CN112654299A

CN112654299A - Ultrasonic imaging method, ultrasonic imaging apparatus, storage medium, processor, and computer apparatus

Info

Publication number: CN112654299A
Application number: CN201880097331.8A
Authority: CN
Inventors: 朱磊; 董国豪; 邹耀贤; 林穆清; 胡锦明
Original assignee: Shenzhen Mindray Bio Medical Electronics Co Ltd
Current assignee: Shenzhen Mindray Bio Medical Electronics Co Ltd
Priority date: 2018-11-22
Filing date: 2018-11-22
Publication date: 2021-04-13
Also published as: WO2020103098A1

Abstract

An ultrasound imaging method, apparatus, storage medium, processor and computer apparatus. Wherein, the method comprises the following steps: transmitting ultrasonic waves to the uterus in a manner of covering the whole uterine region, and receiving ultrasonic echoes to obtain ultrasonic echo signals (S202); obtaining three-dimensional volume data of the uterus according to the ultrasonic echo signals (S204); determining the pregnancy period of the uterus (S206); identifying key anatomical structures of the fetus corresponding to the pregnancy from the three-dimensional volume data (S208); the number of fetuses in the uterus is determined based on the critical anatomical structures (S210). The technical problem of low accuracy rate of fetal quantity detection in the related technology is solved.

Description

Ultrasonic imaging method, ultrasonic imaging apparatus, storage medium, processor, and computer apparatus

Technical Field

The invention relates to the field of ultrasonic detection, in particular to an ultrasonic imaging method, ultrasonic imaging equipment, a storage medium, a processor and computer equipment.

Background

In ultrasonography, the number of fetuses is generally determined in the early stage of pregnancy, the fetuses do not mature, the fetuses are still in the form of gestational sacs, the shape characteristics are not obvious and difficult to identify, and the gestational sacs are in various positions and can be present in various positions in the uterus. In addition, there is a large difference in the shape of the uterus according to individual differences, which increases the difficulty in measuring the number of fetuses.

In the prior art, when detecting the number of fetuses, doctors or inspectors generally make reasonable guesses according to detected ultrasonic images and the imagination of the inspectors. The method has great inaccuracy and low accuracy.

In view of the above problems, no effective solution has been proposed.

Disclosure of Invention

The embodiment of the invention provides an ultrasonic imaging method, ultrasonic imaging equipment, a storage medium, a processor and computer equipment, which are used for at least solving the technical problem of low accuracy rate of fetal quantity detection in the related technology.

According to an aspect of an embodiment of the present invention, there is provided an ultrasound imaging method including: transmitting ultrasonic waves to the uterus in a mode of covering the whole uterus area, and receiving ultrasonic echoes to obtain ultrasonic echo signals; obtaining three-dimensional volume data of the uterus according to the ultrasonic echo signals; determining the pregnancy period in which the uterus is; identifying key anatomical structures of a fetus corresponding to the pregnancy from the three-dimensional volumetric data; determining the number of fetuses in the uterus based on the critical anatomical structures.

In one embodiment, the pregnancy comprises: an early pregnancy period with a week of pregnancy less than a predetermined number of weeks, or an early-intermediate pregnancy period with a week of pregnancy greater than a predetermined number of weeks.

In one embodiment, the critical anatomical structures corresponding to the early pregnancy period comprise at least one of: gestational sac, yolk sac and embryo; the critical anatomical structures corresponding to the early pregnancy include at least one of: cranium, trunk, femur, spine, and limbs.

In one embodiment, identifying key anatomical structures of a fetus corresponding to the pregnancy from the three-dimensional volumetric data comprises: obtaining features that enable discrimination between critical anatomical structures; identifying at least one region from the three-dimensional volume data according to the feature; determining a target region from the at least one region, wherein the target region is determined to have the highest probability of being the key anatomical structure; determining the target region as the critical anatomical structure.

In one embodiment, the features include at least one of: two-dimensional features and three-dimensional features.

In one embodiment, obtaining features that can distinguish whether a critical anatomical structure is present comprises: collecting positive samples determined to be the critical anatomical structure and negative samples determined not to be the critical anatomical structure; training the positive and negative examples based on machine learning to obtain features that can distinguish whether a critical anatomical structure is present.

In one embodiment, identifying key anatomical structures of a fetus corresponding to the pregnancy from the three-dimensional volumetric data comprises: classifying pixel points in the image of the three-dimensional volume data to obtain a classification result; and identifying key anatomical structures according to the classification result.

In one embodiment, identifying key anatomical structures of a fetus corresponding to the pregnancy from the three-dimensional volumetric data comprises: determining a structure template, wherein the structure template comprises a plurality of real key anatomical structures; identifying a target region from the three-dimensional volume data according to the structure template, wherein the target region is a region with the highest matching degree with a key anatomical structure in the structure template; determining the target region as the critical anatomical structure.

In one embodiment, identifying key anatomical structures of a fetus corresponding to the pregnancy from the three-dimensional volumetric data comprises: identifying a pending critical anatomical structure from the three-dimensional volumetric data; and adjusting the undetermined key anatomical structure in a mode of receiving input operation to obtain the key anatomical structure.

