Ultrasound imaging method and ultrasound imaging system of a first trimester fetus

Abstract

An ultrasonic imaging method (200) and an ultrasonic imaging system (100) for an early gestation fetus, the ultrasonic imaging method (200) comprising: emitting ultrasonic waves to the early gestation fetus, receiving echoes of the ultrasonic waves to obtain ultrasonic echo signals (S210); obtaining three-dimensional ultrasonic data of the early gestation fetus based on the ultrasonic echo signals (S220); determining a direction of a target region of the early gestation fetus according to the three-dimensional ultrasonic data (S230); extracting at least one standard section corresponding to the target region from the three-dimensional ultrasonic data according to the direction of the target region (S240); and displaying the at least one standard section (S250). The ultrasonic imaging method (200) and the ultrasonic imaging system (100) for the early gestation fetus automatically extract standard sections of the early gestation fetus from single-acquisition three-dimensional ultrasonic data, without requiring a doctor to manually extract the standard sections one by one, thereby improving the efficiency of extracting the standard sections and the quality of the extracted standard sections.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of ultrasonic imaging, and more particularly to an ultrasonic imaging method and system for early gestation fetuses. BACKGROUND

[0002] Ultrasound examination has a wide range of applications in clinical examination due to its safety, convenience, non-radiation, low cost and other advantages, and has become one of the main auxiliary means for doctors to diagnose diseases. Prenatal ultrasound examination, as the most important imaging examination in prenatal examination, provides the most important imaging evidence for fetal growth and development measurement and structural abnormality screening. Prenatal ultrasound examination is one of the examinations that must be performed during early gestation, mid-gestation and late gestation.

[0003] In actual clinical application, fetal structure examination and malformation screening in early gestation are the current clinical development trend and research hotspot. Carrying out fetal structure screening in early gestation can discover lethal malformations as early as possible, provide pregnant women with the opportunity to terminate pregnancy as early as possible, and minimize physical and mental harm, which has very important clinical significance and value. However, the number of sections for early gestation fetal structure abnormality screening is large, the requirements of each section are different, the acquisition of the sections is relatively cumbersome, and the quality of the sections is greatly affected by the experience and skills of doctors. SUMMARY

[0004] A series of simplified concepts are introduced in the summary section, which will be further described in detail in the specific embodiments section. The summary section of the present application does not mean to attempt to limit the key features and necessary technical features of the claimed technical solutions, nor to attempt to determine the protection scope of the claimed technical solutions.

[0005] The first aspect of the embodiment of the present application provides an ultrasonic imaging method for an early gestation fetus, the method comprising:

[0006] ultrasound waves are emitted to the early gestation fetus, and echoes of the ultrasound waves are received to obtain ultrasonic echo signals;

[0007] three-dimensional ultrasonic data of the early gestation fetus are obtained based on the ultrasonic echo signals;

[0008] a direction of a target region of the early gestation fetus is determined according to the three-dimensional ultrasonic data;

[0009] at least one standard section corresponding to the target region is extracted from the three-dimensional ultrasonic data according to the direction of the target region;

[0010] the at least one standard section is displayed.

[0011] The second aspect of the embodiment of the present application provides an ultrasonic imaging method for an early gestation fetus, and the method comprises the following steps:

[0012] ultrasonic waves are emitted to the early gestation fetus, and echoes of the ultrasonic waves are received to obtain ultrasonic echo signals;

[0013] three-dimensional ultrasonic data of the early gestation fetus are obtained according to the ultrasonic echo signals;

[0014] regions of at least two different early gestation target feature structures are detected from the three-dimensional ultrasonic data;

[0015] at least one section plane that at least partially coincides with each of the regions of the at least two different early gestation target feature structures is determined as at least one standard section plane of the early gestation fetus;

[0016] the at least one standard section plane is displayed.

[0017] The third aspect of the embodiment of the present application provides an ultrasonic imaging method for an early gestation fetus, and the method comprises the following steps:

[0018] ultrasonic waves are emitted to the early gestation fetus, and echoes of the ultrasonic waves are received to obtain ultrasonic echo signals;

[0019] three-dimensional ultrasonic data of the early gestation fetus are obtained according to the ultrasonic echo signals;

[0020] the three-dimensional ultrasonic data are matched with an ultrasonic data template of a preconfigured early gestation standard section plane, and a target standard section plane in the three-dimensional ultrasonic data is determined according to a matching result, wherein the early gestation standard section plane comprises at least one of the following: a transverse section plane at a lateral ventricle level, a biparietal diameter section plane, a median sagittal section plane of a head and neck, a thoracic diameter section plane, an abdominal circumference section plane, an abdominal wall umbilical cord insertion section plane, a bladder section plane, a spinal column longitudinal axis section plane, a trunk long axis section plane and a crown-heel diameter section plane;

[0021] the target standard section plane is displayed.

[0022] The fourth aspect of the embodiment of the present application provides an ultrasonic imaging method for an early gestation fetus, and the method comprises the following steps:

[0023] ultrasonic waves are emitted to the early gestation fetus, and echoes of the ultrasonic waves are received to obtain ultrasonic echo signals;

[0024] three-dimensional ultrasonic data of the early gestation fetus are obtained according to the ultrasonic echo signals;

[0025] image features of a target region of the three-dimensional ultrasonic data are extracted according to the three-dimensional ultrasonic data;

[0026] determine a normal direction of a target standard section and position information of a preset point on the target standard section according to image features of the target region;

[0027] determine the target standard section according to the normal direction of the target standard section and the position information of the preset point on the target standard section;

[0028] display the target standard section.

[0029] A fifth aspect of an embodiment of the present application provides an ultrasonic imaging method for an early gestation fetus, the method comprising:

[0030] transmitting ultrasonic waves to the early gestation fetus and receiving echoes of the ultrasonic waves to obtain ultrasonic echo signals;

[0031] obtaining three-dimensional ultrasonic data of the early gestation fetus based on the ultrasonic echo signals;

[0032] determining a direction of a target region of the early gestation fetus according to the three-dimensional ultrasonic data;

[0033] displaying the direction of the target region of the early gestation fetus.

[0034] A sixth aspect of an embodiment of the present application provides an ultrasonic imaging system, the ultrasonic imaging system comprising:

[0035] an ultrasonic probe;

[0036] transmitting / receiving circuitry configured to excite the ultrasonic probe to transmit ultrasonic waves to an early gestation fetus and receive echoes of the ultrasonic waves to obtain ultrasonic echo signals;

[0037] a processor configured to:

[0038] obtain three-dimensional ultrasonic data of the early gestation fetus based on the ultrasonic echo signals;

[0039] determine a direction of a target region of the early gestation fetus according to the three-dimensional ultrasonic data;

[0040] extract at least one standard section corresponding to the target region from the three-dimensional ultrasonic data according to the direction of the target region;

[0041] a display configured to display the at least one standard section.

[0042] A seventh aspect of an embodiment of the present application provides an ultrasonic imaging system, the ultrasonic imaging system comprising:

[0043] an ultrasonic probe;

[0044] transmit / receive circuitry configured to excite the ultrasound probe to transmit ultrasound waves to an early gestation fetus and receive echoes of the ultrasound waves to obtain ultrasound echo signals;

[0045] a processor configured to:

[0046] display three-dimensional ultrasound data of the early gestation fetus obtained from the ultrasound echo signals according to the at least one standard section;

[0047] regions of at least two different early gestation target features from the three-dimensional ultrasound data;

[0048] determine at least one section at least partially coinciding with each of the regions of the at least two different early gestation target features as at least one standard section of the early gestation fetus;

[0049] a display configured to display the at least one standard section.

[0050] An eighth aspect of the embodiments of the present application provides an ultrasound imaging system, the ultrasound imaging system comprising:

[0051] an ultrasound probe;

[0052] transmit / receive circuitry configured to excite the ultrasound probe to transmit ultrasound waves to an early gestation fetus and receive echoes of the ultrasound waves to obtain ultrasound echo signals;

[0053] a processor configured to:

[0054] obtain three-dimensional ultrasound data of the early gestation fetus according to the ultrasound echo signals;

[0055] match the three-dimensional ultrasound data with an ultrasound data template of preconfigured early gestation standard sections, and determine a target standard section in the three-dimensional ultrasound data according to a matching result, wherein the early gestation standard sections comprise at least one of a transverse section at the level of lateral ventricles, a biparietal diameter section, a median sagittal section of the head and neck, a chest diameter section, an abdominal circumference section, a section at the insertion of the umbilical cord into the abdominal wall, a bladder section, a longitudinal axis section of the spine, a longitudinal axis section of the trunk, and a crown-heel diameter section;

[0056] a display configured to display the target standard section.

[0057] A ninth aspect of the embodiments of the present application provides an ultrasound imaging system, the ultrasound imaging system comprising:

[0058] an ultrasound probe;

[0059] transmit / receive circuitry configured to excite the ultrasound probe to transmit ultrasound waves to an early gestation fetus and receive echoes of the ultrasound waves to obtain ultrasound echo signals;

[0060] a processor configured to:

[0061] extract image features of a target region of the three-dimensional ultrasound data according to the three-dimensional ultrasound data;

[0062] determine a normal direction of a target standard cross-section and position information of a preset point on the target standard cross-section according to the image features of the target region;

[0063] obtain three-dimensional ultrasound data of the early gestation period fetus according to the ultrasound echo signal;

[0064] extract image features of a target region of the three-dimensional ultrasound data according to the three-dimensional ultrasound data;

[0065] determine a normal direction of a target standard cross-section and position information of a preset point on the target standard cross-section according to the image features of the target region;

[0066] determine the target standard cross-section according to the normal direction of the target standard cross-section and the position information of the preset point on the target standard cross-section;

[0067] a display configured to display the target standard cross-section.

[0068] An eleventh aspect of an embodiment of the present application provides an ultrasound imaging system, the ultrasound imaging system comprising:

[0069] an ultrasound probe;

[0070] a transmitting / receiving circuit configured to excite the ultrasound probe to emit ultrasound waves to an early gestation period fetus and receive echoes of the ultrasound waves to obtain an ultrasound echo signal;

[0071] a processor configured to:

[0072] obtain three-dimensional ultrasound data of the early gestation period fetus based on the ultrasound echo signal;

[0073] determine a direction of a target region of the early gestation period fetus according to the three-dimensional ultrasound data;

[0074] a display configured to display the direction of the target region of the early gestation period fetus.

[0075] The ultrasound imaging method and the ultrasound imaging system of the early gestation period fetus according to the embodiments of the present application can automatically extract a standard cross-section of an early gestation period fetus according to three-dimensional ultrasound data collected at a single time, without manually extracting the standard cross-section one by one by a doctor, greatly optimizing a work flow of prenatal examination, effectively improving work efficiency, and improving stability of quality of the obtained standard cross-section, promoting popularization and application of early gestation structure screening. BRIEF DESCRIPTION OF DRAWINGS

[0076] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiment description. Obviously, the drawings described below only show some of the embodiments of the present application, and all other drawings obtained by those skilled in the art without creative effort based on these drawings should fall within the protection scope of the present application.

[0077] In the drawings:

[0078] Figure 1 A schematic block diagram of an ultrasound imaging system according to an embodiment of the present application is shown;

[0079] Figure 2 A schematic flow chart of an ultrasound imaging method of a first trimester fetus according to an embodiment of the present application is shown;

[0080] Figure 3 A schematic flow chart of an ultrasound imaging method of a first trimester fetus according to another embodiment of the present application is shown;

[0081] Figure 4 A schematic flow chart of an ultrasound imaging method of a first trimester fetus according to another embodiment of the present application is shown;

[0082] Figure 5 A schematic flow chart of an ultrasound imaging method of a first trimester fetus according to yet another embodiment of the present application is shown;

[0083] Figure 6 A schematic flow chart of an ultrasound imaging method of a first trimester fetus according to yet another embodiment of the present application is shown. DETAILED DESCRIPTION

[0084] In order to make the objectives, technical solutions and advantages of the present application more apparent, the following will describe the example embodiments according to the present application in detail with reference to the drawings. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application described in the present application, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present application.

