Ultrasonic imaging method and ultrasonic imaging system for early pregnancy fetuses

Abstract

An ultrasonic imaging method (200) and an ultrasonic imaging system (100) for an early pregnancy fetus, the ultrasonic imaging method (200) for an early pregnancy fetus comprising: emitting ultrasonic waves to an early pregnancy fetus, receiving echoes of the ultrasonic waves to obtain an ultrasonic echo signal (S210); obtaining three-dimensional ultrasonic data of the early pregnancy fetus based on the ultrasonic echo signal (S220); determining the direction of the target area of the early pregnancy fetus according to the three-dimensional ultrasonic data (S230); according to the direction of the target region, extracting at least one standard section corresponding to the target region from the three-dimensional ultrasound data (S240); and displaying the at least one standard section (S250). According to the ultrasonic imaging method (200) and the ultrasonic imaging system (100) for the early pregnancy fetus, the standard section of the early pregnancy fetus is automatically extracted according to the three-dimensional ultrasonic data acquired at a single time, a doctor does not need to manually extract the standard section one by one, and the efficiency of extracting the standard section and the quality of the extracted standard section are improved.

Description

[0001] Divisional application information This invention patent application is a divisional application of the invention patent application filed on November 16, 2020, with application number 202080105099.5, and entitled "Ultrasound Imaging Method and Ultrasound Imaging System for Early Pregnancy Fetus". Technical Field

[0002] This application relates to the field of ultrasound imaging technology, and more specifically to an ultrasound imaging method and system for early pregnancy fetuses. Background Technology

[0003] Ultrasound examinations are widely used in clinical practice due to their safety, convenience, lack of radiation, and low cost, becoming one of the main auxiliary tools for doctors to diagnose diseases. Prenatal ultrasound, as the most important imaging examination in prenatal care, provides crucial imaging evidence for measuring fetal growth and development and screening for structural abnormalities. Prenatal ultrasound examinations are now a mandatory examination in early, mid, and late pregnancy.

[0004] In clinical practice, fetal structural examination and malformation screening during early pregnancy is a current trend and research hotspot. Early pregnancy fetal structural screening can detect lethal malformations as early as possible, providing pregnant women with the opportunity to terminate pregnancy as soon as possible, minimizing physical and psychological harm, and has significant clinical importance and value. However, early pregnancy fetal structural abnormality screening involves numerous sections, each with different requirements, and obtaining these sections is quite cumbersome. Furthermore, the quality of these sections is greatly affected by the doctor's experience and technique. Summary of the Invention

[0005] The summary section introduces a series of simplified concepts, which will be further explained in detail in the detailed description section. The summary section of this invention is not intended to limit the key features and essential technical features of the claimed technical solution, nor is it intended to determine the scope of protection of the claimed technical solution.

[0006] The first aspect of this application provides an ultrasound imaging method for a fetus in early pregnancy, the method comprising: Ultrasound waves are emitted towards the fetus in early pregnancy, and the echoes of the ultrasound waves are received to obtain ultrasound echo signals. Three-dimensional ultrasound data of the fetus in early pregnancy are obtained based on the ultrasound echo signal. The orientation of the target region of the fetus in early pregnancy is determined based on the three-dimensional ultrasound data. Based on the orientation of the target region, at least one standard section corresponding to the target region is extracted from the three-dimensional ultrasound data; Display the at least one standard cross-section.

[0007] A second aspect of this application provides an ultrasound imaging method for a fetus in early pregnancy, the method comprising: Ultrasound waves are emitted towards the fetus in early pregnancy, and the echoes of the ultrasound waves are received to obtain ultrasound echo signals. Three-dimensional ultrasound data of the fetus in early pregnancy are obtained based on the ultrasound echo signals. Detect regions of at least two distinct early pregnancy target features from the three-dimensional ultrasound data; Determine at least one cross section that at least partially overlaps with the region of each of the at least two different early pregnancy target feature structures, as at least one standard cross section of the early pregnancy fetus; Display the at least one standard cross-section.

[0008] A third aspect of this application provides an ultrasound imaging method for a fetus in early pregnancy, the method comprising: Ultrasound waves are emitted towards the fetus in early pregnancy, and the echoes of the ultrasound waves are received to obtain ultrasound echo signals. Three-dimensional ultrasound data of the fetus in early pregnancy are obtained based on the ultrasound echo signals. The three-dimensional ultrasound data is matched with a pre-configured ultrasound data template of early pregnancy standard sections, and the target standard section in the three-dimensional ultrasound data is determined according to the matching result. The early pregnancy standard section includes at least one of the following: lateral ventricle level transverse section, biparietal diameter section, head and neck midsagittal section, thoracic diameter section, abdominal circumference section, abdominal wall umbilical cord insertion site section, bladder section, spinal longitudinal axis section, trunk long axis section, and parietal-rump diameter section. Display the target standard cross-section.

[0009] A fourth aspect of this application provides an ultrasound imaging method for a fetus in early pregnancy, the method comprising: Ultrasound waves are emitted towards the fetus in early pregnancy, and the echoes of the ultrasound waves are received to obtain ultrasound echo signals. Three-dimensional ultrasound data of the fetus in early pregnancy are obtained based on the ultrasound echo signal. Based on the three-dimensional ultrasound data, image features of the target region of the three-dimensional ultrasound data are extracted; The normal direction of the target standard section and the position information of the preset points on the target standard section are determined based on the image features of the target region. The target standard section is determined based on the normal direction of the target standard section and the position information of the preset points on the target standard section; Display the target standard cross-section.

[0010] The fifth aspect of this application provides an ultrasound imaging method for a fetus in early pregnancy, the method comprising: Ultrasound waves are emitted towards the fetus in early pregnancy, and the echoes of the ultrasound waves are received to obtain ultrasound echo signals. Three-dimensional ultrasound data of the fetus in early pregnancy are obtained based on the ultrasound echo signal. The orientation of the target region of the fetus in early pregnancy is determined based on the three-dimensional ultrasound data. This indicates the orientation of the target area of ​​the fetus in early pregnancy.

[0011] A sixth aspect of this application provides an ultrasound imaging system, the ultrasound imaging system comprising: Ultrasonic probe; A transmitting / receiving circuit is used to excite the ultrasound probe to emit ultrasound waves toward the fetus in early pregnancy and to receive the echo of the ultrasound waves to obtain an ultrasound echo signal. Processor, used for: Three-dimensional ultrasound data of the fetus in early pregnancy are obtained based on the ultrasound echo signal. The orientation of the target region of the fetus in early pregnancy is determined based on the three-dimensional ultrasound data. Based on the orientation of the target region, at least one standard section corresponding to the target region is extracted from the three-dimensional ultrasound data; A display for showing the at least one standard cross-section.

[0012] A seventh aspect of this application provides an ultrasound imaging system, the ultrasound imaging system comprising: Ultrasonic probe; A transmitting / receiving circuit is used to excite the ultrasound probe to emit ultrasound waves toward the fetus in early pregnancy and to receive the echo of the ultrasound waves to obtain an ultrasound echo signal. Processor, used for: The at least one standard section is displayed to obtain three-dimensional ultrasound data of the fetus in early pregnancy based on the ultrasound echo signal; From the three-dimensional ultrasound data, regions of at least two distinct early pregnancy target feature structures; Determine at least one cross section that at least partially overlaps with the region of each of the at least two different early pregnancy target feature structures, as at least one standard cross section of the early pregnancy fetus; A display for showing the at least one standard cross-section.

[0013] An eighth aspect of this application provides an ultrasound imaging system, the ultrasound imaging system comprising: Ultrasonic probe; A transmitting / receiving circuit is used to excite the ultrasound probe to emit ultrasound waves toward the fetus in early pregnancy and to receive the echo of the ultrasound waves to obtain an ultrasound echo signal. Processor, used for: Three-dimensional ultrasound data of the fetus in early pregnancy are obtained based on the ultrasound echo signal. The three-dimensional ultrasound data is matched with a pre-configured ultrasound data template of early pregnancy standard sections, and the target standard section in the three-dimensional ultrasound data is determined according to the matching result. The early pregnancy standard section includes at least one of the following: lateral ventricle level transverse section, biparietal diameter section, head and neck midsagittal section, thoracic diameter section, abdominal circumference section, abdominal wall umbilical cord insertion site section, bladder section, spinal longitudinal axis section, trunk long axis section, and parietal-rump diameter section. A display for showing the target standard cross-section.

[0014] A ninth aspect of this application provides an ultrasound imaging system, the ultrasound imaging system comprising: Ultrasonic probe; A transmitting / receiving circuit is used to excite the ultrasound probe to emit ultrasound waves toward the fetus in early pregnancy and to receive the echo of the ultrasound waves to obtain an ultrasound echo signal. Processor, used for: Based on the three-dimensional ultrasound data, image features of the target region of the three-dimensional ultrasound data are extracted; The normal direction of the target standard section and the position information of the preset points on the target standard section are determined based on the image features of the target region. Three-dimensional ultrasound data of the fetus in early pregnancy are obtained based on the ultrasound echo signal. Based on the three-dimensional ultrasound data, image features of the target region of the three-dimensional ultrasound data are extracted; The normal direction of the target standard section and the position information of the preset points on the target standard section are determined based on the image features of the target region. The target standard section is determined based on the normal direction of the target standard section and the position information of the preset points on the target standard section; A display for showing the target standard cross-section.

[0015] A tenth aspect of this application provides an ultrasound imaging system, the ultrasound imaging system comprising: Ultrasonic probe; A transmitting / receiving circuit is used to excite the ultrasound probe to emit ultrasound waves toward the fetus in early pregnancy and to receive the echo of the ultrasound waves to obtain an ultrasound echo signal. Processor, used for: Three-dimensional ultrasound data of the fetus in early pregnancy are obtained based on the ultrasound echo signal. The orientation of the target region of the fetus in early pregnancy is determined based on the three-dimensional ultrasound data. A display for showing the orientation of the target area of ​​the fetus in early pregnancy.

[0016] The ultrasound imaging method and system for early pregnancy fetus according to the embodiments of this application can automatically extract standard sections of the early pregnancy fetus based on a single acquisition of three-dimensional ultrasound data, eliminating the need for doctors to manually extract standard sections one by one. This greatly optimizes the workflow of prenatal examinations, effectively improves work efficiency, and enhances the stability of the quality of the obtained standard sections, thus promoting the widespread application of early pregnancy structural screening. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] In the attached diagram: Figure 1 A schematic block diagram of an ultrasound imaging system according to an embodiment of this application is shown; Figure 2 A schematic flowchart illustrating an ultrasound imaging method for a fetus in early pregnancy according to an embodiment of the present invention is shown. Figure 3 A schematic flowchart illustrating an ultrasound imaging method for a fetus in early pregnancy according to another embodiment of the present invention; Figure 4 A schematic flowchart illustrating an ultrasound imaging method for a fetus in early pregnancy according to another embodiment of the present invention; Figure 5 A schematic flowchart illustrating an ultrasound imaging method for a fetus in early pregnancy according to yet another embodiment of the present invention is shown. Figure 6 A schematic flowchart illustrating an ultrasound imaging method for a fetus in early pregnancy according to another embodiment of the present invention is shown. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this application more apparent, exemplary embodiments according to this application will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this application, and not all embodiments of this application. It should be understood that this application is not limited to the exemplary embodiments described herein. Based on the embodiments of this application described herein, all other embodiments obtained by those skilled in the art without inventive effort should fall within the protection scope of this application.

[0020] The following description provides numerous specific details to offer a more thorough understanding of this application. However, it will be apparent to those skilled in the art that this application can be practiced without one or more of these details. In other instances, certain technical features well-known in the art have not been described to avoid confusion with this application.

[0021] It should be understood that this application can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. Rather, providing these embodiments will make the disclosure thorough and complete, and will fully convey the scope of this application to those skilled in the art.

[0022] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of this application. When used herein, the singular forms “a,” “an,” and “the” are also 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, identify the presence of the stated features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups. When used herein, the term “and / or” includes any and all combinations of the associated listed items.

[0023] To fully understand this application, a detailed structure will be presented in the following description to illustrate the technical solution proposed in this application. Optional embodiments of this application are described in detail below; however, in addition to these detailed descriptions, this application may have other implementation methods.

