A method of ultrasonic imaging and related apparatus

Abstract

The application relates to a method and related device for ultrasonic imaging, the method comprising: acquiring ultrasonic volume data of a subject; determining position information of a target anatomical structure from the ultrasonic volume data; determining an ultrasonic image of the target anatomical structure from the ultrasonic volume data according to the position information of the target anatomical structure; and displaying the ultrasonic image.

Description

Technical Field

[0001] This application relates to the field of medical imaging, and in particular to a method and related equipment for ultrasound imaging. Background Technology

[0002] With the development of science and technology, more and more doctors are using ultrasound instruments to observe the internal structure of the human body. When using ultrasound instruments for testing, doctors place the ultrasound probe on the skin surface corresponding to the part of the human body to obtain an ultrasound image of that part.

[0003] In recent years, ultrasound examinations have been widely used in clinical practice, as ultrasound instruments can obtain complete image information in a single scan. However, the resulting image area is relatively large, requiring the ultrasound instrument to receive multiple position adjustment commands from the operator to achieve the correct image display position. This results in long operating times for the ultrasound instrument and a waste of its resources. Summary of the Invention

[0004] Therefore, it is necessary to provide an ultrasound imaging method and related equipment to address the above-mentioned problems.

[0005] A method for ultrasound imaging, the method comprising:

[0006] Acquire ultrasound data of the subject;

[0007] The location information of the target anatomical structure is determined from the ultrasound data;

[0008] The ultrasound image of the target anatomical structure is determined from the ultrasound body data based on the location information of the target anatomical structure.

[0009] The ultrasound image is displayed.

[0010] A method for optimizing ultrasound body data, the method comprising:

[0011] Acquire ultrasound data of the subject;

[0012] The location information of the target anatomical structure is determined from the ultrasound data;

[0013] The ultrasound data is optimized based on the location information of the target anatomical structure.

[0014] A method for optimizing ultrasound images, the method comprising:

[0015] Acquire ultrasound data of the subject;

[0016] The location information of the target anatomical structure is determined from the ultrasound data;

[0017] The ultrasound image of the target anatomical structure is determined from the ultrasound body data based on the location information of the target anatomical structure.

[0018] Optimize the ultrasound image.

[0019] An ultrasound imaging system, the ultrasound imaging system comprising:

[0020] An ultrasonic probe is used to emit ultrasonic waves to the object under test and receive ultrasonic echoes to obtain ultrasonic signals obtained by performing ultrasonic testing on the object under test.

[0021] A memory that stores computer-readable instructions;

[0022] A processor, when the computer-readable instructions are executed by the processor, causes the processor to perform the following steps: processing the ultrasound signal to obtain ultrasound body data corresponding to the object under test; determining the location information of the target anatomical structure from the ultrasound body data; and determining the ultrasound image of the target anatomical structure from the ultrasound body data based on the location information of the target anatomical structure.

[0023] A display for showing the ultrasound images.

[0024] An ultrasound imaging system, the ultrasound imaging system comprising:

[0025] An ultrasonic probe is used to emit ultrasonic waves to the object under test and receive ultrasonic echoes to obtain ultrasonic signals obtained by performing ultrasonic testing on the object under test.

[0026] A memory that stores computer-readable instructions;

[0027] When the computer-readable instructions are executed by the processor, the processor performs the following steps: processing the ultrasound signal to obtain ultrasound body data corresponding to the object under test; determining the location information of the target anatomical structure from the ultrasound body data; and optimizing the ultrasound body data based on the location information of the target anatomical structure.

[0028] An ultrasound imaging system, the ultrasound imaging system comprising:

[0029] An ultrasonic probe is used to emit ultrasonic waves to the object under test and receive ultrasonic echoes to obtain ultrasonic signals obtained by performing ultrasonic testing on the object under test.

[0030] A memory that stores computer-readable instructions;

[0031] When the computer-readable instructions are executed by the processor, the processor performs the following steps: processing the ultrasound signal to obtain ultrasound body data corresponding to the test object; acquiring the ultrasound body data of the test object; determining the location information of the target anatomical structure from the ultrasound body data; determining the ultrasound image of the target anatomical structure from the ultrasound body data based on the location information of the target anatomical structure; and optimizing the ultrasound image.

[0032] Details of one or more embodiments of this application are set forth in the following drawings and description. Other features, objects, and advantages of this application will become apparent from the specification, drawings, and claims. Attached Figure Description

[0033] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0034] Figure 1 This is a structural block diagram of an ultrasound imaging system provided in one embodiment;

[0035] Figure 2 Here is a flowchart of an ultrasound imaging method in one embodiment;

[0036] Figure 3 This is a schematic diagram of three-dimensional volume data in one embodiment;

[0037] Figure 4 This is a flowchart illustrating how an ultrasound image of a target anatomical structure is determined from ultrasound body data based on the location information of the target anatomical structure in one embodiment.

[0038] Figure 5 This is a flowchart illustrating how an ultrasound image of a target anatomical structure is determined from ultrasound body data based on the location information of the target anatomical structure in one embodiment.

[0039] Figure 6 This is a flowchart illustrating how an ultrasound image of a target anatomical structure is determined from ultrasound body data based on the location information of the target anatomical structure in one embodiment.

[0040] Figure 7 Here is a flowchart of an ultrasound imaging method in one embodiment;

[0041] Figure 8 This is a schematic diagram of a grayscale histogram in one embodiment;

[0042] Figure 9This is a flowchart of a method for optimizing ultrasound body data in one embodiment;

[0043] Figure 10 Here is a flowchart of a method for optimizing ultrasound images in one embodiment;

[0044] Figure 11 This is a block diagram of the internal structure of a computer device in one embodiment. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0046] It is understood that the terms "first," "second," etc., used in this application may be used herein to describe various elements, but unless otherwise stated, these elements are not limited by these terms. These terms are used only to distinguish one element from another. For example, without departing from the scope of this application, a first threshold may be referred to as a second threshold, and similarly, a second threshold may be referred to as a first threshold.

