Ultrasonic imaging method and system for fetus in mid- to late-pregnancy

Abstract

A method and system for ultrasound imaging of a mid- to late-trimester fetus includes the following steps: (S220) obtaining three-dimensional ultrasound data of a mid- to late-trimester fetus; (S230) determining the longitudinal direction of a body region of the mid- to late-trimester fetus based on the three-dimensional ultrasound data; (S540) extracting information on target characteristic structures of the mid- to late-trimester fetus from the three-dimensional ultrasound data, wherein the target characteristic structures include at least one of the following: gastric alveoli, spinal column, liver, umbilical vein, descending aorta, inferior vena cava, umbilical cord insertion, umbilical cord, anterior abdominal wall, bladder, legs, umbilical artery, and gallbladder; and (S560) extracting and displaying at least one standard abdominal section of the mid- to late-trimester fetus from the three-dimensional ultrasound data based on the longitudinal direction and the information on the target characteristic structures. The method and system automatically extract standard abdominal sections of the mid- to late-trimester fetus from a single acquisition of three-dimensional ultrasound data, eliminating the need for a doctor to manually extract standard abdominal sections one by one, thereby improving the efficiency and quality of the extracted standard abdominal sections.

Description

[0001] manual Technical Field

[0002] The present application relates to the field of ultrasound imaging technology, and more specifically to an ultrasound imaging method and ultrasound imaging system for a fetus in mid- to late-gestational stages. Background Art

[0003] With the improvement of people's living standards and social progress, people have high expectations for the accuracy of prenatal ultrasound examinations. In recent years, as the level of prenatal ultrasound examinations has continued to improve, the clinical demand for prenatal ultrasound examinations has also increased accordingly. At the same time, there is no unified standard for prenatal ultrasound examination methods, examinations, and image acquisition among different regions, hospitals, and ultrasound physicians. This lack of standardization has directly affected the quality of prenatal ultrasound examinations and the development of the discipline.

[0004] Abdominal ultrasound is an essential part of prenatal ultrasound examinations. Abdominal ultrasound often uses standardized sections to screen for abnormalities. These sections examine the fetal abdominal wall, liver, stomach, kidneys, bladder, umbilical cord entrance, and other structures for abnormalities. This prenatal examination method can effectively detect fetal abdominal abnormalities in a timely manner and provide appropriate diagnosis and treatment.

[0005] In the actual operation of obtaining standard abdominal sections, doctors often need to constantly adjust the position of the probe to obtain these sections. This process not only requires doctors to be proficient in image acquisition techniques, but also the operation process is relatively cumbersome and time-consuming. When hospitals need to examine a large number of pregnant women, there is a lot of repetitive work, which greatly limits the efficiency of prenatal examinations. At the same time, in grassroots hospitals, many doctors are limited by their skills and experience and find it difficult to obtain the optimal standard abdominal sections. There is also no unified standard for the extraction of standard abdominal sections among different regions, hospitals, and doctors. Summary of the Invention

[0006] The Summary of the Invention introduces a series of simplified concepts that will be further described in the Detailed Description of the Invention. The Summary of the Invention is not intended to limit the key features and essential features of the claimed technical solution, nor is it intended to determine the scope of protection of the claimed technical solution.

[0007] In a first aspect, an embodiment of the present application provides a method for ultrasound imaging of a fetus in the second and third trimesters of pregnancy, the method comprising:

[0008] transmitting ultrasound to a fetus in the second or third trimester and receiving an echo of the ultrasound to obtain an ultrasound echo signal;

[0009] obtaining three-dimensional ultrasound data of the mid- to late-gestation fetus based on the ultrasound echo signal;

[0010] determining the long axis direction of the body region of the mid- to late-gestation fetus based on the three-dimensional ultrasound data;

[0011] Extracting information of target characteristic structures of the fetus in the second and third trimesters from the three-dimensional ultrasound data, wherein the target characteristic structures in the second and third trimesters include at least one of the following: gastric bubble, spine, liver, umbilical vein, descending aorta, inferior vena cava, umbilical cord insertion, umbilical cord, anterior abdominal wall, bladder, legs, umbilical artery, and gallbladder;

[0012] extracting at least one standard abdominal section of the mid- to late-pregnancy fetus from the three-dimensional ultrasound data according to the long-axis direction of the body region of the mid- to late-pregnancy fetus and information of the target characteristic structure of the mid- to late-pregnancy fetus;

[0013] The at least one standard abdominal section is displayed.

[0014] A second aspect of the present application provides a method for ultrasound imaging of a fetus in the second and third trimesters, the method comprising:

[0015] transmitting ultrasound to a fetus in the second or third trimester and receiving an echo of the ultrasound to obtain an ultrasound echo signal;

[0016] obtaining three-dimensional ultrasound data of the mid- to late-gestation fetus based on the ultrasound echo signal;

[0017] determining a target direction of the body region of the mid- to late-gestation fetus based on the three-dimensional ultrasound data;

[0018] extracting information of the target characteristic structure of the mid- to late-gestation fetus from the three-dimensional ultrasound data;

[0019] extracting at least one standard abdominal section of the mid- to late-pregnancy fetus from the three-dimensional ultrasound data according to the target direction and information about the mid- to late-pregnancy target characteristic structure;

[0020] The at least one standard abdominal section is displayed.

[0021] A third aspect of the present application provides a method for ultrasound imaging of a fetus in the second and third trimesters of pregnancy, the method comprising:

[0022] transmitting ultrasound to a fetus in the second or third trimester and receiving an echo of the ultrasound to obtain an ultrasound echo signal;

[0023] obtaining three-dimensional ultrasound data of the mid- to late-gestation fetus based on the ultrasound echo signal;

[0024] Detecting regions of at least two different target characteristic structures of mid- to late pregnancy from the three-dimensional ultrasound data, wherein the at least two different target characteristic structures of mid- to late pregnancy include at least two of the following: gastric bubble, spinal column, liver, umbilical vein, descending aorta, inferior vena cava, umbilical cord insertion, umbilical cord, anterior abdominal wall, bladder, legs, umbilical artery, and gallbladder;

[0025] Determining at least one section that at least partially overlaps with each of the at least two different mid- to late-pregnancy target characteristic structure regions as at least one standard abdominal section of the mid- to late-pregnancy fetus;

[0026] The at least one standard abdominal section is displayed.

[0027] A fourth aspect of an embodiment of the present application provides an ultrasound imaging system, which includes an ultrasound probe, a transmitting / receiving circuit, a memory, a processor, and a display. The memory stores a computer program run by the processor, and when the computer program is run by the processor, it executes the steps of the ultrasound imaging method for a mid- to late-pregnancy fetus of the first aspect of the embodiment of the present application.

[0028] A fifth aspect of an embodiment of the present application provides an ultrasound imaging system, which includes an ultrasound probe, a transmitting / receiving circuit, a memory, a processor and a display. The memory stores a computer program run by the processor, and when the computer program is run by the processor, it executes the steps of the ultrasound imaging method for a fetus in the middle and late pregnancy of the second aspect of the embodiment of the present application.

[0029] A sixth aspect of an embodiment of the present application provides an ultrasound imaging system, which includes an ultrasound probe, a transmitting / receiving circuit, a memory, a processor, and a display. The memory stores a computer program run by the processor, and when the computer program is run by the processor, it executes the steps of the ultrasound imaging method for a fetus in the middle and late pregnancy of the third aspect of the embodiment of the present application.

[0030] According to the ultrasound imaging method and ultrasound imaging system of the mid-to-late pregnancy fetus in the embodiments of the present application, the standard abdominal sections of the mid-to-late pregnancy fetus can be automatically extracted based on the three-dimensional ultrasound data collected in a single time, without the need for the doctor to manually extract the standard sections one by one. This greatly optimizes the workflow of prenatal examinations, effectively improves work efficiency, and can improve the stability of the quality of the obtained standard sections, thereby promoting the promotion and application of mid-to-late pregnancy structural screening. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0032] In the attached figure:

[0033] Figure 1 A schematic block diagram of an ultrasound imaging system according to an embodiment of the present application is shown;

[0034] Figure 2 A schematic flow chart showing a method for ultrasound imaging of a fetus in the second and third trimesters according to an embodiment of the present invention;

[0035] Figure 3 A schematic diagram showing the relationship between the long axis direction of the body region of a mid- to late-gestation fetus and a standard abdominal section according to an embodiment of the present invention;

[0036] Figure 4 A schematic diagram showing a cross-section of the umbilical cord insertion site of a fetus in the second or third trimester according to an embodiment of the present invention;

[0037] Figure 5 A schematic flow chart showing a method for ultrasound imaging of a fetus in the second and third trimesters according to another embodiment of the present invention;

[0038] Figure 6 A schematic flow chart showing a method for ultrasound imaging of a fetus in the second and third trimesters according to yet another embodiment of the present invention is shown. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solutions and advantages of the present application more apparent, the following is a detailed description of example embodiments of the present application with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application described in this application, all other embodiments obtained by those skilled in the art without creative work should fall within the scope of protection of this application.

[0040] In the following description, a large number of specific details are provided to provide a more thorough understanding of the present application. However, it will be apparent to those skilled in the art that the present application can be implemented without one or more of these details. In other examples, some technical features well known in the art are not described in order to avoid confusion with the present application.

