Method for assessing fetal posture, ultrasound imaging method and ultrasound imaging system

Abstract

The application provides a fetal posture evaluation method, an ultrasonic imaging method and an ultrasonic imaging system. The fetal posture evaluation method comprises the following steps: acquiring three-dimensional ultrasonic data of an early-pregnancy fetus; acquiring a head region and a body region of the early-pregnancy fetus in the three-dimensional ultrasonic data; evaluating a posture of the early-pregnancy fetus based on a relative positional relationship between the head region and the body region of the early-pregnancy fetus, to obtain a posture evaluation result; and displaying the posture evaluation result. The method can facilitate a doctor to observe the posture of the fetus and quickly learn whether the posture of the early-pregnancy fetus is in a natural posture.

Description

Technical Field

[0001] The present invention generally relates to the field of medical equipment technology, and more particularly to a fetal posture assessment method, an ultrasound imaging method, and an ultrasound imaging system. Background Art

[0002] Ultrasound examinations are widely used in clinical settings due to their safety, convenience, lack of radiation, and low cost, becoming one of the primary diagnostic aids for physicians. In clinical practice, fetal structural examinations and malformation screening during early pregnancy are a current clinical trend and research hotspot. Early pregnancy fetal structural screening can detect lethal malformations early, providing pregnant women with the opportunity to terminate the pregnancy as early as possible, minimizing physical and mental harm, and possesses significant clinical significance and value.

[0003] Standard sections during early pregnancy are one of the primary methods for observing fetal structural abnormalities. Numerous sections are used to screen for fetal structural abnormalities during early pregnancy, including the parietal diameter section, the horizontal transverse section of the lateral ventricles, the biparietal diameter section, and the abdominal circumference section. Systematic observation of these sections is used to determine whether the fetus has structural abnormalities. Furthermore, during early pregnancy, the head and body often assume unnatural postures (head tilted, head lowered, neck crooked, etc.), resulting in some standard sections (such as the NT section and parietal diameter section) not meeting clinical quality control requirements. Summary of the Invention

[0004] The present invention is proposed to solve at least one of the above problems. Specifically, in a first aspect, the present invention provides a method for assessing fetal posture, the method comprising:

[0005] Acquire three-dimensional ultrasound data of the fetus during early pregnancy;

[0006] Acquiring a head region and a body region of the early pregnancy fetus from the three-dimensional ultrasound data;

[0007] evaluating the posture of the early pregnancy fetus based on the relative positional relationship between the head region and the body region of the early pregnancy fetus to obtain a posture evaluation result;

[0008] The posture evaluation result is displayed.

[0009] A second aspect of the present invention provides a method for assessing fetal posture, the method comprising: acquiring three-dimensional ultrasound data of a fetus in early pregnancy;

[0010] registering the three-dimensional ultrasound data of the early-trimester fetus and the three-dimensional fetal model to obtain a registered fetal public model corresponding to the posture of the three-dimensional ultrasound data of the early-trimester fetus;

[0011] based on the posture of the registered three-dimensional fetus model, evaluating the posture of the early gestation fetus to obtain a posture evaluation result;

[0012] displaying the posture evaluation result.

[0013] The third aspect of the present application provides an ultrasonic imaging method, which comprises:

[0014] acquiring three-dimensional ultrasonic data of an early gestation fetus;

[0015] based on the three-dimensional ultrasonic data, acquiring at least one standard section of the early gestation fetus;

[0016] registering the three-dimensional ultrasonic data with a three-dimensional fetus model;

[0017] based on the registration result and the position information of the at least one standard section in the three-dimensional ultrasonic data, determining the spatial position of the at least one standard section in the three-dimensional fetus model;

[0018] displaying the three-dimensional fetus model and the spatial position of the at least one standard section in the three-dimensional fetus model.

[0019] The fourth aspect of the present application provides an ultrasonic imaging system, which comprises:

[0020] an ultrasonic probe;

[0021] a transmitting / receiving sequence controller for controlling the ultrasonic probe to transmit ultrasonic waves to an early gestation fetus, receiving ultrasonic echoes based on the ultrasonic waves returned from the early gestation fetus to obtain ultrasonic echo signals;

[0022] a processor for acquiring three-dimensional ultrasonic data of the early gestation fetus according to the ultrasonic echo signals;

[0023] a memory for storing executable program instructions;

[0024] the processor is further used for executing the program instructions stored in the memory, so that the processor executes the aforementioned fetus posture evaluation method or the aforementioned ultrasonic imaging method;

[0025] a display device for displaying visual information.

[0026] According to the fetal posture evaluation method of the first aspect and the second aspect of the present application, the posture of the early pregnancy fetus can be evaluated, and the posture evaluation result is output and displayed, so that the doctor can conveniently observe the posture of the fetus, quickly learn whether the posture of the early pregnancy fetus is in a natural posture, and assist the doctor in quickly judging whether the posture of the fetus leads to that part of the standard section does not meet the clinical quality control requirement based on the posture evaluation result, so that the doctor can obtain the standard section meeting the clinical quality control requirement according to the posture evaluation result, and the efficiency and accuracy of checking the abnormal structure of the fetus based on the standard section are improved.

[0027] According to the ultrasonic imaging method of the third aspect of the present application, the positions of the standard sections of the early pregnancy fetus can be more intuitively displayed, so that the doctor can quickly judge the accuracy of the sections and can assist in adjusting the positions of the sections, and thus the efficiency and accuracy of checking the abnormal structure of the fetus based on the standard section are improved. BRIEF DESCRIPTION OF DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0029] Figure 1 A flowchart of a fetal posture evaluation method in an embodiment of the present application is shown;

[0030] Figure 2 A schematic diagram of a three-dimensional ultrasonic image of a fetal posture being a tilted head posture in an embodiment of the present application is shown;

[0031] Figure 3 A schematic diagram of a fetal posture evaluation method in another embodiment of the present application is shown;

[0032] Figure 4 A flowchart of an ultrasonic imaging method in an embodiment of the present application is shown;

[0033] Figure 5 A schematic diagram of matching of a heart standard section with a common model in an embodiment of the present application is shown;

[0034] Figure 6 A schematic block diagram of an ultrasonic imaging system in an embodiment of the present application is shown;

[0035] Figure 7 A schematic block diagram of an ultrasonic imaging system in another embodiment of the present application is shown. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solutions and advantages of the present invention more apparent, exemplary embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments of the present invention, and it should be understood that the present invention is not limited to the exemplary embodiments described herein. Based on the embodiments of the present invention described in the present invention, all other embodiments obtained by those skilled in the art without creative work should fall within the scope of protection of the present invention.

[0037] In the following description, numerous specific details are provided to provide a more thorough understanding of the present invention. However, it will be apparent to those skilled in the art that the present invention may be practiced without one or more of these details. In other instances, certain technical features well known in the art are not described to avoid confusion with the present invention.

[0038] It should be understood that the present invention can be implemented in different forms and should not be interpreted as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to make disclosure thorough and complete and to fully convey the scope of the present invention to those skilled in the art.