[0047] like Figure 1 This is a structural block diagram of the ultrasound imaging system 10. The ultrasound imaging system 10 may include an ultrasound probe 100, a transmit / receive selection switch 101, a transmit / receive sequence controller 102, a processor 103, and a display 104. The transmit / receive sequence controller 102 can excite the ultrasound probe 100 to emit ultrasound waves towards the object under test, and can also control the ultrasound probe 100 to receive ultrasound echoes returned from the object under test, thereby obtaining ultrasound echo signals / data. The processor 103 processes the ultrasound echo signals / data to obtain ultrasound body data of the object under test, and ultrasound images from which the target anatomical structures are determined. The ultrasound images obtained by the processor 103 can be stored in a memory 105, and these ultrasound images can be displayed on the display 104.

[0048] In this embodiment, the display 104 of the aforementioned ultrasound imaging system 10 can be a touch screen, a liquid crystal display, or an independent display device such as a liquid crystal display or a television set, which is separate from the ultrasound imaging system 10. It can also be a display screen on an electronic device such as a mobile phone or a tablet computer.

[0049] In this embodiment of the application, the memory 105 of the aforementioned ultrasound imaging system 10 can be a flash memory card, solid-state memory, hard disk, etc.

[0050] This application also provides a computer-readable storage medium that stores a plurality of program instructions. When the plurality of program instructions are invoked and executed by the processor 103, they can execute some or all of the steps or any combination of the steps in the various method embodiments of this application below.

[0051] In one embodiment, the computer-readable storage medium may be a memory 105, which may be a non-volatile storage medium such as a flash memory card, a solid-state memory, or a hard disk.

[0052] In this embodiment, the processor 103 of the aforementioned ultrasound imaging system 10 can be implemented by software, hardware, firmware, or a combination thereof. It can use circuits, one or more application-specific integrated circuits (ASICs), one or more general-purpose integrated circuits, one or more microprocessors, one or more programmable logic devices, or a combination of the aforementioned circuits or devices, or other suitable circuits or devices, so that the processor 103 can perform the corresponding steps in the following method embodiments.

[0053] like Figure 2 As shown, in one embodiment, a method for ultrasound imaging is proposed, which may specifically include the following steps:

[0054] Step S202: Obtain ultrasound data of the subject.

[0055] In this embodiment, the ultrasound volume data can be either three-dimensional or four-dimensional. Three-dimensional volume data is a set of data representing the pixel positions of an image in three-dimensional spatial coordinates, with each position corresponding to a pixel and its value. Four-dimensional volume data adds a time dimension to the three-dimensional volume data; that is, four-dimensional volume data is three-dimensional volume data that changes over time, dynamically reflecting the activity of the object being measured. Figure 3 The image shown is a schematic diagram of three-dimensional volume data. From Figure 3 As can be seen, this volumetric data can be composed of F image frames of size W×H, where W is the width of the image frame, H is the height of the image frame, and the specific value of F can be any integer greater than or equal to 2. Furthermore, from... Figure 3 As can be seen, Figure 3The width direction of the image frame is defined as the X direction, the height direction as the Y direction, and the direction in which multiple image frames are arranged as the Z direction. It is understood that the X, Y, and Z directions can also be defined in different ways. The object under test can be various tissues and organs of a human or animal. This can be set as needed; for example, the object under test can be one or more of the following: pelvic floor, endometrium, fetal heart, adult heart, liver, and fetal brain. The object under test can be three-dimensionally scanned by the ultrasound probe 100 in the ultrasound imaging system 10. Ultrasound waves are emitted to the object, and the ultrasound probe 100 receives the ultrasound echoes to obtain ultrasound echo signals. The processor 103 processes the ultrasound echo signals as described above to obtain the ultrasound body data of the object under test. The ultrasound body data can be obtained by sending ultrasound waves to the object under test in real time, or it can be pre-stored in the memory of the ultrasound imaging system.

[0056] Step S204: Determine the location information of the target anatomical structure from the ultrasound body data.

[0057] After obtaining the ultrasound body data, in this embodiment of the application, the processor 103 can automatically or by receiving instructions input by the user to detect the target anatomical structure in the test object from the ultrasound body data. The processor 103 determines the ultrasound image corresponding to the target anatomical structure based on the location information of the target anatomical structure, thereby providing the doctor with good image information and analysis data in real time.

[0058] In this embodiment, the target anatomical structure can be one or more, or two or more, and the specific value can be set as needed. The target anatomical structure whose location information needs to be determined is related to the type of the tested object and the image to be viewed. For example, in pelvic floor body data, anatomical structures such as the pubic symphysis, vaginal gas line, and anorectal angle are relatively obvious, and at least one of these anatomical structures can be found and identified as the target anatomical structure; similarly, in endometrial body data, the echo of the endometrium is significantly different from that of the surrounding tissues, making its characteristics relatively clear, and the endometrium can be segmented as the target anatomical structure; similarly, in fetal cranial body data, anatomical structures such as the cranial halo, sagittal plane, cerebellum, and cavum septum pellucidum are relatively obvious, and at least one of these anatomical structures can be found and identified as the target anatomical structure; similarly, in fetal heart body data, anatomical structures such as the aorta, four chambers of the heart, and gastric bubble are relatively obvious, and at least one of these anatomical structures can be found and identified as the target anatomical structure. The target anatomical structure whose location information needs to be determined for each tested object can be preset or obtained in real time based on user selection. For example, if the target anatomical structures to be obtained for the pelvic floor are pre-set as the cranial halo, sagittal plane, and cerebellum, after obtaining the ultrasound body data, the processor of the ultrasound imaging system can determine the location information of the target anatomical structures from the ultrasound body data.