[0041] It should be understood that the present application can be implemented in different forms and should not be interpreted as being limited to the embodiments set forth herein. On the contrary, providing these embodiments will make the disclosure thorough and complete and will fully convey the scope of the present application to those skilled in the art.

[0042] The purpose of the terms used herein is only to describe specific embodiments and is not intended to limit the present application. When used herein, the singular forms "a", "an", and "the" are intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "comprising" and / or "including", when used in this specification, determine the presence of the features, integers, steps, operations, elements and / or parts, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, parts and / or groups. When used herein, the term "and / or" includes any and all combinations of the relevant listed items.

[0043] In order to fully understand the present application, a detailed structure will be provided in the following description to illustrate the technical solution proposed by the present application. The optional embodiments of the present application are described in detail below. However, in addition to these detailed descriptions, the present application may also have other implementation methods.

[0044] Next, first refer to Figure 1 An ultrasound imaging system according to an embodiment of the present application is described. Figure 1 FIG. 1 shows a schematic structural block diagram of an ultrasound imaging system 100 according to an embodiment of the present application.

[0045] like Figure 1 As shown, the ultrasound imaging system 100 includes an ultrasound probe 110, a transmit / receive circuit 112, a processor 114, a display 116, and a memory 118. Furthermore, the ultrasound imaging system 100 may further include a beamforming circuit and a transmit / receive selection switch.

[0046] Specifically, the ultrasound probe 110 includes multiple transducer array elements. These can be arranged in a row to form a linear array, or arranged in a two-dimensional matrix to form a planar array. The transducers can also form a convex array. The transducers are used to transmit ultrasonic waves based on excitation electrical signals, or to convert received ultrasonic waves into electrical signals. Therefore, each array element can be used to convert electrical pulse signals into and from ultrasonic waves, thereby transmitting ultrasonic waves to the tissue of the target area of ​​the subject being measured, and also to receive ultrasonic echoes reflected from the tissue. During ultrasound imaging, the transmit and receive sequences can be used to control which transducers are used to transmit ultrasonic waves and which are used to receive ultrasonic waves, or to control the time slots used to transmit ultrasonic waves or receive ultrasonic echoes. Transducers involved in ultrasonic transmission can be excited simultaneously by electrical signals, thereby simultaneously transmitting ultrasonic waves; alternatively, transducers involved in ultrasonic beam transmission can be excited by multiple electrical signals with a certain time interval, thereby continuously transmitting ultrasonic waves with a certain time interval.

[0047] The transmit / receive circuit 112 can be connected to the ultrasound probe 110 via a transmit / receive selector switch. The transmit / receive selector switch, also known as a transmit / receive controller, can include a transmit controller and a receive controller. The transmit controller is used to activate the ultrasound probe 110 to transmit ultrasound waves via the transmit circuit toward the region where the mid- to late-pregnancy fetus is located. The receive controller is used to receive ultrasound echoes returned from the region where the mid- to late-pregnancy fetus is located via the receive circuit via the ultrasound probe 110, thereby obtaining ultrasound echo data. The transmit / receive circuit 112 then transmits the ultrasound echo electrical signal to the beamforming circuit, which performs processing on the electrical signal, such as focusing delay, weighting, and channel summing, and then transmits the processed ultrasound echo data to the processor 114.

[0048] Alternatively, the processor 114 may be implemented by software, hardware, firmware, or any combination thereof, and may include a circuit, 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 any combination of the aforementioned circuits and / or devices, or other suitable circuits or devices, so that the processor 114 can execute the corresponding steps of the methods described in various embodiments of this specification. Furthermore, the processor 114 may control other components in the ultrasound imaging system 100 to perform desired functions.

[0049] The processor 114 processes the received ultrasound echo data to obtain three-dimensional ultrasound data of a mid- to late-gestation fetus. For example, the ultrasound probe 110 transmits and receives ultrasound waves within a series of scanning planes, which the processor 114 integrates based on their three-dimensional spatial relationships to achieve three-dimensional scanning of the mid- to late-gestation fetus and reconstruction of a three-dimensional image. Finally, the processor 114 performs some or all of the image post-processing steps, including denoising, smoothing, and enhancement, to obtain three-dimensional ultrasound data of the mid- to late-gestation fetus. The processor 114 can obtain three-dimensional ultrasound data of the entire body of the mid- to late-gestation fetus or only of the head or body of the mid- to late-gestation fetus. The processor 114 is also configured to extract standard cross-sections of the mid- to late-gestation fetus from the three-dimensional ultrasound data. The standard cross-sections obtained by the processor 114 can be stored in a memory or displayed on the display 116. Furthermore, the processor 114 can render the three-dimensional ultrasound data and display it on the display 116.

[0050] The display 116 is connected to the processor 114 and can be a touch screen display, liquid crystal display, or the like. Alternatively, the display 116 can be an independent display device such as a liquid crystal display or a television that is independent of the ultrasound imaging system 100. Alternatively, the display 116 can be a display screen of an electronic device such as a smartphone or tablet computer. The number of displays 116 can be one or more. For example, the display 116 can include a main screen and a touch screen, with the main screen primarily used to display ultrasound images and the touch screen primarily used for human-computer interaction.

[0051] The display 116 can display the ultrasound image generated by the processor 114. In addition to displaying the ultrasound image, the display 116 can also provide a user with a graphical interface for human-computer interaction. One or more controlled objects can be set on the graphical interface, allowing the user to input operating instructions using a human-computer interaction device to control these controlled objects and perform corresponding control operations. For example, icons can be displayed on the graphical interface, and the human-computer interaction device can be used to operate the icons to execute specific functions.

[0052] Optionally, the ultrasound imaging system 100 may further include other human-computer interaction devices in addition to the display 116, which are connected to the processor 114. For example, the processor 114 may be connected to the human-computer interaction device via an external input / output port. The external input / output port may be a wireless communication module, a wired communication module, or a combination of the two. The external input / output port may also be implemented based on USB, a bus protocol such as CAN, and / or a wired network protocol.

[0053] The human-computer interaction device may include an input device for detecting user input information. The input information may be, for example, a control instruction for the timing of ultrasonic transmission / reception, an operation input instruction for drawing a point, line, or frame on an ultrasonic image, or other instruction types. The input device may include one or a combination of a keyboard, a mouse, a scroll wheel, a trackball, a mobile input device (such as a mobile device with a touch screen display, a mobile phone, etc.), a multi-function knob, etc. The human-computer interaction device may also include an output device such as a printer.

[0054] The ultrasound imaging system 100 may further include a memory 118 for storing instructions executed by the processor, storing received ultrasound echoes, storing ultrasound images, etc. The memory 118 may be a flash memory card, a solid-state memory, a hard disk, etc. It may be a volatile memory and / or a non-volatile memory, a removable memory and / or a non-removable memory, etc.

[0055] It should be understood that Figure 1 The components included in the ultrasound imaging system 100 are merely illustrative, and the system may include more or fewer components, which is not limited in the present application.

[0056] Below, we will refer to Figure 2 The ultrasound imaging method of a fetus in the second and third trimesters according to an embodiment of the present application is described. Figure 2 2 is a schematic flow chart of a method 200 for ultrasound imaging of a fetus in the second and third trimesters of pregnancy according to an embodiment of the present application.

[0057] like Figure 2 As shown, a method 200 for ultrasound imaging of a fetus in the second and third trimesters of pregnancy according to one embodiment of the present application includes the following steps:

[0058] First, in step S210, ultrasonic waves are transmitted to a fetus in the middle or late stages of pregnancy, and echoes of the ultrasonic waves are received to obtain ultrasonic echo signals.

[0059] Among them, the mid-to-late pregnancy fetus includes the mid-to-late pregnancy fetus and the late pregnancy fetus. The mid-to-late pregnancy fetus generally refers to the fetus between the 14th and 27th weeks of pregnancy, and the late pregnancy fetus generally refers to the fetus at the 28th week of pregnancy and above. Figure 1The ultrasound imaging system 100 shown performs ultrasound scanning. The user moves the ultrasound probe 110 to select an appropriate position and angle. The transmitting circuit in the transmit / receive circuit 120 sends a set of delayed and focused pulses to the ultrasound probe 110, which then transmits ultrasound waves along a 2D scanning plane toward a fetus in the second or third trimester. After receiving the reflected ultrasound echoes, the ultrasound probe 110 converts them into electrical signals. The beamforming circuit then performs beamforming on the ultrasound echo signals generated by multiple transmissions and receptions, performing appropriate delays and weighted summation. These signals are then sent to the processor 114 for subsequent signal processing.

[0060] In step S220, three-dimensional ultrasound data of the mid- to late-gestation fetus is obtained based on the ultrasound echo signal.

[0061] Specifically, the three-dimensional spatial relationship between ultrasound echoes transmitted and received by the ultrasound probe 110 within a series of scanning planes can be integrated to achieve three-dimensional spatial scanning of a mid- to late-gestation fetus and reconstruction of three-dimensional ultrasound data. Finally, after undergoing some or all of the image post-processing steps, such as denoising, smoothing, and enhancement, three-dimensional ultrasound data of the mid- to late-gestation fetus is obtained. Three-dimensional ultrasound data can be obtained for the entire body of the mid- to late-gestation fetus, or for only a region of the fetus.