In one embodiment, determining the number of fetuses in the uterus based on the critical anatomical structures comprises: acquiring the number of fetuses in the uterus, which is determined according to a plurality of key anatomical structures respectively, under the condition that the number of the key anatomical structures is multiple; determining the number of fetuses in the uterus that is the highest in consistency.

According to another aspect of the embodiments of the present invention, there is also provided an ultrasound imaging method, including: displaying three-dimensional volume data of the uterus, wherein the three-dimensional volume data is obtained after scanning the uterus in a mode of covering the whole uterus area through ultrasound; displaying a pregnancy in which the uterus is located, and displaying key anatomical structures of a fetus corresponding to the pregnancy; displaying the number of fetuses in the uterus determined from the key anatomical structures.

In one embodiment, displaying the key anatomical structures of the fetus corresponding to the pregnancy includes: displaying features that can distinguish whether a critical anatomical structure is present; displaying at least one region identified from the three-dimensional volume data according to the feature; highlighting a target region, wherein the target region is determined to have the highest probability of being the critical anatomical structure.

In one embodiment, displaying the key anatomical structures of the fetus corresponding to the pregnancy includes: and displaying a pixel contour obtained after classifying the pixel points in the image of the three-dimensional volume data, wherein the pixel contour is used for distinguishing a key anatomical structure from a non-key anatomical structure.

In one embodiment, displaying the key anatomical structures of the fetus corresponding to the pregnancy includes: displaying key anatomical structures in a structure template, wherein the structure template comprises a plurality of real key anatomical structures; and displaying a target region identified from the three-dimensional volume data according to the structure template, wherein the target region is a region with the highest matching degree with a key anatomical structure in the structure template.

In one embodiment, displaying the key anatomical structures of the fetus corresponding to the pregnancy includes: displaying pending critical anatomical structures identified from the three-dimensional volumetric data; displaying the input operation; and displaying the key anatomical structure obtained after the undetermined key anatomical structure is adjusted according to the operation.

According to another aspect of the embodiments of the present invention, there is also provided another ultrasound imaging method, including: acquiring three-dimensional volume data of a uterus, wherein the three-dimensional volume data is obtained by scanning the uterus through ultrasound; identifying key anatomical structures from the three-dimensional volumetric data; determining the number of fetuses in the uterus based on the critical anatomical structures.

According to another aspect of the embodiments of the present invention, there is also provided an ultrasound imaging apparatus including: a probe; a transmitting circuit, wherein the transmitting circuit stimulates the probe to transmit ultrasonic waves to the uterus; a receiving circuit that receives an ultrasound echo returned from the uterus by the probe to obtain an ultrasound echo signal; a processor that processes the ultrasound echo signals to obtain three-dimensional volumetric data of the uterus; a display that displays the three-dimensional volume data; wherein the processor further performs the steps of: identifying key anatomical structures from the three-dimensional volumetric data; and determining the number of fetuses in the uterus based on the critical anatomical structures.

In one embodiment, the display is further configured to display at least one of: the critical anatomy, the number of fetuses in the uterus, the pregnancy period in which the uterus is located.

According to another aspect of the embodiments of the present invention, there is also provided a storage medium including a stored program, wherein when the program runs, a device in which the storage medium is located is controlled to execute the ultrasound imaging method according to any one of the above.

According to another aspect of the embodiments of the present invention, there is also provided a processor for executing a program, wherein the program is executed to perform the ultrasound imaging method described in any one of the above.

According to another aspect of the embodiments of the present invention, there is also provided a computer device, including: a memory and a processor, the memory storing a computer program; the processor is configured to execute the computer program stored in the memory, and the computer program performs any one of the above ultrasound imaging methods when running.

In the embodiment of the invention, ultrasonic waves are transmitted to the uterus in a mode of covering the whole uterus area, and ultrasonic echoes are received to obtain ultrasonic echo signals; obtaining three-dimensional volume data of the uterus according to the ultrasonic echo signals; determining the pregnancy period in which the uterus is; identifying key anatomical structures of a fetus corresponding to the pregnancy from the three-dimensional volumetric data; according to the key anatomical structure, the number of the fetuses in the uterus is determined, the purpose of effectively detecting and calculating the number of the fetuses in the uterus is achieved by detecting three-dimensional volume data of the fetuses in the uterus and identifying the key anatomical structure capable of accurately representing the number of the fetuses, so that the technical effect of improving the accuracy of detecting the number of the fetuses is achieved, and the technical problem that the accuracy of detecting the number of the fetuses in the related technology is low is solved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:

fig. 1 is a schematic block diagram illustrating an ultrasound imaging apparatus 10 according to an embodiment of the present application;

FIG. 2 is a flow chart of a method of ultrasound imaging according to an embodiment of the present invention;

FIG. 3 is a flow chart of another method of ultrasound imaging according to an embodiment of the present invention;

FIG. 4 is a flow chart of another method of ultrasound imaging according to an embodiment of the present invention;

fig. 5 is a flowchart of a fetal quantity measuring method according to an embodiment of the present invention;

fig. 6 is a schematic structural diagram of an ultrasound imaging apparatus according to an embodiment of the present invention.