[0024] Below, first refer to Figure 1 An ultrasound imaging system according to an embodiment of this application is described. Figure 1 A schematic structural block diagram of an ultrasound imaging system 100 according to an embodiment of this application is shown.

[0025] 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 also include a beamforming circuit and a transmit / receive selection switch, etc.

[0026] Specifically, the ultrasound probe 110 includes multiple transducer elements. These elements can be arranged in a row to form a linear array, or in a two-dimensional matrix to form a planar array. They can also form a convex array. The transducers are used to emit ultrasonic waves based on excitation electrical signals, or to convert received ultrasonic waves into electrical signals. Therefore, each element can be used to achieve the mutual conversion between electrical pulse signals and ultrasonic waves, thereby enabling the emission of ultrasonic waves to the target area of ​​the object being measured, and also to receive ultrasonic wave echoes reflected back from the tissue. During ultrasound imaging, the transmission and reception sequences can be used to control which transducers are used to emit ultrasonic waves and which are used to receive ultrasonic waves, or to control the transducers to be used in time-slotted manner for emitting ultrasonic waves or receiving ultrasonic wave echoes. Transducers involved in ultrasonic wave emission can be simultaneously excited by electrical signals, thus emitting ultrasonic waves simultaneously; or, transducers involved in ultrasonic beam emission can be excited by several electrical signals with a certain time interval, thus continuously emitting ultrasonic waves with a certain time interval.

[0027] The transmit / receive circuit 112 can be connected to the ultrasound probe 110 via a transmit / receive selection switch. The transmit / receive selection switch, also referred to as a transmit / receive controller, may include a transmit controller and a receive controller. The transmit controller is used to excite the ultrasound probe 110 to transmit ultrasound waves to the area where the fetus is located in early pregnancy via the transmit circuit; the receive controller is used to receive the ultrasound echoes returning from the area where the fetus is located in early pregnancy via the receive circuit through the ultrasound probe 110, thereby obtaining ultrasound echo data. Subsequently, the transmit / receive circuit 112 sends the electrical signal of the ultrasound echo to a beamforming circuit. The beamforming circuit performs focusing delay, weighting, and channel summation on the electrical signal, and then sends the processed ultrasound echo data to the processor 114.

[0028] Optionally, the processor 114 can be implemented by software, hardware, firmware, or any combination thereof. It may use circuitry, 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 foregoing circuits and / or devices, or other suitable circuits or devices, thereby enabling the processor 114 to perform the corresponding steps of the methods in the various embodiments of this specification. Furthermore, the processor 114 can control other components in the ultrasound imaging system 100 to perform desired functions.

[0029] Processor 114 processes the received ultrasound echo data to obtain three-dimensional ultrasound data of the fetus in early pregnancy. As an example, ultrasound probe 110 emits / receives ultrasound waves in a series of scanning planes, which are integrated by processor 114 according to their three-dimensional spatial relationships to achieve scanning of the fetus in three-dimensional space and reconstruction of the three-dimensional image. Finally, after performing some or all image post-processing steps such as denoising, smoothing, and enhancement, processor 114 obtains three-dimensional ultrasound data of the fetus in early pregnancy. Processor 114 can acquire three-dimensional ultrasound data of the entire fetus in early pregnancy, or it can acquire only three-dimensional ultrasound data of the fetus's head or body. Processor 114 is also used to extract standard cross-sections of the fetus in early pregnancy from the three-dimensional ultrasound data. The standard cross-sections obtained by processor 114 can be stored in memory or displayed on display 116. Furthermore, processor 114 can also draw the three-dimensional ultrasound data and display it on display 116.

[0030] The display 116 is connected to the processor 114. The display 116 can be a touch screen, an LCD screen, or a separate display device such as an LCD screen or a television, independent of the ultrasound imaging system 100. Alternatively, the display 116 can be the screen of an electronic device such as a smartphone or tablet, etc. There can be one or more displays 116. For example, the display 116 may include a main screen and a touch screen; the main screen is primarily used to display ultrasound images, and the touch screen is primarily used for human-computer interaction.

[0031] The display 116 can display the ultrasound images obtained by the processor 114. Furthermore, while displaying the ultrasound images, the display 116 can also provide a graphical user interface for human-machine interaction. One or more controlled objects can be set on the graphical interface, allowing the user to input operation commands using a human-machine interaction device to control these controlled objects and execute corresponding control operations. For example, icons can be displayed on the graphical interface, and the human-machine interaction device can be used to operate these icons to perform specific functions.

[0032] Optionally, the ultrasound imaging system 100 may also include other human-machine interface devices besides the display 116, which are connected to the processor 114. For example, the processor 114 may be connected to the human-machine interface device via an external input / output port, which may be a wireless communication module, a wired communication module, or a combination of both. The external input / output port may also be implemented based on USB, bus protocols such as CAN, and / or wired network protocols.

[0033] The human-computer interaction device may include an input device for detecting user input information. This input information may be, for example, control commands for the timing of ultrasound transmission / reception, operational input commands for drawing points, lines, or boxes on an ultrasound image, or other types of commands. The input device may include one or a combination of several of the following: a keyboard, mouse, scroll wheel, trackball, mobile input device (such as a mobile device with a touchscreen, a mobile phone, etc.), a multi-function knob, etc. The human-computer interaction device may also include an output device such as a printer.

[0034] The ultrasound imaging system 100 may also include a memory for storing instructions executed by the processor, received ultrasound echoes, ultrasound images, and so on. The memory may be a flash memory card, solid-state memory, hard disk, etc. It may be volatile and / or non-volatile memory, removable memory and / or non-removable memory, etc.

[0035] It should be understood that Figure 1 The components included in the ultrasound imaging system 100 shown are merely illustrative and may include more or fewer components. This application is not limiting in this regard.

[0036] Below, we will refer to Figure 2 This application describes an ultrasound imaging method for a fetus in early pregnancy according to embodiments of the present application. Figure 2 This is a schematic flowchart of an ultrasound imaging method 200 for a fetus in early pregnancy according to an embodiment of this application.

[0037] like Figure 2 As shown, an embodiment of the ultrasound imaging method 200 for a fetus in early pregnancy according to this application includes the following steps: First, in step S210, ultrasound waves are emitted to the fetus in early pregnancy, and the echoes of the ultrasound waves are received to obtain ultrasound echo signals.

[0038] In early pregnancy, the fetus generally refers to a fetus below 14 weeks of gestation. During early pregnancy, the fetus has grown to a certain size, most organs have differentiated and formed, and a significant number of characteristic structures can be identified through ultrasound imaging. The ultrasound imaging method provided in this application can automatically extract standard sections reflecting characteristic structural information, thereby enabling structural examination and malformation screening of the fetus in early pregnancy. Compared to ultrasound examinations in the mid-to-late stages of pregnancy, this method can provide pregnant women with relevant pregnancy information as early as possible.

[0039] For example, it can be based on Figure 1The ultrasound imaging system 100 shown acquires ultrasound images. The user moves the ultrasound probe 110 to select a suitable position and angle. The transmitting circuit in the transmitting / receiving circuit 120 sends a set of delayed-focused pulses to the ultrasound probe 110. The ultrasound probe 110 emits ultrasound waves along the 2D scanning plane towards the fetus in early pregnancy. After receiving the reflected ultrasound echo, the ultrasound probe 110 converts it into an electrical signal. The beamforming circuit performs corresponding delay and weighted summation processing on the signals obtained from multiple transmissions / receives to achieve beamforming, which is then sent to the processor 114 for subsequent signal processing.

[0040] For example, the function of automatically extracting standard sections can be automatically enabled or manually enabled by the user before performing step S210. In some embodiments, a user interface can also be provided before or after performing step S210 to allow the user to manually select the standard sections to be extracted. However, this step is optional, and in other embodiments, all standard sections referred to below can be extracted by default.

[0041] In step S220, three-dimensional ultrasound data of the fetus in early pregnancy are obtained based on the ultrasound echo signal.

[0042] Specifically, the three-dimensional spatial relationship of ultrasound echoes transmitted / received by the ultrasound probe 110 in a series of scanning planes can be integrated to achieve scanning of the fetus in early pregnancy in three-dimensional space and reconstruction of 3D images. Finally, after some or all image post-processing steps such as denoising, smoothing, and enhancement, three-dimensional ultrasound data of the fetus in early pregnancy are obtained.

[0043] This process can involve acquiring 3D ultrasound data of the entire fetus in early pregnancy, or only the fetal head region or the fetal body region, depending on the standard section to be extracted. When the standard section to be extracted includes a standard section corresponding to the fetal head region in early pregnancy, the 3D ultrasound data must include at least the 3D ultrasound data of the fetal head region. When the standard section to be extracted includes a standard section corresponding to the fetal body region in early pregnancy, the 3D ultrasound data must include at least the 3D ultrasound data of the fetal body region. When the standard section to be extracted includes a standard section corresponding to the entire fetal body region in early pregnancy, then 3D ultrasound data of the entire fetal body region in early pregnancy must be acquired.

[0044] In this embodiment, the standard section is a two-dimensional section containing key information in a three-dimensional ultrasound image. This two-dimensional section allows observation of clinically valuable physiological features. Exemplarily, the subsequently extracted standard sections include at least one of the following: parietal-rump diameter section (i.e., the whole-body midsagittal section), lateral ventricle level transverse section, biparietal diameter section (i.e., the thalamus level transverse section), NT standard section (i.e., the head and neck midsagittal section), thoracic diameter section (i.e., the four-chamber view), abdominal circumference section (i.e., the gastric bubble section), abdominal wall umbilical cord insertion site section, bladder section, spinal longitudinal axis section (i.e., the body midsagittal section), and trunk long axis section (i.e., the body coronal section). Multiple standard sections from the above can be extracted subsequently for comprehensive screening of the fetus in early pregnancy.

[0045] Among the above standard sections, the transverse section at the level of the lateral ventricle, the biparietal diameter section, and the NT standard section are standard sections corresponding to the fetal head region in early pregnancy, and the 3D ultrasound data must include at least the 3D ultrasound data of the fetal head region in early pregnancy; the thoracic diameter section, abdominal circumference section, abdominal wall umbilical cord insertion site section, bladder section, spinal longitudinal axis section, and trunk long axis section are standard sections corresponding to the fetal body region in early pregnancy, and the 3D ultrasound data must include at least the 3D ultrasound data of the fetal body region in early pregnancy; while the crown-rump diameter section is the standard section corresponding to the fetal whole body region in early pregnancy, therefore the 3D ultrasound data must include the 3D ultrasound data of the fetal whole body region in early pregnancy.

[0046] In some embodiments, after acquiring three-dimensional ultrasound data, visualization algorithms can be used to draw the three-dimensional ultrasound data to obtain a three-dimensional ultrasound image, which can then be displayed using a display device. The drawing process includes, for example, surface drawing methods or volume drawing methods, and this embodiment of the invention does not limit the scope of the method.

[0047] In step S230, the orientation of the target region of the early pregnancy fetus is determined based on the three-dimensional ultrasound data.

[0048] Determining the orientation of the target region of the fetus in early pregnancy can include determining the orientation of the fetal head region, the orientation of the fetal body region, or both. When the standard section to be extracted includes a standard section corresponding to the fetal head region, the orientation of the fetal head region is determined based on the three-dimensional ultrasound data of the fetal head region. The orientation of the head region can also be used to extract standard sections corresponding to the entire fetal body region in early pregnancy, such as the crown-rump diameter section. When the standard section to be extracted includes a standard section corresponding to the fetal body region, the orientation of the fetal body region is determined based on the three-dimensional ultrasound data of the fetal body region.

[0049] Below, several exemplary methods for determining the orientation of the fetal head region in early pregnancy are described. The orientation of the target region includes a first orientation of the fetal head region in early pregnancy, which is the left-right orientation of the head region. Since the standard cross-section corresponding to the head region is generally parallel or perpendicular to the left-right orientation of the head, and the determination of the left-right orientation of the head is relatively more accurate, determining the orientation of the fetal head region in early pregnancy can at least include determining the left-right orientation of the fetal head region in early pregnancy. However, in other embodiments, the determined orientation of the fetal head region in early pregnancy can also be other directions, such as the up-down orientation of the head region.

