameters and computational complexity of the active contour model, making it more suitable for extracting the wall information of the inferior vena cava, improving the extraction speed, and facilitating the real-time acquisition of the wall information of the inferior vena cava. Furthermore, based on the real-time acquired wall information of the inferior vena cava, the parameters of the inferior vena cava during a respiratory cycle can be calculated in real time, which can effectively improve the accuracy of the inferior vena cava parameter calculation and meet the real-time requirements of inferior vena cava measurement.

[0072] like Figures 2 to 6 As shown, in one embodiment, the feature score of the candidate region includes at least the relative position score of the candidate region and the inferior vena cava contour at the previous time step, the mean grayscale score of the candidate region, the width score of the candidate region, and the depth score of the candidate region. Further, step S200 includes the following steps:

[0073] Step S210: Calculate the average gray value of each row of pixels in the ultrasound image data.

[0074] In step S210, the ultrasound image data is a two-dimensional matrix composed of pixels, each pixel having a corresponding gray value to represent the brightness information of that point. By calculating the average gray value of each row of pixels, a gray value sequence representing the average brightness of each row of the image can be obtained. The gray value sequence can provide a preliminary understanding of the gray value variation trend of the ultrasound image data in the depth direction, providing basic data for subsequent analysis of the features of the ultrasound image data.

[0075] Step S220: Perform one-dimensional Gaussian smoothing on the grayscale mean.

[0076] In step S220, the characteristics of the Gaussian function are used to smooth the gray-level mean sequence. The Gaussian function has the characteristic of having a larger weight in the central region and gradually decreasing on both sides. By performing a convolution operation between the gray-level mean sequence and the Gaussian function, the gray-level mean of each point can be affected by its neighboring points, thereby reducing local fluctuations, highlighting the overall gray-level change trend, making the gray-level mean sequence smoother, and better reflecting the true characteristics of the ultrasound image data.

[0077] Step S230: Calculate the Otsu threshold of the ultrasound image data based on the Otsu method.

[0078] In step S230, the grayscale values ​​of the ultrasound image data are divided into two classes by calculating the grayscale histogram of the ultrasound image data, so that the inter-class variance between the two classes is maximized. The larger the inter-class variance, the more obvious the difference between the two classes. The Otsu threshold determined in this way can better distinguish the inferior vena cava from the background in the ultrasound image data.

[0079] Step S240: Based on the Otsu threshold and the grayscale mean of each row of pixels, calculate the valley under each Otsu threshold and use the valley as a candidate region.

[0080] In step S240, after obtaining the Otsu threshold, the Otsu threshold is compared with the average gray value of each row of pixels. Since the inferior vena cava typically appears as a relatively dark area in ultrasound images, its corresponding average gray value will be lower than the surrounding area, forming troughs in the average gray value sequence. By finding these troughs, some areas that may contain the inferior vena cava can be preliminarily identified, and these areas are used as candidate areas.

[0081] Furthermore, the calculation method for the candidate areas is as follows:

[0082] First, initialize the number of rows in the ultrasound image data: i = 1; p = N; where D is the number of rows in the ultrasound image data (index: 0, 1, 2, ..., N); i is the current row i = 1, 2, ..., N-2; p is the upper edge of the candidate region.

[0083] When the current row is i, calculate the difference between the grayscale value of the (i-1)th and (i+1)th rows and the Otsu threshold, respectively. The calculation formula is as follows:

[0084] d i-1 =G(i-1)-Th

[0085] d i+1 =G(i+1)-Th;

[0086] Where, d i-1 d is the difference between the grayscale value of the (i-1)th row and the Otsu threshold. i+1 G(i-1) is the difference between the gray value of the (i+1)th row and the Otsu threshold; G(i+1) is the average gray value of the (i-1)th row; G(i+1) is the average gray value of the (i+1)th row; Th is the Otsu threshold.