Detailed Description

In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Fig. 1 is a schematic structural block diagram of an ultrasound imaging apparatus 10 in an embodiment of the present application. The ultrasound imaging device 10 may include a probe 100, a transmit circuit 101, a transmit/receive select switch 102, a receive circuit 103, a beam forming circuit 104, a processor 105, and a display 106. The transmit circuit 101 may excite the probe 100 to transmit ultrasound waves to the target object. The receiving circuit 103 may receive an ultrasonic echo returned from the target object through the probe 100, thereby obtaining an ultrasonic echo signal. The ultrasonic echo signal is subjected to beamforming processing by the beamforming circuit 104, and then sent to the processor 105. The processor 105 processes the ultrasound echo signals to obtain an ultrasound image of the target object. The ultrasound images obtained by the processor 105 may be stored in the memory 107. These ultrasound images may be displayed on the display 106.

In accordance with an embodiment of the present invention, there is provided a method embodiment of an ultrasound imaging method, it being noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system, such as a set of computer-executable instructions, and that while a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than presented herein.

Fig. 2 is a flow chart of a method of ultrasound imaging according to an embodiment of the present invention, as shown in fig. 2, the method comprising the steps of:

step S202, transmitting ultrasonic waves to the uterus in a mode of covering the whole uterus area, and receiving ultrasonic echoes to obtain ultrasonic echo signals;

step S204, obtaining three-dimensional data of the uterus according to the ultrasonic echo signals;

step S206, determining the pregnancy period of the uterus;

step S208, identifying a key anatomical structure of a fetus corresponding to a pregnancy period from the three-dimensional volume data;

step S210, determining the number of fetuses in the uterus based on the critical anatomical structures.

Through the steps, the number of the fetuses in the uterus is determined according to the key anatomical structures identified from the three-dimensional data, and the key anatomical structures can accurately represent the number of the fetuses in the uterus to a certain extent, so that the identification of the key anatomical structures can realize the identification of the fetuses in the uterus, the number of the fetuses in the uterus is determined according to the identified key anatomical structures, the purpose of effectively and accurately detecting the number of the fetuses in the uterus is achieved, the technical effect of improving the accuracy of detecting the number of the fetuses is achieved, and the technical problem that the accuracy of detecting the number of the fetuses in the related technology is low is solved.

The ultrasound imaging region of the ultrasound covers the entire uterine region. In acquiring three-dimensional volume data of the uterus, the ultrasound imaging region of the ultrasound probe covers the entire uterine region. Since the fetus is in the form of a gestational sac during the early pregnancy, the gestational sac can be located in various locations within the uterus. Such as the fundus of the uterus, the anterior wall of the uterus, the posterior wall of the uterus, the upper uterus or the middle uterus, etc. To prevent missed or false detections, the range of the ultrasound imaging region is extended to the entire uterine region. It should be noted that the ultrasound imaging region may be smaller than or equal to the ultrasound detection region, and therefore, the ultrasound detection region should cover at least the entire uterine region, so that the number of fetuses determined is accurate, and the problem of missing due to the hidden location of the fetuses is avoided. In this embodiment, the entire uterine region is used as the ultrasound probe region, and the ultrasound echo signal may be obtained by transmitting the ultrasound waves to the uterus in a manner covering the entire uterine region and receiving the ultrasound echoes.

When the ultrasonic echo signal is obtained by transmitting the ultrasonic wave to the uterus in such a manner as to cover the entire uterine region and receiving the ultrasonic echo, the ultrasonic echo signal may be obtained by transmitting the ultrasonic wave once and receiving it. It is also possible to obtain an ultrasonic multiple ultrasonic echo signal by transmitting and receiving ultrasonic waves multiple times. The number of times of sending the ultrasonic waves can be determined according to actual requirements, and the three-dimensional volume data of the whole uterine region can be determined by sending the ultrasonic waves for many times and receiving ultrasonic echo signals for many times under the condition that the three-dimensional volume data of the whole uterine region cannot be determined by sending the ultrasonic waves once or the number of fetuses is difficult to know by the obtained three-dimensional volume data.

The three-dimensional data of the uterus obtained according to the ultrasonic echo signals can comprise three-dimensional coordinates of measuring points in the uterus in a spatial three-dimensional coordinate system and can also comprise a position function of the uterus in the three-dimensional coordinate system. The three-dimensional volume data may further include three-dimensional dimensions of the uterus, which may be length, width, and height. The three-dimensional volume data may be a stereo array obtained after scanning by ultrasound, that is, the internal environment of the uterus is represented by an array mode. The three-dimensional size of the uterus can be determined according to the three-dimensional data. The three-dimensional volume data may be determined in various ways, and in this embodiment, the three-dimensional volume data is acquired by ultrasonic detection. The acquisition of the three-dimensional volume data may be performed by scanning in real time or may be performed by scanning in advance and storing the data, and reading the data from a memory when the number of fetuses in the uterus needs to be determined. The three-dimensional volume data of the uterus may include internal structures of the uterus, for example, the position where the pregnancy sac is landed in the uterus and morphological data of the pregnancy sac.