[0059] In one embodiment, determining the location information of a target anatomical structure from ultrasound body data includes: acquiring identification information that identifies the target anatomical structure; and determining the location information of the target anatomical structure from the ultrasound body data based on the identification information.

[0060] In this embodiment, the identification information is used to identify the target anatomical structure from the ultrasound body data. For example, the ultrasound image corresponding to the ultrasound body data can be displayed, and user actions such as clicking or sliding on the ultrasound image using input tools like a keyboard or mouse can be received to identify the target anatomical structure. The location corresponding to the identification action is taken as the location of the target anatomical structure. Furthermore, the name of the target anatomical structure at that location can also be obtained. The name of the target anatomical structure can be obtained from user input.

[0061] In one embodiment, determining the location information of a target anatomical structure from ultrasound body data includes: acquiring structural feature information of the target anatomical structure; and determining the location information of the target anatomical structure from the ultrasound body data based on the structural feature information.

[0062] In this embodiment, the target anatomical structure has unique structural features. For example, the cavum pellucidum in the brain is crescent-shaped. The gastric bubble in the fetal heart is typically hypoechoic or anechoic ellipsoid. Therefore, structural feature information corresponding to each anatomical structure can be pre-set. When it is necessary to identify the target anatomical structure, the structural feature information of the target anatomical structure is obtained and matched in the ultrasound data. The location information of the matched anatomical structure is used as the location information of the target anatomical structure. The identification method can employ one or more of image segmentation or template matching methods. For example, the gastric bubble can be segmented using image segmentation. First, the ultrasound data is binarized and morphologically processed based on grayscale data to obtain multiple candidate regions. Then, the probability that each candidate region is the gastric bubble is determined based on features such as shape, and the region with the highest probability is selected as the gastric bubble region. Other image segmentation methods can also be used, such as level set methods, graph cut, snake model, random walk, and one or more deep learning image segmentation methods. Deep learning image segmentation methods can include, for example, one or more of FCN (Fully Convolutional Networks) or UNet (Unity Networking). For another example, template matching can be used to identify the cavum pellucidum in the brain. Grayscale data of the cavum pellucidum can be collected in advance to create a template. The grayscale data of each image region in the ultrasound body data is matched with the grayscale data of the template. Regions with high similarity are selected as the regions corresponding to the target anatomical structure. The ultrasound body data can be divided into multiple regions that match the template. The region division method for the ultrasound body data can be set as needed. Similarity is used to measure the similarity between the template and each image region in the ultrasound body data. The higher the similarity, the greater the probability that the image region is the target anatomical structure. Therefore, the region with the highest similarity can be selected as the region corresponding to the target anatomical structure. The similarity calculation method can be set as needed. For example, the similarity can be the sum of the absolute differences between the grayscale values ​​of pixels in the template and the image region. This can be expressed by the following formula:

[0063]

[0064] Where E is the similarity, I L I represents the grayscale value of the pixel in the image region corresponding to the ultrasound body data. R H represents the grayscale value of a pixel in the template. H is the number of pixels in the template, and I is the grayscale value of the pixel. L —I RThis refers to subtracting the grayscale value of the pixel at the same location in the image region from the template's. It is understood that other methods can be used to determine similarity, such as the Euclidean distance between the image regions corresponding to the template and the ultrasound body, the cosine similarity between the image regions corresponding to the template and the ultrasound body, etc. This application is not limited to how the above-mentioned similarity calculation method is defined; any calculation method based on measuring the similarity between the image regions corresponding to the template and the ultrasound body can be used in various embodiments of this application.

[0065] In one embodiment, a machine learning model can also be used to identify the location information of the target anatomical structure. The machine learning model can be a learned model trained using one or more of the following algorithms: Adaboost, Support Vector Machine (SVM), Neural Network, Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Fast RCNN, and SSD (Single Shot MultiBox Detector). During model training, supervised learning can be used to learn the feature extraction parameters in the machine learning network, enabling it to establish a mapping from ultrasound body data to the location information of the target anatomical structure. Positive and negative samples can be collected for model training. Using these samples, the model parameters can be trained to distinguish between positive and negative samples, resulting in an anatomical structure recognition model. Then, the ultrasound body data is input into the anatomical structure recognition model to obtain the probability that each image region corresponding to the ultrasound body data is a target anatomical sample. The region with the highest probability is selected as the region corresponding to the target anatomical structure. Here, a positive sample refers to a sample that is the target anatomical structure, and a negative sample refers to a sample that is not the target anatomical structure.

[0066] Step S206: Determine the ultrasound image of the target anatomical structure from the ultrasound body data based on the location information of the target anatomical structure.

[0067] In this embodiment, the ultrasound image of the target anatomical structure includes all or part of the target anatomical structure. The ultrasound image of the target anatomical structure can be one or both an ultrasound image of a cross-section corresponding to the target anatomical structure and an ultrasound image of a volume of interest corresponding to the target anatomical structure. The cross-section corresponding to the target anatomical structure is a cross-section that includes all or part of the target anatomical structure, and the volume of interest corresponding to the target anatomical structure surrounds all or part of the target anatomical structure. After obtaining the target anatomical structure, the processor 103 determines the image region including the target anatomical structure based on the location information of the target anatomical structure, and extracts the image corresponding to that region from the ultrasound volume data, thereby obtaining the ultrasound image.