[0087] When d i-1 >0&&d i+1 When p = 1, it indicates that the gray value from row (i-1) to row (i+1) has changed from being higher than the Otsu threshold to being lower than the Otsu threshold. This may be the starting point of a trough. At this time, the upper edge p of the candidate area is set to 1, indicating the start of a new candidate area.

[0088] When d i-1<0&&d i+1 When it is >0, if (p < i), save the alternative region (p, i) and p = N; this indicates that there is a change in the grayscale value from below the Otsu threshold to above the Otsu threshold from the (i - 1)-th row to the (i + 1)-th row, which may be the end position of a wave valley. And when the current row i is greater than the upper edge p of the recorded alternative region (p < i), it means that a complete wave valley region has been found. Save this wave valley region as the alternative region, then reset p to N and prepare to find the next alternative region.

[0089] Finally, perform a loop termination judgment: if (i < N - 1): i = i + 1; else: end the loop and the calculation ends. By judging whether the current row i is less than the total number of rows minus 1, that is, (i < N - 1), if so, increment the value of i by 1 and continue to process the next row; if i is equal to or greater than N - 1, it means that all rows have been processed, the loop ends, and the entire calculation process of the alternative region also ends.

[0090] Through the above steps, based on the grayscale mean value and the Otsu threshold of each row of the ultrasonic image, the alternative regions that may contain the inferior vena cava can be gradually determined, providing a basis for further screening and determining the accurate position of the inferior vena cava in the follow-up.

[0091] Step S250: Calculate the feature scores of each alternative region, adopt a voting algorithm to select the alternative region most similar to the inferior vena cava, and use the most similar alternative region as the region where the inferior vena cava is located.

[0092] In step S250, after obtaining multiple alternative regions, it is necessary to further evaluate the similarity between the alternative regions and the inferior vena cava. By calculating the features of each alternative region, the region most similar to the inferior vena cava is selected through voting. Taking the feature calculation of three alternative regions as an example, calculate the relative position score of each alternative region with the contour of the inferior vena cava at the previous moment, denoted as S0, and the scores are: 1, 2, 3; calculate the grayscale mean value score of each alternative region, denoted as S1, and the scores are: 1, 2, 3; calculate the width score of each alternative region, denoted as S2, and the scores are: 1, 3, 2; calculate the depth score of each alternative region, denoted as S3, and the scores are: 1, 2, 3.

[0093] S0 represents the ranking result of the difference between the center depth of the candidate region and the average depth difference between the centers of the upper and lower walls of the inferior vena cava at the previous moment. The closer the candidate region is to the location of the inferior vena cava at the previous moment, the higher the score. First, the inferior vena cava wall has been extracted from the data before the current input data. A fixed length of data is taken from the current input data, and then the average value of the centers of the upper and lower walls of the inferior vena cava is calculated, which is the depth of the inferior vena cava at the previous moment. Then, after the current input data, three candidate regions are calculated, and the average value of the upper and lower edges of the candidate regions is their respective depths. Finally, the absolute value of the difference between the depth of each candidate region and the depth of the inferior vena cava at the previous moment is taken, and the ranking result after sorting is the score. The smaller the difference, the higher the score. S1 is the gray value score of the candidate region, that is, the lower the average ultrasound echo in the candidate region, the higher the score. S2 is the width score of the candidate region. Within the width range of the inferior vena cava (determined according to the actual width of the human inferior vena cava), the wider the candidate region, the higher the score. S3 is the depth score of the candidate regions. The deeper the depth (i.e., the depth of each candidate region), the higher the score.

[0094] The total score for each candidate region is calculated based on S0, S1, S2, and S3, using the following formula:

[0095] S = 2 × S0 + 2 × S1 + S2 + S3

[0096] The above formula can be used to determine the three candidate regions. The total scores of each candidate region are 6, 13, and 17 respectively. Therefore, candidate region 3 has the highest score and is most similar to the features of the inferior vena cava. Candidate region 3 is selected as the region where the inferior vena cava is located.

[0097] like Figures 7 to 9 As shown, in one embodiment, step S300 includes the following steps:

[0098] Step S310: Based on the location of the inferior vena cava, construct the initial contour curve of the inferior vena cava. The initial contour curve is formed by combining multiple control points.