[0050] In one embodiment, the orientation of the fetal head region in early pregnancy can be determined using a trained machine learning model.

[0051] Before model training, a fetal ultrasound database for early pregnancy needs to be established. This database contains a large amount of early pregnancy fetal ultrasound data, with each data point labeled with the orientation of the fetal head region, or the location and orientation of the head region. The location of the head region can be the location of a region of interest (ROI), such as the position of each vertex of the ROI or the center point and size of the ROI; alternatively, the location can be the specific extent of the fetal head region. The orientation of the head region can be left-right.

[0052] After constructing the database, the ultrasound data in the database is used as training samples to train a traditional machine learning model or a deep learning model to predict the position and orientation of the fetal head region in early pregnancy. Specifically, based on the ultrasound data in the early pregnancy fetal ultrasound database, an optimal mapping function is learned to map ultrasound data to the position and orientation of the head region, minimizing the error between the head region position and orientation mapped from the early pregnancy data in the database and the actual calibrated head region position and orientation. Applying this optimal mapping function to the three-dimensional ultrasound data obtained in step S220 yields the predicted position and orientation of the head region.

[0053] Traditional machine learning methods include Support Vector Machines (SVM), logistic regression, and least squares. For traditional machine learning methods, the first step is to extract image features from ultrasound images in an early pregnancy fetal ultrasound database. These features include SIFT features, gradient features, texture features such as LBP, PCA, LDA, Haar features, HOG, and LOG features. Then, the optimal mapping function between these image features and the position and orientation of the fetal head region is learned. For deep learning models, an end-to-end neural network can be trained as the optimal mapping function to directly construct the mapping relationship between early pregnancy fetal ultrasound data and the orientation of the fetal head region.

[0054] In another embodiment, the first direction of the head region, i.e., the left-right direction, can be determined based on the symmetry of the head. Specifically, the head region of the fetus in early pregnancy is first detected in the three-dimensional ultrasound data acquired in step S220, and then the first direction of the fetal head in early pregnancy, i.e., the left-right direction, is determined based on the symmetry of the head region of the fetus in early pregnancy.

[0055] For example, machine learning methods, skull halo detection methods, or any other suitable 3D image segmentation methods can be used to detect the head of a fetus in early pregnancy from 3D ultrasound data.

[0056] In machine learning methods, a database of early pregnancy fetal ultrasound data is first established. The location of the head region is marked for each early pregnancy fetal 3D ultrasound data in the database, such as the location of the head region of interest (ROI) or the specific range of the head. Then, traditional machine learning or deep learning methods are used to learn an optimal mapping function to obtain the location of the head region of interest (ROI) or the specific range of the head from the early pregnancy fetal 3D ultrasound data, thereby realizing the detection or segmentation of the early pregnancy fetal head.

[0057] In the detection of skull halo, methods such as Hough transform and RANSAC can be used to detect the brightest, strongest gradient, or largest brightness and gradient weighted circular, elliptical, spherical, or ellipsoidal surfaces in the three-dimensional ultrasound data of the fetus in early pregnancy, so as to serve as the detection results of the fetal head region in early pregnancy.

[0058] Once the fetal head region in early pregnancy is determined, its left-right direction can be determined based on the symmetry of the head region. For example, the left and right hemispheres of the fetal head region can be determined based on the symmetry of the fetal head in early pregnancy, and the normal direction of the interface between the left and right hemispheres of the head region can be determined as the left-right direction of the head region.

[0059] The optimal left and right hemisphere regions for symmetry can be obtained through methods such as pre-defined search, gradient update, and reinforcement learning. In the pre-defined search method, multiple candidate interfaces for the left and right hemisphere regions of the head are first generated according to predetermined rules, with the candidate left and right hemisphere regions on either side of the interface. Then, each interface is evaluated to find the optimal left and right hemisphere region for symmetry. In the gradient update and reinforcement learning methods, a fixed cross-section is first chosen as the initial interface between the left and right hemisphere regions. Then, based on the gradient direction of the symmetry function or the iteration direction obtained from the reinforcement learning method, the interface between the left and right hemisphere regions of the head is iterated continuously until the symmetry of the left and right hemisphere regions reaches its optimal value.

[0060] The above methods can evaluate the symmetry of the left and right hemisphere regions based on various suitable indicators such as the absolute error, squared error, correlation function, correlation coefficient, and output results of deep learning networks such as Siamese networks and CNNs, so as to find the left and right hemisphere regions with optimal symmetry.

[0061] In another embodiment, the direction of the head region can also be determined by midsagittal plane detection. Specifically, the midsagittal plane of the fetal head region in early pregnancy is extracted from the three-dimensional ultrasound data obtained in step S220, and the normal direction of the midsagittal plane is determined as the left-right direction of the head region.

[0062] For example, methods such as preset search, gradient update, and reinforcement learning can be used to extract the midsagittal plane from the three-dimensional ultrasound data of the fetus in early pregnancy.

[0063] In the pre-defined search and gradient update method, a database of fetal cross-sectional images from early pregnancy is first established. Each cross-sectional image in the database represents a section from the three-dimensional data of the fetus in early pregnancy, and is labeled with whether or not the section is a median sagittal plane. After establishing the database, traditional machine learning or deep learning methods can be used to learn an optimal mapping function from the fetal cross-sectional images from early pregnancy to the category of whether or not it is a median sagittal plane. This function is used to determine whether each section is a median sagittal plane, or the probability that each section belongs to the median sagittal plane.

[0064] In the preset search method, multiple candidate median sagittal planes are first generated according to predetermined rules. Then, the candidate median sagittal plane with the highest probability of belonging to the median sagittal plane is taken as the detection result. In the gradient update method, a fixed section is first selected as the starting position of the median sagittal plane. Then, according to the gradient direction of the probability function of the median sagittal plane, the section is iteratively updated until the probability value belonging to the median sagittal plane reaches its maximum or exceeds a predetermined threshold, thus obtaining the detection result of the median sagittal plane.

[0065] In reinforcement learning methods, a reward function is first determined for each section in the early pregnancy fetal 3D ultrasound data and for each section transformation (translation, rotation, etc.). This reward function can be related to the image similarity between the current section and the actual midsagittal plane, image error, and deviations in position and orientation. The reward function for section transformation is the difference between the reward functions of the sections before and after the transformation. In the actual search for the midsagittal plane, a fixed section is first selected as the starting position, and then the sections are iteratively updated until the reward function of the final section reaches its maximum, thus obtaining the detection result of the midsagittal plane.

[0066] When the target area includes a body region, the orientation of the target area includes at least one of the following: a second orientation of the body region, a third orientation of the body region, and a fourth orientation of the body region, wherein the second, third, and fourth orientations of the body region are respectively the up-down, front-back, and left-right directions of the body region, and any two of the second, third, and fourth orientations are perpendicular to each other. Determining the body orientation of the fetus in early pregnancy includes, but is not limited to, the following methods: In one implementation, body orientation can be determined using a trained machine learning model.

[0067] This method is similar to the head orientation determination method described above, which uses a trained machine learning model. Specifically, a database of early pregnancy fetal ultrasound data is first established. Each ultrasound data point in the database is labeled with the orientation of a body region of the early pregnancy fetus, or the location and orientation of a body region of the early pregnancy fetus. After the database is built, a traditional machine learning model or a deep learning model is trained to predict the orientation or location and orientation of the body region of the early pregnancy fetus from the 3D ultrasound data to be identified. During training, an optimal mapping function is learned from the 3D data of the early pregnancy fetus to the orientation or location and orientation of the body region, minimizing the error between the orientation or location and orientation of the body region obtained by mapping the ultrasound data in the database using this optimal mapping function and the actual labeled true value. Applying the optimal mapping function to the 3D ultrasound data of the early pregnancy fetus to be identified yields the predicted orientation or location and orientation of its body region.

[0068] As another approach, spinal detection can be used to determine the orientation of the body regions. Specifically, the spinal region of the fetus in early pregnancy is detected in the three-dimensional ultrasound data acquired in step S220, and the orientation of the fetus's body regions is determined based on the orientation of the spinal region. Since the spinal region is relatively prominent in the three-dimensional ultrasound image, the orientation of the fetus's body regions in early pregnancy can be accurately determined based on the location of the spinal region.

[0069] Methods for detecting or segmenting the fetal spine region in early pregnancy include machine learning methods and traditional image processing methods. Machine learning methods are similar to those described above; a database of early pregnancy fetal ultrasound data is pre-built, with each 3D ultrasound data point labeled with the location of the fetal spine region, such as a region of interest (ROI) or a specific area of ​​the spine. Then, traditional machine learning or deep learning methods are used to learn an optimal mapping function to extract the ROI or specific area of ​​the spine from the 3D ultrasound data of the early pregnancy fetus, thus achieving the detection or segmentation of the fetal spine region. Traditional image processing methods can employ Hough transform, RANSAC, etc., to detect the brightest straight line or arc in the 3D ultrasound data of the early pregnancy fetus, serving as the detection result for the fetal spine region.

[0070] The vertical and anteroposterior directions of the fetal body region in early pregnancy can be directly determined by detecting the spinal region. Specifically, determining the vertical direction of the fetal body region in early pregnancy based on the spinal region involves identifying a straight line closest to the spinal region and defining the direction of this line as the second direction of the fetal body region in early pregnancy, i.e., the vertical direction. For example, the straight line closest to the spinal region can be fitted using methods such as least squares, or the brightest straight line obtained using traditional image processing methods such as Hough transform and RANSAC can be directly used as the straight line closest to the spinal region.

[0071] After determining the vertical direction of the fetal body region in early pregnancy based on the spinal region detection results, a third direction, namely the anterior-posterior direction, can be further determined based on this vertical direction. Specifically, one or more body cross-sections perpendicular to the vertical direction determined above can be extracted from the 3D ultrasound data of the fetus in early pregnancy. Machine learning or traditional image processing methods are used to detect the position of the body center point and the spine in the body cross-section, and the direction of the line connecting the body center point and the spine is determined as the anterior-posterior direction of the fetal body region in early pregnancy. On this line, the spine is located closer to the posterior side of the body cross-section, and the body center point is located closer to the anterior side of the body cross-section.

[0072] In another embodiment, the anteroposterior direction of the body region can be determined directly based on the detection results of the spinal region, without needing to determine the anteroposterior direction based on the vertical direction of the body region. Specifically, since the spine protrudes posteriorly, a curve close to the spine can be determined, and the direction of the protrusion of this curve can be determined as the anteroposterior direction of the fetal body region in early pregnancy. This can be achieved by using methods such as least squares to fit the arc closest to the spine as the aforementioned curve, or by directly obtaining the brightest arc obtained from the aforementioned conventional image processing methods as the aforementioned curve.

[0073] In addition, the orientation of the fetal body region can be determined based on its shape characteristics in early pregnancy. This involves detecting the fetal body region in early pregnancy from 3D ultrasound data and determining its orientation based on the shape of the body region. Since the vertical shape characteristics of the fetal body region in early pregnancy are relatively obvious, while the differences in shape in the front-back and left-right directions are smaller, this method is primarily used to determine the vertical orientation of the fetal body region in early pregnancy.

[0074] Specifically, machine learning or image processing methods can be used to determine the body region of the fetus in early pregnancy from the three-dimensional ultrasound data acquired in step S220. The determined body region can be a region of interest (ROI) enclosing the fetus's body, or a segmented area representing the specific extent of the fetus's body. Then, based on the detection or segmentation results of the fetus's body region, the long axis of the body region is determined according to its shape, and the direction of this long axis is defined as the vertical direction of the fetus's body region. For example, principal component analysis (PCA) can be used to determine the long axis of the body region, or the two furthest points in the body region can be detected, and the line connecting these two points becomes the long axis of the body region.