[0039] In order to fully understand the present invention, a detailed structure will be provided in the following description to illustrate the technical solution proposed by the present invention. Optional embodiments of the present invention are described in detail below. However, in addition to these detailed descriptions, the present invention may also have other implementations.

[0040] In order to facilitate doctors to intuitively know the posture of early pregnancy fetuses, the present application provides a method for evaluating fetal posture, the evaluation method also includes: obtaining three-dimensional ultrasound data of the early pregnancy fetus; obtaining the head area and body area of ​​the early pregnancy fetus in the three-dimensional ultrasound data; based on the relative position relationship between the head area and the body area of ​​the early pregnancy fetus, evaluating the posture of the early pregnancy fetus to obtain a posture evaluation result; and displaying the posture evaluation result. According to the evaluation method of the present application, the posture of the early pregnancy fetus can be evaluated and the posture evaluation result can be output and displayed, so that it is convenient for doctors to observe the posture of the fetus and quickly know whether the posture of the early pregnancy fetus is in a natural posture. It can also assist doctors in quickly judging whether the posture of the fetus causes some standard sections to fail to meet clinical quality control requirements based on the posture evaluation results, thereby facilitating doctors to obtain standard sections that meet clinical quality control requirements based on the posture evaluation results, thereby improving the efficiency and accuracy of screening for abnormal fetal structures based on these standard sections.

[0041] Specifically, the fetal posture assessment method, ultrasound imaging method, and ultrasound imaging system of the present application are described in detail below with reference to the accompanying drawings. The features of the following embodiments and implementations may be combined with each other unless they conflict.

[0042] First, refer to Figures 1 to 7 The fetal posture assessment method, ultrasound imaging method and ultrasound imaging system according to the embodiments of the present invention are described, wherein: Figure 1 A flowchart showing a method for assessing fetal posture in one embodiment of the present invention is shown; Figure 2 A schematic diagram showing a three-dimensional ultrasound image of a fetus with a head tilted posture in one embodiment of the present invention is shown; Figure 3 A schematic diagram showing a method for assessing fetal posture in another embodiment of the present invention; Figure 4 A flow chart showing an ultrasound imaging method according to an embodiment of the present invention is shown; Figure 5 A schematic diagram showing the matching of a standard cardiac section with a public model in one embodiment of the present invention is shown; Figure 6 FIG1 shows a schematic block diagram of an ultrasound imaging system in one embodiment of the present invention; Figure 7 A schematic block diagram of an ultrasound imaging system in another embodiment of the present invention is shown.

[0043] First, refer to the attached Figure 1 A method for assessing fetal posture in one embodiment of the present invention is described.

[0044] As an example, Figure 1 As shown, the fetal posture assessment method of the present application includes the following steps:

[0045] Specifically, in step S110, three-dimensional ultrasound data of an early pregnancy fetus is obtained; in step S120, the head region and body region of the early pregnancy fetus in the three-dimensional ultrasound data are obtained; in step S130, the posture of the early pregnancy fetus is evaluated based on the relative positional relationship between the head region and the body region of the early pregnancy fetus to obtain a posture evaluation result; in step S140, the posture evaluation result is displayed.

[0046] In step S110, the three-dimensional ultrasound data of the early pregnancy fetus can be obtained based on any suitable method known to those skilled in the art. For example, the three-dimensional ultrasound data of the early pregnancy fetus can be obtained based on the ultrasound video data of the early pregnancy fetus obtained by the ultrasound imaging system, wherein the ultrasound video data may include a continuous multi-frame two-dimensional ultrasound image. In the embodiment of the present application, the two-dimensional ultrasound image includes but is not limited to an image of any mode such as a B-ultrasound image. Figure 6As shown, the ultrasound imaging system may include a probe 1, a transmitting / receiving module 2, a beamforming module 3, a signal processing module 4, a 3D imaging module 5, and an image processing module 6. The doctor moves the probe 1 to select an appropriate position and angle. The transmitting circuit in the transmitting / receiving module 2 sends a set of delayed and focused pulses to the probe 1. The probe 1 then transmits the corresponding ultrasonic waveforms along the corresponding two-dimensional (2D) scanning plane toward the tissue being examined. After a certain delay, the receiving circuit receives the reflected ultrasonic waveforms and converts them into electrical signals. The beamforming module 3 performs corresponding delay and weighted summation on the signals obtained from multiple transmissions / receptions to achieve beamforming, which is then processed by the signal processing module 4. Simultaneously, the probe 1 transmits and receives ultrasonic waveforms within a series of scanning planes. The 3D imaging module 5 integrates these waveforms based on their 3D spatial relationships, achieving 3D scanning of the entire fetus and reconstruction of a 3D image. Finally, the image post-processing module 6 performs some or all of the image processing steps, such as denoising, smoothing, and enhancement, to obtain 3D ultrasound data of the early pregnancy fetus.

[0047] In step S120, the head and body regions of the early-pregnancy fetus can be obtained from the three-dimensional ultrasound data using any suitable method. For example, methods for obtaining the head and body regions include segmentation and detection. Segmentation methods include first sampling the three-dimensional ultrasound data to obtain surfaces, i.e., extracting surfaces according to preset specifications, such as obtaining sections by rotating a circle at a preset angle or obtaining sections at preset intervals along the depth. After extracting the surfaces, the sections are segmented, and the segmentation results are interpolated three-dimensionally to obtain the head and body regions. Alternatively, a three-dimensional segmentation algorithm can be directly applied to the three-dimensional ultrasound data to directly segment the head and body regions of the early-pregnancy fetus. Two-dimensional and three-dimensional segmentation algorithms include deep learning methods and traditional segmentation methods, such as FCN, DeepLab, and PSPnet, and traditional methods such as threshold segmentation and watershed. Detection-based methods for obtaining the head and body regions of the early-pregnancy fetus include two-dimensional and three-dimensional detection methods. After detecting the head or body region of the early-pregnancy fetus, the head and body regions are extracted and their boundary information is obtained (segmentation can be performed using either deep learning or traditional methods). Or directly perform detection and boundary information extraction. Common methods include deep learning methods such as MaskRcnn and YoLact.

[0048] In step S130, the posture of the early pregnancy fetus can be evaluated based on any suitable method, for example, based on the spatial position information of the head region of the early pregnancy fetus, the orientation of the head region is obtained; based on the spatial position information of the body region of the early pregnancy fetus, the orientation of the body region is obtained; based on the angle between the orientation of the head region and the orientation of the body region, the posture of the early pregnancy fetus is evaluated to obtain a posture evaluation result. Optionally, the posture evaluation result includes the posture and / or posture parameters of the early pregnancy fetus, wherein the posture of the early pregnancy fetus includes the head posture of the early pregnancy fetus, the posture parameters include the head posture parameters of the early pregnancy fetus, the head posture includes abnormal posture and standard posture, and the abnormal posture includes at least one of the following postures: tilted head posture, tilted head posture, lowered head posture, raised head posture or other abnormal posture. The head posture parameters of a fetus in early pregnancy can be the angle between the orientation of the fetal head area and the orientation of the body area. For example, when the posture of the fetal head is a tilted head posture, the posture parameters include the degree of head tilt; when the posture of the fetal head is a tilted head posture, the posture parameters include the degree of head tilt; when the posture of the fetal head is a lowered head posture, the posture parameters include the degree of lowered head; when the posture of the fetal head is a tilted head posture, the posture parameters include the degree of tilted head.