Since the morphology of the fetus differs from pregnancy to pregnancy and is very different from pregnancy to pregnancy, the above-mentioned determination of the pregnancy in which the uterus is located is performed before the critical anatomical structures of the fetus are identified from the three-dimensional volume data. The pregnancy period of the uterus can be determined in various ways, for example, the pregnancy period of the uterus can be obtained by performing human-computer interaction with a detected person to whom the uterus belongs; the pregnancy period of the uterus can be determined by calling the historical detection data in the case (or the detection record) for the detected person with the case (or the detection record), and other common ways for determining the pregnancy period of the detected person with the uterus can also be adopted. Since the morphology of the uterus key anatomical structures of different pregnancy periods has a large difference, in this embodiment, in order to accurately determine the number of fetuses corresponding to the corresponding pregnancy period, the pregnancy period in which the uterus is located may be determined before the step of identifying the key anatomical structures from the three-dimensional volume data. It should be noted that, in an embodiment, the step of determining the pregnancy period of the uterus may be performed before the step of transmitting ultrasonic waves to the uterus in a manner of covering the whole uterus area, and receiving ultrasonic echoes to obtain ultrasonic echo signals. For example, pregnancy may be determined by determining the pregnancy of the uterus in the manner exemplified above, prior to transmitting ultrasound waves to the uterus. The pregnancy may also be determined in the above-described manner before the step of obtaining three-dimensional volume data of the uterus from the ultrasound echo signals, for example, before obtaining three-dimensional volume data of the uterus from the ultrasound echo signals.

When the pregnancy period of the uterus can not be determined by the method, the pregnancy period of the uterus can be determined by the three-dimensional data of the uterus. When the pregnancy is determined, the pregnancy can be determined according to morphological characteristics of different pregnancies in the ultrasonic detection image corresponding to the three-dimensional volume data, wherein the morphological characteristics comprise the morphological characteristics of the uterus and the morphological characteristics of the fetus.

In one embodiment, the fetal number measurement is generally performed during the early pregnancy when the fetus is immature, and because the fetus has a poor morphology during the early and middle pregnancy, the ultrasound image is required to be combined with key anatomical structures to determine the fetal number. After the late and middle pregnancy, the fetus gradually develops, the fetus morphologically develops completely, the fetus has obvious morphological characteristics of the skull, the limbs and the like, the skull has clear halo, key anatomical structures of the spine, the limbs and the like are all appeared, and the fetus can be used as a basis for identifying the fetus. In addition, the volume of the fetus is large, and the number can be directly identified and counted through the ultrasonic image. Therefore, in the step of determining the uterine pregnancy in this embodiment, the pregnancy is generally an early pregnancy or an early-intermediate pregnancy. The pregnancy period comprises: an early pregnancy period with a week of pregnancy less than a predetermined number of weeks, or an early-intermediate pregnancy period with a week of pregnancy greater than a predetermined number of weeks. For example, an early pregnancy period of less than 8 weeks of gestation, and a mid-pregnancy period of greater than 8 weeks of gestation. It should be noted that 8 weeks is only one reference week, and the reference week may be different according to different individual uterus, and is required according to specific situations.

Key anatomical structures are identified from the acquired three-dimensional volumetric data of the uterus, which may be the overall structure of the uterus, as well as the structure of the intrauterine fetal development. The anatomical structures can be various key anatomical structures such as an early pregnancy anatomical structure, an early-middle pregnancy anatomical structure, a middle pregnancy anatomical structure or other anatomical structures of pregnancy. Wherein the anatomical structure of early pregnancy may comprise at least one of: amnion, pedicles, thick chorion, blastoderm, yolk sac, chorion, etc. The anatomical structure of the early pregnancy may further comprise at least one of: primitive streak, yolk sac, chorion, etc. The early-intermediate stage of pregnancy may include at least one of: chorion, amniocentum, intestine, umbilical cord, yolk sac. The early-intermediate stage of pregnancy may also include at least one of: placenta, yolk sac vestige, amnion, and chorionic villus.

The number of fetuses is determined based on the identified key anatomical structures, which differ from pregnancy to pregnancy due to their different morphology. For example, in early pregnancy, the morphology of the fetus may be represented as a blastoderm, and thus, in the critical anatomy of early pregnancy, the number of fetuses may be determined based on the number of blastoderms. The number of fetuses can be determined according to key anatomical structures corresponding to other pregnancy periods in other pregnancy periods. In one embodiment, the critical anatomical structures corresponding to the early pregnancy period include at least one of: gestational sac, yolk sac and embryo; the critical anatomical structures corresponding to early pregnancy include at least one of: cranium, trunk, femur, spine, and limbs.