[0075] Regarding the determination of the fourth direction (i.e., the left-right direction) of the fetal body region in early pregnancy, after determining the vertical and front-back directions of the fetal body region using any of the methods mentioned above or any other feasible methods, the direction perpendicular to the vertical and front-back directions is determined as the left-right direction of the fetal body region in early pregnancy. Alternatively, the left-right direction of the fetal body region in early pregnancy can also be determined based on certain specific structural features of the fetus. For example, the location of symmetrical structural features in the fetal body region can be detected in 3D ultrasound data, and the direction of the line connecting these symmetrical structural features is determined as the left-right direction of the fetal body region in early pregnancy. Symmetrical structural features include, for example, the two kidneys, two lungs, and the left and right ribs. Alternatively, the left and right atria of the fetus in early pregnancy can be detected. The direction of the line connecting the left and right atria generally forms a 45° angle with the left-right direction of the fetal body region in early pregnancy; this characteristic can also be used to determine the left-right direction of the fetal body region in early pregnancy.

[0076] For example, step S230 can be executed automatically after the three-dimensional ultrasound data is acquired, or it can be executed according to a received user instruction. For instance, the user can activate the automatic standard section extraction function by triggering a button to extract standard sections. This button can be a virtual button on the user interface of the display or a physical button. After acquiring the three-dimensional ultrasound data, step S230 is executed when a user instruction to extract standard sections is received. In some embodiments, the user can also activate the automatic standard section extraction function before starting to acquire ultrasound data, in which case step S230 is executed automatically after the three-dimensional ultrasound data is acquired.

[0077] In some embodiments, before performing step S230, the standard section to be extracted can be determined based on the received user input. For example, the names of ten standard sections, such as the parietal-hip diameter section and the biparietal diameter section, can be displayed on the user interface, and the standard section to be extracted can be determined based on the user's selection. Alternatively, the options for head region standard section, body region standard section, and whole body region standard section can be displayed on the user interface, and the head region standard section, body region standard section, or whole body region standard section can be extracted based on the user's selection.

[0078] Since the orientation of each target region can be determined relatively accurately based on the three-dimensional ultrasound data of the fetus in early pregnancy, determining the orientation of the target region first and then extracting standard sections based on the orientation of the target region can improve the quality of the extracted standard sections.

[0079] In step S240, at least one standard section corresponding to the target region is extracted from the three-dimensional ultrasound data according to the target direction.

[0080] As described above, the orientation of the target area determined in step S230 mainly includes the orientation of the head region and the orientation of the body region. Therefore, in step S240, a standard section of the head region can be determined from the three-dimensional ultrasound data including the head region of the fetus in early pregnancy, based on the orientation of the head region; or, a standard section of the body region can be determined from the three-dimensional ultrasound data including the body region of the fetus in early pregnancy, based on the orientation of the body region. The standard section of the head region includes at least one of the following: a transverse section at the level of the lateral ventricle, a biparietal diameter section, and a midsagittal section of the head and neck. The standard section of the body region includes at least one of the following: a thoracic diameter section, an abdominal circumference section, an abdominal wall section at the umbilical cord insertion site, a bladder section, a longitudinal axis section of the spine, and a long axis section of the trunk. In addition, the standard section can also include a standard section of the entire fetal body in early pregnancy, such as a parietal-rump diameter section (midsagittal section of the entire body). The parietal-rump diameter section can be determined based on the orientation of the head region or the orientation of the body region of the fetus in early pregnancy.

[0081] In one embodiment, extracting at least one standard section based on the orientation of the target region includes: determining multiple candidate sections in the three-dimensional ultrasound data of the fetus in early pregnancy based on the orientation of the target region determined in step S230, and selecting at least one standard section from the multiple candidate sections.

[0082] For the standard section of the head region, firstly, a set of candidate sections of the head region is generated based on the orientation of the fetal head region in early pregnancy. Then, the optimal standard section of the head region is determined from among the multiple candidate sections. For example, in the detection of the NT section and the crown-rump diameter section, the interface or midsagittal plane of the left and right hemispheres of the head obtained in step S230 can be directly used as the detection result of the NT section or the crown-rump diameter section. Alternatively, based on the left-right direction of the head region determined in step S230, a set of multiple candidate sections perpendicular to that direction can be generated, or a set of multiple candidate sections approximately perpendicular to that direction can be generated within a certain angle range. Then, the final NT section or crown-rump diameter section is selected from among the multiple candidate sections.

[0083] For example, in the detection of transverse sections of the fetal head in early pregnancy (such as transverse sections of the lateral ventricle, biparietal diameter, and cerebellum), a set of multiple candidate sections parallel or approximately parallel to the left-right direction of the head region determined in step S230 can be generated, and then the final transverse section of the lateral ventricle, biparietal diameter, or cerebellum can be selected from the multiple candidate sections.

[0084] For the standard section of the body region, similar to the standard section of the head region, a set of candidate sections of the body region is first generated based on the orientation of the body region of the fetus in early pregnancy, and then the optimal standard section of the body region is determined from the multiple candidate sections of the body region.

[0085] For example, when determining the cross-section of the fetal body region in early pregnancy, such as the four-chamber view, the gastric bubble view, the abdominal wall umbilical cord insertion site view, the bladder view, etc., a set of multiple parallel cross-sections perpendicular to the vertical direction of the fetal body region in early pregnancy can be generated as candidate cross-sections based on the vertical direction of the fetal body region in early pregnancy determined in step S230, or a set of multiple cross-sections approximately perpendicular to the vertical direction can be generated as candidate cross-sections within a certain angle range, and then a standard cross-section can be selected from the multiple candidate cross-sections.

[0086] For example, when determining the coronal section of the fetal body region in early pregnancy, such as the coronal section of the two kidneys or the coronal section of the spine, a set of candidate sections parallel to the left-right or up-down direction of the body region determined in step S230 can be generated, or a set of candidate sections approximately parallel to the direction can be generated within a certain angle range, and then the standard coronal section can be selected from the multiple candidate sections.

[0087] In addition, when determining the midsagittal plane of the fetus's body in early pregnancy, a set of candidate sections parallel to the direction can be generated based on the vertical or anteroposterior direction of the body region determined in step S230, or a set of candidate sections approximately parallel to the direction can be generated within a certain angle range, and then the standard midsagittal plane can be selected from multiple candidate sections.

[0088] After generating candidate slices, in one embodiment, a trained machine learning model can be used to determine the probability of each candidate slice corresponding to the target region being a standard slice, and the candidate slices whose probabilities satisfy a first threshold are determined as at least one standard slice corresponding to the target region. For example, if there are at least two candidate slices whose probabilities satisfy the first threshold, the final selected standard slice can be determined based on the received selection operation; that is, the user selects the best standard slice from the at least two candidate slices whose probabilities satisfy the first threshold. The machine learning model can be a traditional machine learning model or a deep learning model.

[0089] Optionally, a trained machine learning model can be used to determine the probability of each candidate section corresponding to the target region being a standard section, and the candidate section with the highest probability can be determined as a standard section corresponding to the target region. That is, the system directly determines the final standard section, thereby simplifying the operation process. In another embodiment, selecting a standard section from multiple candidate sections includes: detecting the early pregnancy target feature structure corresponding to at least one standard section corresponding to the target region on multiple candidate sections corresponding to the target region, and determining the candidate section whose probability of the early pregnancy target feature structure exists satisfies a second threshold or the candidate section with the highest probability of the early pregnancy target feature structure existing as the standard section. The target structures for early pregnancy in the parietal-rump diameter section include the nasal bone and genital ridge; the target structures for early pregnancy in the transverse section at the lateral ventricle level include the falx cerebri, lateral ventricles, and choroid plexus; the target structures for early pregnancy in the biparietal diameter section include the thalamus and cranial halo; the target structures for early pregnancy in the midsagittal section of the head and neck include the nuchal translucency and nasal bone; the target structures for early pregnancy in the thoracic diameter section include the four chambers of the heart; the target structures for early pregnancy in the abdominal circumference section include the stomach bubble; the target structures for early pregnancy in the abdominal wall section at the umbilical cord insertion site include the umbilical cord insertion site; the target structures for early pregnancy in the bladder section include the legs or bladder; the target structures for early pregnancy in the longitudinal axis section of the spine include the spine and skin margins; and the target structures for early pregnancy in the long axis section of the trunk include the kidneys, stomach bubble, and spine.

[0090] For example, for a standard section of the head region, after generating a set of multiple candidate sections parallel or approximately parallel to the left-right direction of the head region, the target feature structures of early pregnancy corresponding to the standard section of the head region can be detected on the multiple candidate sections. For example, the lateral ventricle or choroid plexus corresponding to the transverse section of the lateral ventricle, the thalamus corresponding to the biparietal diameter section, and the cerebellum corresponding to the transverse section of the cerebellum. The candidate section with the highest probability of the existence of the target feature structure of early pregnancy is taken as the detection result of the corresponding standard section of the head.

[0091] As another way to extract the standard section corresponding to the target region based on the direction of the target region, the early pregnancy target feature structure corresponding to the standard section to be determined can be detected first from the three-dimensional ultrasound data obtained in step S220. Then, combined with the direction of the target region determined above, the section that at least partially coincides with the early pregnancy target feature structure and whose angle with the direction of the target region meets the preset requirements can be determined as at least one standard section corresponding to the target region. Further, the section that substantially coincides with the early pregnancy target feature structure and whose angle with the direction of the determined target region is 0 degrees can be determined as a standard section corresponding to the target region. Alternatively, the section that substantially coincides with the early pregnancy target feature structure and whose angle with the direction of the determined target region is 90 degrees can be determined as a standard section corresponding to the target region.

[0092] For the standard section of the head region, the target features of early pregnancy corresponding to the standard section of the head to be determined can be detected. Combined with the orientation of the fetal head region in early pregnancy, the corresponding standard section of the head region is determined. For example, the target features of early pregnancy corresponding to the horizontal section at the level of the lateral ventricle include the falx cerebri, lateral ventricles, and choroid plexus; the target features of early pregnancy corresponding to the biparietal diameter section include the thalamus and cranial halo; and the target features of early pregnancy corresponding to the midsagittal section of the head and neck include the nuchal translucency and nasal bones. In addition, the standard sections of the whole body region can also be determined based on the orientation of the head region and the target features of early pregnancy in the head region. When the standard section is the parietal-rump diameter section, the corresponding target features of early pregnancy include the nasal bones and genital ridge.

[0093] For example, in the NT standard section (i.e., the midsagittal section of the head and neck), one or more characteristic structures among the nasal bone, NT (nuchal translucency), IT (intracranial translucency), and posterior fossa cistern can be detected in three-dimensional ultrasound data. Then, a section that at least partially overlaps with these characteristic structures and is perpendicular to the left-right direction of the head region is determined as the result of the NT standard section. Similarly, in the parietal-rump diameter section, one or more characteristic structures among the nasal bone, NT (nuchal translucency), bladder, and genital ridge can be detected. Then, a section that at least partially overlaps with these characteristic structures and is perpendicular to the left-right direction of the head region is determined in three-dimensional ultrasound data as the result of the parietal-rump diameter section.

[0094] In the examination of transverse sections of the fetal head during early pregnancy, the lateral ventricle and / or choroid plexus corresponding to the transverse section of the lateral ventricle, the thalamus and / or cerebral peduncle corresponding to the transverse section of the biparietal diameter, and the thalamus, cerebellum and / or IT (intracranial translucency) corresponding to the transverse section of the cerebellum can be detected in three-dimensional ultrasound data. Then, one or more sections are determined so that they pass through the above characteristic structures and are parallel to the left and right directions of the head region, so as to serve as the detection results of transverse sections of the lateral ventricle, biparietal diameter, or cerebellum, respectively.

[0095] Similarly, for a standard section of a body region, the target feature structure of early pregnancy corresponding to the standard section of the body region to be determined can be detected, and then combined with the orientation of the body region of the fetus in early pregnancy, the standard section of the corresponding body region can be determined.

[0096] For example, in the detection of the midsagittal plane of the fetal body region in early pregnancy, if the direction of the body region is determined according to the location of the spinal region in step S230, a section that is closest to the spine or its fitted arc and is parallel or approximately parallel to the vertical or anteroposterior direction of the body region (i.e., the angle between the section and the vertical or anteroposterior direction is 0°) can be determined based on the location of the spinal region or its fitted arc, and this section can be used as the detection result of the midsagittal plane of the fetal body region in early pregnancy.