[0049] It is worth mentioning that the degree of head tilt refers to the angle between the direction of the fetal head area and the direction of the body area (for example, the angle at which the head is tilted to the left or right relative to the body) when the fetus is in a tilted posture (for example, the head is tilted to the left or right relative to the body); the degree of head deflection refers to the angle between the direction of the fetal head area and the direction of the body area (for example, the rotation angle of the head relative to the body) when the head is in a tilted posture (for example, the head is rotated relative to the body); the degree of head descent refers to the angle between the direction of the fetal head area and the direction of the body area when the fetus is in a head-down posture; the degree of head tilt refers to the angle between the direction of the fetal head area and the direction of the body area when the fetus is in a head-up posture.

[0050] The orientation of the fetal head region can be determined based on the orientation of the fetal face or based on other landmark structures of the head region. For example, the orientation of the fetal face can be upward, to the upper left, to the upper right, to the left, to the right, downward, to the lower left, to the lower right, or in other directions. The fetal posture is determined based on the angle between the orientation of the head region and the orientation of the body region. Generally, the orientation of the head region can be represented by a vector, and the orientation of the body region can also be represented by a vector. The angle is determined based on the relative relationship between the two vectors.

[0051] In one example, the method of the present application further includes: when the posture assessment result indicates that the posture of the fetus in early pregnancy is an abnormal posture, outputting a prompt message. Optionally, the prompt message includes abnormal posture information and / or section information of the standard section affected by the abnormal posture information. The abnormal posture information may include abnormal posture information including at least one of the following postures: tilted head posture, tilted head posture, lowered head posture, and raised head posture. The standard section affected by the abnormal posture information refers to the abnormal posture that may cause the section to not meet the preset requirements of the standard section. The section information includes but is not limited to text information for characterizing the section type. In the present application, the standard section includes at least one of the following sections: parietal diameter section, horizontal transverse section of the lateral ventricle, biparietal diameter section, NT standard section, chest diameter section, abdominal circumference section, abdominal wall umbilical cord insertion section, bladder section, spinal longitudinal section, and trunk long axis section.

[0052] The prompt information may be output when the posture parameter is greater than a preset value, or the corresponding prompt information may be issued once the fetus is in an abnormal posture. In the method of the present application, prompt information may also be displayed to show and prompt the user that certain standard sections cut out under the current fetal posture do not meet the requirements of the standard sections.

[0053] Usually, slight posture abnormalities may not affect the images and measurements of standard sections, but when the degree of posture abnormality is more serious, for example, when the posture parameter is greater than the preset value, it is very likely that some standard sections will not meet the clinical quality control requirements (that is, they will not meet the preset requirements of the standard sections). For example, when the head tilt angle is greater than the first preset angle value, or the head tilt angle is greater than the second preset angle value, or the head tilt angle is greater than the third preset angle value, or the head tilt angle is greater than the fourth preset angle value, it may cause some standard sections (such as NT standard section, crown-hip diameter section) to not meet the clinical quality control requirements. The values ​​of the first preset angle value, the second preset angle value, the third preset angle value, and the fourth preset angle value can be reasonably set according to actual conditions. They can be a priori empirical values. For example, the values ​​of the first preset angle value, the second preset angle value, the third preset angle value, and the fourth preset angle can be angle values ​​between 5° and 15°. For example, the values ​​of the first preset angle value, the second preset angle value, the third preset angle value, and the fourth preset angle can be 5°, 10°, 15°, etc.

[0054] In a specific example, when the fetus in early pregnancy is in a head tilt posture and the tilt angle is greater than 15 degrees, it may cause the standard sections such as the NT standard section or the crown-rump diameter section to not meet the requirements of the standard section. At this time, a prompt message can be output to prompt the doctor to re-scan to obtain a section that better meets the requirements, thereby improving the efficiency and accuracy of screening for abnormal fetal structures based on these standard sections. Figure 2As shown, if the early pregnancy fetus is in a head tilt posture, a prompt message may be provided to remind the user that the crown-rump diameter section of the early pregnancy fetus in the current posture cannot be used.

[0055] In one example, the evaluation method of the present application further includes: acquiring a three-dimensional ultrasound image of a fetus in early pregnancy based on the three-dimensional ultrasound data; displaying the three-dimensional ultrasound image (such as Figure 2 (The figure shows a schematic diagram of a fetus in a head-tilted position). To facilitate subsequent presentation of the 3D ultrasound image, such as on a display device, the 3D ultrasound image can also be a rendered 3D ultrasound image, which can serve as a representation of the 3D ultrasound image. When the rendered 3D ultrasound image is displayed on the display device, the user can observe the same visual effect as the 3D ultrasound image. By observing the 3D ultrasound image, the user can intuitively obtain the posture of the early pregnancy fetus. Alternatively, the user can display the posture and posture parameters of the early pregnancy fetus in the posture assessment results, such as text, on the side of the displayed 3D ultrasound image.

[0056] In addition to the above evaluation method, this application also provides another fetal posture evaluation method, which is referred to below. Figure 3 The evaluation method in another embodiment of the present application is described. It is worth mentioning that some details of this embodiment have been described above and will not be repeated here.

[0057] In another embodiment, Figure 3 As shown, the fetal posture assessment method of the present application also includes the following steps: in step S310, three-dimensional ultrasound data of an early pregnancy fetus is acquired; in step S320, the three-dimensional ultrasound data of the early pregnancy fetus and the fetal three-dimensional model are aligned to obtain a registered fetal common model corresponding to the posture of the three-dimensional ultrasound data of the early pregnancy fetus; in step S330, the posture of the early pregnancy fetus is evaluated based on the posture of the aligned fetal three-dimensional model to obtain a posture assessment result; in step S340, the posture assessment result is displayed.

[0058] The detailed description of step S310 in this embodiment can refer to step S110 in the previous text and will not be repeated here.

[0059] In one example, in step S320, the three-dimensional ultrasound data of the early pregnancy fetus and the three-dimensional model of the fetus can be aligned based on any suitable method known to those skilled in the art to obtain a aligned three-dimensional model of the fetus. For example, the alignment can be performed based on the method shown below.