[0099] In step S310, after determining the location of the inferior vena cava in the ultrasound image, a general range is provided for constructing the initial contour curve. Multiple control points are then combined to form the initial contour curve; specifically, multiple control points can be connected using a specific interpolation or fitting algorithm to form a curve that approximately represents the contour of the inferior vena cava.

[0100] Step S320: Construct an energy function based on the initial contour curve of the inferior vena cava.

[0101] In step S320, the energy function expression is constructed as follows:

[0102] E = E int +Eext

[0103] Where E is the total energy of the upper or lower pipe wall profile model; E int Internal energy is used to ensure the smoothness and continuity of ultrasound images; E ext External energy is used to ensure that the contour model approximates the real contour.

[0104] Since the internal energy is only related to the contour model itself and is independent of the ultrasound image data, it consists of the first and second derivatives of the contour (the contour itself), as shown in the following equation:

[0105]

[0106] Where α and β are the weights of the first derivative energy and the second derivative energy, respectively, and are used to control the continuity and smoothness of the contour line; (or represented by v(s)) is the profile model curve. For the curve The first derivative on, For the curve The second derivative on; ∫ s ds is in The line integral on the surface.

[0107] Since external energy is only related to ultrasound images and is constructed from gradients in the ultrasound images, considering the practical significance of M-mode ultrasound and the characteristics of the inferior vena cava, this invention uses only the gradient in the depth direction (y-axis direction) when constructing the external force, as shown in the following formula:

[0108]

[0109] in, I(v(s)) represents the gradient value of the gray level of a point on the curve in the y direction; I(v(s)) represents the gray level of a point on the ultrasound image curve.

[0110] After discretization, the profile curve is a set of points consisting of a finite number of control points, as shown in the following equation:

[0111] v={v i =(x i ,y i |i = 0, 1, 2, ..., n-1}

[0112] Where v is the set of all control points on the contour line; v i Let be the i-th control point on the contour curve; n is the number of control points; (x i ,y i ) represents the coordinates of the i-th control point.

[0113] The formulas for calculating internal and external energy change accordingly:

[0114]

[0115] Among them, (x i-1 ,y i-1 ), (x i+1 ,y i+1 ) are the coordinates of the (i-1)th and (i+1)th control points, respectively; I(x) i ,y i ) represents the coordinates (x, y) on the ultrasound image. i ,y i The corresponding grayscale value.

[0116] Step S330: Iteratively update the energy function based on the gradient descent algorithm, and obtain the final contour curve of the inferior vena cava after satisfying the iterative update conditions.

[0117] like Figure 10 As shown, step S330 specifically includes the following steps:

[0118] Step S331: Based on the current contour curve, ultrasound image data, and preset step size, and combined with the Euler equation and gradient descent algorithm, calculate the control point position after iteration.

[0119] In step S331, the current contour curve records the current estimation of the inferior vena cava contour. The preset step size is a pre-set parameter used to control the distance the control point moves in each iteration. The Euler equation describes the deformation and motion of the curve under the influence of energy, and can calculate the trend of the curve in the next step based on the current state of the contour curve and the characteristics of the energy function. The gradient descent algorithm adjusts the position of the control point according to the gradient direction of the energy function. The energy function reflects the degree of matching between the contour curve and the actual features of the inferior vena cava in the ultrasound image. The gradient descent algorithm moves the control point along the direction of decreasing energy function, making the contour curve gradually approach the real inferior vena cava contour. By combining the Euler equation and the gradient descent algorithm, the position of the control point after iteration can be obtained; the contour curve after iteration is closer to the real contour of the inferior vena cava than the contour curve at the previous moment.

[0120] Furthermore, the formula for calculating the position of the control points after the iteration is as follows:

[0121] The formula for calculating the upper pipe wall is:

[0122] y t =(A+γI) -1 (y t-1 -f y (x t-1 ,x t-1 ))

[0123] x t=x t-1

[0124] Among them, (x t ,y t Let be the set of x-coordinates of all control points after the t-th iteration, i.e.