[0097] In the detection of cross-sections of the fetal body region in early pregnancy, the heart corresponding to the four-chamber view, the gastric bubble corresponding to the gastric bubble view, the umbilical cord and its insertion point in the abdominal wall corresponding to the umbilical cord insertion point view, and the bladder or umbilical artery corresponding to the bladder view can be detected. Then, one or more views are determined so that they at least partially overlap with the above-mentioned early pregnancy target feature structures and are perpendicular or approximately perpendicular to the vertical direction of the early pregnancy fetal body region determined in step S230. The view is used as the detection result of the four-chamber view, the gastric bubble view, the abdominal wall umbilical cord insertion point view, or the bladder view.

[0098] In the coronal section detection of the fetal body region during early pregnancy, the kidneys, stomach bubble, or spine corresponding to the coronal section of the kidneys, and the spine or ribs corresponding to the coronal section of the spine can be detected. One or more sections are then determined so that they coincide with the aforementioned early pregnancy target features and are parallel to the left-right or up-down direction of the early pregnancy fetal body region determined in step S230. These sections are then used as the detection results for the kidney coronal section or the spine coronal section. Furthermore, in some embodiments, other standard sections can be determined based on one or more established standard sections and the position of the early pregnancy target features within those standard sections.

[0099] For example, in the detection of transverse sections of the fetal head in early pregnancy, the location of early pregnancy target feature structures related to the above-mentioned transverse sections of the fetal head can be detected at the interface between the left and right hemispheres of the head, the midsagittal plane, the standard NT section, or the parieto-rump diameter section. These target feature structures include the choroid plexus, thalamus, third ventricle, cerebellar vermis, and IT (intracranial translucency). Then, one or more sections are determined so that they pass through the above feature structures and are perpendicular to the interface between the left and right hemispheres of the head, the midsagittal plane, the NT section, or the parieto-rump diameter section, to serve as the detection results of the transverse sections of the head.

[0100] Similarly, for standard sections of fetal body regions in early pregnancy, such as in the detection of the bilateral renal coronal section, the positions of the stomach bubble and spine can be determined from the already detected stomach bubble section. Then, a new section is determined that passes through the stomach bubble or spine and is perpendicular to the stomach bubble section, and this new section is used as the detection result of the bilateral renal coronal section. In the detection of the spinal coronal section, the positions of the spine and ribs can be determined from one or more already detected transverse sections of body regions. Then, a new section is determined that passes through the spine or ribs and is perpendicular to the transverse body section, and this new section is used as the detection result of the spinal coronal section.

[0101] Step S250: Display the at least one standard cross-section.

[0102] The displayed standard cross-sections can be all the standard cross-sections extracted in step S240, or only a portion of them. For example, when displaying the standard cross-sections extracted in step S240, a portion of the standard cross-sections can be displayed according to the received user instructions. For instance, the name or thumbnail of the standard cross-section can be displayed on the display interface, and the corresponding standard cross-section can be displayed according to the user's selection.

[0103] In some embodiments, if the target feature structure of early pregnancy is detected in the three-dimensional ultrasound data in step S230 or step S240, the target feature structure of early pregnancy detected from the three-dimensional ultrasound data can also be displayed for the user to perform comparative analysis.

[0104] In addition, the target direction determined in step S230 can be displayed so that the user can view the associated standard cross-section in conjunction with the target direction. As an example, the target direction can be displayed while displaying the three-dimensional ultrasound image. For example, the left-right direction of the fetal head region in early pregnancy, or the up-down, front-back, and left-right directions of the fetal body region in early pregnancy can be displayed using graphic markers such as arrows.

[0105] In some embodiments, the names of the determined standard sections can also be displayed to allow users to intuitively determine the type of standard section or select the standard section to view based on its name. The names of the standard sections can be displayed synchronously with the standard sections, or the names of each standard section can be displayed on the display interface first, and the corresponding standard section can be displayed when the user selects the name of the standard section.

[0106] In summary, the ultrasound imaging method 200 for early pregnancy fetus in this application embodiment can automatically determine at least one standard section corresponding to the target area based on the direction of the target area of ​​the early pregnancy fetus, eliminating the need for doctors to manually extract standard sections one by one, greatly optimizing the workflow of prenatal examination, effectively improving work efficiency, and improving the stability of the quality of the obtained standard sections, thus promoting the popularization and application of early pregnancy structural screening.

[0107] Now refer to it again Figure 1 The ultrasound imaging system 100 provided in this application embodiment can be used to implement the ultrasound imaging method 200 for fetuses in early pregnancy described above. 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 relevant descriptions of each component can be found above.

[0108] When used to implement ultrasound imaging method 200, the transmitting / receiving circuit 112 is used to excite the ultrasound probe 110 to emit ultrasound waves toward the fetus in early pregnancy and receive the echo of the ultrasound waves to obtain an ultrasound echo signal; the processor 114 is used to: obtain three-dimensional ultrasound data of the fetus in early pregnancy based on the ultrasound echo signal; determine the orientation of a target region of the fetus in early pregnancy based on the three-dimensional ultrasound data; extract at least one standard section corresponding to the target region from the three-dimensional ultrasound data based on the orientation of the target region; and the display 116 is used to display the at least one standard section.

[0109] As an example, the target area includes at least one of the following: head area, body area, and whole body area.

[0110] In one embodiment, the target region includes a head region, and the direction of the target region includes a first direction of the head region, wherein the first direction is the left-right direction of the head region.

[0111] In another embodiment, the target region includes a body region, and the orientation of the target region includes at least one of the following: a second direction, a third direction, and a fourth direction of the body region, wherein the second direction, the third direction, and the fourth direction are respectively the up-down direction, the front-back direction, and the left-right direction of the body region in the three-dimensional ultrasound data, and any two of the second direction, the third direction, and the fourth direction are perpendicular to each other.

[0112] As an example, extracting at least one standard section corresponding to the target region from three-dimensional ultrasound data based on the orientation of the target region includes: determining multiple candidate sections corresponding to the target region in the three-dimensional ultrasound data based on the orientation of the target region; and selecting at least one standard section corresponding to the target region from the multiple candidate sections.

[0113] As an example, based on the orientation of the target region, at least one standard section corresponding to the target region is extracted from the three-dimensional ultrasound data, including: detecting the early pregnancy target feature structure corresponding to the standard section corresponding to the target region in the three-dimensional ultrasound data; and determining the section that at least partially overlaps with the early pregnancy target feature structure and whose angle with the orientation of the target region meets a preset requirement as at least one standard section corresponding to the target region.

[0114] In one embodiment, the display 116 is further configured to display the early pregnancy target feature structure. The display 116 may also be configured to display the orientation of the identified target region. The display 116 may also be configured to display the name of the identified standard cross-section.

[0115] The above only describes the main functions of each component of the ultrasound imaging system 100. For more details, please refer to the relevant description of the ultrasound imaging method 200 for early pregnancy fetus. The ultrasound imaging system 100 of this application embodiment can automatically determine the standard section of the early pregnancy fetus, improving work efficiency and the quality of the standard section.

[0116] Below, we will refer to Figure 3 A method for ultrasound imaging of a fetus in early pregnancy according to another embodiment of this application is described. Figure 3 This is a schematic flowchart of an ultrasound imaging method 300 for a fetus in early pregnancy according to an embodiment of this application.

[0117] like Figure 3 As shown, the ultrasound imaging method 300 for the fetus in early pregnancy includes the following steps: In step S310, ultrasound waves are emitted to the fetus in early pregnancy, and the echoes of the ultrasound waves are received to obtain ultrasound echo signals. In step S320, three-dimensional ultrasound data of the fetus in early pregnancy are obtained based on the ultrasound echo signal; In step S330, at least two distinct regions of early pregnancy target feature structures are detected from the three-dimensional ultrasound data; In step S340, at least one cross section is determined that at least partially overlaps with the region of each of the at least two different early pregnancy target feature structures in the region, as at least one standard cross section of the early pregnancy fetus. In step S350, the at least one standard cross-section is displayed.

[0118] Steps S310, S320, and S350 of the ultrasound imaging method 300 for early pregnancy fetus according to the embodiments of this application are consistent with reference to... Figure 2 Steps S210, S220, and S250 in the described ultrasound imaging method 200 are largely similar. For the sake of brevity, the same details will not be repeated here. The following mainly describes in detail the method of determining the standard section based on the three-dimensional ultrasound data in steps S330 and S340.

[0119] Similar to ultrasound imaging method 200, in ultrasound imaging method 300 for early pregnancy fetus, the extracted standard sections include at least one of a standard section of the head region, a standard section of the body region, or a standard section of the whole body region of the early pregnancy fetus. When the standard section includes a standard section of the head region, the three-dimensional ultrasound data acquired in step S320 includes at least three-dimensional ultrasound data of the head region of the early pregnancy fetus. When the standard section includes a standard section of the body region, the three-dimensional ultrasound data acquired in step S320 includes at least three-dimensional ultrasound data of the body region of the early pregnancy fetus. When the standard section includes a standard section of the whole body region, the three-dimensional ultrasound data acquired in step S320 includes three-dimensional ultrasound data of the whole body region of the early pregnancy fetus.

[0120] Specifically, the standard sections may include at least one of the following standard sections: parietal-rump diameter section, lateral ventricle level transverse section, biparietal diameter section, NT standard section, thoracic diameter section, abdominal circumference section, abdominal wall umbilical cord insertion site section, bladder section, spinal longitudinal axis section, and trunk long axis section. Among them, the standard sections for the fetal head region in early pregnancy include the lateral ventricle level transverse section, biparietal diameter section, and NT standard section, and the three-dimensional ultrasound data must include at least the three-dimensional ultrasound data of the fetal head region in early pregnancy; the standard sections for the fetal body region in early pregnancy include the thoracic diameter section, abdominal circumference section, abdominal wall umbilical cord insertion site section, bladder section, spinal longitudinal axis section, and trunk long axis section, and the three-dimensional ultrasound data must include at least the three-dimensional ultrasound data of the fetal body region in early pregnancy; and the standard section for the whole fetal region in early pregnancy includes the parietal-rump diameter section, and the three-dimensional ultrasound data must include the three-dimensional ultrasound data of the whole fetal region in early pregnancy.

[0121] In step S330, any suitable image detection or segmentation method can be used to determine the location of the early pregnancy target feature structure. For example, traditional machine learning or deep learning methods can be used to train a machine learning model for the feature structure corresponding to each standard section, in order to determine the location of the feature structure. Before model training, an early pregnancy fetal ultrasound database is pre-established, in which each 3D ultrasound data point is labeled with the location of the early pregnancy target feature structure, such as its region of interest (ROI) or specific region. Then, traditional machine learning or deep learning methods are used to learn an optimal mapping function to obtain the region of interest (ROI) or specific region of the early pregnancy target feature structure from the 3D ultrasound data of the early pregnancy fetus, thereby realizing the detection or segmentation of the early pregnancy target feature structure.

[0122] In step S340, for the standard section to be extracted, firstly, the type of the standard section is obtained, the early pregnancy target feature structure corresponding to the type of the standard section is determined, and regions of at least two different early pregnancy target feature structures corresponding to the type of the standard section are detected from the three-dimensional ultrasound data. Then, sections that at least partially overlap with the at least two different early pregnancy target feature structures are determined as the detection result of the standard section. Specifically, a section that substantially overlaps with the region of each early pregnancy target feature structure in the at least two different early pregnancy target feature structure regions can be determined as the standard section. To make the obtained standard section more accurate, sections that at least partially overlap with three or more different early pregnancy target feature structures can be determined as the detection result of the standard section.

[0123] For example, when the standard section is a parietal-rump diameter section, the corresponding target features of early pregnancy include the nasal bone and genital ridge; when the standard section is a transverse section at the level of the lateral ventricle, the corresponding target features of early pregnancy include the falx cerebri, lateral ventricle, and choroid plexus; when the standard section is a biparietal diameter section, the corresponding target features of early pregnancy include the thalamus and cranial halo; when the target features of early pregnancy include the midsagittal plane of the head and neck, the corresponding target features of early pregnancy include the nuchal translucency and nasal bone; when the standard section is a thoracic diameter section, the corresponding target features of early pregnancy include the heart, ribs, and The spine; when the standard section is the abdominal circumference section, the corresponding target features of early pregnancy include the stomach bubble, spine, and liver; when the standard section is the abdominal wall section at the umbilical cord insertion point, the corresponding target features of early pregnancy include the umbilical cord insertion point, umbilical cord, spine, and anterior abdominal wall; when the standard section is the bladder section, the corresponding target features of early pregnancy include the legs and bladder; when the standard section is the longitudinal axis section of the spine, the corresponding target features of early pregnancy include the spine and skin margin; when the standard section is the long axis section of the trunk, the corresponding target features of early pregnancy include the kidneys, stomach bubble, and spine.