It should be noted that, in the early pregnancy, the fetus exists in the form of gestational sac, and the number of the fetus can be determined according to the gestational sac and yolk sac, i.e. embryo. In the early, middle and pregnant period, the fetus gradually develops, key anatomical structures such as cranium, limbs and the like appear, and the number of the fetus can be determined according to the cranium, the trunk, the femur, the spine and the limbs.

In identifying key anatomical structures from three-dimensional volumetric data, a variety of processing approaches may be employed, as exemplified below.

For example, the critical anatomical structures may be identified in terms of their features, e.g., identifying the critical anatomical structures from the three-dimensional volumetric data may include: obtaining features that enable discrimination between critical anatomical structures; identifying at least one region from the three-dimensional volume data based on the features; determining a target region from the at least one region, wherein the target region is determined to have the highest probability of being a key anatomical structure; the target region is determined to be a critical anatomical structure.

The identification of the key anatomical structures from the three-dimensional volume data may be performed in a fully automatic manner, which may be monitored according to a machine learning or deep learning method, or in a semi-automatic manner, which may be a manner in which features corresponding to the pregnancy are determined according to machine learning or deep learning in combination with manual identification. The semi-automatic mode may be that a region with the highest probability of joint anatomical structures is determined as a target region from the at least one region through machine learning, and then the target region is manually identified to be a key anatomical structure, so as to determine the number of fetuses according to the identified key anatomical structure. The area may be an area suspected of having critical anatomical structures, for example, an area where the probability of a pregnant sac occurring during an early pregnancy period is high, and even if the structure of the pregnant sac is not identified, there is a certain probability of a pregnant sac occurring in the area. The above-mentioned regions may also be regions having structures similar to critical anatomical structures.

The target region is determined from the at least one region, wherein the probability that the target region is determined to be the critical anatomical structure is the largest. The determined target region can be determined according to a machine learning or deep learning method, and a machine learning model or a deep learning model is adopted for training by judging whether a plurality of regions are the recognition results of the key anatomical structures. And determining the probability of the region being judged as the key anatomical structure according to the trained machine learning model or deep learning model. The probability of determining whether a region is a critical anatomical structure may also be determined empirically. The target region is a region of the at least one region that is most likely to be a critical anatomical structure. Since the number of structures included in the key anatomical structures is large, and not every key anatomical structure can be used for identifying the number of fetuses, in this embodiment, the key anatomical structures can be identified from the three-dimensional volume data according to the above manner, so that the identification area of the key anatomical structures can be effectively reduced, and the identification efficiency can be improved.

The above features may be two-dimensional features, which are easy, quick and convenient to obtain and handle. And the method can also be used for three-dimensional characteristics, and has high accuracy. The method can also be a mode of combining two-dimensional features and three-dimensional features, is convenient to obtain and process, and can ensure certain accuracy.

In one embodiment, when obtaining the features that can distinguish whether the features are the key anatomical structures, various methods can be used, for example, to obtain the features of the key anatomical structures efficiently, quickly and accurately, the following methods can be used: collecting positive samples determined to be critical anatomical structures and negative samples determined not to be critical anatomical structures; based on machine learning, positive and negative examples are trained to obtain features that can distinguish whether a critical anatomical structure is present.

When the key anatomical structures are identified from the three-dimensional volume data, the method may be a fully automatic method for monitoring according to a machine learning or deep learning method. It may be that positive samples determined to be critical anatomical structures are collected first, and negative samples determined not to be critical anatomical structures are collected first. Based on machine learning, positive and negative examples are trained to obtain features that can distinguish whether a key anatomical structure is present. For example, in early pregnancy, the embryo can be used as a feature to distinguish whether it is a critical anatomical structure, and the location of the embryo can be determined as a critical anatomical feature. When machine learning is performed based on a true sample and a negative sample, the learning model can be trained based on the true sample and the negative sample, where the positive sample can be a embryo image and the negative sample can be a non-embryo image.

For another example, the key anatomical structures may be identified in a manner that classifies pixels in an image of the three-dimensional volume data, for example, identifying key anatomical structures from the three-dimensional volume data includes: classifying pixel points in the image of the three-dimensional volume data to obtain a classification result; and identifying key anatomical structures according to the classification result.

When identifying key anatomical structures from three-dimensional volume data, the key anatomical structures are identified and segmented by an identification algorithm. The identification algorithm can be used for identifying and segmenting in various modes, classifying pixel points in the influence of three-dimensional volume data to obtain a classification result, and identifying a key anatomical structure according to the classification result. For example, the pixels of the fetal torso, skull, and limbs are generally the same type of pixel, and the above-mentioned critical anatomical structures may be determined according to the classification of the type of pixel.

For example, the critical anatomical structures may be identified in terms of a structural template, e.g., in one embodiment, identifying the critical anatomical structures from the three-dimensional volumetric data includes: determining a structure template, wherein the structure template comprises a plurality of real key anatomical structures; and identifying a target region from the three-dimensional volume data according to the structure template, wherein the target region is a region with the highest matching degree with the key anatomical structures in the structure template.