[0125] The formula for calculating the lower pipe wall is:

[0126] y t =(A+γI) -1 (y t-1 +f y (x t-1 ,y t-1 ))

[0127] x t =x t-1

[0128] Where, matrix i is the identity matrix of the same order as matrix A; γ is the set iteration step size; (x t-1 ,y t-1 f is the coordinate matrix of the contour before iteration, i.e., the set of control points; y (x t-1 ,y t-1 ) represents the longitudinal gradient of all control points; A is the coefficient matrix for solving the local optimum using the Euler equations, which is only related to the internal force weights α and β. The pixel values ​​of each matrix are as follows:

[0129]

[0130] Step S332: Calculate the energy function after iteration based on the control point positions after iteration, and calculate the difference between the current iteration result and the previous iteration result of the energy function.

[0131] Step S333: Based on the difference between the current iteration result and the previous iteration result of the energy function, determine whether to continue iterating and updating the contour curve or terminate the iteration update. When the iteration is terminated, output the final contour result.

[0132] In step S333, if the difference between the current iteration result and the previous iteration result is greater than a preset threshold, it is considered that the contour curve of the continued iteration is closer to the true contour of the inferior vena cava than the contour curve at the previous moment, so the control points are updated iteratively.

[0133] When the difference between the current iteration result and the previous iteration result of the energy function is less than the preset threshold, it indicates that the value of the energy function has become stable. Further iterations will have very little effect on the value of the energy function. At this point, it can be considered that the contour curve has converged to a relatively accurate position. Therefore, the iteration update is stopped, and the current contour curve is output as the final contour curve of the inferior vena cava.

[0134] Furthermore, a maximum number of iterations can be preset. If the number of iterations of the energy function reaches this preset value, the iteration update will stop even if the change in the energy function value has not yet fallen below a preset threshold. This is to avoid excessive computation time due to non-convergence, ensuring that the algorithm terminates within a certain time and outputs the currently obtained contour curve as the result.

[0135] Step S340: Determine the wall information of the inferior vena cava based on the final contour curve of the inferior vena cava.

[0136] In step S340, as the energy function continuously guides the curve towards a direction that better matches the characteristics of the inferior vena cava during the iteration process, the final contour curve obtained after iterative updates using the gradient descent algorithm is closer to the true contour of the inferior vena cava than the initial contour curve. By analyzing the position and shape of the final contour curve, information such as the diameter of the inferior vena cava can be obtained.

[0137] like Figure 11 As shown, in one embodiment, the inferior vena cava wall information includes upper wall information and lower wall information; step S400 includes:

[0138] Based on the information of the upper and lower tube walls, the distance between the upper and lower tube walls in each column of the ultrasound image data is calculated to obtain the lumen diameter of all columns in one respiratory cycle.

[0139] Based on the lumen diameter of all columns in the respiratory cycle, calculate the parameters of the inferior vena cava, including at least one of the following: maximum diameter, minimum diameter, collapse index, dilation index, and respiratory variability.

[0140] In this embodiment, based on the upper and lower wall information of the inferior vena cava in one respiratory cycle, the distance between the upper and lower walls of each column can be calculated. For example, in the 10th column, the coordinates of the upper wall are (10, 100) and the coordinates of the lower wall are (10, 140), so the lumen diameter of the inferior vena cava in the 10th column is 40 pixels. Then, according to this calculation method, the lumen diameter of all columns in one respiratory cycle is calculated. Among all the lumen diameters in all columns, the maximum value is the maximum diameter, and the minimum value is the minimum diameter. When calculating the maximum and minimum diameters, the lumen diameter needs to be multiplied by the physical distance of each pixel, for example, 40 × 0.2 mm = 8 mm, to determine the diameter size.

[0141] Further calculations of the inferior vena cava's collapse index, dilation index, and respiratory variability based on the maximum and minimum diameters were performed to determine the parameters of the inferior vena cava.