[0124] In step S350, the displayed standard cross-section can be part or all of the standard cross-sections extracted in step S340. In addition to displaying the extracted standard cross-sections, the name of the standard cross-section can also be displayed. Furthermore, the early pregnancy target feature structure detected from the three-dimensional ultrasound data can also be displayed. The early pregnancy target feature structure can be displayed in the three-dimensional ultrasound image of the fetus in early pregnancy, for example, by displaying the ROI box surrounding the early pregnancy target feature structure or by displaying the outline of the early pregnancy target feature structure.

[0125] Now refer to it again Figure 1 The ultrasound imaging system 100 provided in this application embodiment can be used to implement the ultrasound imaging method 300 for fetuses in early pregnancy described above. 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 relevant descriptions of each component can be found above.

[0126] When used to implement ultrasound imaging method 300, the transmitting / receiving circuit 112 is used to excite the ultrasound probe 110 to emit ultrasound waves toward the fetus in early pregnancy and receive the echo of the ultrasound waves to obtain an ultrasound echo signal; the processor 114 is used to: obtain three-dimensional ultrasound data of the fetus in early pregnancy based on the ultrasound echo signal; detect regions of at least two early pregnancy target feature structures from the three-dimensional ultrasound data; determine at least one cross-section that at least partially overlaps with each of the at least two different early pregnancy target feature structures as at least one standard cross-section of the fetus in early pregnancy; and the display 116 is used to display the at least one standard cross-section.

[0127] The above only describes the main functions of each component of the ultrasound imaging system 100. For more details, please refer to the relevant description of the ultrasound imaging method 300 for early pregnancy fetuses.

[0128] The ultrasound imaging method 300 and ultrasound imaging system for early pregnancy fetus in this application embodiment can automatically determine the standard section of the early pregnancy fetus based on the early pregnancy target feature structure, eliminating the need for doctors to manually extract the standard section one by one, greatly optimizing the workflow of prenatal examination, effectively improving work efficiency, and improving the stability of the quality of the obtained standard section, thus promoting the popularization and application of early pregnancy structure screening.

[0129] Below, we will refer to Figure 4 A method for ultrasound imaging of a fetus in early pregnancy according to another embodiment of this application is described. Figure 4 This is a schematic flowchart of an ultrasound imaging method 400 for a fetus in early pregnancy according to an embodiment of this application.

[0130] like Figure 4 As shown, an embodiment of the ultrasound imaging method 400 for a fetus in early pregnancy according to this application includes the following steps: In step S410, ultrasound waves are emitted to the fetus in early pregnancy, and the echoes of the ultrasound waves are received to obtain ultrasound echo signals. In step S420, three-dimensional ultrasound data of the fetus in early pregnancy are obtained based on the ultrasound echo signal; In step S430, the three-dimensional ultrasound data is matched with a pre-configured ultrasound data template of early pregnancy standard sections, and the target standard section in the three-dimensional ultrasound data is determined according to the matching result. The early pregnancy standard section includes at least one of the following: lateral ventricle level transverse section, biparietal diameter section, head and neck midsagittal section, thoracic diameter section, abdominal circumference section, abdominal wall umbilical cord insertion site section, bladder section, spinal longitudinal axis section, trunk long axis section, and parietal-rump diameter section. In step S440, the target standard cross-section is displayed.

[0131] Steps S410, S420, and S440 of the ultrasound imaging method 400 for early pregnancy fetus according to embodiments of this application are consistent with reference to... Figure 2 Steps S210, S220, and S250 in the described ultrasound imaging method 200 are largely similar. For the sake of brevity, the same details will not be repeated here. The following mainly describes in detail the method of determining the standard section based on the three-dimensional ultrasound data in step S430.

[0132] In step S430, a standard section is determined by matching the three-dimensional ultrasound data of the fetus in early pregnancy with a pre-configured ultrasound data template of a standard section for early pregnancy. Exemplarily, the pre-configured ultrasound data template of the standard section for early pregnancy includes a matching template comprising a pre-configured three-dimensional data template of the standard section for early pregnancy (hereinafter referred to as the standard three-dimensional data template), a pre-configured two-dimensional data template of the standard section for early pregnancy (hereinafter referred to as the standard two-dimensional section template), a pre-configured early pregnancy target feature structure template of the standard section for early pregnancy (hereinafter referred to as the standard early pregnancy target feature structure template), and a pre-configured key point template of the standard section for early pregnancy (hereinafter referred to as the standard key point template). The matching with the template includes at least one of the following: three-dimensional data matching with the standard three-dimensional data template, two-dimensional section matching with the standard two-dimensional section template, early pregnancy target feature structure matching with the standard early pregnancy target feature structure template, and key point matching with the standard key point template.

[0133] As an example, matching the 3D data of the fetus in early pregnancy with a standard 3D data template involves finding an optimal 3D spatial transformation relationship that maximizes the similarity or minimizes the difference between the 3D ultrasound data obtained in step S420 and the standard 3D data template. In another example, image feature extraction can be performed first on the 3D ultrasound data of the fetus in early pregnancy obtained in step S420 and the standard 3D data template. This extraction can include features such as gradient features, LBP texture features, Haar features, and HOG / LOG features. Then, an optimal 3D spatial transformation relationship can be found that maximizes the similarity or minimizes the difference between the image features extracted from the 3D ultrasound data of the fetus in early pregnancy and the standard 3D data template. After matching, the position of the target standard section in the 3D ultrasound data of the fetus in early pregnancy can be determined based on the position of the standard 3D section pre-configured in the standard 3D data template and the matched 3D spatial transformation relationship.

[0134] As an example, matching the three-dimensional ultrasound data of the fetus in early pregnancy with a standard two-dimensional section template involves finding an optimal two-dimensional section from the three-dimensional ultrasound data of the fetus in early pregnancy obtained in step S420, such that the two-dimensional section has the highest similarity or the lowest difference with the standard two-dimensional section template, or that the image features extracted from the optimal two-dimensional section have the highest similarity or the lowest difference with the standard two-dimensional section template. Image features include, but are not limited to, gradient features, LBP and other texture features, Haar features, and HOG / LOG features. After matching is completed, the optimal two-dimensional section found from the three-dimensional data can be used as the target standard section.

[0135] As an example, matching three-dimensional ultrasound data of a fetus in early pregnancy with a standard early pregnancy target feature structure template includes finding an optimal image patch in the three-dimensional ultrasound data obtained in step S420 such that the image patch has the highest similarity or the lowest difference with the standard early pregnancy target feature structure template, or the image features extracted from the image patch have the highest similarity or the lowest difference with the standard early pregnancy target feature structure template.

[0136] In another example, early pregnancy target feature structure matching may also include using target detection methods such as Faster RCNN, Mask RCNN, SSD, YOLO, Retinanet, Efficientnet, Cornernet, Centernet, FCOS, etc., to detect candidate early pregnancy target feature structure regions in the three-dimensional ultrasound data acquired in step S420, and then match them with the standard early pregnancy target feature structure template.

[0137] Matching with the standard early pregnancy target feature structure template can include finding an optimal candidate early pregnancy target feature structure in the three-dimensional ultrasound data, such that its similarity with the standard early pregnancy target feature structure template is the highest or the difference is the lowest; it can also include extracting image features of the candidate early pregnancy target feature structure and the standard early pregnancy target feature structure template, and then finding an optimal candidate early pregnancy target feature structure, such that the image features extracted from it have the highest similarity with the image features extracted from the standard early pregnancy target feature structure template; or it can also include finding an optimal candidate early pregnancy target feature structure and an optimal spatial transformation, such that the spatial position difference between the candidate early pregnancy target feature structure and the standard early pregnancy target feature structure template is the lowest.

[0138] After matching, the location of the target standard section can be determined based on the position of the target features in early pregnancy in the three-dimensional ultrasound data and the target features in early pregnancy corresponding to the standard section. Specifically, when the standard section in early pregnancy is the parietal-rump diameter section, the corresponding target features include the nasal bone and genital ridge; when the standard section in early pregnancy is a transverse section at the level of the lateral ventricle, the corresponding target features include the falx cerebri, lateral ventricle, and choroid plexus; when the standard section in early pregnancy is the biparietal diameter section, the corresponding target features include the thalamus and cranial halo; when the standard section in early pregnancy includes the midsagittal plane of the head and neck, the corresponding target features include the nuchal translucency and nasal bone; when the standard section in early pregnancy is the thoracic diameter section, the corresponding target features... The structure includes the four chambers of the heart; when the standard section for early pregnancy is the abdominal circumference section, the corresponding target feature structure for early pregnancy includes the stomach bubble; when the standard section for early pregnancy is the abdominal wall section at the umbilical cord insertion site, the corresponding target feature structure for early pregnancy includes the umbilical cord insertion site; when the standard section for early pregnancy is the bladder section, the corresponding target feature structure for early pregnancy includes both legs or the bladder; when the standard section for early pregnancy is the longitudinal axis section of the spine, the corresponding target feature structure for early pregnancy includes the spine and skin margins; when the standard section for early pregnancy is the long axis section of the trunk, the corresponding target feature structure for early pregnancy includes both kidneys, the stomach bubble, and the spine. Alternatively, the position of the target standard section in the three-dimensional ultrasound data can be determined based on the optimal spatial transformation obtained and the position of the standard section for early pregnancy in the standard early pregnancy target feature structure template.

[0139] As an example, matching three-dimensional ultrasound data with a standard keypoint template includes finding one or more optimal points in the three-dimensional ultrasound data acquired in step S420, such that the image features near the optimal point have the highest similarity or the smallest difference with the image features of the standard keypoint template.

[0140] Keypoint matching can also include using injected feature point extraction methods (e.g., SIFT), corner detection methods (e.g., Harris method), or neural network-based prediction of candidate keypoint coordinates or candidate keypoint regions to identify at least one candidate keypoint in the 3D ultrasound data, and then matching the candidate keypoint with a standard keypoint template. Matching a candidate keypoint with a standard keypoint template can include finding an optimal candidate keypoint such that the image features in its vicinity have the highest similarity or lowest difference with the image features of the standard keypoint template; alternatively, matching a candidate keypoint with a standard keypoint template can also include finding an optimal candidate keypoint and an optimal spatial transformation relationship such that the spatial position of the optimal candidate keypoint differs least from that of the standard keypoint template.

[0141] After matching is completed, a cross section including these key points can be determined as the target standard cross section based on the location of the key points corresponding to the standard cross section; alternatively, the location of the target standard cross section in the three-dimensional ultrasound data can be determined based on the location of the early pregnancy standard cross section in the standard key point template, according to the obtained optimal spatial transformation relationship.

[0142] Now refer to it again Figure 1 The ultrasound imaging system 100 provided in this application embodiment can be used to implement the ultrasound imaging method 400 for fetuses in early pregnancy described above. 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 relevant descriptions of each component can be found above.

[0143] When used to implement ultrasound imaging method 400, the transmitting / receiving circuit 112 is used to excite the ultrasound probe 110 to emit ultrasound waves to the fetus in early pregnancy and receive the echo of the ultrasound waves to obtain an ultrasound echo signal; the processor 114 is used to: obtain three-dimensional ultrasound data of the fetus in early pregnancy based on the ultrasound echo signal; match the three-dimensional ultrasound data with an ultrasound data template with a pre-configured standard section for early pregnancy, and determine the target standard section in the three-dimensional ultrasound data according to the matching result, wherein the standard section for early pregnancy includes at least one of the following: transverse section at the level of the lateral ventricle, biparietal diameter section, midsagittal section of the head and neck, thoracic diameter section, abdominal circumference section, abdominal wall section at the umbilical cord insertion site, bladder section, longitudinal axis section of the spine, long axis section of the trunk, and parietal-rump diameter section; the display 116 is used to display the target standard section.