[0060] The first registration method involves directly registering the 3D ultrasound data of the early pregnancy fetus with the 3D fetal model. The 3D ultrasound data and the 3D fetal model are matched to obtain a spatial transformation. Based on the spatial transformation, the spatial coordinates of the 3D ultrasound data are mapped to the spatial coordinates of the 3D fetal model. The spatial transformation can be obtained based on the following method. In one embodiment, the spatial transformation can be a transformation matrix. For example, in one example, an optimal 3D spatial transformation (also referred to as a transformation matrix) is obtained that maximizes the similarity or minimizes the difference between the acquired 3D ultrasound data of the early pregnancy fetus (e.g., voxel values ​​of the 3D ultrasound data) and the 3D fetal model (e.g., voxel values ​​of the 3D fetal model). Alternatively, in another example, image features of the 3D ultrasound data and the 3D fetal model can be first extracted. These image features include, but are not limited to, gradient features, texture features such as LBP, Harr features, HOG / LOG features, etc., and then an optimal 3D spatial transformation (also referred to as a transformation matrix) is obtained that maximizes the similarity or minimizes the difference between the acquired 3D ultrasound data of the early pregnancy fetus and the image features extracted from the 3D fetal model. In another embodiment, the spatial transformation amount can be a rotation axis (Euler angle), and the fetal 3D ultrasound data can be rotated about the rotation axis, thereby mapping the spatial coordinates of the 3D ultrasound data to the spatial coordinates of the fetal 3D model, thereby achieving registration of the fetal 3D ultrasound data and the fetal 3D model. The description of the spatial transformation amount in this application can be understood with reference to the above description.

[0061] In step S320, the position information of the fetal head and body regions in the three-dimensional ultrasound data of the early pregnancy fetus can be segmented, and the fetal three-dimensional model can be directly matched according to the spatial position of the fetal head and body in the three-dimensional ultrasound data of the early pregnancy fetus. Specifically, the method may include: obtaining the head region and body region of the early pregnancy fetus in the three-dimensional ultrasound data; and registering the head region and body region of the early pregnancy fetus with the fetal three-dimensional model to obtain a registered fetal three-dimensional model corresponding to the posture of the early pregnancy fetus. Among them, deep learning and traditional image methods can be used to directly segment and locate the position of the head and body. The deep learning-based method directly trains a segmentation network model, and the network model may include a two-dimensional convolutional network or a three-dimensional convolutional network. The position of the head and body is directly segmented and located based on the trained segmentation network model; the traditional method includes algorithms such as threshold segmentation and edge extraction by the canny operator.

[0062] Any suitable method known to those skilled in the art can be used to align the head region and body region of the early pregnancy fetus with the fetal three-dimensional model respectively. For example, the head region of the early pregnancy fetus can be aligned with the fetal three-dimensional model first, and then the body region of the early pregnancy fetus can be aligned with the fetal three-dimensional model. Alternatively, the body region can be aligned first, and then the head region can be aligned.

[0063] In the second registration method: the two-dimensional sections of the three-dimensional ultrasound data of the early pregnancy fetus are matched with the sections of the three-dimensional model of the fetus, and the three-dimensional ultrasound data are registered with the three-dimensional model of the fetus, including: obtaining multiple two-dimensional sections in the three-dimensional ultrasound data, wherein the two-dimensional sections can be standard sections or arbitrary sections of the three-dimensional ultrasound data of the early pregnancy fetus; matching each two-dimensional section with the two-dimensional standard section template data in the three-dimensional model of the fetus to obtain an optimal two-dimensional section with the highest similarity to the two-dimensional standard section template data; determining the spatial transformation amount between the three-dimensional ultrasound data and the three-dimensional model of the fetus based on the mapping relationship between the position information of the optimal two-dimensional section and the position information of the two-dimensional standard section template data; and mapping the spatial coordinates of the three-dimensional ultrasound data to the spatial coordinates of the three-dimensional model of the fetus based on the spatial transformation amount.

[0064] Each two-dimensional section is matched with the two-dimensional standard section template data in the three-dimensional fetal model to obtain an optimal two-dimensional section with the highest similarity to the two-dimensional standard section template data. For example, an optimal two-dimensional section is obtained in the three-dimensional ultrasound data of the early pregnancy fetus, so that the optimal two-dimensional section has the highest similarity or the smallest difference with the section of the fetal three-dimensional model, for example, the pixel information of the optimal two-dimensional section is made to have the highest similarity or the smallest difference with the pixel information of the section of the fetal three-dimensional model, or the image features extracted from the section of the optimal two-dimensional section and the fetal three-dimensional model (such as gradient features, texture features such as LBP, Harr features, HOG / LOG features, etc.) are made to have the highest similarity or the smallest difference. Then, based on the mapping relationship between the position information of the optimal two-dimensional section and the position information of the section of the fetal three-dimensional model, the spatial transformation amount between the three-dimensional ultrasound data and the fetal three-dimensional model is determined; based on the spatial transformation amount, the spatial coordinates of the three-dimensional ultrasound data are mapped to the spatial coordinates of the fetal three-dimensional model.

[0065] In the third registration method: the key anatomical structures in the three-dimensional ultrasound data can also be matched with the corresponding anatomical structures in the fetal three-dimensional model, for example, including: matching multiple image areas in the three-dimensional ultrasound data with the key anatomical structure standard data in the fetal three-dimensional model respectively to obtain a target image area with the highest similarity to the key anatomical structure standard data; determining the spatial transformation amount between the three-dimensional ultrasound data and the fetal three-dimensional model based on the mapping relationship between the position information of the target image area and the position information of the key anatomical structure standard data; and mapping the spatial coordinates of the three-dimensional ultrasound data to the spatial coordinates of the fetal three-dimensional model based on the spatial transformation amount.

[0066] Matching multiple image regions in the three-dimensional ultrasound data with the standard data of key anatomical structures in the three-dimensional fetal model to obtain a target image region with the highest similarity to the standard data of key anatomical structures, for example, including: obtaining an optimal image block in the three-dimensional ultrasound data of the early pregnancy fetus, so that the optimal image block has the highest similarity or the smallest difference with the standard data of the early pregnancy key anatomical structures of the three-dimensional fetal model, or the image features of the optimal image block have the highest similarity or the smallest difference; for another example, also including using target detection methods such as Faster RCNN, Mask RCNN, SSD, YOLO, Retinanet, Efficientnet, Cornernet, Centernet, FCOS, etc. to detect candidate early pregnancy key anatomical structure regions in the obtained three-dimensional ultrasound data of the early pregnancy fetus, and then matching them with the standard data of the early pregnancy key anatomical structures in the three-dimensional fetal model. The matching method includes finding an optimal candidate early pregnancy key anatomical structure so that it has the highest similarity or the smallest difference with the standard data of the early pregnancy key anatomical structure in the fetal three-dimensional model; it also includes extracting image features of the candidate early pregnancy key anatomical structure and the standard data of the early pregnancy key anatomical structure, and then finding an optimal candidate early pregnancy key anatomical structure so that its image features have the highest similarity or the smallest difference with the image features of the standard data of the early pregnancy key anatomical structure; it also includes finding the optimal candidate early pregnancy key anatomical structure and an optimal spatial transformation so that the spatial position difference between the candidate early pregnancy key anatomical structure and the standard data of the early pregnancy key anatomical structure is minimized. Optionally, the key anatomical structures include but are not limited to: one or more of the kidneys, liver, heart, etc.