[0062] In some embodiments, after acquiring 3D ultrasound data, a visualization algorithm can be used to render the 3D ultrasound data to obtain a 3D ultrasound image, which can then be displayed on a display device. The methods used to render the 3D image include, for example, surface rendering or volume rendering, and are not limited in this embodiment of the present application.

[0063] In the embodiments of this application, standard abdominal sections are two-dimensional sections within a three-dimensional ultrasound image that contain key abdominal information. These sections allow observation of clinically valuable physiological structures and serve as an important basis for screening for abdominal deformities. For example, the subsequently extracted standard abdominal sections include at least one of the following standard sections: an abdominal circumference section, an umbilical cord insertion section, a gallbladder section, a transverse section of both kidneys, and a section of the bladder and both umbilical arteries.

[0064] Specifically, the abdominal circumference section is usually circular or elliptical, and contains information about the gastric bubble, umbilical vein, and spinal column cross section. The umbilical cord insertion section is usually circular or elliptical. The normal umbilical cord abdominal wall entrance is located in the center of the anterior abdominal wall, forming a straight line with the posterior abdominal wall spinal column echo, forming the anterior-posterior midline of the umbilical cord insertion section. The gallbladder section is usually circular or elliptical, and contains information about structures such as the gallbladder. The bilateral kidney cross section is usually circular or elliptical, and contains information about structures such as the two kidneys. The bladder and bilateral umbilical artery section is a cross section of the lower abdomen, which shows an echo-free area of ​​the bladder, and the color Doppler image shows the umbilical arteries on both sides of the bladder. Subsequently, some or all of the above standard abdominal sections can be extracted to conduct a comprehensive screening of the body areas of the fetus in the middle and late pregnancy.

[0065] In step S230, the long axis direction of the body region of the mid- to late-gestation fetus is determined based on the three-dimensional ultrasound data.

[0066] Since the long axis direction of a body region can be determined relatively accurately based on the three-dimensional ultrasound data of a mid- to late-pregnancy fetus, and since the standard abdominal section generally has a certain angle relationship with the long axis direction of the body region, first determining the long axis direction of the body region and then further extracting the standard abdominal section based on the long axis direction of the body region can improve the quality of the extracted standard abdominal section. For example, determining the long axis direction of a mid- to late-pregnancy fetus includes but is not limited to the following implementation methods:

[0067] In one approach, the spinal region of a mid- to late-trimester fetus can be determined in the three-dimensional ultrasound data acquired in step S220, and the long axis of the fetus can be determined based on the orientation of the spinal region. Because the spinal region is relatively prominent in three-dimensional ultrasound images of a mid- to late-trimester fetus, the long axis of the fetus can be accurately determined based on the location of the spinal region.

[0068] Exemplarily, determining the spinal region of a mid- to late-gestation fetus in three-dimensional ultrasound data includes segmenting the spinal region of the mid- to late-gestation fetus in the three-dimensional ultrasound data, and the methods include but are not limited to the following two: one is to convert the three-dimensional spinal region segmentation into two-dimensional spinal region segmentation, that is, to segment the spinal region in multiple two-dimensional section images of the three-dimensional ultrasound data, and to integrate the segmentation results of the spinal region on multiple two-dimensional section images to obtain a three-dimensional segmentation result of the spine in the three-dimensional ultrasound image; the second is to directly perform three-dimensional segmentation on the three-dimensional ultrasound data to obtain a three-dimensional segmentation result of the spinal region.

[0069] When converting the three-dimensional spinal region segmentation into two-dimensional spinal region segmentation, the multiple two-dimensional sections extracted from the three-dimensional ultrasound data can be all the two-dimensional sections of the three-dimensional ultrasound data, and then the segmentation results of the spinal region of all the two-dimensional sections can be combined to obtain the segmentation result of the spine in the entire three-dimensional ultrasound data. For example, the three-dimensional ultrasound data can be divided into horizontal sections, upper and lower sections, etc. to obtain all the two-dimensional sections of the three-dimensional ultrasound data. Alternatively, the multiple two-dimensional sections extracted from the three-dimensional ultrasound data can also be part of the two-dimensional sections in the three-dimensional ultrasound data, that is, the two-dimensional sections are sampled images obtained by sampling the three-dimensional ultrasound data according to a preset rule, for example, the sampled images can be obtained equidistantly in a certain direction or rotated according to a center point to obtain the sampled images, and the spinal region in the sampled images is segmented. After that, the segmentation results of the spinal region of the multiple sampled images are three-dimensionally interpolated to obtain the three-dimensional segmentation result of the entire spinal region.

[0070] As an example, a machine learning method or a traditional image processing method may be used to segment the spinal region in multiple two-dimensional cross-sectional images of three-dimensional ultrasound data.

[0071] Specifically, when using a machine learning algorithm to segment the spinal region in a two-dimensional cross-sectional image, it is necessary to pre-build a two-dimensional cross-sectional image database of mid-to-late pregnancy fetuses, in which each two-dimensional cross-sectional image data is marked with the corresponding position of the spinal region. Then, an optimal mapping function is learned to map from the two-dimensional cross-sectional image to the domain region of interest box of the spinal region or the specific area range of the spinal region.

[0072] When segmenting the spinal region based on deep learning methods, the three-dimensional ultrasound data in the database is first processed to obtain multiple two-dimensional cross-sectional images as training samples. Each two-dimensional cross-sectional image is labeled with the location of the spinal region. These training samples are fed into a pre-built network model, and the network model's loss function is optimized for training until the network model reaches convergence. During the training process, the network model can learn how to identify the location of the spinal region from a single two-dimensional cross-sectional image. After the network model is trained, only a single two-dimensional cross-sectional image needs to be input into the network model to obtain the segmentation result of the spinal region.

[0073] When segmenting the spinal region based on traditional image processing methods, pixel clustering, edge segmentation, graph cuts, or threshold-based image segmentation algorithms can be used. Among these, threshold-based image segmentation algorithms are relatively simple and direct. Because the spinal region and other regions in ultrasound images have different grayscale values, threshold-based image segmentation can achieve better results based on this characteristic of the spinal region. When performing threshold-based image segmentation, one or more grayscale values ​​can be pre-set as thresholds, thereby dividing the ultrasound image into the spinal region and the background region based on the grayscale values ​​of the ultrasound image.

[0074] In addition to the above methods, other suitable methods can also be used to segment the spinal region in a two-dimensional cross-sectional image. For example, the two-dimensional cross-sectional image is first pre-segmented using methods such as threshold segmentation, Snake, level set, GraphCut, ASM, and AAM to obtain a set of candidate boundary ranges. Feature extraction is then performed on each candidate boundary range. The feature extraction method can be traditional image features such as PCA, LDA, HOG, Harr, and LBP, or image features can be extracted based on a neural network. The extracted image features are then matched with image features extracted from the marked spinal regions in a pre-constructed database, and classified using a discriminator such as KNN, SVM, random forest, or neural network to determine whether the current candidate boundary range contains the spinal region.

[0075] When three-dimensional ultrasound data is directly segmented, a three-dimensional convolutional neural network can be used to perform three-dimensional segmentation to obtain a three-dimensional spinal region, determine the long axis direction of the spinal region, and then determine the long axis direction of the body region. Specifically, a three-dimensional ultrasound database is pre-constructed, in which each three-dimensional ultrasound data is marked with the position corresponding to the spinal region, and then the three-dimensional convolutional neural network is trained based on the pre-constructed database. Based on the three-dimensional convolutional neural network, there is no need to perform section processing on the three-dimensional ultrasound data. The segmentation result of the spinal region can be obtained by directly inputting the three-dimensional ultrasound data into the trained model. Available three-dimensional convolutional neural networks include but are not limited to 3DUnet, 3DFCN, Medical-Net, etc.

[0076] Alternatively, a traditional 3D segmentation algorithm can be used to segment the spinal region from the 3D ultrasound data. Optional 3D segmentation algorithms include, but are not limited to, 3D Otsu's method, 3D threshold segmentation, 3D region growing, 3D level set, and split-merge methods. Using a 3D segmentation algorithm, the 3D spinal region can be directly segmented, and the fetal long axis can then be calculated using the spine.

[0077] After the spinal region in the three-dimensional ultrasound data is segmented using the above method, its long axis direction is determined based on the range of the spinal region. The long axis direction is the long axis direction of the body region of the fetus in the middle and late pregnancy period. For example, a straight line close to the spinal region can be determined, and the direction of the straight line is determined as the direction of the spinal region. Among them, the least squares method can be used to fit the straight line closest to the spinal region. Alternatively, in traditional image processing methods, methods such as Hough transform and random sampling consensus algorithm (RANSAC) can be used to detect the brightest straight line in the three-dimensional ultrasound data of the fetus in the middle and late pregnancy period as the detection result of the spinal region, and the direction of the straight line is determined as the direction of the spinal region.