When the key anatomical structures are identified from the three-dimensional volume data, some key anatomical structures can be detected in the volume data by adopting a template matching method. For example, the embryo structure in the early pregnancy period is relatively fixed, some early pregnancy embryo data can be collected in advance to establish a template, all possible regions in the volume data are traversed during detection, similarity matching is performed with the template, and the region with the highest similarity is selected as the target region.

In one embodiment, to make identifying the critical anatomical structures more accurate, identifying the critical anatomical structures from the three-dimensional volume data may further include: identifying a pending key anatomical structure from the three-dimensional volume data; and adjusting the key anatomical structure to be determined by receiving the input operation to obtain the key anatomical structure. By adopting the processing mode of adjustment and correction, the situation that some three-dimensional volume data cannot reflect the key anatomical structure more truly can be avoided to a certain extent.

The above-mentioned method of identifying the position of a specific anatomical structure in the volume data may also be a semi-automatic method for identifying a critical anatomical structure that may die from the three-dimensional volume data. Under the condition that the full-automatic method cannot accurately identify, a user can manually perform operations such as supplementing, deleting and modifying on a detection structure through a certain workflow by means of a keyboard, a mouse and other tools, and semi-automatic anatomical structure detection is achieved, for example, by means of a mouse.

In one embodiment, determining the number of fetuses in the uterus based on the critical anatomical structure comprises: acquiring the number of fetuses in the uterus, which is determined according to the plurality of key anatomical structures respectively, under the condition that the number of the key anatomical structures is multiple; the number of fetuses in utero is determined to be the number of most consistent.

In determining the number of fetuses according to the key anatomical structures, since the number of the key anatomical structures may be plural, for example, in the early pregnancy, the gestational sac, the yolk sac, the embryo and the like may be used as the key anatomical structures. And when determining the number of fetuses, selecting the number with the highest consistency as the number of fetuses in the uterus according to the number of fetuses respectively determined by a plurality of key anatomical structures. The consistency of the number of fetuses may be that, among the plurality of key anatomical structures, the number of identified key anatomical structures having the same number of fetuses accounts for a proportion of the total number of all key anatomical structures. For example, in the early pregnancy period, there may be three key anatomical structures, namely, gestational sac, yolk sac and embryo, when determining the number of fetuses, one fetus is determined according to the gestational sac, one fetus is determined according to the yolk sac, two fetuses are determined according to the embryo, the consistency of one fetus is two thirds, the consistency of two fetuses is one third, and the number with the highest consistency is determined as the number of fetuses in uterus, that is, one fetus is determined as the number of fetuses in uterus, that is, the number of fetuses in uterus is determined as one.

Fig. 3 is a flowchart of another ultrasound imaging method according to an embodiment of the present invention, and as shown in fig. 3, according to another aspect of the embodiment of the present invention, there is also provided another ultrasound imaging method including the steps of:

step S302, displaying three-dimensional volume data of the uterus, wherein the three-dimensional volume data is obtained by scanning the uterus in a mode of covering the whole uterus area through ultrasound;

step S304, displaying the pregnancy period of the uterus, and displaying the key anatomical structure of the fetus corresponding to the pregnancy period;

step S306, displaying the number of fetuses in the uterus determined according to the key anatomical structure.

The main body of execution of the above steps may be a display device. Through the display steps, the number of the fetuses in the uterus can be accurately represented to a certain extent by the key anatomical structures according to the key anatomical structures identified from the three-dimensional volume data, so that the identification of the key anatomical structures can be realized, the number of the fetuses in the uterus can be determined according to the identified key anatomical structures, the purpose of effectively and accurately detecting the number of the fetuses in the uterus is achieved, the technical effect of improving the accuracy of detecting the number of the fetuses is achieved, and the technical problem that the accuracy of detecting the number of the fetuses in the related technology is low is solved.

As the display device side, data processing and acquisition may be performed by a processor of the display device, and display may be performed by the display device. The data may also be received and processed in accordance with the processing means and the displayed data may be transmitted by the processing means to the display device for display by the display device.

In one embodiment, the pregnancy period comprises: an early pregnancy period with a week of pregnancy less than a predetermined number of weeks, or an early-intermediate pregnancy period with a week of pregnancy greater than a predetermined number of weeks.

The display device displays the pregnancy period of the uterus: the early pregnancy period with the gestational weeks less than the preset number of weeks or the early-middle pregnancy period with the gestational weeks more than the preset number of weeks can prompt a doctor or a detector through the display device, so that the doctor or the detector can refer to the doctor or the detector when the doctor or the detector needs to reasonably guess or judge according to the detection condition.

Fig. 4 is a flowchart of another ultrasound imaging method according to an embodiment of the present invention, and as shown in fig. 4, according to another aspect of the embodiment of the present invention, there is also provided another ultrasound imaging method including the steps of:

step S402, acquiring three-dimensional volume data of the uterus, wherein the three-dimensional volume data is obtained by scanning the uterus with ultrasound;

step S404, identifying a key anatomical structure from the three-dimensional volume data;

step S406, determining the number of fetuses in the uterus based on the critical anatomical structures.