[0144] The above only describes the main functions of each component of the ultrasound imaging system 100. For more details, please refer to the relevant description of the ultrasound imaging method 400 for early pregnancy fetuses.

[0145] The ultrasound imaging method 400 and ultrasound imaging system for early pregnancy in this application embodiment can automatically determine the standard section of the early pregnancy fetus by matching it with the ultrasound data template of the pre-configured standard section of early pregnancy, eliminating the need for doctors to manually extract the standard sections one by one. This greatly optimizes the workflow of prenatal examination, effectively improves work efficiency, and can improve the stability of the quality of the obtained standard sections, thus promoting the popularization and application of early pregnancy structural screening.

[0146] Below, we will refer to Figure 5 A method for ultrasound imaging of a fetus in early pregnancy according to another embodiment of this application is described. Figure 5 This is a schematic flowchart of an ultrasound imaging method 500 for a fetus in early pregnancy according to an embodiment of this application.

[0147] like Figure 5As shown, an embodiment of the ultrasound imaging method 500 for early pregnancy of the fetus in this application includes the following steps: In step S510, ultrasound waves are emitted to the fetus in early pregnancy, and the echoes of the ultrasound waves are received to obtain ultrasound echo signals. In step S520, three-dimensional ultrasound data of the fetus in early pregnancy are obtained based on the ultrasound echo signal; In step S530, image features of the target region of the three-dimensional ultrasound data are extracted based on the three-dimensional ultrasound data; In step S540, the normal direction of the target standard section and the position information of the preset points on the target standard section are determined based on the image features of the target region. In step S550, the target standard section is determined based on the normal direction of the target standard section and the position information of the preset points on the target standard section. In step S560, the target standard cross-section is displayed.

[0148] Steps S510 and S520 of the ultrasound imaging method 500 for early pregnancy fetus according to the embodiments of this application are consistent with reference to... Figure 2 Steps S210 and S220 in the ultrasound imaging method 200 are largely similar. For the sake of brevity, the same details will not be repeated here. The following mainly describes in detail the method of determining the standard section based on three-dimensional ultrasound data in method 500.

[0149] In step S530, image features of the target region are first extracted from the three-dimensional ultrasound data of the fetus in early pregnancy. As an example, the methods for extracting image features of the target region include traditional image processing methods or deep learning methods. Traditional image processing methods include extracting image features such as SIFT features, gradient features, LBP texture features, PCA, LDA, Haar features, HOG and LOG features, and also include image edge extraction, such as using the Canny operator for edge extraction. Deep learning methods involve training a neural network model for one or more specific tasks, such as regressing the position and orientation of a standard cross-section, estimating the position, size, and / or orientation of the fetus in early pregnancy, and identifying the target feature structure and / or landmarks of the fetus in early pregnancy. Then, the output of one or more network nodes in the middle of the neural network model is taken as the image features of the target region, or the front-end feature extraction network in the trained neural network is used to extract image features of the target region.

[0150] After extracting the image features of the target region, the normal direction of the target standard section can be determined based on the mapping relationship between the image features of the target region and the normal direction of the standard section corresponding to the image features of the target region. Similarly, the position information of the preset points on the target standard section can be determined based on the mapping relationship between the image features of the target region and the position information of preset points on the standard section corresponding to the image features of the target region. For example, the preset point can be a point where the standard section intersects with the X-axis, Y-axis, or Z-axis, or it can be the position information of the standard section in a preset direction, such as the intersection point of the standard section and the normal direction.

[0151] For example, a machine learning model or deep learning model can be used to regress the mapping relationship between the image features of the target region and the normal direction of the standard section corresponding to the target image features; alternatively, a machine learning model or deep learning model can be used to regress the mapping relationship between the image features of the target region and preset points on the standard section corresponding to the image features of the target region. Specifically, an early pregnancy fetal ultrasound database is pre-established, where each ultrasound data includes early pregnancy 3D data and / or image features of its target region, as well as the preset point positions and normal directions of one or more standard sections. During model training, an optimal mapping function from the image features of the target region to the preset point positions and normal directions is sought, minimizing the error between the preset point positions and normal directions obtained from the image features of the target region in the database and the preset point positions and normal directions of the actual standard sections. Using this mapping function, the preset point positions and normal directions can be predicted based on the image features of the target region in the 3D ultrasound image.

[0152] Subsequently, in step S550, standard sections can be extracted from the three-dimensional ultrasound data based on the preset point positions and normal directions. For example, sections passing through preset points can be extracted from all sections perpendicular to the normal direction. Standard sections include one or more of the following sections: lateral ventricle level transverse section, biparietal diameter section, head and neck midsagittal section, thoracic diameter section, abdominal circumference section, abdominal wall umbilical cord insertion site section, bladder section, spinal longitudinal axis section, trunk long axis section, and parietal-hip diameter section.

[0153] For example, traditional machine learning methods include support vector machines (SVM), least squares, logistic regression, etc., and their mapping functions include linear functions, polynomial functions, logistic functions, etc.; deep learning methods use deep neural networks as mapping functions, including but not limited to convolutional neural networks (CNN), multilayer perceptrons (MLP), recurrent neural networks (RNN), etc.

[0154] Now refer to it again Figure 1The ultrasound imaging system 100 provided in this application embodiment can be used to implement the ultrasound imaging method 500 for fetuses in early pregnancy described above. 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, and the relevant descriptions of each component can be found above.

[0155] When used to implement ultrasound imaging method 500, the transmitting / receiving circuit 112 is used to excite the ultrasound probe 110 to emit ultrasound waves toward the fetus in early pregnancy and receive the echo of the ultrasound waves to obtain an ultrasound echo signal; the processor 114 is used to: obtain three-dimensional ultrasound data of the fetus in early pregnancy based on the ultrasound echo signal; extract image features of the target area of ​​the three-dimensional ultrasound data according to the three-dimensional ultrasound data; determine the normal direction of the target standard section and the position information of the preset points on the target standard section according to the image features of the target area; determine the target standard section according to the normal direction of the target standard section and the position information of the preset points on the target standard section; and the display 116 is used to display the standard section.

[0156] The above only describes the main functions of each component of the ultrasound imaging system 100. For more details, please refer to the relevant description of the ultrasound imaging method 500 for early pregnancy fetus.

[0157] The ultrasound imaging method 500 and ultrasound imaging system for early pregnancy of the present application embodiment can automatically determine the standard section of the early pregnancy fetus based on the image features of the target area of ​​the three-dimensional ultrasound data of the early pregnancy fetus, eliminating the need for doctors to manually extract the standard sections one by one, thus improving work efficiency and the quality of the standard sections.

[0158] Below, we will refer to Figure 6 A method for ultrasound imaging of a fetus in early pregnancy according to another embodiment of this application is described. Figure 6 This is a schematic flowchart of an ultrasound imaging method 600 for a fetus in early pregnancy according to an embodiment of this application.

[0159] like Figure 6 As shown, an embodiment of the ultrasound imaging method 600 for a fetus in early pregnancy according to this application includes the following steps: In step S610, ultrasound waves are emitted to the fetus in early pregnancy, and the echoes of the ultrasound waves are received to obtain ultrasound echo signals. In step S620, three-dimensional ultrasound data of the early pregnancy fetus are obtained based on the ultrasound echo signal; In step S630, the orientation of the target region of the early pregnancy fetus is determined based on the three-dimensional ultrasound data; In step S640, the orientation of the target region of the early pregnancy fetus is displayed.

[0160] The method and reference for determining the orientation of a target region in the ultrasound imaging method 600 for early pregnancy fetus according to embodiments of this application. Figure 2 The methods for determining the orientation of the target region in the described ultrasound imaging method 200 are generally consistent. Specifically, the target region includes at least one of the following: a head region, a body region, and a whole-body region.

[0161] In one embodiment, the target region includes a head region, and the direction of the target region includes a first direction of the head region, wherein the first direction is the left-right direction of the head region.

[0162] For example, machine learning methods or cranial halo detection methods can be used to detect the head region of the fetus in early pregnancy in three-dimensional ultrasound data. The left and right hemisphere regions of the head region are determined based on the symmetry of the head region of the fetus in early pregnancy, and the normal direction of the interface between the left and right hemisphere regions of the head region is determined as the first direction of the head region.

[0163] Alternatively, the midsagittal plane of the fetal head region in early pregnancy can be extracted from 3D ultrasound data; the normal direction of the midsagittal plane of the head region can be determined as the first direction of the head region.

[0164] The target area may also include a body area, and the direction of the target area includes at least one of the following: a second direction of the body area, a third direction of the body area, and a fourth direction of the body area, wherein the second direction, the third direction, and the fourth direction are respectively the up-down direction, the front-back direction, and the left-right direction of the body area, and any two of the second direction, the third direction, and the fourth direction are perpendicular to each other.

[0165] For example, the spinal region of the fetus in early pregnancy can be detected in three-dimensional ultrasound data; the orientation of the body region can be determined based on the orientation of the spinal region. For instance, a straight line close to the spinal region can be determined, and the orientation of this straight line can be defined as a second orientation of the body region, namely, the up-down direction.

[0166] After determining the second direction, one or more body cross-sections perpendicular to the second direction can be extracted from the three-dimensional ultrasound data of the fetus in early pregnancy. The position of the body center point and the spine in the body cross-section is detected, and the line connecting the body center point and the spine is determined as the third direction of the fetal body region in early pregnancy, i.e., the anterior-posterior direction. Alternatively, the anterior-posterior direction can be determined by identifying a curve close to the spine region and determining the direction of the curve's convexity as the third direction of the fetal body region in early pregnancy.

[0167] In one embodiment, a method for determining body regions may include: detecting body regions of the fetus in early pregnancy from three-dimensional ultrasound data; and determining the orientation of the body regions based on their shape.

[0168] For example, a method for determining the fourth direction of a body region may include: determining a second direction and a third direction of the fetal body region in early pregnancy, and determining the direction perpendicular to the second direction and the third direction as the fourth direction of the fetal body region in early pregnancy. Alternatively, the location of the bilateral kidney regions in the fetal body in early pregnancy may be detected in three-dimensional ultrasound data, and the direction of the line connecting the regions of symmetrical feature structures may be determined as the fourth direction of the fetal body region in early pregnancy.

[0169] As an example, after determining the orientation of the target region, at least one standard section corresponding to the target region can be extracted from the three-dimensional ultrasound data based on the orientation of the target region. For example, multiple candidate sections corresponding to the target region can be determined in the three-dimensional ultrasound data based on the orientation of the target region; and at least one standard section corresponding to the target region can be selected from the multiple candidate sections. Specifically, the early pregnancy target feature structure corresponding to the standard section corresponding to the target region can be detected in the three-dimensional ultrasound data, and the section that at least partially overlaps with the early pregnancy target feature structure and whose angle with the orientation of the target region meets a preset requirement is determined as at least one standard section corresponding to the target region. Further details regarding the determination of the standard section based on the orientation of the target region can be found in the relevant description of the ultrasound imaging method 200.

[0170] Now refer to it again Figure 1 The ultrasound imaging system 100 provided in this application embodiment can be used to implement the ultrasound imaging method 600 for fetuses in early pregnancy described above. 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 relevant descriptions of each component can be found above.

[0171] When used to implement ultrasound imaging method 600, the transmitting / receiving circuit 112 is used to excite the ultrasound probe 110 to emit ultrasound waves toward the fetus in early pregnancy and receive the echo of the ultrasound waves to obtain an ultrasound echo signal; the processor 114 is used to: obtain three-dimensional ultrasound data of the fetus in early pregnancy based on the ultrasound echo signal; determine the direction of the target area of ​​the fetus in early pregnancy according to the three-dimensional ultrasound data; and the display 116 is used to display the direction of the target area.

[0172] The above only describes the main functions of each component of the ultrasound imaging system 100. For more details, please refer to the relevant description of the ultrasound imaging method 600 for early pregnancy fetuses. Furthermore, according to embodiments of this 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 perform the corresponding steps of methods 200, 300, 400, 500, or 600 of embodiments of this application. The storage medium may, for example, include 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 disc 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.