[0078] In another method of determining the long axis direction of the body of a second- to third-trimester fetus, the body region of the second- to third-trimester fetus can be determined in three-dimensional ultrasound data, and the long axis direction of the body of the second- to third-trimester fetus can be determined based on the shape of the body region.

[0079] The method for determining the body region of a mid- to late-gestation fetus in three-dimensional ultrasound data is similar to the method for determining the spinal region described above. For example, the body region can be first segmented in multiple two-dimensional cross-sectional images of the three-dimensional ultrasound data, and the segmentation results of the body region in the multiple two-dimensional cross-sectional images can be combined to obtain a three-dimensional segmentation result of the body region in the three-dimensional ultrasound image. Methods for segmenting the body region in the two-dimensional cross-sectional images include, but are not limited to, machine learning methods and traditional image processing methods. Alternatively, a three-dimensional convolutional neural network or a traditional three-dimensional segmentation algorithm can be used to directly process the three-dimensional ultrasound data to directly segment the body region of the mid- to late-gestation fetus.

[0080] Then, based on the segmentation results of the mid- to late-gestation fetal body region, the long axis of the body region is determined based on the shape of the body region, and the direction of the long axis is determined as the up-down direction of the mid- to late-gestation fetal body region. For example, the long axis direction of the body region can be determined using a principal component analysis (PCA) method or a least squares method, or the long axis of the body region can be determined by segmenting the two farthest points in the body region.

[0081] In addition to the automatic segmentation methods described above, manual segmentation can also be used to determine the longitudinal axis orientation of a mid- to late-pregnancy fetus. This method receives a user instruction to determine the longitudinal axis orientation and then determines the longitudinal axis orientation of the mid- to late-pregnancy fetus based on the received user instruction. The user only needs to specify the longitudinal axis orientation to obtain at least one standard abdominal section, eliminating the need to manually extract each standard abdominal section.

[0082] In step S240, information on the target characteristic structure of the fetus in the second and third trimester is extracted from the three-dimensional ultrasound data, where the target characteristic structure includes at least one of the following: gastric bubble, spine, liver, umbilical vein, descending aorta, inferior vena cava, umbilical cord insertion, umbilical cord, anterior abdominal wall, bladder, legs, umbilical artery, and gallbladder.

[0083] The above-mentioned target characteristic structures of the second and third trimesters are specific target characteristic structures of the second and third trimesters of pregnancy and are also the landmark structures for obtaining specific standard abdominal sections. Therefore, it is first necessary to analyze the information of these target characteristic structures of the second and third trimesters, such as obtaining their positions and volumes. Among them, the region where the target characteristic structures of the second and third trimesters are located can be detected in multiple two-dimensional section images of the three-dimensional ultrasound data, and the segmentation results of the target characteristic structures of the second and third trimesters on the multiple two-dimensional section images can be combined to obtain the three-dimensional segmentation results of the target characteristic structures of the second and third trimesters in the three-dimensional ultrasound images; or the three-dimensional ultrasound data can be directly segmented to obtain the three-dimensional segmentation results of the target characteristic structures of the second and third trimesters.

[0084] Similar to the spinal region segmentation method described above, a pre-trained target segmentation network can be used to extract target structures from multiple 2D sections of 3D ultrasound data. Machine learning-based segmentation methods require the construction of a database of ultrasound images, each labeled with information about target structures from various standard abdominal sections. Specifically, this information includes the presence, type, and location of target structures.

[0085] The deep learning-based object segmentation method primarily involves stacking convolutional and fully connected layers to learn features and regress parameters from a pre-built database. This allows the network to directly predict the location and category of target structures in the middle and late pregnancy period after receiving an input ultrasound image. Available networks include RCNN, Fast RCNN, Faster-RCNN, YOL%, SSD, Retina-Net, and others. To train the network, two-dimensional slice images of 3D ultrasound data from the database are first acquired. Each 2D slice image is assigned a label containing the location and category of the target structure. Finally, a segmentation model for the target structure is trained using the 2D slice images and corresponding labels. Once the segmentation model is trained, the 2D slice images of the 3D ultrasound data to be segmented are simply fed into the trained model to determine the location and category of each target structure.

[0086] When directly performing three-dimensional segmentation on three-dimensional ultrasound data, a three-dimensional convolutional neural network can be used to perform the segmentation to obtain the three-dimensional region where the target characteristic structure of the second and third trimester is located. Specifically, a three-dimensional ultrasound database is pre-constructed, in which each three-dimensional ultrasound data is labeled with information such as the location and type corresponding to the target characteristic structure of the second and third trimester. The three-dimensional convolutional neural network is then trained based on the pre-constructed database. Based on the three-dimensional convolutional neural network, there is no need to perform cross-section processing on the three-dimensional ultrasound data. Instead, the three-dimensional ultrasound data can be directly input into the trained model to obtain information about the target characteristic structure of the second and third trimester.

[0087] In addition, at least one candidate feature structure can be identified in the three-dimensional ultrasound data based on the morphological characteristics of the target feature structure in the second and third trimesters. A classifier can then be used to determine the category of the candidate feature structure, and the target feature structure in the second and third trimesters can be determined from the candidate feature structures based on its category. For example, traditional image processing methods can be used to perform threshold segmentation and morphological operations on low-echo structures such as the transparent bladder, gastric alveoli, gallbladder, and umbilical vein to obtain the locations of these low-echo structures. Classifiers such as KNN, SVM, random forest, or neural networks can then be used to determine the categories of these locations to determine the locations of the target feature structures in the second and third trimesters.

[0088] In step S250, at least one standard abdominal section of the mid- to late-pregnancy fetus is extracted from the three-dimensional ultrasound data based on the long axis direction of the body of the mid- to late-pregnancy fetus and information about the target characteristic structure of the mid- to late-pregnancy fetus.

[0089] In one embodiment, a section that forms a preset angle with respect to the long axis of the mid- to late-pregnancy fetal body region and whose overlap with the target characteristic structure of the mid- to late-pregnancy fetus meets preset requirements can be determined as the standard abdominal section. When the standard abdominal section is a transverse abdominal section, the preset angle can be approximately or equal to 90°, i.e., the standard abdominal section is perpendicular to the long axis. Figure 3 It shows the three-dimensional ultrasound image of a fetus in the second and third trimesters, the long axis direction, and the direction of the standard abdominal section perpendicular to the long axis direction.

[0090] Since the target characteristic structure of the middle and late pregnancy has a certain volume, there may be multiple sections that are at a preset angle to the long axis and pass through the area where the target characteristic structure of the middle and late pregnancy is located. Therefore, it is necessary to select a section whose overlapping area with the target characteristic structure of the middle and late pregnancy meets the preset requirements as the standard abdominal section. Optionally, the overlapping area with the target characteristic structure of the middle and late pregnancy that meets the preset requirements can be that the target characteristic structure of the middle and late pregnancy has the largest area on the standard abdominal section, or that the standard abdominal section passes through the center point of the target characteristic structure of the middle and late pregnancy. The standard abdominal section extracted in this way can provide more information and is conducive to standardizing the extraction standards of the standard abdominal section between different regions, different hospitals and different doctors. In some embodiments, a section that is perpendicular to the long axis and at least partially overlaps with at least two target characteristic structures of the middle and late pregnancy can also be determined as the standard abdominal section to improve the accuracy of the extracted standard abdominal section.

[0091] For example, the abdominal section is a section perpendicular to the long axis section and at least partially overlaps with the gastric bubble region and the umbilical vein region; the umbilical cord insertion section is a section perpendicular to the long axis direction and at least partially overlaps with the umbilical cord insertion region, such as Figure 4 As shown; the gallbladder section is a section perpendicular to the long axis and at least partially overlaps with the gallbladder region; the bilateral kidney section is a section perpendicular to the long axis and at least partially overlaps with the bilateral kidney region; the bladder section is a section perpendicular to the long axis and at least partially overlaps with the bladder region and the umbilical artery regions on both sides of the bladder.

[0092] While the above describes a method for automatically acquiring standard abdominal sections, a semi-automatic detection method can also be employed. Specifically, the extraction range of the standard abdominal sections is first defined. The ultrasound imaging system then receives a user instruction to determine the extraction range for the standard abdominal sections, determines the extraction range based on the received user instruction, and extracts the standard abdominal sections within the extraction range. The user can limit the extraction range to the abdominal region of a mid- to late-pregnancy fetus to remove unnecessary interference, thereby improving the quality of the standard abdominal sections.

[0093] Exemplarily, the automatic extraction of standard abdominal sections can be performed automatically after the three-dimensional ultrasound data is acquired, or it can be performed according to a received user instruction. For example, the user can activate the function of automatically extracting standard abdominal sections by triggering a button for extracting standard abdominal sections. The button can be a virtual button set on the user interaction interface of the display, or it can be a physical button. After acquiring the three-dimensional ultrasound data, when a user instruction to extract standard abdominal sections is received, the standard abdominal sections are extracted. In some embodiments, the user can also activate the function of automatically extracting standard abdominal sections before starting to collect ultrasound data, and then the standard abdominal sections are automatically extracted after the three-dimensional ultrasound data is acquired. The standard abdominal section is an important basis for screening abdominal deformities. By observing the standard abdominal section, it can be determined whether the abdominal development of the fetus in the middle and late pregnancy is normal.