[0085] In the following description, a large number of specific details are given in order to provide a more thorough understanding of the present application. However, it is obvious to those skilled in the art that the present application can be implemented without one or more of these details. In other examples, in order to avoid obscuring the present application, some technical features known in the art are not described.

[0086] It is to be understood that the application can assume various alternative embodiments, and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the application to those skilled in the art.

[0087] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising", when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. As used herein the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0088] For a thorough understanding of the application, reference will be made to the following detailed description, taken in conjunction with the accompanying drawings, in which:

[0089] Below, reference will first be made to Figure 1 An ultrasound imaging system according to an embodiment of the application is described, Figure 1 A schematic block diagram of an ultrasound imaging system 100 according to an embodiment of the application is shown.

[0090] As Figure 1 is shown, the ultrasound imaging system 100 comprises an ultrasound probe 110, transmit / receive circuitry 112, a processor 114, a display 116, and a memory 118. Further, the ultrasound imaging system 100 can also comprise beamforming circuitry and transmit / receive selection switches, etc.

[0091] Specifically, the ultrasound probe 110 includes a plurality of transducer elements, which can be arranged in a row to form a linear array, or arranged in a two-dimensional matrix to form a planar array, or arranged to form a convex array. The transducer elements are used to emit ultrasound waves according to excitation electrical signals, or convert received ultrasound waves into electrical signals, and thus each transducer element can be used to realize the mutual conversion between electrical pulse signals and ultrasound waves, so as to realize the emission of ultrasound waves to the target region of the object under test, and also can be used to receive the ultrasound echo reflected by the object under test. When performing ultrasound imaging, it can be controlled by a transmission sequence and a reception sequence which transducer elements are used to emit ultrasound waves and which transducer elements are used to receive ultrasound waves, or control the transducer elements to be used for emitting ultrasound waves or receiving echo of ultrasound waves in time slots. The transducer elements participating in the emission of ultrasound waves can be excited by electrical signals at the same time, so as to emit ultrasound waves at the same time; or the transducer elements participating in the emission of ultrasound beams can also be excited by several electrical signals with a certain time interval, so as to continuously emit ultrasound waves with a certain time interval.

[0092] The transmit / receive circuit 112 can be connected with the ultrasound probe 110 through a transmit / receive selection switch. The transmit / receive selection switch can also be referred to as a transmit / receive controller, which can include a transmission controller and a reception controller. The transmission controller is used to excite the ultrasound probe 110 to emit ultrasound waves to the region where the early gestation period fetus is located via a transmission circuit; and the reception controller is used to receive the ultrasound echo returned from the region where the early gestation period fetus is located through the ultrasound probe 110 via a reception circuit, so as to obtain the ultrasound echo data. Then, the transmit / receive circuit 112 sends the electrical signals of the ultrasound echo into the beamforming circuit, and the beamforming circuit performs focusing delay, weighting and channel summation on the electrical signals, and then sends the processed ultrasound echo data into the processor 114.

[0093] Optionally, the processor 114 can be implemented by software, hardware, firmware or any combination thereof, and can use circuits, single or multiple application specific integrated circuits (ASIC), single or multiple general purpose integrated circuits, single or multiple microprocessors, single or multiple programmable logic devices, or any combination of the foregoing circuits and / or devices, or other suitable circuits or devices, so that the processor 114 can perform the corresponding steps of the method in each embodiment of the present specification. Moreover, the processor 114 can control other components in the ultrasound imaging system 100 to perform the desired functions.

[0094] The processor 114 processes the received ultrasonic echo data to obtain three-dimensional ultrasonic data of the early-stage fetus. As an example, the ultrasonic probe 110 transmits / receives ultrasonic waves in a series of scanning planes, which are integrated by the processor 114 according to their three-dimensional spatial relationship to realize scanning of the early-stage fetus in three-dimensional space and reconstruction of a three-dimensional image. Finally, the three-dimensional ultrasonic data of the early-stage fetus is obtained after the processor 114 performs partial or complete image post-processing steps such as denoising, smoothing, and enhancement on the three-dimensional ultrasonic data. The processor 114 can obtain three-dimensional ultrasonic data of the whole body of the early-stage fetus, or only the head or body of the early-stage fetus. The processor 114 is also used to extract standard sections of the early-stage fetus from the three-dimensional ultrasonic data. The standard sections obtained by the processor 114 can be stored in the memory or displayed on the display 116. In addition, the processor 114 can also render the three-dimensional ultrasonic data and display it on the display 116.

[0095] The display 116 is connected to the processor 114, and the display 116 can be a touch display screen, a liquid crystal display screen, etc.; or the display 116 can be a liquid crystal display, a television, etc. independent display device independent of the ultrasonic imaging system 100; or the display 116 can be a display screen of a smart phone, a tablet computer, etc. electronic device, etc. The number of displays 116 can be one or more. For example, the display 116 can include a main screen and a touch screen, the main screen is mainly used to display ultrasonic images, and the touch screen is mainly used for human-computer interaction.

[0096] The display 116 can display the ultrasonic images obtained by the processor 114. In addition, the display 116 can also provide a graphical interface for the user to interact with while displaying the ultrasonic images, set one or more controlled objects on the graphical interface, and provide the user with an input operation instruction using a human-computer interaction device to control these controlled objects, thereby executing a corresponding control operation. For example, an icon is displayed on the graphical interface, and the icon can be operated using a human-computer interaction device to execute a specific function.

[0097] Optionally, the ultrasonic imaging system 100 can also include other human-computer interaction devices other than the display 116, which are connected to the processor 114. For example, the processor 114 can be connected to the human-computer interaction device through an external input / output port, which can be a wireless communication module, a wired communication module, or a combination of the two. The external input / output port can also be implemented based on a USB, a bus protocol such as CAN, and / or a wired network protocol, etc.

[0098] The human-computer interaction device can include an input device for detecting input information of the user, which can be, for example, a control instruction for the ultrasonic wave emission / reception timing, an operation input instruction for drawing a point, a line, or a frame on the ultrasonic image, or can also include other instruction types. The input device can include one or a combination of a keyboard, a mouse, a scroll wheel, a trackball, a mobile input device (such as a mobile device with a touch display screen, a mobile phone, and the like), a multifunction knob, and the like. The human-computer interaction device can also include an output device such as a printer.

[0099] The ultrasonic imaging system 100 can also include a memory for storing instructions executed by the processor, storing received ultrasonic echoes, storing ultrasonic images, and the like. The memory can be a flash memory card, a solid-state memory, a hard disk, and the like. It can be a volatile memory and / or a non-volatile memory, a removable memory and / or a non-removable memory, and the like.

[0100] It should be understood that Figure 1 The components included in the illustrated ultrasonic imaging system 100 are only schematic, and the system can include more or fewer components. The present application is not limited thereto.

[0101] In the following, the ultrasonic imaging method for a first-trimester fetus according to an embodiment of the present application will be described with reference to the accompanying drawings. Figure 2 An ultrasonic imaging method for a first-trimester fetus according to an embodiment of the present application will be described. Figure 2 is a schematic flowchart of an ultrasonic imaging method for a first-trimester fetus 200 according to an embodiment of the present application.

[0102] As Figure 2 shown, the ultrasonic imaging method for a first-trimester fetus 200 according to an embodiment of the present application includes the following steps:

[0103] First, in step S210, ultrasonic waves are emitted to the first-trimester fetus, and echoes of the ultrasonic waves are received to obtain an ultrasonic echo signal.

[0104] The first-trimester fetus generally refers to a fetus below 14 weeks of gestation. The first-trimester fetus has already grown to a certain size, most organs have been differentiated, and a considerable part of the characteristic structures can be identified by ultrasonic imaging. The ultrasonic imaging method provided by the present application can automatically extract a standard section reflecting the characteristic structure information, thereby realizing structural examination and malformation screening of the fetus in the first trimester. Compared with ultrasonic examination in the second and third trimester, the present application can provide relevant pregnancy information to the pregnant woman as early as possible.

[0105] Exemplarily, the standard section can be determined based on Figure 1The illustrated ultrasound imaging system 100 performs ultrasound image acquisition. A user moves the ultrasound probe 110 to select a suitable position and angle, a set of delay-focused pulses are transmitted to the ultrasound probe 110 by the transmit circuit in the transmit / receive circuit 120, and the ultrasound probe 110 transmits ultrasound waveforms to the early gestation fetus along a 2D scan plane. After the ultrasound probe 110 receives the reflected ultrasound echoes, it converts them into electrical signals, and the signals obtained by multiple transmissions / receptions are processed by the beamforming circuit to achieve beamforming by corresponding delay and weighted summation, and then sent to the processor 114 for subsequent signal processing.

[0106] Exemplarily, the function of automatically extracting the standard section can be automatically started or manually started by the user before step S210 is performed. In some embodiments, a user interface can also be provided before or after step S210 is performed to allow the user to manually select the standard section desired to be extracted. However, this step is optional, and in other embodiments, all the standard sections involved below can be extracted by default.

[0107] In step S220, three-dimensional ultrasound data of the early gestation fetus is obtained based on the ultrasound echo signals.

[0108] Specifically, the three-dimensional spatial relationship of the ultrasound echoes obtained by the ultrasound probe 110 in a series of scan planes can be integrated to achieve scanning of the early gestation fetus in three-dimensional space and reconstruction of a 3D image. Finally, after partial or complete image post-processing steps such as denoising, smoothing, and enhancement, three-dimensional ultrasound data of the early gestation fetus is obtained.

[0109] Among them, three-dimensional ultrasound data of the whole body of the early gestation fetus can be obtained, or only three-dimensional data of the head region of the early gestation fetus or the body region of the early gestation fetus can be obtained, depending on the standard section to be extracted. When the standard section to be extracted includes the standard section corresponding to the head region of the early gestation fetus, the three-dimensional ultrasound data at least includes three-dimensional ultrasound data of the head region of the early gestation fetus. When the standard section to be extracted includes the standard section corresponding to the body region of the early gestation fetus, the three-dimensional ultrasound data at least includes three-dimensional ultrasound data of the body region of the early gestation fetus. When the standard section to be extracted includes the standard section corresponding to the whole body region of the early gestation fetus, three-dimensional ultrasound data of the whole body region of the early gestation fetus needs to be obtained.

[0110] In the embodiments of the present application, the standard section is a two-dimensional section containing key information in the three-dimensional ultrasound image, and physiological characteristic structures with clinical value can be observed through the two-dimensional section. Exemplarily, the standard sections to be extracted include at least one of the following standard sections: a biparietal diameter section (i.e., a whole-body median sagittal section), a lateral ventricle horizontal transverse section, a bi-parietal diameter section (i.e., a thalamic horizontal transverse section), an NT standard section (i.e., a head-neck median sagittal section), a chest diameter section (i.e., a four-chamber heart section), an abdominal circumference section (i.e., a gastric bubble section), an abdominal wall umbilical cord insertion section, a bladder section, a spinal longitudinal axis section (i.e., a body median sagittal section), and a trunk long axis section (i.e., a body coronal section). Multiple standard sections in the above standard sections can be extracted to comprehensively screen the early-stage fetus.