Through the steps, the number of the fetuses in the uterus can be accurately represented to a certain extent by the key anatomical structure according to the key anatomical structure identified from the three-dimensional data, so that the identification of the key anatomical structure can realize the identification of the fetuses in the uterus, the number of the fetuses in the uterus is determined according to the identified key anatomical structure, the purpose of effectively and accurately detecting the number of the fetuses in the uterus is achieved, the technical effect of improving the accuracy of detecting the number of the fetuses is achieved, and the technical problem that the accuracy of detecting the number of the fetuses in the related technology is low is solved.

It should be noted that, in the embodiment of the invention, a method for detecting the number of fetuses in uterus is also provided. This detection method can be regarded as a preferred embodiment of the present embodiment, which will be described in detail below.

The ultrasonic technology has the advantages of safety, reliability, rapidness, convenience, repeatable examination and the like, and has become an examination means which is most widely applied in medical image examination, has the highest use frequency and has the fastest popularization speed of new technology. The development of the ultrasonic technology and the artificial intelligence technology further promotes the progress of the clinical diagnosis and treatment technology. However, the population base of China is large, and with the comprehensive opening of the two-child policy, the ultrasonic examination in hospitals faces more severe examination and the demand is more and more vigorous. Meanwhile, medical resource distribution is unbalanced, and the professional technical ability of primary doctors is greatly improved. The intellectualization of the ultrasonic equipment can enable a hospital to obtain more shared resources and technical support, and the cost is lowered systematically; the doctor is helped to improve the examination efficiency and reduce the misdiagnosis rate; provides more accurate diagnosis suggestions and personalized treatment schemes for patients. Therefore, the development and development of intelligent ultrasonic products are of great importance and necessity in all levels of society.

Obstetrical ultrasound is one of the most widely applied fields of ultrasound diagnosis, and in obstetrical early pregnancy ultrasound examination, the determination of the number of surviving fetuses is the basis of all other examinations, and misdiagnosis can bring about a series of serious problems.

In the early pregnancy, the embryo does not develop well and exists in the form of a pregnant sac, and the position of the embryo can be in the uterine fundus, the front wall, the rear wall, the upper part, the middle part and the like; the two-dimensional ultrasonic examination cannot acquire the spatial position information of the uterus, and a doctor needs to have certain abstract spatial imagination to accurately judge the number of fetuses. For inexperienced ultrasound clinicians, miscalculation and miscalculation are prone to occur in situations where the uterine environment is relatively complex. For example, in the early pregnancy, the decidua of the uterine pouch is separated from the decidua of the wall due to the implantation of the pregnant pouch with a small amount of bleeding and mucus accumulation in the uterine cavity, so that the 'double-pouch character' is displayed, the real double-pouch is easier to be misdetected with the real double-pouch in the ultrasonic examination, and the real double-pouch is also easy to be misdetected as one pouch, and the other pouch is interpreted as bleeding; in the middle and late pregnancy, a double-fetus transfusion syndrome sometimes occurs in pregnancy, one fetus is adhered to the uterine wall due to hypo-amniotic fluid, and is easily missed to only find another fetus with over-amniotic fluid; or one fetus dies at an early stage in a multiple pregnancy to form a "paper-like fetus", which is likely to be missed or mistakenly considered as a placental cyst or umbilical cord cyst, etc. during the ultrasound examination.

The embodiment provides a method and a device for automatically counting the number of fetuses, after a doctor finishes 3D ultrasonic data acquisition, the method and the device can automatically identify anatomical structures of different pregnancy periods, count the number of fetuses, solve the problem that counting errors easily occur in multiple fetuses in ultrasonic examination, save prenatal examination time and reduce the technical dependence on ultrasonic clinicians.

In the ultrasonic prenatal examination process, the two-dimensional ultrasound can only acquire the information of a single section of an examination object, so that misdiagnosis and missed diagnosis of multiple fetuses are easily caused, and certain limitations are realized. The three-dimensional ultrasound makes up the deficiency of two-dimensional ultrasound space imaging, and can completely display the three-dimensional shape, the internal structure and the spatial position relation with the surrounding tissues of the anatomical part through a plurality of imaging modes. However, accurate statistics of twins or multiple twins is time-consuming and labor-consuming, and especially under the conditions that the internal environment of the uterus is complex and the position of the fetus is not easy to observe, the requirements on the experience of an ultrasonic clinician are high. The embodiment is based on the uterus volume data of the pregnant women, and the three-dimensional volume data of the whole uterus range is processed through pattern recognition or a machine learning algorithm, so that the key anatomical parts of the fetus are automatically recognized, and the number of the fetus can be accurately and quickly counted.