[0068] In one embodiment, the processor 103 can select multiple feature points from the target anatomical structure, fit the cross-sectional equation corresponding to the cross-section based on the multiple feature points, and thus obtain the target cross-section. Determining a plane based on multiple feature points can be achieved using various methods, such as at least one of the weighted Hough transform, stochastic Hough transform, least squares estimation, and Radon transform. The feature points can be one or more arbitrarily selected from each target anatomical structure. The selected location can be set as needed; for example, the center point of each target anatomical structure can be used as the feature point.

[0069] For example, a section of the cerebellum in the brain includes anatomical structures such as the cerebellum, cavum septum pellucidum, and thalamus. Therefore, by selecting one location point from each of the cerebellum, cavum septum pellucidum, and thalamus, three location points can be obtained. These three location points are not collinear. Based on the principle that a unique plane can be obtained from three non-collinear points, a plane can be determined, and this plane can pass through each target anatomical structure.

[0070] Step S208: Display the ultrasound image.

[0071] In this embodiment of the application, after obtaining the ultrasound image, the ultrasound image is displayed on the display 104 in the ultrasound imaging system 10.

[0072] The aforementioned ultrasound imaging method, by determining the corresponding ultrasound image based on the location of the target anatomical structure, reduces the time required to acquire ultrasound images and saves ultrasound equipment resources. Furthermore, it provides doctors with more precisely located ultrasound images, allowing them to easily observe the ultrasound image of the subject, providing physicians with a wealth of important and crucial information and improving work efficiency.

[0073] In one embodiment, such as Figure 4 As shown, step S206, which involves determining the ultrasound image of the target anatomical structure from the ultrasound body data based on the location information of the target anatomical structure, includes:

[0074] Step S402: Determine the position information of the target section based on the position information of the target anatomical structure.

[0075] In this embodiment, the target section is a section that includes all or part of the target anatomical structure. After obtaining the target anatomical structure, the target section can be determined according to a pre-set method. For example, a traversal method can be used to obtain candidate sections that can pass through each target anatomical structure, and then the candidate section with the largest area including the target anatomical structure can be selected as the target section. Alternatively, during the traversal, if the area occupied by each target anatomical structure in the obtained candidate sections is greater than a preset threshold, then the candidate section is selected as the target section, and the traversal stops.

[0076] In one embodiment, determining the position information of the target section based on the position information of the target anatomical structure includes: determining the target section equation based on the position information of the target anatomical structure; and obtaining the position information of the target section based on the target section equation.

[0077] In this embodiment of the application, the plane equation in three-dimensional space can be expressed as aX + bY + cZ + d = 0 or Express it, where a, b, c, and d are the plane parameters that determine a plane, or These are planar parameters. After obtaining the location information of the target anatomical structure, one or more feature points can be selected from the target anatomical structure. The location information of the feature points is substituted into the planar equation to solve for the planar parameters, thereby obtaining the sectional function corresponding to the target section. The region corresponding to the sectional function is obtained from the ultrasound data to obtain the location information of the target section.

[0078] In one embodiment, the target section equation can be determined based on the positional information of the three sub-target anatomical structures using a three-point non-collinear method.

[0079] In this embodiment, if there are three target anatomical structures, a location point can be obtained from each of the three target anatomical structures, resulting in three non-collinear location points. Therefore, the target section equation can be determined based on the location information of the three target anatomical structures according to the non-collinearity of the three points. That is, the location information corresponding to each location point can be substituted into the section equation, and then the target section equation, i.e., the section function, can be obtained. The section function corresponding to this section function in the ultrasound body data is the target section. The method for obtaining the location points from the target anatomical structures can be set as needed; for example, it can be to obtain the center point of each target anatomical structure.

[0080] In one embodiment, if there are at least four target anatomical structures, the target section equation can be determined by fitting based on the positional information of the at least four target anatomical structures. The fitting method includes at least one of least squares estimation and Hough transform.

[0081] In this embodiment, the least squares method is a mathematical optimization technique. It finds the best function match for the data by minimizing the sum of squared errors. The least squares method can easily obtain unknown data, ensuring that the sum of squared errors between the obtained data and the actual data is less than a preset value. The principle of the Hough transform is to transform points on a specific graphic onto a set of parameter spaces. Based on the cumulative results of the points in the parameter space, a solution corresponding to a maximum value is found, and this solution corresponds to the parameters of the geometric shape to be found. Since there are four or more target anatomical structures, four or more feature points are obtained. Four or more non-collinear feature points can determine multiple cross-sections. Therefore, a fitting method can be used to determine the target cross-section equation based on the positional information of at least four target anatomical structures. When using least squares estimation for fitting, feature points can be selected from each target anatomical structure to obtain the function parameters corresponding to the cross-section. The steps of selecting feature points and obtaining function parameters are repeated until the sum of squared errors between the obtained data and the actual data is less than a preset value or the number of repetitions reaches a preset number. The final function parameters are then used as the parameters of the cross-section equation. When fitting data using the Hough transform, feature points can be selected from various target anatomical structures. The positional information of these feature points is used to calculate the function parameters corresponding to the cross-section. These function parameters are then used to update the Hough matrix. This process of selecting feature points, obtaining function parameters, and updating the Hough matrix is ​​repeated until a preset number of repetitions is reached. Finally, the function parameter corresponding to the maximum value in the Hough matrix is ​​calculated, and the final function value is obtained based on this parameter. The preset number of repetitions can be set as needed, for example, 10,000 times.