[0094] In some embodiments, the standard section to be extracted may be determined based on received user input. For example, options for standard abdominal sections such as the abdominal circumference section and the umbilical cord insertion section may be displayed on the user interface, and the standard abdominal section to be extracted may be determined based on the user's selection.

[0095] Finally, in step S260, the standard abdominal section is displayed.

[0096] The displayed standard sections may be all of the standard sections extracted in step S250, or some of them. For example, when displaying the standard sections extracted in step S250, some of them may be displayed according to the received user instructions. For example, the names or thumbnails of the standard sections may be displayed on the display interface, and corresponding standard sections may be displayed according to the user's selection.

[0097] In some embodiments, since the target characteristic structure of the mid-to-late pregnancy is detected in the three-dimensional ultrasound data in step S240, the location of the target characteristic structure of the mid-to-late pregnancy detected from the three-dimensional ultrasound data can also be displayed for the user to perform comparative analysis.

[0098] In addition, the long-axis direction determined in step S230 can also be displayed, so that the user can view the corresponding standard abdominal section in conjunction with the target direction. As an example, the target direction can be displayed simultaneously with the three-dimensional ultrasound image. For example, the long-axis direction of the fetal body region in the middle or late pregnancy can be displayed using a graphical marker such as an arrow.

[0099] In some embodiments, the names of the determined standard sections can also be displayed to facilitate the user to intuitively determine the type of standard section or select the standard section to be viewed based on the name of the standard section. The name of the standard section can be displayed synchronously with the standard section, or the names of the standard sections can be displayed on the display interface first, and when the user selects the name of a standard section, the corresponding standard section is displayed.

[0100] In summary, the ultrasound imaging method 200 for a fetus in the second and third trimester of pregnancy in the embodiment of the present application can automatically determine at least one standard abdominal section based on the long-axis direction of the body region of the fetus in the second and third trimester of pregnancy and the information of the target characteristic structure of the second and third trimester of pregnancy. There is no need for the doctor to manually extract the standard abdominal sections one by one, which greatly optimizes the workflow of prenatal examinations, effectively improves work efficiency, and can improve the stability of the quality of the obtained standard abdominal sections, thereby promoting the promotion and application of structural screening in the second and third trimester of pregnancy.

[0101] The present application also provides an ultrasound imaging system for implementing the above-mentioned ultrasound imaging method 200 for a fetus in the second and third trimesters. The ultrasound imaging system includes an ultrasound probe, a transmitting / receiving circuit, a memory, a processor, and a display. The memory stores a computer program executed by the processor. When the computer program is executed by the processor, the steps of the ultrasound imaging method 200 for a fetus in the second and third trimesters are executed. Figure 1 , the ultrasound imaging system can be implemented as follows Figure 1 The ultrasound imaging system 100 is shown. As described above, the ultrasound imaging system 100 may include an ultrasound probe 110, a transmitting / receiving circuit 112, a processor 114, and a display 116. The description of each component may refer to the above.

[0102] When used to implement the ultrasound imaging method 200, the transmitting / receiving circuit 112 is used to stimulate the ultrasound probe 110 to transmit ultrasound waves toward a mid- to late-pregnancy fetus and receive echoes of the ultrasound waves to obtain ultrasound echo signals. The processor 114 is used to: obtain three-dimensional ultrasound data of the mid- to late-pregnancy fetus based on the ultrasound echo signals; determine the long-axis direction of the mid- to late-pregnancy fetal body region based on the three-dimensional ultrasound data; extract information on target characteristic structures of the mid- to late-pregnancy fetus from the three-dimensional ultrasound data, where the target characteristic structures include at least one of the following: gastric bubble, spine, liver, umbilical vein, descending aorta, inferior vena cava, umbilical cord insertion, umbilical cord, anterior abdominal wall, bladder, legs, umbilical artery, and gallbladder; extract at least one standard abdominal section of the mid- to late-pregnancy fetus from the three-dimensional ultrasound data based on the long-axis direction of the mid- to late-pregnancy fetal body region and the information on the target characteristic structures. The display 116 is used to display the at least one standard abdominal section of the mid- to late-pregnancy fetus.

[0103] The above description only describes the primary functions of the various components of the ultrasound imaging system 100. For more details, see the description of the ultrasound imaging method 200 for a mid- to late-gestation fetus. The ultrasound imaging system of the present embodiment can automatically determine standard abdominal sections for a mid- to late-gestation fetus, thereby improving work efficiency and the quality of the standard abdominal sections.

[0104] Below, we will refer to Figure 5 A method for ultrasound imaging of a fetus in the second and third trimesters according to another embodiment of the present application is described. Figure 5 4 is a schematic flow chart of a method 500 for ultrasound imaging of a fetus in the second and third trimesters of pregnancy according to an embodiment of the present application.

[0105] like Figure 5 As shown, the ultrasound imaging method 500 for a fetus in the second and third trimesters includes the following steps:

[0106] In step S510, an ultrasonic wave is transmitted to a fetus in the second or third trimester, and an echo of the ultrasonic wave is received to obtain an ultrasonic echo signal;

[0107] In step S520, three-dimensional ultrasound data of the mid- to late-gestation fetus is obtained based on the ultrasound echo signal;

[0108] In step S530, a target direction of the body region of the mid- to late-gestation fetus is determined based on the three-dimensional ultrasound data;

[0109] In step S540, information on the target characteristic structure of the fetus in the middle and late pregnancy is extracted from the three-dimensional ultrasound data;

[0110] In step S550, at least one standard abdominal section of the mid- to late-pregnancy fetus is extracted from the three-dimensional ultrasound data according to the target direction and the information of the mid- to late-pregnancy target characteristic structure;

[0111] In step S560, the at least one standard abdominal section is displayed.

[0112] The steps S510 and S520 in the ultrasound imaging method 500 for a fetus in the second and third trimesters of the present invention are the same as those in the reference method. Figure 2 Step S210 and step S220 in the described ultrasound imaging method 200 are substantially similar. For the sake of brevity, the same details are not repeated here. The following mainly describes in detail the method of determining the standard section based on the three-dimensional ultrasound data in method 500.

[0113] The ultrasound imaging method 500 of a mid- to late-gestation fetus in this embodiment differs from the ultrasound imaging method 200 described above primarily in that the target direction determined based on the three-dimensional ultrasound data is not limited to the long axis of the body region of the mid- to late-gestation fetus. For example, the target direction may include the up-down direction (also referred to as the long axis direction above), the front-to-back direction, and the left-to-right direction of the body region, hereinafter referred to as the first direction, the second direction, and the third direction, respectively.

[0114] In one embodiment, determining the target direction of a body region of a fetus in the middle or late pregnancy period based on three-dimensional ultrasound data includes: determining the spinal region of the fetus in the middle or late pregnancy period in the three-dimensional ultrasound data, and determining the target direction of the body region of the fetus in the middle or late pregnancy period based on the direction of the spinal region. Since the spinal region is relatively obvious in a three-dimensional ultrasound image, the target direction of the body region of the fetus in the middle or late pregnancy period can be accurately determined based on the position of the spinal region. Among them, the method for determining the spinal region may include segmenting the spinal region in multiple two-dimensional cross-sectional images of the three-dimensional ultrasound data, and integrating the segmentation results of the spinal region on the multiple two-dimensional cross-sectional images to obtain a three-dimensional segmentation result of the spine in the three-dimensional ultrasound image; or, directly performing three-dimensional segmentation on the three-dimensional ultrasound data to obtain a three-dimensional segmentation result of the spinal region. The specific details of the method for determining the spinal region in three-dimensional ultrasound data can be referred to above.

[0115] The up-down direction and the front-back direction of the fetal body region in the middle and late pregnancy period can be directly determined by the segmentation result of the spine region. Among them, determining the up-down direction of the fetal body region in the middle and late pregnancy period according to the direction of the spine region includes: determining a straight line close to the spine region, and determining the direction of the straight line as the first direction of the fetal body region in the middle and late pregnancy period, that is, the up-down direction. For example, the straight line closest to the spine region can be fitted by least squares or other methods, or the brightest straight line obtained by Hough transform, RANSAC or other methods in traditional image processing methods can be directly used as the straight line closest to the spine region.

[0116] After determining the up-down direction of the body region of a mid- to late-gestation fetus based on the segmentation results of the spine region, a second direction of the body region of the mid- to late-gestation fetus, i.e., the front-to-back direction, can be further determined based on the up-down direction. Specifically, one or more cross-sections of the body region perpendicular to the up-down direction determined above can be extracted from the three-dimensional ultrasound data of the body of the mid- to late-gestation fetus. Machine learning or traditional image processing methods can be used to detect the positions of the center points of the body regions and the spine in the cross-sections of the body regions. The direction of the line connecting the positions of the center points of the body regions and the spine is then determined as the second direction of the body region of the mid- to late-gestation fetus, i.e., the front-to-back direction, which is perpendicular to the first direction.