[0142] Furthermore, the formula for calculating the collapse index is:

[0143] CI = (D max -D min ) / D max

[0144] The expansion index is calculated using the following formula:

[0145] DI = (D max -D min ) / D min

[0146] The formula for calculating respiratory variability is:

[0147] IVCV=(D max -D min ) / [(D max +D min ) / 2]

[0148] Where CI is the collapse index of the inferior vena cava; DI is the dilation index of the inferior vena cava; IVCV is the respiratory variability of the inferior vena cava; D max D is the maximum diameter of the inferior vena cava; min This is the minimum diameter of the inferior vena cava.

[0149] Secondly, such as Figure 12 As shown, the present invention also provides an ultrasound measuring device for the inferior vena cava, comprising:

[0150] The acquisition module 100 is used to acquire ultrasound image data of the inferior vena cava at the current moment;

[0151] The positioning module 200 is used to locate the region of the inferior vena cava based on the characteristics of the inferior vena cava in ultrasound image data and by adopting a voting algorithm.

[0152] The contour extraction module 300 is used to extract the wall information of the inferior vena cava based on the location of the inferior vena cava and combined with a simplified active contour model.

[0153] The calculation module 400 is used to calculate the parameters of the inferior vena cava during a respiratory cycle based on the wall information of the inferior vena cava.

[0154] In one embodiment, the positioning module 200 includes:

[0155] The first calculation unit is used to calculate the average gray value of each row of pixels in the ultrasound image data;

[0156] The smoothing unit is used to perform one-dimensional Gaussian smoothing on the grayscale mean.

[0157] The second calculation unit is used to calculate the Otsu threshold of ultrasound image data based on the Otsu method.

[0158] The third calculation unit is used to calculate the valley under each Otsu threshold based on the Otsu threshold and the gray value of each row of pixels, and to use the valley as a candidate region.

[0159] The fourth calculation unit is used to calculate the feature score of each candidate region. A voting algorithm is used to select the candidate region that is most similar to the inferior vena cava, and the most similar candidate region is taken as the region where the inferior vena cava is located. The feature score of the candidate region is the weighted sum of the relative position score of the candidate region and the contour of the inferior vena cava at the previous time, the gray average score of the candidate region, the width score of the candidate region, and the depth score of the candidate region.

[0160] In one embodiment, the contour extraction module 300 includes:

[0161] The first building unit is used to construct the initial contour curve of the inferior vena cava based on the region where the inferior vena cava is located. The initial contour curve is formed by combining multiple control points.

[0162] The second building unit is used to construct the energy function based on the initial contour curve of the inferior vena cava;

[0163] The iterative unit is used to iteratively update the energy function based on the gradient descent algorithm, and obtain the final contour curve of the inferior vena cava after the iterative update condition is met;

[0164] The contour extraction unit is used to extract the wall information of the inferior vena cava based on the final contour curve of the inferior vena cava.

[0165] In one embodiment, the iteration unit includes:

[0166] The first calculation subunit is used to calculate the position of the control point after iteration based on the current contour curve, ultrasound image data and preset step size, combined with Euler equation and gradient descent algorithm.

[0167] The comparison sub-unit is used to calculate the energy function after iteration based on the control point positions after iteration, and to calculate the difference between the current iteration result and the previous iteration result of the energy function;

[0168] The updated sub-unit is used to determine whether to continue iterating and updating the contour curve or terminate the iteration based on the difference between the current iteration result and the previous iteration result of the energy function. When the iteration is terminated, the final contour curve is output.

[0169] In one embodiment, the computing module 400 includes:

[0170] The fifth calculation unit is used to calculate the distance between the upper and lower walls of each column in the ultrasound image data based on the upper and lower wall information, so as to obtain the lumen diameter of all columns in one respiratory cycle.