[0082] Step S404: Determine the cross-sectional image of the target anatomical structure from the ultrasound body data based on the position information of the target cross-section.

[0083] Step S406: The cross-sectional image is identified as the ultrasound image of the target anatomical structure.

[0084] In this embodiment of the application, after obtaining the location information of the target cross-section, the processor 103 obtains the gray value of the pixel corresponding to the location information in the ultrasound body data to obtain the cross-section image, and uses the cross-section image as the ultrasound image of the target anatomical structure.

[0085] In one embodiment, such as Figure 5 As shown, step S206, which involves determining the ultrasound image of the target anatomical structure from the ultrasound body data based on the location information of the target anatomical structure, may specifically include the following steps:

[0086] Step S502: Determine the position information of the target section based on the position information of the target anatomical structure.

[0087] In this embodiment, the determination of the target section's position information based on the target anatomical structure's position information can be referred to the description in step S402. This embodiment will not be repeated here.

[0088] Step S504: Set the size and location information of the volume of interest (VOI) from the ultrasound body data based on the location information of the target section. The VOI surrounds all or part of the target anatomical structure.

[0089] In this embodiment, the volume of interest (VOI) is the region of the stereoscopic image to be viewed. The size of the VOI refers to its dimensions. For example, the dimensions of the VOI in the length, width, and height directions can be set. The size and position of the VOI can be determined based on the location information of the target section, so that the VOI surrounds all or part of the target anatomical structure. For example, a volume threshold can be preset, and the proportion of the volume of the target anatomical structure surrounded by the VOI to the total volume of the target anatomical structure can be set to be greater than the preset volume threshold. Therefore, after obtaining the location information of the target section, the size and position of the volume of interest (VOI) in the ultrasound volume data are adjusted so that the proportion of the volume of the target anatomical structure surrounded by the VOI to the total volume of the target anatomical structure is greater than the preset volume threshold.

[0090] Step S506: Render the VOI to obtain a three-dimensional image of the target anatomical structure, and determine the three-dimensional image as the ultrasound image of the target anatomical structure.

[0091] In this embodiment of the application, after obtaining the VOI, the processor 103 renders the image based on the grayscale value of the pixel corresponding to the VOI to obtain a stereoscopic image, which serves as an ultrasound image of the target anatomical structure.

[0092] The following uses an actual test subject as an example to illustrate the method provided in this embodiment of the invention. In cerebellar section detection, the spatial position of the cerebellar section is calculated based on the positions of target anatomical structures such as the cranial halo, cerebellum, and cavum septum pellucidum, resulting in the corresponding cerebellar section. Based on this, the size and position of the VOI (Void of Image) are set so that the VOI encompasses at least one target anatomical structure, such as the cranial halo, cerebellum, or cavum septum pellucidum, thus obtaining a three-dimensional image of the cerebellar section, i.e., the image corresponding to the VOI. Similarly, in pelvic floor levator hiatus imaging, the positions of target structures such as the lower edge of the pubic symphysis and the anorectal angle are identified. Based on the positions of the lower edge of the pubic symphysis and the anorectal angle, they are automatically rotated to the same horizontal position, and the VOI is adjusted so that it exactly encompasses the lower edge of the pubic symphysis and the anorectal angle. Then, the VOI is rendered to obtain the levator hiatus image. For example, in endometrial imaging, the location of the endometrium is identified. Based on the location of the endometrium, the VOI curve is adjusted to coincide with the lower edge of the endometrium by adjusting the body data orientation and VOI. Then, the area corresponding to the VOI is rendered to obtain a three-dimensional image.

[0093] In one embodiment, such as Figure 6 As shown, step S206, which is the step of determining the ultrasound image of the target anatomical structure from the ultrasound body data based on the location information of the target anatomical structure, may specifically include the following steps:

[0094] Step S602: Determine the position information of the target section based on the position information of the target anatomical structure.

[0095] In this embodiment, the processor 103 determines the position information of the target cross-section based on the position information of the target anatomical structure, as described in step S402. This embodiment will not be repeated here.

[0096] Step S604: Obtain the preset stereoscopic image size.

[0097] In this embodiment, the size of the stereoscopic image is preset. The specific size can be set as needed. For example, when the object being tested is the pelvic floor levator hiatus, the VOI can be set to 2cm in length, width, and height.

[0098] Step S606: Obtain the position information of VOI from the ultrasound body data based on the position information of the target section and the preset stereoscopic image size.

[0099] In this embodiment, the target section is located within the volume of interest (VOI). The VOI can be obtained by extending it along various spatial dimensions, centered on the target section and according to a preset stereoscopic image size. For example, assuming the length, width, and height of the VOI are all 2cm, then in the ultrasound body data, with the center point of the target section as the center, extending it by 1cm in each of the positive X-axis, negative X-axis, positive Y-axis, negative Y-axis, positive Z-axis, and negative Z-axis directions, respectively, yields the position information of the VOI.

[0100] Step S608: Render the VOI to obtain a three-dimensional image of the target anatomical structure, and determine the three-dimensional image as the ultrasound image of the target anatomical structure.

[0101] In this embodiment of the application, after obtaining the VOI, the processor 103 renders the region corresponding to the VOI to obtain a stereoscopic image, which serves as an ultrasound image of the target anatomical structure.

[0102] In one embodiment, such as Figure 7 As shown, after the processor 103 determines the location information of the target anatomical structure from the ultrasound body data, the ultrasound imaging method may further include step S702: optimizing the ultrasound body data based on the location information of the target anatomical structure.