[0117] In another embodiment, the anterior-posterior direction of the body region can be determined directly based on the segmentation results of the spinal region, without having to determine the anterior-posterior direction based on the up-down direction of the body region. Specifically, because the spine bulges toward the back of the body, a curve close to the spine can be determined, and the convex direction of this curve can be determined as the anterior-posterior direction of the body region of the mid- to late-pregnancy fetus. The curve can be obtained by fitting an arc closest to the spine using methods such as least squares, or by directly obtaining the brightest arc obtained using traditional image processing methods.

[0118] In addition, the orientation of a fetus in the second and third trimester can be determined based on its shape. Specifically, the fetus's body region is detected from 3D ultrasound data and the target orientation is determined based on its shape. Because the up-down shape of the fetus in the second and third trimester is more distinct, while the differences in the front-to-back and left-to-right directions are smaller, this method is primarily used to determine the up-down orientation of the fetus in the second and third trimester.

[0119] Specifically, machine learning or image processing methods can be used to determine the body region of a mid- to late-pregnancy fetus in three-dimensional ultrasound data, wherein the determined body region can be a region of interest (ROI) box that surrounds the body of a mid- to late-pregnancy fetus, or a specific region range of the body of a mid- to late-pregnancy fetus can be segmented. Afterwards, the long axis of the body region is determined based on the shape of the body region, and the direction of the long axis is determined as the up-down direction of the body region of the mid- to late-pregnancy fetus. For example, the principal component analysis (PCA) method can be used to determine the long axis of the body region, or the two points with the farthest distance from each other in the above-mentioned body region can be detected, and the line between the two points is the long axis of the body region.

[0120] As for the determination of the third direction (i.e., the left-right direction) of the body region of the fetus in the middle and late pregnancy period, after determining the up-down direction and the front-back direction of the body region of the fetus in the middle and late pregnancy period by any of the above methods or any other feasible methods, the direction perpendicular to the up-down direction and the front-back direction can be determined as the left-right direction of the body region of the fetus in the middle and late pregnancy period. In addition, the left-right direction of the body region of the fetus in the middle and late pregnancy period can also be determined based on some specific target characteristic structures of the fetus in the middle and late pregnancy period. For example, the position of the symmetrical characteristic structure in the body region of the fetus in the middle and late pregnancy period can be detected in the three-dimensional ultrasound data, and the direction of the line connecting the symmetrical characteristic structures can be determined as the left-right direction of the body region of the fetus in the middle and late pregnancy period. Among them, the symmetrical characteristic structure is, for example, a characteristic structure with symmetry such as the two kidneys, two lungs, left and right ribs. Alternatively, the left and right atria of the fetus in the middle and late pregnancy period can also be detected. The direction of the line connecting the left and right atria is generally at a 45° angle to the left-right direction of the body region of the fetus in the middle and late pregnancy period. Based on this characteristic, the left and right direction of the body region of the fetus in the middle and late pregnancy period can also be determined.

[0121] In step S540, information about target characteristic structures of the fetus in the second and third trimesters is extracted from the three-dimensional ultrasound data. The target characteristic structures in the second and third trimesters include at least one of the following: gastric alveoli, spinal column, liver, umbilical vein, descending aorta, inferior vena cava, umbilical cord insertion, umbilical cord, anterior abdominal wall, bladder, legs, umbilical artery, and gallbladder.

[0122] The target characteristic structure for mid- to late-pregnancy pregnancy corresponds to the standard abdominal section to be extracted. In some embodiments, the type of standard abdominal section to be extracted is first determined, and then the target characteristic structure for mid- to late-pregnancy pregnancy pregnancy corresponding to the type of standard abdominal section is determined. Specifically, the standard abdominal sections include at least one of the following: abdominal circumference section, umbilical cord insertion section, gallbladder section, bilateral kidney cross-section, and bladder and bilateral umbilical artery section. When the standard abdominal section is the abdominal circumference section, the target characteristic structures of mid-to-late pregnancy include at least one of the following: gastric bubble, spine, liver, umbilical vein, descending aorta and inferior vena cava; when the standard abdominal section is the umbilical cord insertion section, the target characteristic structures of mid-to-late pregnancy include at least one of the following: umbilical cord insertion, umbilical cord, spine, anterior abdominal wall and descending aorta; when the standard abdominal section is the bladder and double umbilical artery section, the target characteristic structures of mid-to-late pregnancy include at least one of the following: bladder and umbilical artery; when the standard abdominal section is the gallbladder section, the target characteristic structures of mid-to-late pregnancy include gallbladder and spine; when the standard abdominal section is the bilateral kidney cross-section, the target characteristic structures of mid-to-late pregnancy include bilateral kidney and spine.

[0123] In step S540, any suitable image detection or segmentation method can be used to determine the location of the target characteristic structure of the second trimester. For example, a traditional machine learning method or a deep learning method can be used to train a machine learning model for the target characteristic structure of the second trimester corresponding to each standard abdominal section, so as to determine the location of the target characteristic structure. Before model training, a second trimester fetal ultrasound database is established in advance, and each three-dimensional ultrasound data in the database is marked with the location of the target characteristic structure of the second trimester of the fetus, such as its region of interest box or specific region range. Then, a traditional machine learning method or a deep learning method is used to learn an optimal mapping function for obtaining the region of interest box or specific region range of the target characteristic structure of the second trimester of the fetus from the three-dimensional ultrasound data of the second trimester of the fetus, so as to realize the detection or segmentation of the target characteristic structure of the second trimester of the fetus.

[0124] In step S550, based on the target direction determined in step S530 and the information of the target characteristic structure of the second trimester determined in step S540, at least one standard abdominal section of the second trimester fetus is extracted from the three-dimensional ultrasound data. Specifically, a section that is at a preset angle to the target direction and whose overlapping area with the target characteristic structure of the second trimester meets preset requirements can be determined as a standard abdominal section. Exemplarily, the overlapping area with the target characteristic structure of the second trimester meeting the preset requirements includes: the target characteristic structure of the second trimester has the largest area on the standard abdominal section, or the standard abdominal section passes through the center point of the target characteristic structure of the second trimester.

[0125] The preset angles are different for different target directions. For example, if a cross-section of a body region, such as the abdominal circumference section, the umbilical cord insertion section, or the kidney cross-section, is parallel or approximately parallel to the anterior-posterior or lateral direction of the body region, the preset angle between the cross-section and the anterior-posterior or lateral direction is approximately 0°; if a cross-section is perpendicular or approximately perpendicular to the vertical direction of the body region, the preset angle between the cross-section and the vertical direction is approximately 90°.

[0126] In step S560, the displayed standard abdominal sections may be some or all of the standard sections extracted in step S550. In addition to displaying the extracted standard sections, the names of the standard abdominal sections may also be displayed. Furthermore, target characteristic structures of the second and third trimesters detected from the 3D ultrasound data may also be displayed. These target characteristic structures may be displayed in the 3D ultrasound image of the second and third trimester fetus, for example, by displaying an ROI box enclosing the target characteristic structure or displaying its outline.

[0127] The present application also provides an ultrasound imaging system for implementing the above-mentioned ultrasound imaging method 500 for a fetus in the second or third trimester. The ultrasound imaging system includes an ultrasound probe, a transmitting / receiving circuit, a memory, a processor, and a display. The memory stores a computer program executed by the processor. When the computer program is executed by the processor, the steps of the ultrasound imaging method 500 for a fetus in the second or third trimester are executed. Figure 1 , the ultrasound imaging system can be implemented as follows Figure 1 The ultrasound imaging system 100 is shown. As described above, the ultrasound imaging system 100 may include an ultrasound probe 110, a transmitting / receiving circuit 112, a processor 114, and a display 116. The description of each component may refer to the above.

[0128] When used to implement the ultrasound imaging method 500, the transmitting / receiving circuit 112 is used to stimulate the ultrasound probe 110 to transmit ultrasound waves to a mid- to late-pregnancy fetus and receive echoes of the ultrasound waves to obtain ultrasound echo signals; the processor 114 is used to: determine a target direction of a body region of the mid- to late-pregnancy fetus based on the three-dimensional ultrasound data; extract information on the target characteristic structure of the mid- to late-pregnancy fetus from the three-dimensional ultrasound data; and extract at least one standard abdominal section of the mid- to late-pregnancy fetus from the three-dimensional ultrasound data based on the target direction and the information on the target characteristic structure; and the display 116 is used to display the at least one standard abdominal section.

[0129] The above only describes the main functions of the components of the ultrasound imaging system 100. For more details, please refer to the relevant description of the ultrasound imaging method 500 for a fetus in the middle and late pregnancy.

[0130] The ultrasound imaging method 500 and ultrasound imaging system of the mid- to late-pregnancy fetus in the embodiment of the present application automatically determine the standard abdominal sections of the mid- to late-pregnancy fetus based on the target direction and target characteristic structure of the mid- to late-pregnancy fetus, eliminating the need for doctors to manually extract standard abdominal sections one by one. This greatly optimizes the workflow of prenatal examinations, effectively improves work efficiency, and can improve the stability of the quality of the obtained standard abdominal sections, thereby promoting the promotion and application of mid- to late-pregnancy structural screening.

[0131] Below, we will refer to Figure 6 A method for ultrasound imaging of a fetus in the second and third trimesters according to another embodiment of the present application is described. Figure 6 6 is a schematic flow chart of a method 600 for ultrasound imaging of a fetus in the second and third trimesters of pregnancy according to an embodiment of the present application.