[0067] Optionally, a spatial transformation between the 3D ultrasound data and the 3D fetal model can be determined based on a mapping relationship between the position information of the optimal candidate early pregnancy key anatomical structure and the position information of the standard data for early pregnancy key anatomical structures. Based on the spatial transformation, the spatial coordinates of the 3D ultrasound data are mapped to the spatial coordinates of the 3D fetal model.

[0068] In the fourth registration method: the key points of the three-dimensional ultrasound data of the early pregnancy fetus are matched with the midpoints of the fetal three-dimensional model, including: matching the corresponding key point standard data in the three-dimensional ultrasound data and the fetal three-dimensional model to obtain target key points that match the key point standard data in the three-dimensional ultrasound data; determining the spatial transformation amount between the three-dimensional ultrasound data and the fetal three-dimensional model based on the mapping relationship between the position information of the target key points and the position information of the key anatomical structure standard data; and mapping the spatial coordinates of the three-dimensional ultrasound data to the spatial coordinates of the fetal three-dimensional model based on the spatial transformation amount.

[0069] Matching the three-dimensional ultrasound data with the corresponding key point standard data in the three-dimensional fetal model to obtain target key points in the three-dimensional ultrasound data that match the key point standard data. This may include, for example, finding an optimal point (i.e., the target key point) in the acquired three-dimensional ultrasound data of the early pregnancy fetus, such that the image features near the optimal point have the highest similarity or the smallest difference with the image features of the early pregnancy key point standard data in the three-dimensional fetal model. This may also include using a feature point extraction method (e.g., SIFT method), a corner point detection method (e.g., Harris method), or a neural network method to predict point coordinates or the region where the point is located, detecting candidate key points in the acquired three-dimensional ultrasound data of the early pregnancy fetus, and then matching them with the early pregnancy key point standard data. The matching method may include finding an optimal candidate key point (i.e., the target key point) such that the image features near the optimal point have the highest similarity or the smallest difference with the image features of the early pregnancy key point standard data; or finding an optimal candidate early pregnancy key point (i.e., the target key point) and an optimal spatial transformation such that the spatial position difference between the candidate early pregnancy key point and the early pregnancy key point standard data is minimized. Optionally, the key points include but are not limited to one or more of the top of the head, chin, neck, abdomen, etc.

[0070] After registration, the posture of the fetal head and body can be evaluated based on the posture of the three-dimensional public model, such as whether the head is tilted, tilted, tilted up, or lowered. In step S230, the posture of the early pregnancy fetus is evaluated based on the posture of the registered fetal three-dimensional model to obtain a posture evaluation result, including: obtaining the orientation of the head area and the orientation of the body area in the registered fetal three-dimensional model; based on the angle between the orientation of the head area and the orientation of the body area, the posture of the early pregnancy fetus is evaluated to obtain a posture evaluation result. Specifically, please refer to the relevant description of step S130 above.

[0071] The posture assessment result includes the posture and / or posture parameters of the early pregnancy fetus. Optionally, the early pregnancy fetal posture includes the head posture of the early pregnancy fetus, and the posture parameters include the head posture parameters of the early pregnancy fetus. The head posture includes an abnormal posture and a standard posture, and the abnormal posture includes at least one of the following postures: tilted head posture, tilted head posture, lowered head posture, and raised head posture.

[0072] Optionally, when the posture of the fetal head is a tilted head posture, the posture parameters include the degree of head tilt; when the posture of the fetal head is a tilted head posture, the posture parameters include the degree of head tilt; when the posture of the fetal head is a lowered head posture, the posture parameters include the degree of lowered head; when the posture of the fetal head is a tilted head posture, the posture parameters include the degree of tilted head.

[0073] The evaluation method of the present application may also include displaying a three-dimensional public model so that the user can intuitively observe the posture of the fetus. The three-dimensional public model displayed by the display device may be a rendered three-dimensional public model. When the display device displays the rendered three-dimensional public model, a three-dimensional stereoscopic effect can be presented to the user.

[0074] In the evaluation method of the present application, the posture and posture parameters of the early pregnancy fetus in the posture evaluation results described by, for example, text can also be displayed on one side of the displayed three-dimensional public model.

[0075] In one example, when the posture assessment result indicates that the posture of the fetus in early pregnancy is abnormal, a prompt message is output. The prompt message includes the abnormal posture information and / or the section information of the standard section affected by the abnormal posture information. In the method of the present application, the prompt message can also be displayed. For details about the prompt message, please refer to the relevant description above.

[0076] In summary, according to the fetal posture evaluation method of the present application, the posture of the early pregnancy fetus can be evaluated, and the posture evaluation results can be output and displayed, so that the doctor can observe the fetal posture conveniently and quickly know whether the posture of the early pregnancy fetus is in a natural posture. It can also assist the doctor in quickly judging whether the fetal posture causes some standard sections to fail to meet the clinical quality control requirements based on the posture evaluation results, thereby helping the doctor to obtain standard sections that meet the clinical quality control requirements based on the posture evaluation results, thereby improving the efficiency and accuracy of screening for abnormal fetal structures based on these standard sections.

[0077] Furthermore, the present application also provides an ultrasonic imaging method, which will be referred to below. Figure 4 and Figure 5 The ultrasonic imaging method of the present application is described.

[0078] As an example, Figure 4 As shown, the ultrasound imaging method of the present application includes the following steps: an ultrasound imaging method, characterized in that the ultrasound imaging method includes: in step S410, obtaining three-dimensional ultrasound data of an early pregnancy fetus; in step S420, obtaining at least one standard section of the early pregnancy fetus based on the three-dimensional ultrasound data; in step S430, aligning the three-dimensional ultrasound data with the three-dimensional model of the fetus; in step S440, determining the spatial position of at least one standard section in the three-dimensional model of the fetus based on the result of the alignment and the position information of at least one standard section in the three-dimensional ultrasound data; in step S450, displaying the three-dimensional model of the fetus and the spatial position of at least one standard section in the three-dimensional model of the fetus.

[0079] First, the method of obtaining the three-dimensional ultrasound data of the early pregnancy fetus in step S410 can refer to the description of step S110 in the above text, which will not be repeated here.

[0080] Then, in step S420, optionally, the standard sections include at least one of the following sections: parietal diameter section, horizontal transverse section of the lateral ventricles, biparietal diameter section, NT standard section, thoracic diameter section, abdominal circumference section, abdominal wall umbilical cord insertion section, bladder section, longitudinal section of the spine, long axis section of the trunk, standard heart section or other suitable sections.

[0081] At least one standard section of an early pregnancy fetus can be obtained by any suitable method known to those skilled in the art based on three-dimensional ultrasound data of the early pregnancy fetus. For example, obtaining at least one standard section of an early pregnancy fetus based on three-dimensional ultrasound data of the early pregnancy fetus includes: obtaining key anatomical structure information of the early pregnancy fetus related to the standard section in the three-dimensional ultrasound data, such as the lateral ventricle or choroid plexus in the cross-section of the lateral ventricle, the thalamus in the biparietal diameter section, the cerebellum in the cross-section of the cerebellum, etc.; based on the key anatomical structure information, obtaining a standard section corresponding to the key anatomical structure information from the three-dimensional ultrasound data.