[0103] In this embodiment, after obtaining the location information of the target anatomical structure, the processor 103 can determine an optimized target location region based on the location information of the target anatomical structure, and optimize the ultrasound volume data corresponding to the target location region. For example, the target location region can be the region corresponding to the target section or the region corresponding to VOI. The grayscale value can be optimized, for example, by increasing or decreasing the grayscale value. Immediately after optimizing the ultrasound volume data, the corresponding ultrasound image can be displayed based on the optimized ultrasound volume data.

[0104] In one implementation, the processor 103 can reduce the ultrasound body data parameter values ​​of non-target anatomical structures based on the location information of the target anatomical structure, so that the difference between the ultrasound body data parameter values ​​of the target anatomical structure and the non-target anatomical structure is within a preset range.

[0105] In this embodiment, the ultrasound body data parameter values ​​can be grayscale values. The preset range can be greater than a preset first threshold and less than a preset second threshold, wherein the second threshold is larger than the first threshold, and the specific range can be set as needed. Non-target anatomical structure regions are areas other than the target anatomical structure in the ultrasound body data.

[0106] In one embodiment, the ultrasound body data parameter value of the region corresponding to the target anatomical structure can also be increased so that the difference between the ultrasound body data parameter value of the target anatomical structure and the ultrasound body data parameter value of the non-target anatomical structure region is within a preset range.

[0107] Since the target anatomical structure is usually the area of ​​interest to the user, and the non-anatomical structure location is usually the background or noise area to be suppressed, the gray value outside the target anatomical structure area can be reduced or the gray value of the anatomical structure area itself can be increased according to the location of the target anatomical structure. This can suppress noise, enhance the signal strength of the target anatomical structure, and adaptively improve the contrast of the rendered image.

[0108] In one embodiment, optimizing ultrasound data based on the location information of the target anatomical structure includes: obtaining ultrasound data parameter values ​​for the target anatomical structure and non-target anatomical structure regions based on the location information of the target anatomical structure; and adjusting the ultrasound data parameter values ​​for the target anatomical structure and non-target anatomical structure regions as a whole according to preset conditions.

[0109] In this embodiment, the ultrasound body data parameter values ​​are parameters related to the ultrasound body data, such as grayscale values. Preset conditions may include the difference between the ultrasound body data parameter values ​​of the target anatomical structure and non-target anatomical structure regions falling within a preset range, the contrast falling within a preset range, or the probability density of the grayscale values ​​corresponding to the ultrasound body data being uniformly distributed. Overall adjustment refers to adjusting the ultrasound body data parameter values ​​corresponding to both the target and non-target anatomical structure regions. Based on the location information of the target anatomical structure, the non-target anatomical structure region and the region corresponding to the target anatomical structure can be obtained, and different adjustment strategies or values ​​are adopted for different regions. For example, the average grayscale value of the ultrasound body data can be statistically analyzed, and compared with a preset grayscale value. If the average grayscale value is less than the preset grayscale value, the grayscale value is increased; otherwise, it is decreased. Another example is the use of histogram equalization to adjust the ultrasound body data parameter values. Histogram equalization is a method that non-linearly stretches the image, redistributing image pixels to make the number of pixels within a certain grayscale range approximately the same.

[0110] In one embodiment, the processor 103 can adjust one or both of the ultrasound body data parameter values ​​of the target anatomical structure and the non-target anatomical structure region. For example, it can calculate the average gray value corresponding to the target anatomical structure, compare the average gray value corresponding to the target anatomical structure with a preset gray value, and if the average gray value is less than the preset gray value, increase the gray value; otherwise, decrease the gray value.

[0111] In one embodiment, after step S206, i.e., determining the ultrasound image of the target anatomical structure from the ultrasound body data based on the location information of the target anatomical structure, the ultrasound imaging method further includes: optimizing the ultrasound image.

[0112] In this embodiment, the processor 103 optimizes parameters related to the ultrasound image, such as at least one of the following: threshold, gain, brightness, and contrast. Here, the threshold is the difference in grayscale values ​​between the target anatomical structure and non-target anatomical structure regions. The non-target anatomical structure regions are areas other than the target anatomical structure in the ultrasound body data. The difference in grayscale values ​​between the target anatomical structure and non-target anatomical structure regions can be the difference in their corresponding average grayscale values.

[0113] In one embodiment, optimizing the threshold of an ultrasound image includes: acquiring a threshold for the ultrasound image; and adjusting the threshold of the ultrasound image if the threshold of the ultrasound image does not meet a preset threshold range.

[0114] In this embodiment, the preset threshold range can be set as needed. The preset threshold range can be greater than a preset third threshold and less than a preset fourth threshold, where the fourth threshold is greater than the third threshold. If the threshold of the ultrasound image does not meet the preset threshold range, one or both of the grayscale values ​​of the target anatomical structure and the non-target anatomical structure region can be adjusted to make the resulting threshold meet the preset threshold range. For example, if the threshold of the ultrasound image is less than the third threshold, the grayscale value corresponding to the target anatomical structure can be increased or the grayscale value of the non-target anatomical structure region can be decreased. If the threshold of the ultrasound image is greater than the third threshold, the grayscale value corresponding to the target anatomical structure can be decreased.

[0115] In one embodiment, the processor 103 optimizes at least one of the gain, brightness, and contrast of an ultrasound image by: acquiring a signal strength value of the ultrasound image; if the signal strength value is greater than a preset value, decreasing at least one of the gain, brightness, and contrast of the ultrasound image; and if the signal strength value is less than a preset value, increasing at least one of the gain, brightness, and contrast of the ultrasound image.