[0111] In the above standard sections, the lateral ventricle horizontal transverse section, the bi-parietal diameter section, and the NT standard section are standard sections corresponding to the head region of the early-stage fetus, and the three-dimensional ultrasound data is required to at least include three-dimensional ultrasound data of the head region of the early-stage fetus; the chest diameter section, the abdominal circumference section, the abdominal wall umbilical cord insertion section, the bladder section, the spinal longitudinal axis section, and the trunk long axis section are standard sections corresponding to the body region of the early-stage fetus, and the three-dimensional ultrasound data is required to at least include three-dimensional ultrasound data of the body region of the early-stage fetus; and the biparietal diameter section is a standard section corresponding to the whole body region of the early-stage fetus, and thus the three-dimensional ultrasound data is required to include three-dimensional ultrasound data of the whole body region of the early-stage fetus.

[0112] In some embodiments, after obtaining the three-dimensional ultrasound data, a visualization algorithm can be used to render the three-dimensional ultrasound data to obtain a three-dimensional ultrasound image, which is displayed by a display device. The rendering includes, for example, a surface rendering method or a volume rendering method, and the embodiments of the present application do not limit the same.

[0113] In step S230, a direction of a target region of the early-stage fetus is determined according to the three-dimensional ultrasound data.

[0114] The determination of the direction of the target region of the early-stage fetus can include determination of a direction of a head region of the early-stage fetus, determination of a direction of a body region of the early-stage fetus, or determination of the directions of the head region and the body region of the early-stage fetus. When the standard section to be extracted includes a standard section corresponding to the head region of the early-stage fetus, the direction corresponding to the head region of the early-stage fetus is determined according to three-dimensional ultrasound data of the head region of the early-stage fetus. The direction of the head region can also be used to extract a standard section corresponding to the whole body region of the early-stage fetus, such as the biparietal diameter section. When the standard section to be extracted includes a standard section corresponding to the body region of the early-stage fetus, the direction of the body region of the early-stage fetus is determined according to three-dimensional ultrasound data of the body region of the early-stage fetus.

[0115] Next, first, several implementations of determining the direction of the head region of the early gestation fetus are exemplarily described. Among them, the direction of the target region includes the first direction of the head region of the early gestation fetus, wherein the first direction is the left-right direction of the head region. Since the standard section corresponding to the head region is generally parallel or perpendicular to the left-right direction of the head, and the determination of the left-right direction of the head is relatively more accurate, the determination of the direction of the head region of the early gestation fetus can at least include the determination of the left-right direction of the head region of the early gestation fetus. But in other embodiments, the determined direction of the head region of the early gestation fetus can also be other directions, such as the up-down direction of the head region.

[0116] In one embodiment, the direction of the head region of the early gestation fetus can be determined by a trained machine learning model.

[0117] Before model training, an early gestation fetus ultrasound database needs to be established first, which includes a large amount of ultrasound data of early gestation fetuses, and each ultrasound data is labeled with the direction of the head region of the early gestation fetus, or the position and direction of the head region. Among them, the position of the head region can be the position of the region of interest (ROI) of the head, such as the position of the vertices of the ROI frame or the position of the center point of the ROI frame and the size of the frame, or the position of the head region can be the specific region range of the head region of the fetus; the direction of the head region can be the left-right direction of the head region.

[0118] After the database is constructed, the traditional machine learning model or the deep learning model is trained with the ultrasound data in the database as the training sample, which is used to predict the position and direction of the head region of the early gestation fetus. Specifically, according to the ultrasound data in the early gestation fetus ultrasound database, an optimal mapping function from ultrasound data to head region position and direction can be learned, so that the error between the head region position and direction mapped from the early gestation data in the database and the actually calibrated head region position and direction is minimized. For the three-dimensional ultrasound data obtained in step S220, the optimal mapping function is executed, and the prediction result of the head region position and direction is obtained.

[0119] The traditional machine learning method includes SVM support vector machine, logistic regression method, least square method, etc. For the traditional machine learning method, first, the image features are extracted from the ultrasound images in the early gestation fetus ultrasound database, such as Sift features, gradient features, LBP texture features, PCA, LDA, Harr features, HOG and LOG features, etc., and then the optimal mapping function between the image features and the head region position and direction is learned. For the deep learning model, an end-to-end neural network can be trained as the optimal mapping function to directly construct the mapping relationship between the ultrasound data of the early gestation fetus and the direction of its head region.

[0120] In another embodiment, the first direction of the head region, i.e. the left-right direction, can be determined according to the symmetry of the head. Specifically, the head region of the early gestation fetus is first detected in the three-dimensional ultrasound data obtained in step S220, and then the first direction of the head of the early gestation fetus, i.e. the left-right direction, is determined according to the symmetry of the head region of the early gestation fetus.

[0121] Exemplarily, the head of the early gestation fetus can be detected in the three-dimensional ultrasound data by using a machine learning method, a skull halo detection method, or any other suitable three-dimensional image segmentation method.

[0122] In the machine learning method, an early gestation fetus ultrasound database is first established, in which the position of the head region of each early gestation fetus, such as the position of the head region of interest box (ROI) or the specific region range of the head, is marked, and then a conventional machine learning method or a deep learning method is used to learn an optimal mapping function for obtaining the position of the head region of interest box (ROI) or the specific region range of the head from the three-dimensional ultrasound data of the early gestation fetus, thereby realizing the detection or segmentation of the head of the early gestation fetus.

[0123] In the skull halo detection method, methods such as Hough transform and RANSAC can be used to detect the circular or elliptical, spherical or ellipsoidal shape with the brightest brightness, the strongest gradient, or the maximum brightness and gradient weighting in the three-dimensional ultrasound data of the early gestation fetus, as the detection result of the head region of the early gestation fetus.

[0124] After the head region of the early gestation fetus is determined, the left-right direction of the head region can be determined according to the symmetry of the head region. Exemplarily, the left hemisphere region and the right hemisphere region of the head region can be determined according to the symmetry of the head of the early gestation fetus, and the normal direction of the interface between the left hemisphere region and the right hemisphere region of the head region is determined as the left-right direction of the head region.

[0125] In which, the left hemisphere region and the right hemisphere region with optimal symmetry can be obtained by using methods such as preset search, gradient update, and reinforcement learning. In the preset search method, a plurality of candidate interfaces between the left hemisphere region and the right hemisphere region of the head are first generated according to a predetermined rule, and the left hemisphere region and the right hemisphere region are on both sides of the interface; then, the left hemisphere region and the right hemisphere region with optimal symmetry are found by judging one by one. In the gradient update and reinforcement learning method, a fixed section is first taken as the initial interface between the left hemisphere region and the right hemisphere region of the head, and then the interface between the left hemisphere region and the right hemisphere region of the head is iterated according to the gradient direction of the symmetry function or the iterative direction obtained by the reinforcement learning method until the symmetry of the left hemisphere region and the right hemisphere region reaches the optimal.

[0126] In the above method, the symmetry of the left hemisphere region and the right hemisphere region can be evaluated according to various suitable indexes such as absolute error, square error, correlation function, correlation coefficient, and output results of deep learning networks such as twin networks and CNNs of gray value of the left hemisphere region and the right hemisphere region, so as to find the left hemisphere region and the right hemisphere region with the optimal symmetry.

[0127] In another embodiment, the direction of the head region can also be determined by using the detection of the median sagittal plane. Specifically, the median sagittal plane of the head region of the early gestation fetus is extracted from the three-dimensional ultrasound data obtained in step S220, and the normal direction of the median sagittal plane is determined as the left-right direction of the head region.

[0128] Among them, for example, preset search, gradient update, reinforcement learning and other methods can be used to extract the median sagittal plane from the three-dimensional ultrasound data of the early gestation fetus.

[0129] In the preset search and gradient update method, a database of early gestation fetus section images is first established, each section image in the database is a section in the three-dimensional data of the early gestation fetus, and whether the section is a median sagittal plane is marked. After establishing the database, a traditional machine learning method or a deep learning method can be used to learn an optimal mapping function from the early gestation fetus section image to the category of whether it is a median sagittal plane, which is used to determine whether each section is a median sagittal plane or the probability of each section belonging to a median sagittal plane.

[0130] In the preset search method, a plurality of candidate median sagittal planes are first generated according to a predetermined rule, and then the candidate median sagittal plane with the highest probability of belonging to a median sagittal plane is taken as the detection result of the median sagittal plane. In the gradient update method, a fixed section is first taken as the starting position of the median sagittal plane, and then the section is iteratively updated according to the gradient direction of the probability function of the median sagittal plane until the probability value of belonging to the median sagittal plane reaches the maximum or the probability value exceeds a predetermined threshold, i.e. the detection result of the median sagittal plane is obtained.

[0131] In the reinforcement learning method, a reward function is first determined for each section in the three-dimensional ultrasound data of the early gestation fetus and the transformation (translation, rotation, etc.) of the section. The reward function can be related to the image similarity, image error, position and orientation deviation between the current section and the actual median sagittal plane, and the reward function of the section transformation is the difference between the reward functions of the sections before and after the transformation. When actually finding the median sagittal plane, a fixed section is first taken as the starting position of the median sagittal plane, and then the section is iteratively updated until the reward function of the final section reaches the maximum, i.e. the detection result of the median sagittal plane is obtained.

[0132] When the target region comprises a body region, the direction of the target region comprises at least one of a second direction of the body region, a third direction of the body region, and a fourth direction of the body region, wherein the second direction, the third direction, and the fourth direction of the body region are respectively a vertical direction, a front-rear direction, and a left-right direction of the body region, and any two of the second direction, the third direction, and the fourth direction are perpendicular to each other. Determining the body direction of the early-stage fetus comprises but is not limited to the following implementation manners:

[0133] In an implementation manner, the body direction can be determined by using a trained machine learning model.

[0134] This manner is similar to the determination of the head direction by using a trained machine learning model as described above. Specifically, first, an ultrasound database of early-stage fetuses is established, and each ultrasound data in the database is labeled with the direction of the body region of the early-stage fetus or the position and direction of the body region of the early-stage fetus. After the database is constructed, a conventional machine learning model or a deep learning model is trained to predict the direction of the body region or the position and direction of the body region of an early-stage fetus to be identified from three-dimensional ultrasound data. In the training process, an optimal mapping function from three-dimensional data of an early-stage fetus to the direction of the body region or the position and direction of the body region is learned, so that the error between the direction of the body region or the position and direction of the body region obtained by mapping the ultrasound data in the database by using the optimal mapping function and the actual labeled true value is minimized. For three-dimensional ultrasound data of an early-stage fetus to be identified, the optimal mapping function described above is executed, and the direction of the body region or the direction and position of the body region of the early-stage fetus is obtained.

[0135] As another implementation manner, the direction of the body region can be determined by using a spine detection manner. Specifically, the spine region of the early-stage fetus is detected from the three-dimensional ultrasound data obtained in step S220, and the direction of the body region of the early-stage fetus is determined according to the direction of the spine region. Since the spine region is relatively obvious in the three-dimensional ultrasound image, the direction of the body region of the early-stage fetus can be accurately determined according to the position of the spine region.

[0136] The method for detecting or segmenting the spinal region of the early gestation fetus can include a machine learning method or a traditional image processing method. The machine learning method is similar to the machine learning method described above, that is, an early gestation fetus ultrasound database is established in advance, and each three-dimensional ultrasound data in the database is marked with the position of the spinal region of the early gestation fetus, such as a region of interest box (ROI) of the spinal region or a specific region range of the spinal region. Then, a traditional machine learning method or a deep learning method is used to learn an optimal mapping function for obtaining the region of interest box (ROI) of the spinal region or the specific region range of the spinal region from the three-dimensional ultrasound data of the early gestation fetus, so as to realize the detection or segmentation of the spinal region of the early gestation fetus. In the traditional image processing method, a Hough transform, RANSAC, or the like can be used to detect the straight line or arc line with the highest brightness in the three-dimensional ultrasound data of the early gestation fetus as the detection result of the spinal region of the early gestation fetus.