[0171] The sixth calculation unit is used to calculate the parameters of the inferior vena cava based on the luminal diameter of all columns in the respiratory cycle. These parameters include at least one of the following: maximum diameter, minimum diameter, collapse index, dilation index, and respiratory variability. The formula for calculating the collapse index is:

[0172] CI = (D max -D min ) / D max

[0173] The expansion index is calculated using the following formula:

[0174] DI = (D max -D min ) / D min

[0175] The formula for calculating respiratory variability is:

[0176] IVCV=(D max -D min ) / [(D max +D min ) / 2]

[0177] Where CI is the collapse index of the inferior vena cava; DI is the dilation index of the inferior vena cava; IVCV is the respiratory variability of the inferior vena cava; D max D is the maximum diameter of the inferior vena cava; min This is the minimum diameter of the inferior vena cava.

[0178] Thirdly, the present invention also provides an electronic device, comprising: a memory, a processor, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other through the communication bus; the memory is used to store at least one executable instruction, which causes the processor to perform the aforementioned ultrasound measurement method of the inferior vena cava.

[0179] like Figure 13 As shown, the electronic device may include: a processor 502, a communications interface 504, a memory 506, and a communications bus 508.

[0180] The processor 502, communication interface 504, and memory 506 communicate with each other via communication bus 508. Communication interface 504 is used to communicate with other network elements such as clients or other servers. Processor 502 executes program 510, specifically performing the relevant steps described in the embodiment of the ultrasound measurement method for the inferior vena cava.

[0181] Specifically, program 510 may include program code, which includes computer-executable instructions.

[0182] Processor 502 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The electronic device may include one or more processors of the same type, such as one or more CPUs; or it may include processors of different types, such as one or more CPUs and one or more ASICs.

[0183] Memory 506 is used to store program 510. Memory 506 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0184] Specifically, program 510 can be called by processor 502 to cause the electronic device to perform the relevant steps in the above-described embodiment of the ultrasound measurement method for the inferior vena cava.

[0185] Those skilled in the art will understand that Figure 13 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned device. For example, electronic devices may also include components that are more... Figure 13 The more or fewer components shown, or having the same Figure 13 The different configurations shown.

[0186] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing at least one executable instruction. When the executable instruction is executed on an electronic device / ultrasound measuring device for the inferior vena cava, it causes the electronic device / ultrasound measuring device for the inferior vena cava to perform the aforementioned ultrasound measuring method for the inferior vena cava.

[0187] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system, or other device. Furthermore, the embodiments of this invention are not directed to any particular programming language.

[0188] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. Similarly, for the sake of brevity and to aid in understanding one or more aspects of the invention, in the description of exemplary embodiments of the invention above, various features of the embodiments are sometimes grouped together in a single embodiment, figure, or description thereof. The claims, which follow the detailed description, are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of the invention.

[0189] Those skilled in the art will understand that the modules in the device of the embodiment can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiment can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components, except that at least some of such features and / or processes or units are mutually exclusive.

[0190] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the order of execution.

Claims

1. A method for ultrasound measurement of the inferior vena cava, characterized in that, The method includes: Acquire ultrasound image data of the inferior vena cava at the current moment; Based on the features of the inferior vena cava in the ultrasound image data, a voting algorithm is used to locate the region of the inferior vena cava; Based on the location of the inferior vena cava, and combined with a simplified active contour model, the wall information of the inferior vena cava is extracted. Based on the wall information of the inferior vena cava, the parameters of the inferior vena cava during one respiratory cycle are calculated.

2. The ultrasound measurement method for the inferior vena cava according to claim 1, characterized in that, The step of locating the inferior vena cava region using a voting algorithm based on the features of the inferior vena cava in the ultrasound image data includes: Calculate the average grayscale value of each row of pixels in the ultrasound image data; Perform one-dimensional Gaussian smoothing on the grayscale mean; The Otsu threshold of the ultrasound image data was calculated based on the Otsu method. Based on the Otsu threshold and the average gray value of each row of pixels, calculate the valley under each Otsu threshold and use the valley as a candidate region; Calculate the feature score of each candidate region, use a voting algorithm to select the candidate region that is most similar to the inferior vena cava, and take the most similar candidate region as the region where the inferior vena cava is located.