[0132] like Figure 6 As shown, a method 600 for ultrasound imaging of a fetus in the second and third trimesters of pregnancy according to one embodiment of the present application includes the following steps:

[0133] In step S610, an ultrasonic wave is transmitted to a fetus in the second or third trimester, and an echo of the ultrasonic wave is received to obtain an ultrasonic echo signal;

[0134] In step S620, three-dimensional ultrasound data of the mid- to late-gestation fetus is obtained based on the ultrasound echo signal;

[0135] In step S630, at least two different target characteristic structures of the second and third trimester are detected from the three-dimensional ultrasound data, wherein the at least two different target characteristic structures of the second and third trimester include at least two of the following: a stomach bubble, a spine, a liver, an umbilical vein, a descending aorta, an inferior vena cava, an umbilical cord insertion, an umbilical cord, anterior abdominal wall, a bladder, both legs, an umbilical artery, and a gallbladder;

[0136] In step S640, at least one section that at least partially overlaps with each of the at least two different mid- to late-pregnancy target characteristic structure regions is determined as at least one standard abdominal section of the mid- to late-pregnancy fetus;

[0137] In step S650, the at least one standard abdominal section is displayed.

[0138] The steps S610 and S620 in the ultrasound imaging method 600 for a fetus in the second and third trimesters of the present invention are the same as those in the reference method. Figure 2 Step S210 and step S220 in the described ultrasound imaging method 200 are substantially similar. For the sake of brevity, the same details are not repeated here. The following mainly describes in detail the method of determining the standard section based on the three-dimensional ultrasound data in method 600.

[0139] In step S630, detecting at least two different regions of target characteristic structures of mid- to late pregnancy from the three-dimensional ultrasound data includes: obtaining the type of standard abdominal section; and detecting at least two different regions of target characteristic structures of mid- to late pregnancy corresponding to the type of standard abdominal section from the three-dimensional ultrasound data.

[0140] Exemplarily, the standard abdominal sections of a fetus in the second and third trimesters include at least one of the following: an abdominal circumference section, an umbilical cord insertion section, a gallbladder section, a cross-sectional section of both kidneys, and a section of the bladder and both umbilical arteries. When the standard abdominal section is the abdominal circumference section, the target characteristic structures of the second and third trimesters that need to be detected include at least one of the following: the gastric bubble, the spine, the liver, the umbilical vein, the descending aorta, and the inferior vena cava; when the standard abdominal section is the umbilical cord insertion section, the target characteristic structures of the second and third trimesters that need to be detected include at least one of the following: the umbilical cord insertion, the umbilical cord, the spine, the anterior abdominal wall, and the descending aorta; when the standard abdominal section is the bladder and both umbilical arteries section, the target characteristic structures of the second and third trimesters that need to be detected include at least one of the bladder and the umbilical arteries; when the standard abdominal section is the gallbladder section, the target characteristic structures of the second and third trimesters that need to be detected include at least one of the gallbladder and the spine; when the standard abdominal section is the cross-sectional section of both kidneys, the target characteristic structures of the second and third trimesters that need to be detected include at least one of the kidneys and the spine.

[0141] In step S630, any suitable image detection or segmentation method can be used to determine the location of the target characteristic structure of the second trimester. For example, a traditional machine learning method or a deep learning method can be used to train a machine learning model for the characteristic structure corresponding to each standard section to determine the location of the characteristic structure. Before model training, a second trimester fetal ultrasound database is established in advance. Each three-dimensional ultrasound data in the database is marked with the location of the target characteristic structure of the second trimester of the fetus, such as its region of interest box (ROI) or specific area range. Then, a traditional machine learning method or a deep learning method is used to learn an optimal mapping function for obtaining the region of interest box (ROI) or specific area range of the target characteristic structure of the second trimester of the fetus from the three-dimensional ultrasound data of the second trimester of the fetus, so as to realize the detection or segmentation of the target characteristic structure of the second trimester of the fetus.

[0142] In step S640, for the standard abdominal section to be extracted, the type of the standard abdominal section is first obtained, the target characteristic structure of the middle and late pregnancy corresponding to the type of the standard abdominal section is determined, and the regions of at least two different target characteristic structures of the middle and late pregnancy corresponding to the type of the standard abdominal section are detected from the three-dimensional ultrasound data. Thereafter, a section that at least partially overlaps with the at least two different target characteristic structures of the middle and late pregnancy is determined as the detection result of the standard abdominal section. Specifically, a section that substantially overlaps with the regions of each of the at least two different target characteristic structures of the middle and late pregnancy can be determined as the standard section. Exemplarily, substantially overlapping with the regions of each of the at least two different target characteristic structures of the middle and late pregnancy can be achieved by passing through the center point of the at least two target characteristic structures of the middle and late pregnancy, or by having the largest cross-sectional area on the extracted standard abdominal section, etc. Optionally, in order to make the obtained standard section more accurate, a section that at least partially overlaps with three or more different target characteristic structures of mid- to late pregnancy may be determined as the detection result of the abdominal standard section.

[0143] In step S650, the displayed standard abdominal sections may be some or all of the standard abdominal sections extracted in step S640. In addition to displaying the extracted standard abdominal sections, the names of the standard abdominal sections may also be displayed. Furthermore, target characteristic structures of the second and third trimesters detected from the 3D ultrasound data may also be displayed. These target characteristic structures may be displayed in the 3D ultrasound image of the second and third trimester fetus, for example, by displaying an ROI box enclosing the target characteristic structure or displaying its outline.

[0144] The present application also provides an ultrasound imaging system for implementing the above-mentioned ultrasound imaging method 600 for a fetus in the second and third trimesters. The ultrasound imaging system includes an ultrasound probe, a transmitting / receiving circuit, a memory, a processor, and a display. The memory stores a computer program executed by the processor. When the computer program is executed by the processor, the steps of the ultrasound imaging method 600 for a fetus in the second and third trimesters are executed. Figure 1 , the ultrasound imaging system can be implemented as follows Figure 1 The ultrasound imaging system 100 is shown. As described above, the ultrasound imaging system 100 may include an ultrasound probe 110, a transmitting / receiving circuit 112, a processor 114, and a display 116. The description of each component may refer to the above.

[0145] When used to implement the ultrasound imaging method 600, the transmitting / receiving circuit 112 is used to stimulate the ultrasound probe 110 to transmit ultrasound waves toward a mid- to late-pregnancy fetus and receive echoes of the ultrasound waves to obtain ultrasound echo signals. The processor 114 is used to obtain three-dimensional ultrasound data of the mid- to late-pregnancy fetus based on the ultrasound echo signals. In step S630, at least two different target characteristic structures of the mid- to late-pregnancy fetus are detected from the three-dimensional ultrasound data. The at least two different target characteristic structures of the mid- to late-pregnancy fetus include at least two of the following: gastric alveoli, spinal column, liver, umbilical vein, descending aorta, inferior vena cava, umbilical cord insertion, umbilical cord, anterior abdominal wall, bladder, legs, umbilical artery, and gallbladder. In step S640, at least one section that at least partially overlaps with each of the at least two different target characteristic structures of the mid- to late-pregnancy fetus is determined as at least one standard abdominal section of the mid- to late-pregnancy fetus. The display 116 is used to display the at least one standard abdominal section.

[0146] The above only describes the main functions of the components of the ultrasound imaging system 100. For more details, please refer to the relevant description of the ultrasound imaging method 600 for a fetus in the middle and late pregnancy period.

[0147] The ultrasound imaging method 600 and ultrasound imaging system of the mid- to late-pregnancy fetus in the embodiment of the present application automatically determine the standard abdominal sections of the mid- to late-pregnancy fetus based on at least two mid- to late-pregnancy target characteristic structures of the mid- to late-pregnancy fetus, eliminating the need for doctors to manually extract standard abdominal sections one by one. This greatly optimizes the workflow of prenatal examinations, effectively improves work efficiency, and can improve the stability of the quality of the obtained standard abdominal sections, thereby promoting the promotion and application of mid- to late-pregnancy structural screening.

[0148] In addition, according to an embodiment of the present application, a computer storage medium is also provided, on which program instructions are stored. When the program instructions are executed by a computer or processor, they are used to execute the corresponding steps of method 200, method 500, or method 600 of the embodiment of the present application. The storage medium may include, for example, a memory card of a smartphone, a storage component of a tablet computer, a hard disk of a personal computer, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disk read-only memory (CD-ROM), a USB memory, or any combination of the above storage media. The computer-readable storage medium may be any combination of one or more computer-readable storage media.

[0149] In addition, according to an embodiment of the present application, a computer program is also provided, which can be stored on a cloud or local storage medium. When the computer program is executed by a computer or processor, it is used to perform the corresponding steps of the ultrasound imaging method for a fetus in the second and third trimesters of the present application.