[0137] The up-down direction and the front-back direction of the body region of the early gestation fetus can be directly determined according to the detection result of the spinal region. The up-down direction of the body region of the early gestation fetus is determined according to the direction of the spinal region, which includes determining a straight line closest to the spinal region and determining the direction of the straight line as the second direction of the body region of the early gestation fetus, that is, the up-down direction. For example, a least square method or the like can be used to fit a straight line closest to the spinal region, or the straight line with the highest brightness obtained by the Hough transform, RANSAC, or the like in the traditional image processing method described above can be directly used as the straight line closest to the spinal region.

[0138] After the up-down direction of the body region of the early gestation fetus is determined according to the detection result of the spinal region, the third direction of the body region of the early gestation fetus, that is, the front-back direction, can be further determined according to the up-down direction. Specifically, one or more body cross sections perpendicular to the up-down direction determined above can be extracted from the three-dimensional ultrasound data of the early gestation fetus, and a machine learning method or a traditional image processing method is 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 position of the body center point and the spine is determined as the front-back direction of the body region of the early gestation fetus. In the line, the position of the spine is close to the back of the body cross section, and the position of the body center point is close to the front of the body cross section.

[0139] In another embodiment, the front-back direction of the body region can also be directly determined according to the detection result of the spinal region without determining the front-back direction based on the up-down direction of the body region. Specifically, since the spine protrudes towards the back of the body, a curve closest to the spine can be determined, and the protruding direction of the curve is determined as the front-back direction of the body region of the early gestation fetus. For example, a least square method or the like can be used to fit an arc closest to the spine as the curve, or the arc with the highest brightness obtained by the traditional image processing method described above can be directly used as the curve.

[0140] In addition, the direction of the body region of the early-stage fetus can be determined according to the shape features of the body region of the early-stage fetus, i.e., the body region of the early-stage fetus is detected from the three-dimensional ultrasound data, and the direction of the body region is determined according to the shape of the body region. Since the shape features of the up-down direction of the body region of the early-stage fetus are more obvious, and the shape features of the front-back direction and the left-right direction are less obvious, this method is mainly used to determine the up-down direction of the body region of the early-stage fetus.

[0141] Specifically, the body region of the early-stage fetus can be determined in the three-dimensional ultrasound data obtained in step S220 by using machine learning or image processing methods, wherein the determined body region can be a region of interest frame (ROI) surrounding the body of the early-stage fetus, or a specific region range of the body of the early-stage fetus is segmented. Then, according to the detection or segmentation result of the body region of the early-stage fetus, the long axis of the body region is determined according to the shape of the body region, and the long axis direction is determined as the up-down direction of the body region of the early-stage fetus. For example, the long axis of the body region can be determined by using a principal component analysis (PCA) method, or the two points farthest apart in the body region are detected, and the line connecting the two points is the long axis of the body region.

[0142] As for the determination of the fourth direction (i.e., the left-right direction) of the body region of the early-stage fetus, after the up-down direction and the front-back direction of the body region of the early-stage fetus are determined by using any of the above methods or any other feasible method, the direction perpendicular to the up-down direction and the front-back direction is determined as the left-right direction of the body of the early-stage fetus. In addition, the left-right direction of the body region of the early-stage fetus can also be determined according to some specific features of the early-stage fetus, for example, the position of a region with symmetrical features in the body region of the early-stage fetus can be detected in the three-dimensional ultrasound data, and the direction of the line connecting the region with symmetrical features is determined as the left-right direction of the body region of the early-stage fetus. The symmetrical features include, for example, double kidneys, double lungs, left and right ribs, etc. Alternatively, the left and right atria of the early-stage fetus can be detected, and the direction of the line connecting the left and right atria is generally at a 45° angle with the left-right direction of the body region of the early-stage fetus, and the left-right direction of the body region of the early-stage fetus can also be determined according to this feature.

[0143] Exemplarily, the step S230 can be executed automatically after the three-dimensional ultrasound data is acquired, or can be executed according to the received user instruction. For example, the user can start the function of automatically extracting the standard section by triggering a button for extracting the standard section, which can be a virtual button arranged on the display user interaction interface, or can be a physical button. After the three-dimensional ultrasound data is acquired, the step S230 is started to be executed when the user instruction of extracting the standard section is received. In some embodiments, the user can also start the function of automatically extracting the standard section before starting to collect the ultrasound data, and then the step S230 is automatically executed after the three-dimensional ultrasound data is acquired.

[0144] In some embodiments, before the step S230 is executed, the standard section to be extracted can also be determined according to the received user input. For example, the names of ten standard sections including the biparietal diameter section, the bioccipital diameter section, etc. can be displayed on the user interaction interface, and the standard section to be extracted is determined according to the user selection. Alternatively, the options of the head region standard section, the body region standard section and the whole body region standard section can be displayed on the user interaction interface, and the head region standard section, the body region standard section or the whole body region standard section is determined to be extracted according to the user selection.

[0145] Since the directions of the target regions can be determined relatively accurately according to the three-dimensional ultrasound data of the early gestation period fetus, the quality of the extracted standard section can be improved by first determining the direction of the target region, and then further extracting the standard section according to the direction of the target region.

[0146] In the 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.

[0147] As described above, the direction of the target region determined in the step S230 mainly includes the direction of the head region and the direction of the body region, and then in the step S240, the standard section of the head region can be determined in the three-dimensional ultrasound data including the head region of the early gestation period fetus according to the direction of the head region, or the standard section of the body region can be determined in the three-dimensional ultrasound data including the body region of the early gestation period fetus according to the direction of the body region. The standard section of the head region includes at least one of the lateral ventricle horizontal transverse section, the bioccipital diameter section and the median sagittal section of the head and neck, and the standard section of the body region includes at least one of the chest diameter section, the abdominal circumference section, the abdominal wall umbilical cord insertion section, the bladder section, the spinal longitudinal axis section and the trunk long axis section. In addition, the standard section can also include the standard section of the whole body region of the early gestation period fetus, for example, the bioccipital diameter section (whole body median sagittal section), which can be determined according to the direction of the head region or the direction of the body region of the early gestation period fetus.

[0148] In one embodiment, extracting the at least one standard section according to the orientation of the target region comprises: determining a plurality of candidate sections in the three-dimensional ultrasound data of the early-stage fetus according to the orientation of the target region determined in step S230, and selecting the at least one standard section from the plurality of candidate sections.

[0149] For the standard section of the head region, a set of candidate sections of the head region is first generated according to the orientation of the head region of the early-stage fetus, and an optimal standard section of the head region is then determined from the plurality of candidate sections of the head region. For example, in the detection of the NT section and the crown-rump section, the boundary surface between the left hemisphere region of the head and the right hemisphere region of the head or the median sagittal plane obtained in step S230 can be directly used as the detection result of the NT section or the crown-rump section; or a plurality of candidate sections parallel to the left-right direction of the head region determined in step S230 can be generated, or a plurality of candidate sections approximately parallel to the left-right direction within a certain angle range can be generated, and the final NT section or crown-rump section can be selected from the plurality of candidate sections.

[0150] For example, in the detection of the transverse section of the head of the early-stage fetus (such as the transverse section of the lateral ventricle, the biparietal diameter section, the transverse section of the cerebellum, etc.), a plurality of candidate sections parallel to or approximately parallel to the left-right direction of the head region determined in step S230 can be generated, and the final transverse section of the lateral ventricle, the biparietal diameter section, or the transverse section of the cerebellum can be selected from the plurality of candidate sections.

[0151] 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 according to the orientation of the body region of the early-stage fetus, and an optimal standard section of the body region is then determined from the plurality of candidate sections of the body region.

[0152] For example, in the determination of the transverse section of the body region of the early-stage fetus, such as the four-chamber heart section, the stomach bubble section, the abdominal wall umbilical cord insertion section, the bladder section, etc., a plurality of parallel candidate sections perpendicular to the up-down direction of the body region of the early-stage fetus determined in step S230 can be generated, or a plurality of candidate sections approximately perpendicular to the up-down direction within a certain angle range can be generated, and the standard transverse section can be selected from the plurality of candidate sections.

[0153] For example, in the determination of the coronal section of the body region of the early-stage fetus, such as the coronal section of the double kidney, the coronal section of the spine, etc., a plurality of candidate sections parallel to the left-right direction or the up-down direction of the body region determined in step S230 can be generated, or a plurality of candidate sections approximately parallel to the left-right direction or the up-down direction within a certain angle range can be generated, and the standard coronal section can be selected from the plurality of candidate sections.

[0154] In addition, when determining the median sagittal plane of the fetal body in the early pregnancy stage, a set of candidate sections parallel to the up-down direction or the front-back direction of the body region determined in step S230 can be generated, or a set of candidate sections approximately parallel to the direction within a certain angle range can be generated, and then a standard median sagittal plane can be selected from the plurality of candidate sections.

[0155] After the candidate sections are generated, in an embodiment, a trained machine learning model can be used to determine the probability of each candidate section corresponding to the target region as a standard section, and a candidate section with a probability satisfying a first threshold can be determined as at least one standard section corresponding to the target region. For example, if there are at least two candidate sections with a probability satisfying the first threshold, a final selected standard section can be determined according to a received selection operation, i.e., a user selects the best standard section from the at least two candidate sections with a probability satisfying the first threshold. The machine learning model can be a traditional machine learning model or a deep learning model.

[0156] Alternatively, a trained machine learning model can also be used to determine the probability of each candidate section corresponding to the target region as a standard section, and a candidate section with the highest probability can be determined as one standard section corresponding to the target region, i.e., the final standard section is directly determined by the system, thereby simplifying the operation process. In another embodiment, selecting a standard section from the plurality of candidate sections includes detecting at least one early pregnancy target feature structure corresponding to a standard section in the plurality of candidate sections corresponding to the target region, and determining a candidate section with a probability of the early pregnancy target feature structure satisfying a second threshold or a candidate section with the highest probability of the early pregnancy target feature structure as the standard section. The early pregnancy target feature structure corresponding to the biparietal diameter section includes nasal bone, genital ridge, etc.; the early pregnancy target feature structure corresponding to the lateral ventricle horizontal transverse section includes cerebral falx, lateral ventricle, choroid plexus, etc.; the early pregnancy target feature structure corresponding to the bi-parietal diameter section includes thalamus, skull halo, etc.; the early pregnancy target feature structure corresponding to the head and neck median sagittal plane includes posterior neck transparent layer, nasal bone, etc.; the early pregnancy target feature structure corresponding to the chest diameter section includes four-chamber heart, etc.; the early pregnancy target feature structure corresponding to the abdominal circumference section includes stomach bubble, etc.; the early pregnancy target feature structure corresponding to the abdominal wall umbilical cord insertion site section includes umbilical cord insertion site, etc.; the early pregnancy target feature structure corresponding to the bladder section includes double legs or bladder, etc.; the early pregnancy target feature structure corresponding to the spinal column longitudinal axis section includes spinal column, skin margin, etc.; and the early pregnancy target feature structure corresponding to the trunk long axis section includes double kidneys, stomach bubble, spinal column, etc.

[0157] For example, for the standard section of the head region, after generating a set of candidate sections parallel or approximately parallel to the left-right direction of the head region, the early pregnancy target feature structure corresponding to the standard section of the head region, such as the lateral ventricle or choroid plexus corresponding to the transverse section of the lateral ventricle, the thalamus corresponding to the biparietal diameter section, the cerebellum corresponding to the transverse section of the cerebellum, etc., can be detected on the candidate sections respectively, and the candidate section with the highest probability of existence of the early pregnancy target feature structure is taken as the detection result of the corresponding standard section of the head region.