[0116] In this embodiment, signal strength can be represented by the ultrasonic flow rate returned by the ultrasonic probe. Gain refers to the amplification factor of the signal. Preset values ​​can be set as needed. If the signal strength value is greater than the preset value, at least one of the gain, brightness, and contrast of the ultrasonic image is reduced; if the signal strength value is less than the preset value, at least one of the gain, brightness, and contrast of the ultrasonic image is increased to make the ultrasonic image clearer. The correspondence between the signal strength value and the values ​​of reduced gain, brightness, and contrast can be set as needed. Alternatively, at least one of the gain, brightness, and contrast can be reduced or increased at a preset rate until a stop command input by the user is received.

[0117] In one embodiment, the processor 103 can also optimize the Time Gain Control (TGC) of the ultrasound image based on the signal intensity value of the ultrasound image. Since the ultrasound intensity decreases with increasing detection depth, the intensity of the emitted echoes at different depths varies. Therefore, different gain compensations can be applied to echoes from different depths. If the signal intensity value is greater than a preset value, it indicates that the required gain compensation is small, so the gain compensation of the ultrasound image is reduced; if the signal intensity value is less than the preset value, the gain compensation of the ultrasound image is increased.

[0118] In one embodiment, the processor 103 may further determine a background discrimination grayscale threshold for distinguishing the target anatomical structure from the background based on the grayscale values ​​of the target anatomical structure and the non-target anatomical structure regions. After obtaining the background discrimination grayscale threshold, regions with grayscale values ​​greater than the background discrimination grayscale threshold are rendered to obtain an ultrasound image, while regions with grayscale values ​​lower than the background discrimination grayscale threshold are generally considered as background or noise regions and will not be rendered. Grayscale distribution data of the target anatomical structure and grayscale distribution data of the non-target anatomical structure regions can be acquired, and the background discrimination threshold can be determined based on the grayscale distribution data of the target anatomical structure and the non-target anatomical structure regions.

[0119] like Figure 8As shown, grayscale histograms can be obtained based on the grayscale distribution data of the target anatomical structure and the grayscale distribution data of the non-target anatomical structure region, respectively. The horizontal axis of the grayscale histogram represents the grayscale value, and the vertical axis represents the number of pixels. The intersection of the two histograms (point C in the figure) is selected as the threshold. Alternatively, the peak value of the grayscale histogram corresponding to the non-target anatomical structure region (point A in the figure) and the peak value of the target anatomical structure region (point B in the figure) can be calculated separately. Then, the peak grayscale values ​​corresponding to point A and point B are weighted and summed to obtain the background discrimination grayscale threshold. This can be expressed by the formula T = a * A + (1 - a) * B, where a is a preset weighting coefficient, which can be set as needed, for example, a = 0.5.

[0120] In one embodiment, the grayscale histogram can be smoothed using a Gaussian smoothing method to reduce the impact of random fluctuations in the grayscale values ​​of the ultrasound image on the grayscale distribution data.

[0121] like Figure 9 As shown, in one embodiment, a method for optimizing ultrasound body data is proposed, which may specifically include the following steps:

[0122] Step S902: Obtain ultrasound data of the subject.

[0123] Step S904: Determine the location information of the target anatomical structure from the ultrasound data.

[0124] Step S906: Optimize ultrasound body data based on the location information of the target anatomical structure.

[0125] In this embodiment, the implementation methods of steps S902 to S906 can refer to the corresponding descriptions in any of the above embodiments, and will not be repeated here. Since the ultrasound body data can be optimized based on the location of the target anatomical structure, the time for optimizing the ultrasound body data is reduced, thus saving ultrasound instrument resources.

[0126] like Figure 10 As shown, in one embodiment, a method for optimizing ultrasound images is proposed, which may specifically include the following steps:

[0127] Step S1002: Obtain ultrasound data of the subject.

[0128] Step S1004: Determine the location information of the target anatomical structure from the ultrasound body data.

[0129] Step S1006: Determine the ultrasound image of the target anatomical structure from the ultrasound body data based on the location information of the target anatomical structure.

[0130] Step S1008: Optimize ultrasound images.

[0131] In this application embodiment, the implementation method of steps S1002 to S1008 can refer to the corresponding description in any of the above embodiments, and will not be repeated here.

[0132] Figure 11 An internal structural diagram of a computer device in one embodiment is shown. Figure 11 As shown, the computer device includes a processor, memory, network interface, input system, and display screen connected via a system bus. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and may also store computer-readable instructions. When executed by the processor, these computer-readable instructions enable the processor to implement methods for ultrasound imaging, optimizing ultrasound images, and optimizing ultrasound body data. The internal memory may also store computer-readable instructions, which, when executed by the processor, enable the processor to implement methods for ultrasound imaging, optimizing ultrasound images, and optimizing ultrasound body data. The display screen may be an LCD screen or an e-ink screen. The input system may be a touch layer covering the display screen, buttons, a trackball, or a touchpad located on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0133] Those skilled in the art will understand that Figure 11 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0134] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing related hardware with computer-readable instructions. These computer-readable instructions can be stored in a non-volatile computer-readable storage medium. When executed, these computer-readable instructions can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0135] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0136] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for ultrasound imaging, characterized in that, The method includes: Acquire ultrasound data of the subject; The location information of the target anatomical structure is determined from the ultrasound data; The ultrasound image of the target anatomical structure is automatically determined from the ultrasound body data based on the location information of the target anatomical structure. The ultrasound image of the target anatomical structure includes the ultrasound image of the volume of interest (VOI) corresponding to the target anatomical structure, where the VOI is the region of the three-dimensional image to be viewed. Display the ultrasound image; The step of automatically determining the ultrasound image of the target anatomical structure from the ultrasound body data based on the location information of the target anatomical structure includes: Determine the location information of the target section based on the location information of the target's anatomical structure; The VOI is obtained based on the position information of the target section. The VOI is rendered to obtain a three-dimensional image of the target anatomical structure, and the three-dimensional image is determined as the ultrasound image of the target anatomical structure.