[0082] Methods for obtaining standard sections include automatic, semi-automatic, or manual methods. For example, standard sections can be automatically obtained. The method for automatically obtaining standard sections includes: first, obtaining key anatomical structure information in the three-dimensional ultrasound data, that is, obtaining key anatomical structure information of the early pregnancy fetus related to the standard section in the three-dimensional ultrasound data, such as the lateral ventricle or choroid plexus in the cross-section of the lateral ventricle, the thalamus in the biparietal diameter section, the cerebellum in the cross-section of the cerebellum, etc., and automatically obtaining key anatomical structure information of the fetus under test related to the standard section in the three-dimensional ultrasound data based on an intelligent recognition algorithm. Among them, the intelligent recognition algorithm includes but is not limited to traditional image processing or deep learning methods. Traditional image processing methods include image feature extraction, such as Sift features, gradient features, texture features such as LBP, PCA, LDA, Harr features, HOG and LOG features, etc., and also include image edge extraction, such as edge extraction using the Canny operator; deep learning methods can use segmentation networks (FCN, Unet, etc.), detection networks (Faster RCNN, Mask RCNN, etc.), localization (Hourglass, CenterNet, etc.), etc. After obtaining the anatomical structure information through the above method, standard sections corresponding to the key anatomical structure information are automatically obtained from the 3D ultrasound data. For example, standard abdominal sections and four-chamber heart sections are obtained based on the gastric bubble and heart information.

[0083] For another example, a semi-automatic method can be used to obtain the standard section of the early pregnancy fetus, and the required standard section can be obtained by manual intervention. In the first example, the corresponding key anatomical structures of the standard section are obtained through deep learning or traditional image algorithms, and these key anatomical structures are marked on the three-dimensional ultrasound data of the early pregnancy fetus. The user can obtain the standard section of the early pregnancy fetus through the information of these key anatomical structures. This semi-automatic method can assist the user in obtaining the standard section and accurately locate the tissue structure and position information contained in the section. Secondly, the rough position or initial position of the standard section can also be obtained through deep learning or traditional algorithms based on the located anatomical structure, and the translation or angle (i.e., rotation) can be adjusted based on the user's instructions to obtain a suitable standard section.

[0084] In the second example of a method for obtaining standard cross-sections of an early pregnancy fetus by a semi-automatic method: first, the early pregnancy fetus is automatically straightened to obtain the spatial position of the early pregnancy fetus (the spatial position includes the position of the head and body). Straightening refers to adjusting the position of the early pregnancy fetus to a desired position by rotation, translation or spatial transformation. The desired position can be a position that is convenient for the user to view, such as the fetal neck and buttocks are in a horizontal direction, and the spine is roughly parallel to the horizontal direction, in a lying state, etc., or other suitable positions, and then the rough position of each standard cross-section is given according to its spatial position, and then based on the user's instructions, the cross-section position is fine-tuned to obtain the final standard cross-section. Both deep learning and traditional methods can be used to obtain spatial position. Deep learning methods can directly regress the angle required for body and head rotation at a specific point, or segment or locate specific anatomical structures (such as the spine or the lateral ventricles) through deep learning, and then use the symmetry and position of these structures for alignment. Traditional alignment methods can first extract traditional image features from early pregnancy ultrasound data, such as Sift features, gradient features, texture features like LBP, PCA, LDA, Harm features, HOG, and LOG features. These features are then used to locate the spatial structure of the 3D ultrasound data, and finally, alignment is performed based on this information. Alternatively, after the early pregnancy fetus is straightened, a rough section position is given on the three-dimensional ultrasound data of the early pregnancy fetus, and finally the section position can be fine-tuned (such as translation and / or rotation) based on user instructions to obtain the final standard section position. Alternatively, the position of key anatomical structures can be selected in the three-dimensional ultrasound data of the early pregnancy fetus based on user instructions. User instructions can be input by clicking the mouse, tracing the edges, etc., and then the corresponding standard section is automatically determined according to the position of these key anatomical structures.

[0085] Standard sections can also be obtained in a fully manual manner. Users can obtain the required standard sections through fully manual methods such as translation and rotation.

[0086] In step S430 , the three-dimensional ultrasound data is registered with the three-dimensional fetal model. For details of the registration, reference may be made to the description of step S320 above, which will not be repeated here.

[0087] Furthermore, in step S440, the spatial position of the at least one standard slice in the three-dimensional fetal model is determined based on the pre-registration results and the position information of the at least one standard slice in the three-dimensional ultrasound data. For example, a spatial transformation amount can be obtained based on the aforementioned configuration results. Based on the spatial transformation amount, the position information of the corresponding standard slice in the three-dimensional ultrasound data can be mapped to the three-dimensional fetal model, thereby obtaining the spatial position of the standard slice in the three-dimensional fetal model.

[0088] Furthermore, in step S450, the fetal three-dimensional model and the spatial position of at least one standard section in the fetal three-dimensional model are displayed, for example, the fetal three-dimensional model and a position indication graphic for representing the spatial position of at least one standard section in the fetal three-dimensional model are displayed, wherein the position indication graphic includes at least one of the following graphics: a frame-shaped graphic for representing the spatial position of at least one standard section in the fetal three-dimensional model, such as a square, parallelogram, diamond, etc., a line-shaped indication graphic for representing the spatial position of at least one standard section in the fetal three-dimensional model, or other position indication graphics that can facilitate the user to intuitively know the standard section in the fetal three-dimensional model. In a specific example, as Figure 5 As shown, the left side shows the standard section of the early pregnancy heart, and the right side shows the fetal three-dimensional model 510 and the position indication graphic 520 of the standard section in the fetal three-dimensional model. The indication graphic 520 is a square shape, and it can also be a linear graphic, for example, indicated by two perpendicular intersecting straight lines, or indicated by a directional straight line, etc.

[0089] The above method can be used to align the three-dimensional ultrasound data of the early pregnancy fetus with the three-dimensional model of the fetus. After the alignment, the position of the standard section obtained from the three-dimensional ultrasound data can be displayed in the three-dimensional model of the fetus, thereby intuitively displaying the spatial position of the section, so that the user can quickly judge the accuracy of the section, and can also assist the user in adjusting the position of the section. For example, when the user finds that the position of the standard section does not meet the requirements, the scanning position can be adjusted according to the displayed section position, so as to re-scan and obtain the standard section that meets the requirements.

[0090] Optionally, the ultrasound imaging method further includes: acquiring the head and body of the early pregnancy fetus in the three-dimensional ultrasound data; evaluating the posture of the early pregnancy fetus based on the spatial position information of the early pregnancy fetal head and the spatial position information of the body to obtain a posture evaluation result; and displaying the posture evaluation result. Optionally, the posture evaluation result includes the posture and / or posture parameters of the early pregnancy fetus. Optionally, when the posture evaluation result characterizes that the posture of the early pregnancy fetus is an abnormal posture, a prompt message is output, the prompt message including the abnormal posture information and / or the section information of the standard section affected by the abnormal posture. For details on the posture evaluation, please refer to the relevant description above and will not be repeated here.