[0158] As another implementation manner of extracting the standard section corresponding to the target region according to the direction of the target region, the early pregnancy target feature structure corresponding to the standard section to be determined can be first detected in the three-dimensional ultrasound data obtained in step S220, and then the direction of the target region determined above is combined to determine at least one standard section corresponding to the target region, which at least partially coincides with the early pregnancy target feature structure and has an included angle with the direction of the target region satisfying a preset requirement. Further, the section substantially coinciding with the early pregnancy target feature structure and having an included angle of 0 degrees with the direction of the target region determined can be determined as one standard section corresponding to the target region. Alternatively, the section substantially coinciding with the early pregnancy target feature structure and having an included angle of 90 degrees with the direction of the target region determined can be determined as one standard section corresponding to the target region.

[0159] For the standard section of the head region, the early pregnancy target feature structure corresponding to the standard section to be determined can be detected, and then the direction of the head region of the early pregnancy fetus is combined to determine the corresponding standard section of the head region. As an example, the early pregnancy target feature structure corresponding to the horizontal transverse section of the lateral ventricle includes the cerebral falx, the lateral ventricle, and the choroid plexus; the early pregnancy target feature structure corresponding to the biparietal diameter section includes the thalamus and the skull halo; and the early pregnancy target feature structure corresponding to the median sagittal section of the head and neck includes the posterior neck transparent layer and the nasal bone. In addition, the standard section of the whole body region can also be determined according to the direction of the head region and the early pregnancy target feature structure of the head region. When the standard section is the transverse section of the cerebellum, the corresponding early pregnancy target feature structure includes the nasal bone and the genital ridge.

[0160] For example, in the detection of the NT standard section (i.e. the median sagittal section of the head and neck), one or more of the following features can be detected in the three-dimensional ultrasound data: the nasal bone, the NT (the posterior cervical transparent layer), the IT (the intracranial transparent layer), and one or more features in the posterior fossa pool. Then, a section that at least partially overlaps with the above features and is perpendicular to the left-right direction of the head region is determined as the detection result of the NT standard section. In the detection of the biparietal diameter section, one or more of the following features can be detected: the nasal bone, the NT (the posterior cervical transparent layer), the bladder, and the genital eminence. Then, a section that at least partially overlaps with the above features and is perpendicular to the left-right direction of the head region is determined as the detection result of the biparietal diameter section.

[0161] In the detection of the transverse section of the fetal head in the early gestation period, the lateral ventricle and / or the choroid plexus corresponding to the lateral ventricle transverse section, the thalamus and / or the cerebellar peduncle corresponding to the biparietal diameter section, and the thalamus, the cerebellum and / or the IT (the intracranial transparent layer) corresponding to the cerebellum transverse section can be detected in the three-dimensional ultrasound data. Then, one or more sections that pass through the above features respectively and are parallel to the left-right direction of the head region are determined as the detection results of the lateral ventricle transverse section, the biparietal diameter section or the cerebellum transverse section respectively.

[0162] Similarly, for the standard section of the body region, the early gestation target features corresponding to the standard section of the body region to be determined can be detected, and then the standard section of the corresponding body region is determined in combination with the direction of the body region of the fetus in the early gestation period.

[0163] For example, in the detection of the median sagittal section of the body region of the fetus in the early gestation period, if the direction of the body region is determined according to the position of the spinal region in step S230, a section that is closest to the spinal column or the fitted arc line thereof and is parallel or approximately parallel to the up-down direction or the front-back direction of the body region (i.e. the angle between the up-down direction or the front-back direction and the section is 0°) can be determined according to the position of the spinal region or the fitted arc line thereof, and the section is taken as the detection result of the median sagittal section of the body region of the fetus in the early gestation period.

[0164] In the detection of the transverse section of the body region of the fetus in the early gestation period, the heart corresponding to the four-chamber heart section, the gastric bubble corresponding to the gastric bubble section, the umbilical cord and the abdominal wall insertion site thereof corresponding to the abdominal wall-umbilical cord insertion site section, and the bladder or the umbilical artery corresponding to the bladder section can be detected. Then, one or more sections that at least partially overlap with the above early gestation target features respectively and are perpendicular or approximately perpendicular to the up-down direction of the body region of the fetus in the early gestation period determined in step S230 are determined as the detection results of the four-chamber heart section, the gastric bubble section, the abdominal wall-umbilical cord insertion site section or the bladder section.

[0165] In the detection of the coronal plane of the fetal body region in the early pregnancy, the double kidneys, the stomach bubble or the spine corresponding to the double kidney coronal plane, the spine or the rib corresponding to the spine coronal plane can be detected, and one or more planes are determined to be parallel to the left-right direction or the up-down direction of the fetal body region in the early pregnancy determined in step S230, and the planes are taken as the detection results of the double kidney coronal plane or the spine coronal plane. In addition, in some embodiments, other standard planes can be determined according to the determined one or more standard planes and the positions of the early pregnancy target feature structures in the determined standard planes.

[0166] For example, in the detection of the transverse plane of the fetal head in the early pregnancy, the positions of the early pregnancy target feature structures such as the choroid plexus, the thalamus, the third ventricle, the cerebellar vermis, the IT (intracranial transparent layer) and the like related to the transverse plane of the fetal head in the early pregnancy can be detected on the boundary plane between the left hemisphere region and the right hemisphere region of the head, the median sagittal plane, the NT standard plane or the biparietal diameter plane obtained above, and one or more planes are determined to pass through the above feature structures and be perpendicular to the boundary plane between the left hemisphere region and the right hemisphere region of the head, the median sagittal plane, the NT plane or the biparietal diameter plane, as the detection results of the transverse plane of the fetal head.

[0167] Similarly, for the standard plane of the fetal body region in the early pregnancy, for example, in the detection of the double kidney coronal plane, the positions of the stomach bubble and the spine can be determined in the detected stomach bubble plane, and one plane is determined to pass through the stomach bubble or the spine and be perpendicular to the stomach bubble plane, and the plane is taken as the detection result of the double kidney coronal plane. In the detection of the spine coronal plane, the positions of the spine and the rib can be determined in the detected one or more transverse planes of the body region, and one plane is determined to pass through the spine or the rib and be perpendicular to the transverse plane of the body, and the plane is taken as the detection result of the spine coronal plane.

[0168] In step S250, the at least one standard plane is displayed.

[0169] The displayed standard plane can be all the standard planes extracted in step S240, or part of the standard planes. For example, when the standard planes extracted in step S240 are displayed, part of the standard planes can be displayed according to the received user instruction, for example, the names or thumbnails of the standard planes can be displayed on the display interface, and the corresponding standard planes can be displayed according to the user's selection.

[0170] In some embodiments, if the early pregnancy target feature structures are detected in the three-dimensional ultrasound data in step S230 or step S240, the early pregnancy target feature structures detected from the three-dimensional ultrasound data can also be displayed for the user to perform comparative analysis.

[0171] In addition, the target direction determined in step S230 can be displayed so that the user views the standard cut surface associated therewith in combination 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 head region of the early gestation fetus, or the up-down direction, the front-back direction and the left-right direction of the body region of the early gestation fetus can be displayed by graphical markers such as arrows.

[0172] In some embodiments, the name of each determined standard cut surface can also be displayed so that the user intuitively determines the type of the standard cut surface, or selects the standard cut surface to be viewed according to the name of the standard cut surface. The name of the standard cut surface can be displayed synchronously with the standard cut surface, or the name of each standard cut surface can be first displayed on the display interface, and when the user selects the name of the standard cut surface, the corresponding standard cut surface is displayed.

[0173] In summary, the ultrasound imaging method 200 for the early gestation fetus according to the embodiments of the present application can automatically determine at least one standard cut surface corresponding to the target region of the early gestation fetus according to the direction of the target region, without manually extracting the standard cut surface one by one by the doctor, greatly optimizing the workflow of the prenatal examination, effectively improving the work efficiency, and being capable of improving the stability of the quality of the acquired standard cut surface, promoting the popularization and application of the early gestation structure screening.

[0174] Now referring back to Figure 1 The ultrasound imaging system 100 provided by the embodiments of the present application can be used to implement the ultrasound imaging method 200 for the early gestation fetus described above. As described above, the ultrasound imaging system 100 can include an ultrasound probe 110, a transmitting / receiving circuit 112, a processor 114 and a display 116, and the related descriptions of each component can be referred to the above.

[0175] When used to implement the ultrasound imaging method 200, the transmitting / receiving circuit 112 is configured to excite the ultrasound probe 110 to emit ultrasound waves to the early gestation fetus, and receive the echoes of the ultrasound waves to obtain an ultrasound echo signal; the processor 114 is configured to: obtain three-dimensional ultrasound data of the early gestation fetus based on the ultrasound echo signal; determine the direction of a target region of the early gestation fetus according to the three-dimensional ultrasound data; extract at least one standard cut surface corresponding to the target region from the three-dimensional ultrasound data according to the direction of the target region; and the display 116 is configured to display the at least one standard cut surface.

[0176] As an example, the target region includes at least one of: a head region, a body region and a whole body region.

[0177] 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 a left-right direction of the head region.

[0178] In another embodiment, the target region includes a body region, and the direction of the target region includes at least one of 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 a superior-inferior direction, an anterior-posterior direction and a 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.

[0179] As an example, extracting the at least one standard section corresponding to the target region from the three-dimensional ultrasound data according to the direction of the target region includes: determining a plurality of candidate sections corresponding to the target region in the three-dimensional ultrasound data according to the direction of the target region; and selecting the at least one standard section corresponding to the target region from the plurality of candidate sections corresponding to the target region.

[0180] As an example, extracting the at least one standard section corresponding to the target region from the three-dimensional ultrasound data according to the direction of the target region includes: detecting an early pregnancy target feature structure corresponding to the standard section in the three-dimensional ultrasound data; and determining a section that at least partially coincides with the early pregnancy target feature structure and has an included angle with the direction of the target region satisfying a preset requirement as the at least one standard section corresponding to the target region.

[0181] In one embodiment, the display 116 is further configured to display the early pregnancy target feature structure. The display 116 can also be configured to display the determined direction of the target region. The display 116 can also be configured to display the name of the determined standard section.

[0182] The above only describes the main functions of the components of the ultrasound imaging system 100, and more details can be found in the description of the ultrasound imaging method 200 for the early pregnancy fetus. The ultrasound imaging system 100 of the embodiments of the present application can automatically determine the standard section of the early pregnancy fetus, thereby improving the work efficiency and the quality of the standard section.

[0183] In the following, the ultrasound imaging method 200 for the early pregnancy fetus according to an embodiment of the present application will be described with reference to the accompanying drawings. Figure 3 The ultrasound imaging method 300 for the early pregnancy fetus according to another embodiment of the present application will be described. Figure 3 is a schematic flowchart of the ultrasound imaging method 300 for the early pregnancy fetus according to an embodiment of the present application.

[0184] As shown in Figure 3 The ultrasound imaging method 300 for the early pregnancy fetus includes the following steps:

[0185] In step S310, an ultrasound wave is emitted to the early gestation fetus, and a return wave of the ultrasound wave is received to obtain an ultrasound echo signal.

[0186] In step S320, three-dimensional ultrasound data of the early gestation fetus is obtained according to the ultrasound echo signal.

[0187] In step S330, regions of at least two different early gestation target feature structures are detected from the three-dimensional ultrasound data.

[0188] In step S340, at least one cutting plane that at least partially coincides with each of the regions of the at least two different early gestation target feature structures is determined as at least one standard cutting plane of the early gestation fetus.

[0189] In step S350, the at least one standard cutting plane is displayed.