3. The ultrasound measurement method for the inferior vena cava according to claim 2, characterized in that, The feature score of the candidate region is a weighted sum of the relative position score of the candidate region with the contour of the inferior vena cava at the previous time step, the mean gray value score of the candidate region, the width score of the candidate region, and the depth score of the candidate region.

4. The ultrasound measurement method for the inferior vena cava according to claim 1, characterized in that, Based on the location of the inferior vena cava and combined with a simplified active contour model, the wall information of the inferior vena cava is extracted, including: Based on the location of the inferior vena cava, an initial contour curve of the inferior vena cava is constructed, which is formed by a combination of multiple control points; An energy function is constructed based on the initial contour curve of the inferior vena cava; The energy function is iteratively updated based on the gradient descent algorithm, and the final contour curve of the inferior vena cava is obtained after the iterative update condition is met. The wall information of the inferior vena cava is extracted based on the final contour curve of the inferior vena cava.

5. The ultrasound measurement method for the inferior vena cava according to claim 4, characterized in that, The step of iteratively updating the energy function based on the gradient descent algorithm, and obtaining the final contour curve of the inferior vena cava after satisfying the iterative update conditions, includes: Based on the current contour curve, ultrasound image data, and preset step size, and combined with Euler's equation and gradient descent algorithm, the position of the control point after iteration is calculated; Calculate the iterative energy function based on the control point positions after iteration, and calculate the difference between the current iteration result and the previous iteration result of the energy function; Based on the difference between the current iteration result and the previous iteration result of the energy function, it is determined whether to continue iterating and updating the contour curve or terminate the iteration update. When the iteration is terminated, the final contour curve is output.

6. The ultrasound measurement method for the inferior vena cava according to claim 1, characterized in that, The inferior vena cava wall information includes upper wall information and lower wall information; the calculation of the inferior vena cava parameters during a respiratory cycle based on the inferior vena cava wall information includes: Based on the upper tube wall information and the lower tube wall information, the distance between the upper tube wall and the lower tube wall in each column of the ultrasound image data is calculated to obtain the lumen diameter of all columns in one respiratory cycle. Based on the lumen diameter of all columns in the respiratory cycle, parameters of the inferior vena cava are calculated, including at least one of the following: maximum diameter, minimum diameter, collapse index, dilation index, and respiratory variability.

7. The ultrasound measurement method for the inferior vena cava according to claim 6, characterized in that, The formula for calculating the collapse index is as follows: CI=(D max -D min ) / D max The expansion index is calculated using the following formula: DI=(D max -D min ) / D min The formula for calculating the respiratory variability rate is: IVCV=(D max -D min ) / [(D max +D min ) / 2] Where CI is the collapse index of the inferior vena cava; DI is the dilation index of the inferior vena cava; IVCV is the respiratory variability of the inferior vena cava; D max D is the maximum diameter of the inferior vena cava; min This is the minimum diameter of the inferior vena cava.

8. An ultrasound measuring device for the inferior vena cava, characterized in that, include: The acquisition module is used to acquire ultrasound image data of the inferior vena cava at the current moment; The positioning module is used to locate the region of the inferior vena cava based on the features of the inferior vena cava in the ultrasound image data and by adopting a voting algorithm. The contour extraction module is used to extract the wall information of the inferior vena cava based on the location of the inferior vena cava and in combination with a simplified active contour model. The calculation module is used to calculate the parameters of the inferior vena cava during a respiratory cycle based on the wall information of the inferior vena cava.

9. An electronic device, characterized in that, include: The system includes a memory, a processor, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus. The memory is used to store at least one executable instruction that causes the processor to perform the ultrasound measurement method of the inferior vena cava as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The storage medium stores at least one executable instruction, which, when executed on the electronic device / ultrasound measuring device for the inferior vena cava, causes the electronic device / ultrasound measuring device for the inferior vena cava to perform the ultrasound measuring method for the inferior vena cava as described in any one of claims 1-7.

Images