[0150] Based on the above description, the ultrasound imaging method and ultrasound imaging system of the mid- to late-pregnancy fetus according to the embodiments of the present application can automatically determine the standard abdominal sections of the mid- to late-pregnancy fetus based on the three-dimensional ultrasound data collected in a single time, without the need for the doctor to manually extract the standard abdominal sections one by one, which greatly optimizes the workflow of prenatal examinations, effectively improves work efficiency, and can improve the stability of the quality of the obtained standard abdominal sections, thereby promoting the promotion and application of structural screening in mid- to late-pregnancy.

[0151] Although example embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above example embodiments are merely illustrative and are not intended to limit the scope of the present application. Various changes and modifications may be made therein by those skilled in the art without departing from the scope and spirit of the present application. All such changes and modifications are intended to be included within the scope of the present application as required by the appended claims.

[0152] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0153] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units described is merely a logical function division. In actual implementation, other division methods may be used, such as combining or integrating multiple units or components into another device, or ignoring or not performing some features.

[0154] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known methods, structures, and techniques are not shown in detail so as not to obscure the understanding of this description.

[0155] Similarly, it should be understood that in order to streamline the present application and aid in understanding one or more of the various inventive aspects, in the description of the exemplary embodiments of the present application, the various features of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. However, this approach of the present application should not be interpreted as reflecting the intention that the application claimed for protection requires more features than those explicitly recited in each claim. More precisely, as reflected in the corresponding claims, the inventive point is that the corresponding technical problem can be solved with fewer features than all the features of a single disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into the detailed description, with each claim itself serving as a separate embodiment of the present application.

[0156] It will be understood by those skilled in the art that, except where mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or apparatus disclosed herein may be combined in any combination. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature providing the same, equivalent, or similar purpose.

[0157] Furthermore, those skilled in the art will appreciate that although some embodiments described herein include certain features included in other embodiments but not other features, combinations of features from different embodiments are intended to be within the scope of this application and to form different embodiments. For example, in the claims, any of the claimed embodiments may be used in any combination.

[0158] The various component embodiments of the present application can be implemented in hardware, or in a software module running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all of the functions of some modules according to the embodiments of the present application. The application can also be implemented as a part or all of a device program (e.g., a computer program and a computer program product) for performing the method described herein. Such a program implementing the present application can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0159] It should be noted that the above embodiments illustrate rather than limit the present application, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbols placed between brackets should not be construed as limiting the claims. The present application may be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In a unit claim 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 may be interpreted as names.

[0160] The above description is merely a specific embodiment or illustration of a specific embodiment of the present application, and the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. The scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A method for ultrasound imaging of a fetus in the second and third trimesters, characterized in that: The method comprises: transmitting ultrasound to a fetus in the second or third trimester and receiving an echo of the ultrasound to obtain an ultrasound echo signal; obtaining three-dimensional ultrasound data of the mid- to late-gestation fetus based on the ultrasound echo signal; determining the long axis direction of the body region of the mid- to late-gestation fetus based on the three-dimensional ultrasound data, wherein the long axis direction is consistent with the direction of the spine; Extracting information of target characteristic structures of the fetus in the second and third trimesters from the three-dimensional ultrasound data, wherein the target characteristic structures in the second and third trimesters include at least one of the following: gastric bubble, spine, liver, umbilical vein, descending aorta, inferior vena cava, umbilical cord insertion, umbilical cord, anterior abdominal wall, bladder, legs, umbilical artery, gallbladder, and kidneys; Extracting at least one standard abdominal section of the mid- to late-pregnancy fetus from the three-dimensional ultrasound data based on the long-axis direction of the mid- to late-pregnancy fetal body region and information about the mid- to late-pregnancy target characteristic structure, wherein a section that forms a preset angle with the long-axis direction of the mid- to late-pregnancy fetal body region and whose overlapping area with the mid- to late-pregnancy target characteristic structure meets preset requirements is determined as the standard abdominal section; wherein the overlapping area with the mid- to late-pregnancy target characteristic structure meeting the preset requirements includes: the mid- to late-pregnancy target characteristic structure having a maximum area on the standard abdominal section, or the standard abdominal section passing through the center point of the mid- to late-pregnancy target characteristic structure; The at least one standard abdominal section is displayed.

2. The method according to claim 1, characterized in that The standard abdominal sections include at least one of the following: abdominal circumference section, umbilical cord insertion section, gallbladder section, bilateral kidney cross-section, and bladder and bilateral umbilical artery section.

3. The method according to claim 2, characterized in that When the standard abdominal section is a circumferential section, the target characteristic structures of mid- to late pregnancy include at least one of the following: gastric bubble, spine, liver, umbilical vein, descending aorta and inferior vena cava; When the standard abdominal section is the umbilical cord insertion section, the target characteristic structures of the second and third trimesters include at least one of the following: the umbilical cord insertion, the umbilical cord, the spine, the anterior abdominal wall, and the descending aorta; When the standard abdominal section is the bladder and double umbilical artery section, the target characteristic structure of mid- to late pregnancy includes at least one of the following: bladder, umbilical artery; When the standard abdominal section is a gallbladder section, the target characteristic structures of mid- to late pregnancy include the gallbladder and the spine; When the standard abdominal section is a transverse section of both kidneys, the target characteristic structures of mid- to late pregnancy include both kidneys and the spine.

4. The method according to claim 1, wherein Determining the long axis direction of the body region of the mid- to late-gestation fetus according to the three-dimensional ultrasound data includes: determining a spinal region of the second to third trimester fetus in the three-dimensional ultrasound data; The long axis direction of the body region of the mid- to late-gestation fetus is determined according to the direction of the spinal column region.

5. The method according to claim 4, characterized in that Determining the spinal region of the mid- to late-gestation fetus in the three-dimensional ultrasound data includes: Segmenting the spinal region in a plurality of two-dimensional cross-sectional images of the three-dimensional ultrasound data; The segmentation results of the spinal region on the plurality of two-dimensional section images are integrated to obtain a three-dimensional segmentation result of the spinal region in the three-dimensional ultrasound data.

6. The method according to claim 5, characterized in that The multiple two-dimensional slice images of the three-dimensional ultrasound data are all two-dimensional slice images in the three-dimensional ultrasound data, or, The multiple two-dimensional sections of the three-dimensional ultrasound data are sampled images obtained by sampling the three-dimensional ultrasound data according to preset rules. The integrated segmentation results of the spinal region on the multiple two-dimensional sections include: performing three-dimensional interpolation on the segmentation results of the sampled images to obtain a three-dimensional segmentation result of the spinal region.

7. The method according to claim 4, characterized in that Determining the spinal region of the mid- to late-gestation fetus in the three-dimensional ultrasound data includes: The three-dimensional ultrasound data is segmented in three dimensions to obtain a three-dimensional segmentation result of the spinal column region.

8. The method according to claim 1, characterized in that Determining the long axis direction of the body region of the mid- to late-gestation fetus according to the three-dimensional ultrasound data includes: determining a body region of the second to third trimester fetus in the three-dimensional ultrasound data; The direction of the long axis of the body region is determined as the direction of the long axis of the body region of the mid- to late-gestation fetus.

9. The method according to claim 8, characterized in that Determining the body region of the mid- to late-gestation fetus in the three-dimensional ultrasound data includes: Segmenting the body region in a plurality of two-dimensional slice images of the three-dimensional ultrasound data; The segmentation results of the body region on the plurality of the two-dimensional section images are integrated to obtain a three-dimensional segmentation result of the body region in the three-dimensional ultrasound data.

10. The method according to claim 8, characterized in that Determining the body region of the mid- to late-gestation fetus in the three-dimensional ultrasound data includes: The three-dimensional ultrasound data is subjected to three-dimensional segmentation to obtain a three-dimensional segmentation result of the body region.

11. The method according to claim 1, wherein Determining the long axis direction of the body region of the mid- to late-gestation fetus according to the three-dimensional ultrasound data includes: A user instruction for determining the long-axis direction is received, and the long-axis direction of the body region of the mid- to late-gestation fetus is determined according to the user instruction.

12. The method according to claim 1, characterized in that Extracting information of the target characteristic structure of the mid- to late-gestation fetus from the three-dimensional ultrasound data includes: Extracting the mid- to late-pregnancy target feature structure from the three-dimensional ultrasound data using a pre-trained target detection network; Alternatively, at least one candidate feature structure is determined in the three-dimensional ultrasound data based on the morphological characteristics of the target feature structure of mid-to-late pregnancy, a classifier is used to determine the category of the candidate feature structure, and the target feature structure of mid-to-late pregnancy is determined in the candidate feature structures based on the category of the candidate feature structure.

13. The method according to claim 1, wherein The method further includes: receiving a user instruction for determining an extraction range of the standard abdominal section, determining the extraction range according to the user instruction, and extracting the standard abdominal section within the extraction range.

14. The method according to claim 1, wherein The method further includes at least one of the following: displaying the location of the target characteristic structure of mid- to late pregnancy in the standard abdominal section, and displaying the long axis direction.

15. The method according to claim 1, wherein The preset angle is 90°.

16. An ultrasonic imaging system, characterized in that: The invention comprises an ultrasound probe, a transmitting / receiving circuit, a memory, a processor and a display, wherein the memory stores a computer program to be run by the processor, and when the computer program is run by the processor, the steps of the ultrasound imaging method for a mid- to late-gestation fetus according to any one of claims 1 to 15 are executed.

Images