[0190] The steps S310, S320 and S350 in the method 300 for ultrasonic imaging of an early gestation fetus according to the embodiments of the present application are generally similar to the steps S210, S220 and S250 in the method 200 for ultrasonic imaging described with reference to Figure 2 The steps S310, S320 and S350 in the method 300 for ultrasonic imaging of an early gestation fetus according to the embodiments of the present application are generally similar to the steps S210, S220 and S250 in the method 200 for ultrasonic imaging described with reference to

[0191] Similar to the method 200 for ultrasonic imaging, the standard cutting plane extracted in the method 300 for ultrasonic imaging of an early gestation fetus includes at least one of a standard cutting plane of a head region, a standard cutting plane of a body region or a standard cutting plane of a whole body region of the early gestation fetus. When the standard cutting plane includes the standard cutting plane of the head region, the three-dimensional ultrasound data obtained in step S320 includes at least three-dimensional ultrasound data of the head region of the early gestation fetus. When the standard cutting plane includes the standard cutting plane of the body region, the three-dimensional ultrasound data obtained in step S320 includes at least three-dimensional ultrasound data of the body region of the early gestation fetus. When the standard cutting plane includes the standard cutting plane of the whole body region, the three-dimensional ultrasound data obtained in step S320 includes three-dimensional ultrasound data of the whole body region of the early gestation fetus.

[0192] Specifically, the standard sections can include at least one of the following standard sections: a biparietal diameter section, a transverse section of lateral ventricles, a bi-parietal diameter section, an NT standard section, a thoracic diameter section, an abdominal circumference section, an abdominal wall umbilical cord insertion section, a bladder section, a longitudinal axis section of spine, and a long axis section of trunk. The standard sections of the head region of the early gestation fetus include the transverse section of lateral ventricles, the bi-parietal diameter section, and the NT standard section, and the three-dimensional ultrasound data at least includes the three-dimensional ultrasound data of the head region of the early gestation fetus; the standard sections of the body region of the early gestation fetus include the thoracic diameter section, the abdominal circumference section, the abdominal wall umbilical cord insertion section, the bladder section, the longitudinal axis section of spine, and the long axis section of trunk, and the three-dimensional ultrasound data at least includes the three-dimensional ultrasound data of the body region of the early gestation fetus; and the standard section of the whole body region of the early gestation fetus includes the biparietal diameter section, and the three-dimensional ultrasound data at least includes the three-dimensional ultrasound data of the whole body region of the early gestation fetus.

[0193] In step S330, the position of the early gestation target feature structure can be determined by using any suitable image detection or segmentation method. For example, a machine learning model can be trained for each feature structure corresponding to each standard section by using a traditional machine learning method or a deep learning method, so as to determine the position of the feature structure. Before the model training, an ultrasound database of the early gestation fetus is established in advance, and the position of the early gestation target feature structure of the early gestation fetus is marked in each three-dimensional ultrasound data in the database, for example, a region of interest frame (ROI) or a specific region range, and then an optimal mapping function is learned by using the traditional machine learning method or the deep learning method, so as to obtain the region of interest frame (ROI) or the specific region range of the early gestation target feature structure from the three-dimensional ultrasound data of the early gestation fetus, and realize the detection or segmentation of the early gestation target feature structure.

[0194] In step S340, for the standard section to be extracted, the type of the standard section is first obtained, the early gestation target feature structure corresponding to the type of the standard section is determined, and the regions of at least two different early gestation target feature structures corresponding to the type of the standard section are detected from the three-dimensional ultrasound data. Then, a section that at least partially coincides with the at least two different early gestation target feature structures is determined as the detection result of the standard section. Specifically, a section that substantially coincides with each of the regions of the at least two different early gestation target feature structures can be determined as the standard section. In order to make the obtained standard section more accurate, a section that at least partially coincides with three or more different early gestation target feature structures can be determined as the detection result of the standard section.

[0195] Exemplarily, when the standard cross section is a top-buttocks cross section, the corresponding early-pregnancy target feature structure includes a nasal bone and a genital eminence; when the standard cross section is a lateral ventricle horizontal cross section, the corresponding early-pregnancy target feature structure includes a cerebral falx, a lateral ventricle and a choroid plexus; when the standard cross section is a biparietal diameter cross section, the corresponding early-pregnancy target feature structure includes a thalamus and a skull halo; when the early-pregnancy target feature structure includes a head-neck median sagittal plane, the corresponding early-pregnancy target feature structure includes a posterior neck transparent layer and a nasal bone; when the standard cross section is a chest diameter cross section, the corresponding early-pregnancy target feature structure includes a heart, a rib and a spinal bone; when the standard cross section is an abdominal circumference cross section, the corresponding early-pregnancy target feature structure includes a stomach bubble, a spinal bone and a liver; when the standard cross section is an abdominal wall umbilical cord insertion cross section, the corresponding early-pregnancy target feature structure includes an umbilical cord insertion, an umbilical cord, a spinal bone and an anterior abdominal wall; when the standard cross section is a bladder cross section, the corresponding early-pregnancy target feature structure includes a double leg and a bladder; when the standard cross section is a spinal longitudinal axis cross section, the corresponding early-pregnancy target feature structure includes a spinal column and a skin margin; when the standard cross section is a trunk long axis cross section, the corresponding early-pregnancy target feature structure includes a double kidney, a stomach bubble and a spinal column.

[0196] 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 section, the name of the standard cross section can also be displayed, and in addition, the early-pregnancy target feature structure detected from the three-dimensional ultrasound data can also be displayed, which can be displayed in the three-dimensional ultrasound image of the early-pregnancy fetus, for example, a ROI frame surrounding the early-pregnancy target feature structure or a contour of the early-pregnancy target feature structure.

[0197] Now referring back to Figure 1 The ultrasound imaging system 100 provided by the embodiments of the present application can be used to implement the ultrasound imaging method 300 of the early-pregnancy fetus described above. As described above, the ultrasound imaging system 100 can include an ultrasound probe 110, a transmitting / receiving circuit 112, a processor 114 and a display 116, and the related descriptions of the respective components can be referred to the above.

[0198] When used to implement the ultrasound imaging method 300, the transmitting / receiving circuit 112 is configured to excite the ultrasound probe 110 to emit ultrasound waves to the early-pregnancy fetus and receive echoes of the ultrasound waves to obtain an ultrasound echo signal; the processor 114 is configured to: obtain three-dimensional ultrasound data of the early-pregnancy fetus 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 coincides with each of the at least two different early-pregnancy target feature structures as at least one standard cross section of the early-pregnancy fetus; and the display 116 is configured to display the at least one standard cross section.

[0199] The above only describes the main functions of the components of the ultrasound imaging system 100, and more details can be found in the related description of the ultrasound imaging method 300 for an early gestation fetus.

[0200] The ultrasound imaging method 300 for an early gestation fetus and the ultrasound imaging system according to the embodiments of the present application can automatically determine the standard section of the early gestation fetus according to the early gestation target feature structure of the early gestation fetus, without manually extracting the standard section by the doctor one by one, greatly optimizing the work flow of the prenatal examination, effectively improving the work efficiency, and being capable of improving the stability of the quality of the acquired standard section, promoting the popularization and application of the early gestation structure screening.

[0201] In the following, the ultrasound imaging method 300 for an early gestation fetus according to the embodiments of the present application will be described in detail with reference to the accompanying drawings. Figure 4 The ultrasound imaging method 300 for an early gestation fetus according to another embodiment of the present application will be described. Figure 4 is a schematic flow chart of the ultrasound imaging method 400 for an early gestation fetus according to the embodiments of the present application.

[0202] As shown in Figure 4 , the ultrasound imaging method 400 for an early gestation fetus according to one embodiment of the present application includes the following steps:

[0203] In step S410, an ultrasound wave is emitted to the early gestation fetus, and the echo of the ultrasound wave is received to obtain an ultrasound echo signal;

[0204] In step S420, three-dimensional ultrasound data of the early gestation fetus is obtained according to the ultrasound echo signal;

[0205] In step S430, the three-dimensional ultrasound data is matched with an ultrasound data template of a pre-configured early gestation standard section, and a target standard section in the three-dimensional ultrasound data is determined according to the matching result, wherein the early gestation standard section includes at least one of the following: a lateral ventricle horizontal transverse section, a biparietal diameter section, a median sagittal section of the head and neck, a chest diameter section, an abdominal circumference section, an abdominal wall umbilical cord insertion section, a bladder section, a spinal longitudinal axis section, a trunk long axis section, and a crown-heel diameter section;

[0206] In step S440, the target standard section is displayed.

[0207] The steps S410, S420 and S440 in the ultrasound imaging method 400 for an early gestation fetus according to the embodiments of the present application are generally similar to the steps S210, S220 and S250 in the ultrasound imaging method 200 described with reference to Figure 2 , and for the sake of brevity, the same details will not be described here again, and in the following, the way of determining the standard section according to the three-dimensional ultrasound data in step S430 will be described in detail.

[0208] In step S430, the standard cut surface is determined by matching the three-dimensional ultrasound data of the early gestation fetus with the pre-configured ultrasound data template of the early gestation standard cut surface. The pre-configured ultrasound data template of the early gestation standard cut surface includes, for example, a three-dimensional data template (hereinafter referred to as a standard three-dimensional data template) of the pre-configured early gestation standard cut surface, a two-dimensional data template (hereinafter referred to as a standard two-dimensional cut surface template) of the pre-configured early gestation standard cut surface, an early gestation target feature structure template data template (hereinafter referred to as a standard early gestation target feature structure template) of the pre-configured early gestation standard cut surface, and a key point template (hereinafter referred to as a standard key point template) of the pre-configured early gestation standard cut surface. The matching with the template includes at least one of three-dimensional data matching with the standard three-dimensional data template, two-dimensional cut surface matching with the standard two-dimensional cut surface template, early gestation target feature structure matching with the standard early gestation target feature structure template, and key point matching with the standard key point template.

[0209] As an example, matching the three-dimensional data of the early gestation fetus with the standard three-dimensional data template includes finding an optimal three-dimensional spatial transformation relationship such that the three-dimensional ultrasound data obtained in step S420 has the highest similarity or the smallest difference with the standard three-dimensional data template. In another example, image features such as gradient features, LBP texture features, Harr features, HOG / LOG features, etc. can be extracted from the three-dimensional ultrasound data of the early gestation fetus obtained in step S420 and the standard three-dimensional data template, and then an optimal three-dimensional spatial transformation relationship is found such that the image features extracted from the three-dimensional ultrasound data of the early gestation fetus and the standard three-dimensional data template have the highest similarity or the smallest difference. After the matching is completed, the position of the target standard cut surface in the three-dimensional ultrasound data of the early gestation fetus can be determined according to the position of the early gestation standard cut surface pre-configured in the standard three-dimensional data template and the three-dimensional spatial transformation relationship obtained by the matching.

[0210] As an example, matching the three-dimensional ultrasound data of the early gestation fetus with the standard two-dimensional cut surface template includes finding an optimal two-dimensional cut surface in the three-dimensional ultrasound data of the early gestation fetus obtained in step S420 such that the optimal two-dimensional cut surface has the highest similarity or the smallest difference with the standard two-dimensional cut surface template, or such that the image features extracted from the optimal two-dimensional cut surface and the standard two-dimensional cut surface template have the highest similarity or the smallest difference, the image features including but not limited to gradient features, LBP texture features, Harr features, HOG / LOG features. After the matching is completed, the optimal two-dimensional cut surface found from the three-dimensional data can be used as the target standard cut surface.

[0211] As an example, matching the three-dimensional ultrasound data of the early-pregnancy fetus with the standard early-pregnancy target feature structure template includes finding an optimal image block in the three-dimensional ultrasound data acquired in step S420, making the similarity between the image block and the standard early-pregnancy target feature structure template highest or the difference smallest, or extracting image features from the image block and the standard early-pregnancy target feature structure template, and making the similarity between the image features highest or the difference smallest.

[0212] In another example, the early-pregnancy target feature structure matching can further include using a target detection method such as Faster RCNN, Mask RCNN, SSD, YOLO, Retinanet, Efficientnet, Cornernet, Centernet, FCOS, etc. to detect a candidate early-pregnancy target feature structure region in the three-dimensional ultrasound data acquired in step S420, and then match the candidate early-pregnancy target feature structure region with the standard early-pregnancy target feature structure template.