[0091] In summary, according to the ultrasound imaging method of the present application, the positions of various standard sections of the early pregnancy fetus can be displayed more intuitively, so that doctors can quickly judge the accuracy of the sections and assist in adjusting the positions of the sections, thereby improving the efficiency and accuracy of screening for abnormal fetal structures based on standard sections.

[0092] The present application also provides an ultrasonic imaging system. Figure 7 The ultrasound imaging system 10 may include an ultrasound probe 100, a transmit / receive selection switch 101, a transmit / receive sequence controller 102, a processor 103, an output device 104, and a memory 105. The transmit / receive sequence controller 102 is configured to control the ultrasound probe to transmit ultrasound waves to a fetus in the early pregnancy, receive ultrasound echoes based on the ultrasound waves returned from the fetus in the early pregnancy, and obtain ultrasound echo signals.

[0093] The doctor moves the ultrasound probe 100 to select an appropriate position and angle. The transmit / receive sequence controller 102 (which can be part or all of the transmit circuit described above) sends a set of delayed, focused pulses to the ultrasound probe 100 via the transmit / receive selector switch 101. The ultrasound probe 100 then transmits the corresponding ultrasonic waveforms along the corresponding two-dimensional (2D) scanning plane toward the tissue being examined, such as a fetus in early pregnancy. After a certain delay, the transmit / receive sequence controller 102 (which can be part or all of the receive circuit described above) receives the reflected ultrasonic waveforms and converts them into electrical signals. The beamforming module performs corresponding delay and weighted summation on the signals obtained from multiple transmissions and receptions to achieve beamforming. The signals are then processed by the processor 103, such as the processor's signal processing module. Simultaneously, the ultrasound probe 100 transmits and receives ultrasonic waveforms within a series of scanning planes. The processor 103, such as the processor's 3D imaging module, integrates the ultrasonic waveforms based on their 3D spatial relationships, achieving 3D scanning of the entire fetus and reconstruction of a 3D image. Finally, the image post-processing module of the processor 103 performs some or all of the image processing steps such as denoising, smoothing, and enhancement to obtain three-dimensional ultrasound data of the early pregnancy fetus.

[0094] The ultrasound probe 100 typically comprises an array of multiple elements. Each time an ultrasonic wave is transmitted, all elements of the ultrasound probe 100, or a portion of all elements, participate in the transmission of the ultrasonic wave. Each element, or a portion of elements, participating in the ultrasonic wave transmission is excited by the transmit pulse and transmits an ultrasonic wave. The ultrasonic waves emitted by these elements superimpose during propagation, forming a composite ultrasonic beam that is transmitted to the scanned target. The direction of this composite ultrasonic beam is the direction of ultrasonic propagation.

[0095] The processor 103 is used to acquire three-dimensional ultrasound volume data of the fetus under examination based on the ultrasound echo signals. For example, the processor 103 is used to process the ultrasound echo signals / data to obtain a continuous multi-frame two-dimensional ultrasound image of the early-pregnancy fetus. The ultrasound image can be a B-image (also referred to herein as a B-ultrasound image), a C-image, or other types of ultrasound images. The processor 103 is used to process the ultrasound echo signals differently based on the imaging mode required by the user, obtaining image data of different modes. The processor 103 then processes the ultrasound echo signals through logarithmic compression, dynamic range adjustment, digital scan conversion, and other processing to form ultrasound images of different modes, such as B-images and C-images. The ultrasound probe 100 transmits and receives ultrasound waveforms in a series of scanning planes, and the processor 103 integrates them according to their three-dimensional spatial relationship. Based on the continuous multi-frame two-dimensional ultrasound images, the processor 103 scans the entire fetus in three dimensions and reconstructs a 3D image. Finally, after performing some or all of the image processing steps such as denoising, smoothing, and enhancement, the processor 103 acquires three-dimensional ultrasound data of the early-pregnancy fetus.

[0096] In one example, the memory 105 of the ultrasound imaging system may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory. Non-volatile memory may include, for example, read-only memory (ROM), a hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 103 may execute the program instructions to implement the functions (implemented by the processor 103) in the embodiment of the present application and / or other desired functions. Various applications and various data, such as various data used and / or generated by the application, may also be stored in the computer-readable storage medium.

[0097] In one example, the processor 103 of the ultrasound imaging system can be implemented by software, hardware, firmware, or a combination thereof, and can use circuits, single or multiple application specific integrated circuits (ASICs), single or multiple general-purpose integrated circuits, single or multiple microprocessors, single or multiple programmable logic devices, or a combination of the aforementioned circuits or devices, or other suitable circuits or devices, so that the processor 103 can perform the functions required to be implemented by it and / or other desired functions.

[0098] In one example, the ultrasound imaging system may further include an input device (not shown), which may be a device used by a user to input instructions and may include one or more of a keyboard, a mouse, a microphone, a touch screen, and the like.

[0099] In one embodiment of the present application, when the program instructions stored in the memory 105 are executed by the processor 103, the processor 103 is used to execute the various related steps of the fetal posture assessment method and the ultrasound imaging method mentioned above. The description of the specific steps can be found in the above text and will not be repeated here.

[0100] The ultrasound imaging system of the present application also includes an output device (not shown) that can output various information (e.g., images or sounds) to an external device (e.g., a user) and can include one or more of a display device 104, a printer, a speaker, etc. The 3D ultrasound images, posture assessment results, 3D fetal models, cross-sectional images, and other information obtained by the processor 103 can be stored in the memory 105 and displayed on, for example, the display device 104.

[0101] The display device 104 is used to display various visual information, including but not limited to three-dimensional ultrasound images, posture assessment results, three-dimensional fetal models, cross-sectional images, and the aforementioned prompt information. In the embodiments of the present application, the display device 104 of the ultrasound imaging system may be a touch screen display, a liquid crystal display, or the like. It may also be an independent display device such as an LCD or television set independent of the ultrasound imaging system, or a display screen on an electronic device such as a mobile phone or tablet computer. The display device 104 may be used to display information input by or provided to the user, as well as various graphical user interfaces of the ultrasound imaging device. These graphical user interfaces may be composed of graphics, text, icons, videos, or any combination thereof.

[0102] Since the ultrasound imaging system of the present application can implement the fetal posture assessment method and ultrasound imaging method mentioned above, it also has the advantages of the aforementioned methods.

[0103] In addition, the embodiments of the present application further provide a computer storage medium, which stores a computer program. One or more computer program instructions can be stored on the computer readable storage medium, and the processor can run the program instructions stored by the storage device to realize the functions (implemented by the processor) in the embodiments of the present application herein and / or other desired functions, for example, to perform the corresponding steps of the fetal posture evaluation method and the ultrasonic imaging method according to the embodiments of the present application. Various application programs and various data can also be stored in the computer readable storage medium, for example, various data used and / or generated by the application programs.