2. The method according to claim 1, characterized in that, Determining the position information of the target section based on the position information of the target anatomical structure includes: Determine the target section equation based on the location information of the target anatomical structure; The position information of the target section is obtained based on the target section equation.

3. The method according to claim 2, characterized in that, The step of determining the target section equation based on the location information of the target anatomical structure includes: The equation of the target section is determined based on the positional information of the target anatomical structure using a three-point non-collinear method. or, The target section equation is determined by fitting the positional information of the target anatomical structure. The fitting method includes at least one of least squares estimation and Hough transform.

4. The method according to claim 1, characterized in that, The determination of the location information of the target anatomical structure from the ultrasound data includes: Obtain the structural feature information of the target anatomical structure; determine the location information of the target anatomical structure from the ultrasound data based on the structural feature information; or, Obtain identification information to identify the target anatomical structure; determine the location information of the target anatomical structure from the ultrasound body data based on the identification information.

5. The method according to claim 1, characterized in that, After determining the location information of the target anatomical structure from the ultrasound body data, the method further includes: The ultrasound data is optimized based on the location information of the target anatomical structure.

6. The method according to claim 5, characterized in that, The optimization of the ultrasound data based on the location information of the target anatomical structure includes: The ultrasound data parameter values ​​of non-target anatomical structures are reduced based on the location information of the target anatomical structure so that the difference between the ultrasound data parameter values ​​of the target anatomical structure and the ultrasound data parameter values ​​of the non-target anatomical structure is within a preset range. The non-target anatomical structure is a region other than the target anatomical structure in the ultrasound data. or, The ultrasound body data parameter values ​​of the target anatomical structure and the non-target anatomical structure region are obtained based on the location information of the target anatomical structure, wherein the non-target anatomical structure region is other regions outside the target anatomical structure in the ultrasound body data; the ultrasound body data parameter values ​​of the target anatomical structure and the non-target anatomical structure region are adjusted as a whole according to preset conditions.

7. The method according to claim 1, characterized in that, After determining the ultrasound image of the target anatomical structure from the ultrasound body data based on the location information of the target anatomical structure, the method further includes: Optimize the ultrasound image.

8. The method according to claim 7, characterized in that, The optimization of the ultrasound image includes: Optimize at least one of threshold, gain, brightness, and contrast of the ultrasound image, wherein the threshold is the difference in grayscale values ​​between the target anatomical structure and a non-target anatomical structure region, the non-target anatomical structure region being other regions in the ultrasound body data besides the target anatomical structure.

9. The method according to claim 8, characterized in that, The thresholds for optimizing the ultrasound image include: The threshold for obtaining the ultrasound image; If the threshold of the ultrasound image does not meet the preset threshold range, then the threshold of the ultrasound image is adjusted.

10. The method according to claim 8 or 9, characterized in that, The optimization of at least one of the gain, brightness, and contrast of the ultrasound image includes: Obtain the signal intensity value of the ultrasound image; If the signal strength value is greater than a preset value, then reduce at least one of the gain, brightness, and contrast of the ultrasound image; If the signal strength value is less than a preset value, then at least one of the gain, brightness, and contrast of the ultrasound image is increased.

11. The method according to claim 1, characterized in that, The step of obtaining the volume of interest (VOI) based on the position information of the target section includes: The size and position of the VOI are set from the ultrasound body data based on the position information of the target section, wherein the VOI surrounds all or part of the target anatomical structure.

12. A method for optimizing ultrasound body data, characterized in that, The method includes: Acquire ultrasound data of the subject; The location information of the target anatomical structure is determined from the ultrasound data; Based on the location information of the target anatomical structure, ultrasound data of the target anatomical structure and non-target anatomical structure regions are determined, wherein the non-target anatomical structure regions are other regions outside the target anatomical structure in the ultrasound data; By employing different adjustment strategies or adjustment values ​​to optimize the ultrasound data of the target anatomical structure and non-target anatomical structure regions, the optimized ultrasound data of the target anatomical structure and non-target anatomical structure regions are obtained.

13. The method according to claim 12, characterized in that, The optimization of the ultrasound data of the target and non-target anatomical structures using different adjustment strategies or values ​​includes: Reduce the ultrasound body data parameter values ​​of non-target anatomical structures so that the difference between the ultrasound body data parameter values ​​of the target anatomical structure and the ultrasound body data parameter values ​​of the non-target anatomical structures is within a preset range. or, The ultrasound data parameter values ​​of the target anatomical structure and the non-target anatomical structure region are adjusted as a whole according to preset conditions; the preset conditions are used to characterize the different adjustment strategies of the target anatomical structure and the non-target anatomical structure region.

14. The method according to claim 12, characterized in that, The determination of the location information of the target anatomical structure from the ultrasound data includes: Obtain the structural feature information of the target anatomical structure; determine the location information of the target anatomical structure from the ultrasound body data based on the structural feature information; or, Obtain identification information to identify the target anatomical structure; determine the location information of the target anatomical structure from the ultrasound body data based on the identification information.

15. An ultrasound imaging system, characterized in that, The ultrasound imaging system includes: An ultrasonic probe is used to emit ultrasonic waves to the object under test and receive ultrasonic echoes to obtain ultrasonic signals obtained by performing ultrasonic testing on the object under test. A memory that stores computer-readable instructions; A processor, wherein when the computer-readable instructions are executed by the processor, the processor causes the processor to perform the method according to any one of claims 1 to 14; A display used to show ultrasound images.

Images