[0213] In another example, the early-pregnancy target feature structure matching can further include using a target detection method such as Faster RCNN, Mask RCNN, SSD, YOLO, Retinanet, Efficientnet, Cornernet, Centernet, FCOS, etc. to detect a candidate early-pregnancy target feature structure region in the three-dimensional ultrasound data acquired in step S420, and then match the candidate early-pregnancy target feature structure region with the standard early-pregnancy target feature structure template.

[0214] After the matching is completed, the position of the target standard section can be determined according to the position of the early pregnancy target feature structure in the three-dimensional ultrasound data and the early pregnancy target feature structure corresponding to the standard section. Specifically, when the early pregnancy standard section is the biparietal diameter section, the corresponding early pregnancy target feature structure includes the nasal bone and the genital eminence; when the early pregnancy standard section is the transverse section at the level of the lateral ventricle, the corresponding early pregnancy target feature structure includes the cerebral falx, the lateral ventricle and the choroid plexus; when the early pregnancy standard section is the bi-parietal diameter section, the corresponding early pregnancy target feature structure includes the thalamus and the skull halo; when the early pregnancy standard section includes the median sagittal section of the head and neck, the corresponding early pregnancy target feature structure includes the posterior neck transparent layer and the nasal bone; when the early pregnancy standard section is the chest diameter section, the corresponding early pregnancy target feature structure includes the four-chambered heart; when the early pregnancy standard section is the abdominal circumference section, the corresponding early pregnancy target feature structure includes the stomach bubble; when the early pregnancy standard section is the section at the umbilical cord insertion site of the abdominal wall, the corresponding early pregnancy target feature structure includes the umbilical cord insertion site; when the early pregnancy standard section is the bladder section, the corresponding early pregnancy target feature structure includes the double legs or the bladder; when the early pregnancy standard section is the longitudinal axis section of the spinal column, the corresponding early pregnancy target feature structure includes the spinal column and the skin margin; and when the early pregnancy standard section is the long axis section of the trunk, the corresponding early pregnancy target feature structure includes the double kidneys, the stomach bubble and the spinal column. Alternatively, the position of the target standard section in the three-dimensional ultrasound data can also be determined according to the position of the early pregnancy standard section in the standard early pregnancy target feature structure template, based on the obtained optimal spatial transformation.

[0215] As an example, matching the three-dimensional ultrasound data with the standard key point template includes finding one or more optimal points in the three-dimensional ultrasound data obtained in step S420, such that the image features near the optimal points have the highest similarity or the smallest difference with the image features of the standard key point template.

[0216] The key point matching can also include using an injected feature point extraction method (such as the SIFT method), an angle point detection method (such as the Harris method), or a neural network-based prediction of candidate key point coordinates or a region where the candidate key point is located, so as to determine at least one candidate key point in the three-dimensional ultrasound data, and then match the candidate key point with the standard key point template. The matching of the candidate key point with the standard key point template can include finding an optimal candidate key point such that the image features near the optimal candidate key point have the highest similarity or the smallest difference with the image features of the standard key point template; or the matching of the candidate key point with the standard key point template can also include finding an optimal candidate key point and an optimal spatial transformation relationship such that the spatial position of the optimal candidate key point has the smallest difference with the spatial position of the standard key point template.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] 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.

[0223] 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:

[0224] 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.

[0225] In step S520, three-dimensional ultrasound data of the fetus in early pregnancy are obtained based on the ultrasound echo signal;

[0226] In step S530, image features of the target region of the three-dimensional ultrasound data are extracted based on the three-dimensional ultrasound data;

[0227] 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.

[0228] 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.

[0229] In step S560, the target standard cross-section is displayed.

[0230] 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.

[0231] 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.

[0232] After the image feature of the target region is extracted, the normal direction of the target standard section can be determined according to a mapping relationship between the image feature of the target region and the normal direction of the standard section corresponding to the image feature of the target region, and the position information of the preset point on the target standard section can be determined according to a mapping relationship between the image feature of the target region and the position information of the preset point on the standard section corresponding to the image feature of the target region. Exemplarily, the preset point can be a point where the standard section intersects with the X-axis, the Y-axis or the Z-axis, or can also be the position information of the standard section in a preset direction, for example, can be an intersection point of the standard section and the normal direction.

[0233] Exemplarily, a machine learning model or a deep learning model can be used to regress the mapping relationship between the image feature of the target region and the normal direction of the standard section corresponding to the image feature of the target region; or a machine learning model or a deep learning model can be used to regress the mapping relationship between the image feature of the target region and the preset point on the standard section corresponding to the image feature of the target region. Specifically, an early pregnancy fetal ultrasound database is established in advance, wherein each ultrasound data includes early pregnancy three-dimensional data and / or image features of a target region thereof, and preset point positions and normal directions of one or more standard sections. When training the model, an optimal mapping function from the image feature of the target region to the preset point position and the normal direction is found, so that the error between the preset point position and the normal direction obtained by the mapping function from the image feature of the target region and the actual preset point position and the normal direction of the standard section is minimized. The mapping function can be used to predict the preset point position and the normal direction according to the image feature of the target region of the three-dimensional ultrasound image.

[0234] Then, in step S550, the standard section can be extracted from the three-dimensional ultrasound data according to the preset point position and the normal direction, for example, a section passing through the preset point is extracted from all sections perpendicular to the normal direction. The standard section includes one or more of the following sections: a horizontal transverse section of the lateral ventricle, a biparietal diameter section, a median sagittal section of the head and neck, a chest diameter section, an abdominal circumference section, an abdominal wall umbilical cord insertion section, a bladder section, a spinal longitudinal axis section, a trunk long axis section, and a crown-hip diameter section.

[0235] Exemplarily, the traditional machine learning method includes SVM support vector machine, least square method, logistic regression method, etc., and the mapping function includes linear function, polynomial function, logistic function, etc.; the deep learning method uses a deep neural network as the mapping function, including but not limited to CNN convolutional neural network, MLP multi-layer perceptron, RNN recurrent neural network, etc.

[0236] Now referring back to 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.

[0237] 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.

[0238] 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.

[0239] 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.

[0240] 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.

[0241] 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:

[0242] 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.

[0243] In step S620, three-dimensional ultrasound data of the early pregnancy fetus are obtained based on the ultrasound echo signal;

[0244] In step S630, the orientation of the target region of the early pregnancy fetus is determined based on the three-dimensional ultrasound data;

[0245] At step S640, a direction of the target region of the early gestation fetus is displayed.

[0246] The method for determining the direction of the target region in the ultrasound imaging method 600 of the early gestation fetus according to the embodiments of the present application is substantially consistent with the method for determining the direction of the target region in the ultrasound imaging method 200. Figure 2 The method for determining the direction of the target region in the ultrasound imaging method 200 is substantially consistent. Specifically, the target region includes at least one of the head region, the body region, and the whole body region.

[0247] In one embodiment, the target region includes the head region, and the direction of the target region includes a first direction of the head region, wherein the first direction is a left-right direction of the head region.

[0248] Exemplarily, the head region of the early gestation fetus can be detected in the three-dimensional ultrasound data by using a machine learning method or a skull halo detection method, the left hemisphere region and the right hemisphere region of the head region are determined according to the symmetry of the head region of the early gestation fetus, and the normal direction of the boundary surface between the left hemisphere region and the right hemisphere region of the head region is determined as the first direction of the head region.

[0249] Alternatively, a mid-sagittal plane of the head region of the early gestation fetus can be extracted from the three-dimensional ultrasound data, and the normal direction of the mid-sagittal plane of the head region is determined as the first direction of the head region.

[0250] The target region can also include the body region, and the direction of the target region includes at least one of a second direction of the body region, a third direction of the body region, and a fourth direction of the body region, wherein the second direction, the third direction, and the fourth direction are respectively an up-down direction, a front-back direction, and a left-right direction of the body region, and any two of the second direction, the third direction, and the fourth direction are perpendicular to each other.

[0251] Exemplarily, the spine region of the early gestation fetus can be detected in the three-dimensional ultrasound data, and the direction of the body region is determined according to the direction of the spine region. For example, a straight line close to the spine region can be determined, and the direction of the straight line is determined as the second direction of the body region, i.e., the up-down direction.

[0252] After the second direction is determined, one or more body cross sections perpendicular to the second direction can be extracted from the three-dimensional ultrasound data of the body of the early gestation fetus, and 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 body region of the early gestation fetus, i.e., the front-back direction. The method for determining the front-back direction can also be to determine a curve close to the spine region, and the convex direction of the curve is determined as the third direction of the body region of the early gestation fetus.

[0253] In one embodiment, the method for determining the body region can comprise: detecting the body region of the early gestation fetus from the three-dimensional ultrasound data; determining the direction of the body region according to the shape of the body region.

[0254] Exemplarily, the method for determining the fourth direction of the body region can comprise: determining the second direction and the third direction of the body region of the early gestation fetus, and determining the direction perpendicular to the second direction and the third direction as the fourth direction of the body region of the early gestation fetus. Alternatively, the position of the double kidney region in the body of the early gestation fetus can also be detected from the three-dimensional ultrasound data, and the direction of the region connecting the symmetrical features is determined as the fourth direction of the body region of the early gestation fetus.

[0255] As an example, after determining the direction of the target region, at least one standard section corresponding to the target region can also be extracted from the three-dimensional ultrasound data according to the direction of the target region. For example, a plurality of candidate sections corresponding to the target region can be determined from the three-dimensional ultrasound data according to the direction of the target region; and at least one standard section corresponding to the target region can be selected from the plurality of candidate sections. Wherein, the early gestation target feature corresponding to the standard section corresponding to the target region can be detected from the three-dimensional ultrasound data, and the section at least partially coinciding with the early gestation target feature and satisfying the preset requirement with the direction of the target region can be determined as the at least one standard section corresponding to the target region. For other specific details of determining the standard section according to the direction of the target region, please refer to the relevant description of the ultrasound imaging method 200.

[0256] Now referring back to Figure 1 The ultrasound imaging system 100 provided by the embodiments of the present application can be used to implement the ultrasound imaging method 600 of the early gestation fetus. As described above, the ultrasound imaging system 100 can comprise an ultrasound probe 110, a transmitting / receiving circuit 112, a processor 114, and a display 116, and the relevant descriptions of the respective components can be referred to the above.

[0257] When used to implement the ultrasound imaging method 600, the transmitting / receiving circuit 112 is configured to excite the ultrasound probe 110 to emit ultrasound waves to the early gestation fetus and receive echoes of the ultrasound waves to obtain ultrasound echo signals; the processor 114 is configured to: obtain three-dimensional ultrasound data of the early gestation fetus based on the ultrasound echo signals; determine the direction of the target region of the early gestation fetus according to the three-dimensional ultrasound data; and the display 116 is configured to display the direction of the target region.

[0258] The above only describes the main functions of the components of the ultrasound imaging system 100, and more details can be found in the related description of the ultrasound imaging method 600 for the early gestation fetus. In addition, according to an embodiment of the present application, a computer storage medium is also provided, and program instructions are stored on the computer storage medium, and when the program instructions are run by a computer or a processor, the corresponding steps of the method 200, the method 300, the method 400, the method 500, or the method 600 of the embodiment of the present application are executed. The storage medium may, for example, include a memory card of a smart phone, 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 can be any combination of one or more computer-readable storage media.

[0259] In addition, according to an embodiment of the present application, a computer program is also provided, which can be stored on a cloud or a local storage medium. When the computer program is run by a computer or a processor, the corresponding steps of the ultrasound imaging method for the early gestation fetus of the embodiment of the present application are executed.