[0173] Furthermore, according to embodiments of this application, a computer program is also provided, which can be stored on a cloud or local storage medium. When this computer program is run by a computer or processor, it is used to perform the corresponding steps of the ultrasound imaging method for early pregnancy fetuses according to embodiments of this application.

[0174] Based on the above description, the ultrasound imaging method and ultrasound imaging system for early pregnancy fetus according to the embodiments of this application can automatically determine the standard section of the early pregnancy fetus based on the three-dimensional ultrasound data acquired in a single session, eliminating the need for doctors to manually extract the standard sections one by one. This greatly optimizes the workflow of prenatal examinations, effectively improves work efficiency, and enhances the stability of the quality of the acquired standard sections, thereby promoting the widespread application of early pregnancy structural screening.

[0175] Although exemplary embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above exemplary embodiments are merely illustrative and are not intended to limit the scope of this application. Various changes and modifications can be made therein by those skilled in the art without departing from the scope and spirit of this application. All such changes and modifications are intended to be included within the scope of this application as claimed in the appended claims.

[0176] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0177] 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 instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed.

[0178] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of this application may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0179] Similarly, it should be understood that, in order to streamline this application and aid in understanding one or more of the various inventive aspects, features of this application may sometimes be grouped together in a single embodiment, figure, or description thereof in the description of exemplary embodiments of this application. However, this approach should not be construed as reflecting an intention that the claimed application requires more features than are expressly recited in each claim. Rather, as reflected in the corresponding claims, its inventive point lies in solving the corresponding technical problem with features fewer than all features of a single disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of this application.

[0180] Those skilled in the art will understand that, apart from the mutual exclusion of features, all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or elements of any method or apparatus so disclosed may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0181] Furthermore, those skilled in the art will understand that although some embodiments described herein include certain features but not others included in other embodiments, combinations of features from different embodiments are intended to be within the scope of this application and form different embodiments. For example, in the claims, any one of the claimed embodiments can be used in any combination.

[0182] The various component embodiments of this application can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some modules according to the embodiments of this application. This application can also be implemented as an apparatus program (e.g., a computer program and computer program product) for performing part or all of the methods described herein. Such an implementation of this application can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0183] It should be noted that the above embodiments are illustrative of this application and not limiting of it, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. This application can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

[0184] The above description is merely a specific embodiment or illustration of the embodiments of this application. The scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. The scope of protection of this application shall be determined by the scope of the claims.

Claims

1. A method for ultrasound imaging of a fetus in early pregnancy, characterized in that, The method includes: Ultrasound waves are emitted towards the fetus in early pregnancy, and the echoes of the ultrasound waves are received to obtain ultrasound echo signals. Three-dimensional ultrasound data of the fetus in early pregnancy are obtained based on the ultrasound echo signals. Detect at least two distinct regions of early pregnancy target features from the three-dimensional ultrasound data, the early pregnancy target features including at least one of the following: nasal bone, ribs, vertebral bones, falx cerebri, lateral ventricle, thalamus, cranial halo, choroid plexus, nuchal translucency, umbilical cord insertion site, umbilical cord, heart, stomach bubble, liver, both kidneys, anterior abdominal wall, both legs, bladder, skin margin, genital ridge; Determine at least one cross section that at least partially overlaps with the region of each of the at least two different early pregnancy target feature structures, as at least one standard cross section of the early pregnancy fetus; Display the at least one standard cross-section.

2. The method according to claim 1, characterized in that, The regions from which at least two distinct early pregnancy target feature structures are detected from the three-dimensional ultrasound data include: Obtain the type of the standard section; Detect regions of at least two distinct early pregnancy target feature structures from the three-dimensional ultrasound data that correspond to the type of the standard section.

3. The method according to claim 1, characterized in that, The method further includes: The regions displaying the at least two different early pregnancy target feature structures.

4. The method according to claim 1, characterized in that, The determination of at least one cross-section that at least partially overlaps with the region of each of the at least two different early pregnancy target feature structures, as at least one standard cross-section of the early pregnancy fetus, includes: A cross section is determined that substantially overlaps with the region of each of the at least two different early pregnancy target feature structures, serving as a standard cross section of the early pregnancy fetus.

5. The method according to claim 1, characterized in that, The standard sections include at least one of the following: a standard section of the head region, a standard section of the body region, and a standard section of the whole body region; the standard section of the head region includes at least one of the following: a transverse section at the level of the lateral ventricle, a biparietal diameter section, and a midsagittal section of the head and neck; the standard section of the body region includes at least one of the following: a thoracic diameter section, an abdominal circumference section, an abdominal wall section at the umbilical cord insertion site, a bladder section, a longitudinal axis section of the spine, and a long axis section of the trunk; the standard section of the whole body region includes a parietal-hip diameter section.

6. The method according to claim 5, characterized in that, When the standard section is the parietal-rump diameter section, the corresponding early pregnancy target feature structures include the nasal bone and genital ridge; when the standard section is a transverse section at the level of the lateral ventricle, the corresponding early pregnancy target feature structures include the falx cerebri, lateral ventricle, and choroid plexus; when the standard section is the biparietal diameter section, the corresponding early pregnancy target feature structures include the thalamus and cranial halo; when the standard section is the midsagittal plane of the head and neck, the corresponding early pregnancy target feature structures include the nuchal translucency and nasal bone; when the standard section is the thoracic diameter section, the corresponding early pregnancy target feature structures include the heart, ribs, and vertebrae; When the standard section is an abdominal section, the corresponding early pregnancy target features include the stomach bubble, spine, and liver; when the standard section is an abdominal wall section at the umbilical cord insertion site, the corresponding early pregnancy target features include the umbilical cord insertion site, umbilical cord, spine, and anterior abdominal wall; when the standard section is a bladder section, the corresponding early pregnancy target features include the legs and bladder; when the standard section is a longitudinal axis section of the spine, the corresponding early pregnancy target features include the spine and skin margin; when the standard section is a long axis section of the trunk, the corresponding early pregnancy target features include the kidneys, stomach bubble, and spine.

7. A method for ultrasound imaging of a fetus in early pregnancy, characterized in that, The method includes: Ultrasound waves are emitted towards the fetus in early pregnancy, and the echoes of the ultrasound waves are received to obtain ultrasound echo signals. Three-dimensional ultrasound data of the fetus in early pregnancy are obtained based on the ultrasound echo signal. Based on the three-dimensional ultrasound data, image features of the target region of the three-dimensional ultrasound data are extracted; The normal direction of the target standard section and the position information of preset points on the target standard section are determined based on the image features of the target region. Specifically, the normal direction of the target standard section is determined based on the mapping relationship between the image features of the target region and the normal direction of the standard section corresponding to the image features of the target region; the position information of the preset points on the target standard section is determined based on the mapping relationship between the image features of the target region and the position information of the preset points on the standard section corresponding to the image features of the target region. The target standard section is determined based on the normal direction of the target standard section and the position information of the preset points on the target standard section; Display the target standard cross-section.

8. The method according to claim 7, characterized in that, The method further includes: The mapping relationship between the image features of the target region and the normal direction of the standard section corresponding to the image features of the target region is regressed using a machine learning model or a deep learning model. A machine learning model or a deep learning model is used to regress the mapping relationship between the image features of the target region and preset points on the standard cross-section corresponding to the image features of the target region.

9. The method according to claim 7 or 8, characterized in that, The standard sections include one or more of the following sections: transverse section at the level of the lateral ventricle, biparietal diameter section, midsagittal section of the head and neck, thoracic diameter section, abdominal circumference section, abdominal wall section at the umbilical cord insertion site, bladder section, longitudinal axis section of the spine, long axis section of the trunk, and parietal-hip diameter section.

10. A method for ultrasound imaging of a fetus in early pregnancy, characterized in that, The method includes: Ultrasound waves are emitted towards the fetus in early pregnancy, and the echoes of the ultrasound waves are received to obtain ultrasound echo signals. Three-dimensional ultrasound data of the fetus in early pregnancy are obtained based on the ultrasound echo signal. The orientation of the target region of the fetus in early pregnancy is determined based on the three-dimensional ultrasound data. When the target region is the head region, the orientation of the target region includes the left-right direction of the head region; when the target region is the body region, the orientation of the target region includes the up-down direction, the front-back direction, and the left-right direction of the body region. The orientation of the target region of the fetus in early pregnancy is displayed in the three-dimensional ultrasound data.

11. The method according to claim 10, characterized in that, The method further includes: Based on the orientation of the target region, at least one standard section is extracted from the three-dimensional ultrasound data; Display the at least one standard cross-section.

12. The method according to claim 11, characterized in that, When the target region is the head region, the at least one standard section includes the standard section corresponding to the head region, wherein the standard section corresponding to the head region includes at least one of the following: a transverse section at the level of the lateral ventricle, a biparietal diameter section, and a midsagittal section of the head and neck. When the target area is a body area, the at least one standard section includes the standard section corresponding to the body area. The standard section corresponding to the body area includes at least one of the following: chest diameter section, abdominal circumference section, abdominal wall umbilical cord insertion site section, bladder section, longitudinal axis section of the spine, and long axis section of the trunk. The standard section corresponding to the whole body area includes the top-to-hip diameter section.

13. The method according to any one of claims 10-12, characterized in that, Determining the orientation of the target region of the fetus in early pregnancy based on the three-dimensional ultrasound data includes: The head region of the fetus in early pregnancy is detected in the three-dimensional ultrasound data, and the left-right direction of the head region is determined based on its symmetry; or The midsagittal plane of the fetal head region in early pregnancy is extracted from the three-dimensional ultrasound data, and the normal direction of the midsagittal plane of the head region is determined as the left-right direction of the head region; or The spinal region of the early-pregnancy fetus is detected in the three-dimensional ultrasound data, and the orientation of the body region is determined based on the orientation of the spinal region; or The body regions of the fetus in early pregnancy are detected from the three-dimensional ultrasound data, and the orientation of the body regions is determined based on their shape.

14. The method according to any one of claims 10-13, characterized in that, Extracting at least one standard section from the three-dimensional ultrasound data based on the orientation of the target region includes: Multiple candidate sections are determined in the three-dimensional ultrasound data based on the orientation of the target region; Select at least one standard cross section that corresponds to the target region from the plurality of candidate cross sections.

15. The method according to claim 14, characterized in that, Selecting at least one standard cross-section corresponding to the target region from the plurality of candidate cross-sections includes: A trained machine learning model is used to determine the probability of each candidate section being a standard section, and the candidate sections whose probabilities satisfy a first threshold are determined as at least one standard section corresponding to the target region; or A trained machine learning model is used to determine the probability of each candidate section being used as a standard section, and the candidate section with the highest probability is determined as the standard section corresponding to the target region; or Early pregnancy target feature structures corresponding to at least one standard section are detected on the multiple candidate sections, and the candidate sections whose probability of the existence of early pregnancy target feature structures satisfies a second threshold are determined as the standard sections.

16. Extracting at least one standard section from the three-dimensional ultrasound data based on the orientation of the target region includes: Detect the early pregnancy target feature structure corresponding to at least one standard section in the three-dimensional ultrasound data; The cross-section that at least partially overlaps with the early pregnancy target feature structure and whose angle with the direction of the target region meets a preset requirement is determined as the at least one standard cross-section.

17. The method according to claim 16, characterized in that, The step of determining the cross-section that at least partially coincides with the early pregnancy target feature structure and whose angle with the direction of the target region meets a preset requirement as the at least one standard cross-section includes: The cross-section that substantially coincides with the early pregnancy target feature structure and has an angle of 0 degrees with the direction of the target region is determined as the standard cross-section.

18. An ultrasound imaging system, characterized in that, The ultrasound imaging system includes: Ultrasonic probe; A transmitting / receiving circuit is used to excite the ultrasound probe to emit ultrasound waves toward the fetus in early pregnancy and to receive the echo of the ultrasound waves to obtain an ultrasound echo signal. Processor for executing the ultrasound data processing method for a fetus in early pregnancy as described in any one of claims 1-17. A display for showing three-dimensional ultrasound data of the fetus in early pregnancy, as well as sections and / or parameters obtained based on the three-dimensional ultrasound data.

Images