[0104] For example, the computer storage medium can 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.

[0105] Although the example embodiments have been described herein with reference to the accompanying drawings, it is to be understood that the above-described example embodiments are merely 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.

[0106] Those of ordinary skill in the art can realize that the units and algorithm steps of each example 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.

[0107] 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 device embodiments described above are merely illustrative, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed.

[0108] 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.

[0109] Similarly, it should be understood that in order to streamline the present invention and aid in understanding one or more of the various inventive aspects, in the description of exemplary embodiments of the present invention, the various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this approach to the present invention should not be interpreted as reflecting the intention that the claimed invention requires more features than those explicitly recited in each claim. More precisely, as reflected in the corresponding claims, the inventive point is that the corresponding technical problem can be solved with fewer features than all the features of a single disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into the detailed description, with each claim itself serving as a separate embodiment of the present invention.

[0110] Those skilled in the art will understand that, except where mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or apparatus disclosed herein may be combined in any combination. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that provides the same, equivalent, or similar purpose.

[0111] Furthermore, those skilled in the art will appreciate that although some embodiments described herein include certain features included in other embodiments but not other features, combinations of features from different embodiments are intended to be within the scope of the present invention and to form different embodiments. For example, in the claims, any of the claimed embodiments may be used in any combination.

[0112] The various component embodiments of the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It will be appreciated by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all of the functions of some modules according to embodiments of the present invention. The present invention can also be implemented as a device program (e.g., a computer program and a computer program product) for executing a part or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0113] It should be noted that the above embodiments illustrate rather than limit the invention, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between brackets should not be construed as limiting the claims. The invention may be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third etc. does not indicate any order. These words may be interpreted as names.

Claims

1. An ultrasonic imaging method, characterized in that: The ultrasonic imaging method comprises: Obtain three-dimensional ultrasound data of the fetus in early pregnancy; acquiring at least one standard section of the early pregnancy fetus based on the three-dimensional ultrasound data; registering the three-dimensional ultrasound data with the three-dimensional fetal model; Determining a spatial position of the at least one standard section in the three-dimensional fetal model based on a result of the registration and position information of the at least one standard section in the three-dimensional ultrasound data; displaying the fetal three-dimensional model and the spatial position of the at least one standard section in the fetal three-dimensional model; The registering of the three-dimensional ultrasound data with the three-dimensional fetal model includes: Acquiring a plurality of two-dimensional slices in the three-dimensional ultrasound data; Matching each of the two-dimensional sections with the two-dimensional standard section template data in the three-dimensional fetal model to obtain an optimal two-dimensional section with the highest similarity to the two-dimensional standard section template data; determining a spatial transformation amount between the three-dimensional ultrasound data and the three-dimensional volume data of the three-dimensional fetal model based on a mapping relationship between the position information of the optimal two-dimensional section and the position information of the two-dimensional standard section template data; Mapping the spatial coordinates of the three-dimensional ultrasound data to the spatial coordinates of the three-dimensional volume data of the three-dimensional fetal model based on the spatial transformation amount; Alternatively, registering the three-dimensional ultrasound data with the three-dimensional fetal model includes: Matching the plurality of image regions in the three-dimensional ultrasound data with the key anatomical structure standard data in the three-dimensional fetal model respectively to obtain a target image region having the highest similarity to the key anatomical structure standard data; determining a spatial transformation amount between the three-dimensional ultrasound data and the three-dimensional volume data of the three-dimensional fetal model based on a mapping relationship between the position information of the target image region and the position information of the key anatomical structure standard data; Mapping the spatial coordinates of the three-dimensional ultrasound data to the spatial coordinates of the three-dimensional volume data of the three-dimensional fetal model based on the spatial transformation amount; Alternatively, registering the three-dimensional ultrasound data with the three-dimensional fetal model includes: matching the three-dimensional ultrasound data with corresponding key point standard data in the three-dimensional fetal model to obtain target key points in the three-dimensional ultrasound data that match the key point standard data; determining a spatial transformation amount between the three-dimensional ultrasound data and the three-dimensional fetal model based on a mapping relationship between the position information of the target key point and the position information of the key anatomical structure standard data; Based on the spatial transformation amount, the spatial coordinates of the three-dimensional ultrasound data are mapped to the spatial coordinates of the three-dimensional fetal model.

2. The ultrasonic imaging method according to claim 1, wherein: The acquiring, based on the three-dimensional ultrasound data, at least one standard section of the early pregnancy fetus comprises: Acquiring key anatomical structure information of the early pregnancy fetus related to the standard section in the three-dimensional ultrasound data; Based on the key anatomical structure information, a standard section corresponding to the key anatomical structure information is acquired from the three-dimensional ultrasound data.

3. The ultrasonic imaging method according to claim 1, wherein: The displaying of the fetal three-dimensional model and the spatial position of at least one standard section in the fetal three-dimensional model includes: The fetal three-dimensional model and a position indication graphic for representing the spatial position of the at least one standard section in the fetal three-dimensional model are displayed, wherein the position indication graphic includes at least one of the following graphics: a frame graphic for representing the spatial position of the at least one standard section in the fetal three-dimensional model, and a line indication graphic for representing the spatial position of the at least one standard section in the fetal three-dimensional model.

4. The ultrasonic imaging method according to claim 1, wherein: The ultrasonic imaging method further comprises: Acquiring the head and body of the early pregnancy fetus from the three-dimensional ultrasound data; evaluating the posture of the early pregnancy fetus based on the spatial position information of the head and the spatial position information of the body of the early pregnancy fetus to obtain a posture evaluation result; The posture evaluation result is displayed.

5. The ultrasonic imaging method according to claim 4, wherein: The posture assessment result includes the posture and / or posture parameters of the early pregnancy fetus.

6. The ultrasonic imaging method according to claim 5, wherein: When the posture assessment result indicates that the posture of the early pregnancy fetus is abnormal, prompt information is output, where the prompt information includes abnormal posture information and / or section information of a standard section affected by the abnormal posture.

7. The ultrasonic imaging method according to any one of claims 1 to 6, wherein: The standard sections include at least one of the following sections: parietal diameter section, lateral ventricle horizontal cross section, biparietal diameter section, NT standard section, chest diameter section, abdominal circumference section, abdominal wall umbilical cord insertion section, bladder section, spinal longitudinal section, heart standard section, and trunk long axis section.

8. An ultrasonic imaging system, characterized in that: The ultrasound imaging system comprises: Ultrasound probe; a transmit / receive sequence controller, configured to control the ultrasound probe to transmit ultrasound waves to the early-trimester fetus, receive ultrasound echoes based on the ultrasound waves returned from the early-trimester fetus, and obtain ultrasound echo signals; a processor, configured to acquire three-dimensional ultrasound data of the early pregnancy fetus according to the ultrasound echo signal; a memory for storing executable program instructions; The processor is further configured to execute the program instructions stored in the memory, so that the processor performs the ultrasonic imaging method according to any one of claims 1 to 7; A display device is used to display visual information.

Images