[0260] Based on the above description, the ultrasound imaging method and the ultrasound imaging system for the early gestation fetus according to the embodiment of the present application can automatically determine the standard section of the early gestation fetus according to the three-dimensional ultrasound data collected at a single time, without manually extracting the standard section by a doctor one by one, greatly optimizing the work flow of the prenatal examination, effectively improving the work efficiency, and improving the stability of the quality of the obtained standard section, promoting the popularization and application of the early gestation structure screening.

[0261] Although the example embodiments have been described herein with reference to the accompanying drawings, it is to be understood that the example embodiments are only exemplary and are not intended to limit the scope of the present application. Those of ordinary skill in the art can make various changes and modifications without departing from the scope and spirit of the present application. All such changes and modifications are intended to be included within the scope of the present application as claimed in the appended claims.

[0262] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in connection with the embodiments disclosed herein can be realized by electronic hardware, or a combination of computer software and electronic hardware. Whether the functions are performed by hardware or software depends on the specific application and design constraints of the technical solution. Those of ordinary skill 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 the present application.

[0263] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the above-described device embodiments are merely illustrative, and the division of the units is merely a logical function division. In actual implementation, another division manner can be used, for example, a plurality of units or components can be combined or integrated into another device, or some features can be omitted or not executed.

[0264] In the specification provided herein, a large number of specific details are described. However, it can be understood that the embodiments of the present application can be practiced without these specific details. In some examples, well-known methods, structures and techniques are not described in detail in order not to obscure the understanding of the present specification.

[0265] Similarly, it should be understood that, in order to simplify the present application and help understand one or more of the various inventive aspects, in the description of the exemplary embodiments of the present application, various features of the present application are sometimes grouped together in a single embodiment, figure, or description of it. However, the method of the present application should not be interpreted as reflecting an intention that the claimed present application requires more features than the features explicitly recited in each claim. Rather, as reflected by the corresponding claims, the inventive point is that the corresponding technical problem can be solved with fewer features than all the features of a certain disclosed single embodiment. Therefore, the claims following the specific embodiments are hereby expressly incorporated into the specific embodiments, in which each claim itself is a separate embodiment of the present application.

[0266] Those skilled in the art can understand that, except for the mutual exclusion between features, any combination of all features disclosed in the specification (including the accompanying claims, abstract and drawings) and all processes or units of any method or device disclosed in this way can be combined. Unless explicitly stated otherwise, each feature disclosed in the specification (including the accompanying claims, abstract and drawings) can be replaced by an alternative feature that provides the same, equivalent or similar purpose.

[0267] In addition, those skilled in the art can understand that, although some embodiments described herein include certain features rather than other features included in other embodiments, the combination of features of different embodiments means that it is within the scope of the present application and forms different embodiments. For example, in the claims, any one of the claimed embodiments can be used in any combination.

[0268] Various component embodiments of the present application can be implemented in hardware, or as software modules running in one or more processors, or in combinations thereof. As will be appreciated by persons skilled in the art, a microprocessor or a digital signal processor (DSP) can be used in practice to implement some or all of the functions of some of the modules according to the embodiments of the present application. The present application can also be implemented as a program for executing, in whole or in part, the methods described herein, such as a computer program and a computer program product. Such a program implementing the present application can be stored on a computer readable medium or can be in the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or in any other form.

[0269] It should be noted that the above-mentioned embodiments illustrate rather than limit the application, and that one skilled in the art will be able to design many alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The application can be implemented by means of both hardware and software, and any combination thereof. In the claims, the word comprising does not exclude other elements being included in the composition. The word "comprising" does not exclude other elements being present in addition to or instead of those identified. Where an indefinite or definite article is used, such as "an" or "a" or "an" or "the", such article is also not intended to exclude the presence of the species having the identified property. The word "comprising" is intended to mean "consisting at least in part of. Where an indefinite or definite article is used, such as "an" or "a" or "an" or "the", such article is also not intended to exclude the presence of the species having the identified property. The word "a" or "an" preceding an element does not exclude the presence of two or more such elements. The word "or" in reference to a list of two or more terms does not exclude that those terms can be present simultaneously. Where an indefinite or definite article is used, such as "an" or "a" or "an" or "the", such article is also not intended to exclude the presence of the species having the identified property. The word "a" or "an" preceding an element does not exclude the presence of two or more such elements. The word "or" in reference to a list of two or more terms does not exclude that those terms can be present simultaneously. On the contrary, the use of the word "or" should be understood to present "one, some or all" of the elements so described.

[0270] The above description is only specific embodiments of the present application or explanations of specific embodiments, the protection scope of the present application is not limited to this, any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered in the protection scope of the present application. The protection scope of the present application should be subject to the protection 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 signal. The orientation of the target region of the fetus in early pregnancy is determined based on the three-dimensional ultrasound data, and the orientation of the target region includes the orientation of the head region and / or the orientation of the body region. Based on the orientation of the target region, at least one standard section is extracted from the three-dimensional ultrasound data. The at least one standard section includes a standard section corresponding to a body region and / or a standard section corresponding to a whole body region. This includes: extracting the standard section corresponding to the body region from the three-dimensional ultrasound data based on the orientation of the body region, and / or, extracting the standard section corresponding to the whole body region from the three-dimensional ultrasound data based on the orientation of the head region or the orientation of the body region. Display the at least one standard cross-section.

2. The method according to claim 1, characterized in that, The standard sections corresponding to the body regions include 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 sections corresponding to the whole body regions include the top-to-hip diameter section.

3. The method according to claim 1, characterized in that, The at least one standard section also includes a standard section corresponding to the head region. Extracting at least one standard section from the three-dimensional ultrasound data according to the direction of the target region further includes: extracting the standard section corresponding to the head region from the three-dimensional ultrasound data according to the direction of the head region.

4. The method according to claim 3, characterized in that, The standard sections corresponding to the head region include at least one of the following: the transverse section at the level of the lateral ventricle, the biparietal diameter section, and the midsagittal section of the head and neck.

5. The method according to claim 1, characterized in that, The direction of the head target region includes a first direction of the head region, wherein the first direction is the left-right direction of the head region.

6. The method according to claim 5, characterized in that, The process of determining the orientation of the target region of the early pregnancy fetus based on the three-dimensional ultrasound data includes: The head region of the fetus in early pregnancy was detected in the three-dimensional ultrasound data; The first orientation of the head region is determined based on the symmetry of the head region of the fetus in early pregnancy.

7. The method according to claim 6, characterized in that, The detection of the fetal head region in early pregnancy from the three-dimensional ultrasound data includes: The head region of the fetus in early pregnancy can be detected in the three-dimensional ultrasound data using machine learning methods or cranial aura detection methods.

8. The method according to claim 6, characterized in that, Determining the first orientation of the head region based on the symmetry of the head region of the early pregnancy fetus includes: Based on the symmetry of the head region of the fetus in early pregnancy, the left and right hemispheres of the head region are determined, and the normal direction of the interface between the left and right hemispheres of the head region is determined as the first direction of the head region.

9. The method according to claim 5, characterized in that, Determining the orientation of the head region includes: The midsagittal plane of the head region of the fetus in early pregnancy was extracted from the three-dimensional ultrasound data; The normal direction of the midsagittal plane of the head region is defined as the first direction of the head region.

10. The method according to claim 1, characterized in that, The orientation of the body region 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 orientation, the third orientation, and the fourth orientation are respectively the up-down direction, the front-back direction, and the left-right direction of the body region, and any two of the second orientation, the third orientation, and the fourth orientation are perpendicular to each other.

11. The method according to claim 10, characterized in that, Determining the orientation of the target region for the fetus in early pregnancy based on the three-dimensional ultrasound data includes: The spinal region of the early-pregnancy fetus was detected in the three-dimensional ultrasound data; The orientation of the body region is determined based on the orientation of the spinal region.

12. The method according to claim 11, characterized in that, Determining the orientation of the body region based on the orientation of the spinal region includes: A straight line close to the spinal region is determined, and the direction of the straight line is defined as the second direction of the body region.

13. The method according to claim 12, characterized in that, Determining the orientation of the body region based on the orientation of the spinal region includes: Extract one or more body cross-sections perpendicular to the second direction from the three-dimensional ultrasound data of the fetus in early pregnancy; The position of the body center point and the spine in the cross-section of the body is detected, and the line connecting the position of the body center point and the position of the spine is determined as the third direction of the body region of the fetus in early pregnancy.

14. The method according to claim 11, characterized in that, Determining the orientation of the body region based on the orientation of the spinal region includes: A curve close to the spinal region is determined, and the direction of the curve's convexity is defined as the third direction of the fetal body region in early pregnancy.

15. The method according to claim 10, characterized in that, Determining the orientation of the target region for the fetus in early pregnancy based on the three-dimensional ultrasound data includes: The body regions of the early pregnancy fetus were detected from the three-dimensional ultrasound data; The orientation of the body region is determined based on its shape.

16. The method according to claim 15, characterized in that, Determining the orientation of the body region based on its shape includes: The major axis of the body region is determined based on its shape. The direction of the long axis is determined as the second direction of the fetal body region in early pregnancy.

17. The method according to any one of claims 10-16, characterized in that, Determining the orientation of the target region for the fetus in early pregnancy based on the three-dimensional ultrasound data includes: The second and third directions of the fetal body region in early pregnancy are determined, and the direction perpendicular to the second and third directions is determined as the fourth direction of the fetal body region in early pregnancy.

18. The method according to any one of claims 10-16, characterized in that, Determining the orientation of the target region for the fetus in early pregnancy based on the three-dimensional ultrasound data includes: The location of symmetrical feature structures in the body of the fetus in early pregnancy is detected in the three-dimensional ultrasound data, and the direction of the line connecting the symmetrical feature structures is determined as the fourth direction of the body region of the fetus in early pregnancy.

19. The method according to any one of claims 1-16, 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.

20. The method according to claim 19, characterized in that, Selecting at least one standard section corresponding to the target region from the plurality of candidate sections includes: Each candidate section is used as the probability of a standard section by a trained machine learning model, and the candidate section whose probability satisfies a first threshold is determined as at least one standard section corresponding to the target region.

21. The method according to claim 19, characterized in that, Selecting at least one standard section corresponding to the target region from the plurality of candidate sections includes: 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 a standard section corresponding to the target region.

22. The method according to claim 19, characterized in that, Selecting at least one standard section corresponding to the target region from the plurality of candidate sections includes: 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.

23. The method according to any one of claims 1-16, characterized in that, 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.

24. The method according to claim 23, 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.

25. 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, 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, and the orientation of the target region includes the orientation of the head region and / or the orientation of the body region. Based on the direction of the target region, at least one standard section is extracted from the three-dimensional ultrasound data. The standard section includes a standard section corresponding to the body region and / or a standard section corresponding to the whole body region. This includes: extracting the standard section corresponding to the body region from the three-dimensional ultrasound data based on the direction of the body region, and / or, extracting the standard section corresponding to the whole body region from the three-dimensional ultrasound data based on the direction of the head region or the direction of the body region. A display for showing the at least one standard cross-section.

26. The ultrasound imaging system according to claim 25, characterized in that, The direction of the head region includes a first direction of the head region, wherein the first direction is the left-right direction of the head region.

27. The ultrasound imaging system according to claim 25, characterized in that, The orientation of the body 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.

28. The ultrasound imaging system according to any one of claims 25-27, characterized in that, Extracting at least one standard section from the three-dimensional ultrasound data based on the orientation of the target region includes: Based on the orientation of the target region, multiple candidate cross-sections corresponding to the target region are extracted from the three-dimensional ultrasound data; At least one standard section is selected from the plurality of candidate sections.

29. The ultrasound imaging system according to any one of claims 25-27, characterized in that, 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 the 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.

Images