Fig. 5 is a flowchart of a fetal quantity measuring method according to an embodiment of the present invention, and as shown in fig. 5, in order to realize automatic counting of fetal quantity, the implementation process of the technical solution of the embodiment is divided into three steps, which are respectively: acquiring three-dimensional volume data of a uterus of a pregnant woman; automatically identifying fetal critical anatomical structures in the three-dimensional volumetric data; and determining the number of fetuses based on the number of identified key structures. The specific details of the three steps are as follows:

step 1, acquiring three-dimensional data of a uterus of a pregnant woman;

to realize the counting of the number of fetuses in the whole uterus, three-dimensional ultrasound data of the whole uterus Region needs to be obtained, and a Region of Interest (ROI) and a fan scanning angle can be set to be large enough during scanning so that the scanning range covers the whole uterus Region. Since the uterine region is small during the early pregnancy stage, three-dimensional ultrasound can typically be scanned over the entire uterine region.

Step 2, identifying a fetal key anatomical structure in the three-dimensional volume data;

after acquiring the three-dimensional data of the uterus, the system needs to identify key anatomical structures, and can distinguish and identify according to two conditions of early pregnancy and early-middle pregnancy. The identification method can be semi-automatic or fully automatic.

In this embodiment, the key anatomical structures of each pregnancy can be automatically identified. Key anatomical structures such as gestational sac, yolk sac and embryo can be detected for early pregnancy stages of less than 8 weeks (about gestational week, not necessarily very accurate, the same below). The pregnancy sign discovered by ultrasound is the gestational sac, the gestational sac can be discovered by the transabdominal ultrasound generally 5-6 weeks after menopause, and the gestational sac can be seen by the vaginal ultrasound 4 weeks after the last menstruation. After 5-6 weeks of gestation, 100% of normal pregnancies can show yolk sac and simultaneously embryo and heart pulsation can be detected through vaginal ultrasonic examination.

For early-middle pregnancy stages greater than 8 weeks, critical anatomical structures of the fetus, such as the cranium, trunk, femur, spine, etc., may be detected. The abdomen probe can observe the fetal outline around 9 weeks of pregnancy, and the placenta embryonic form is already obvious; after 12 weeks of gestation, the fetus gradually develops completely, the craniocerebral aureola is clear, and key anatomical structures such as the spine, the limbs and the like are all appeared and can be used as the basis for identifying the fetus.

The identification of the key anatomical region may be performed in a fully automatic manner or in a semi-automatic manner. Key anatomical structures may be detected, as well as the entire fetus. There are many ways to automatically detect key anatomical structures. The method of machine learning or deep learning can be adopted to detect key anatomical structures in the three-dimensional volume data. For example, embryo in early pregnancy can collect a certain number of early pregnancy embryo images (called positive samples) and a certain number of non-embryo images (called negative samples) in advance, then based on a machine learning or deep learning algorithm, an artificial neural network is designed, features capable of distinguishing the positive samples from the negative samples are automatically learned by using a multi-layer network structure, all possible regions in three-dimensional volume data are traversed by using the features during detection, the probability that the region is judged as the positive sample is calculated, and the region with the maximum probability is selected as a target region. The traditional machine learning algorithm needs to extract features (such as gray scale, texture, spatial information and the like) in advance based on a certain feature extraction method, and the method is commonly referred to as Adaboost algorithm, Support Vector Machine (SVM), Random Forest (Random Forest) and the like; the deep learning algorithm can be used for directly carrying out feature extraction and network training on the basis of multi-frame two-dimensional video or three-dimensional volume data to carry out effective anatomical structure detection, and common methods of the method include a convolutional neural network algorithm (CNN), a recurrent neural network algorithm (RNN), FastCNN, YOLO, SSD and the like.

Besides the pattern recognition method, the key anatomical structures in the three-dimensional volume data can be accurately segmented by an image segmentation method.

Segmentation is to classify which category each pixel point in an image belongs to, and can directly obtain the outline and position of a key anatomical structure in the image. Common segmentation methods include level set (LevelSet), Graph Cut (Graph Cut), Snake, Random walk (Random walk), watershed algorithm, threshold segmentation and other methods; in addition to traditional methods, methods of deep learning also enable segmentation of critical anatomical structures, such as FCN, UNet, SegNet, Deeplab, etc.

The method can also be used for detecting some key anatomical structures in the three-dimensional data by adopting a template matching method, for example, the embryo structures in the early pregnancy period are relatively fixed, some early pregnancy embryo data can be collected in advance to establish a template, all possible regions in the three-dimensional data are traversed during detection, similarity matching is carried out on the regions and the template, and the region with the highest similarity is selected as a target region.

By one or more of the above methods, the location of a particular anatomical structure in the three-dimensional volume data may be identified. If the full-automatic method cannot accurately identify, the user can also perform operations such as supplementing, deleting and modifying on the detection structure through a certain workflow by means of tools such as a keyboard and a mouse, so as to realize semi-automatic anatomical structure detection, for example, by means of a mouse.

The core of the embodiment is to determine the number of fetuses through the number of key anatomical structures, and the purpose of detecting the anatomical structures can be achieved by using other methods without changing the substantive process.

Step 3, determining the number of fetuses according to the number of key anatomical structures;

after the key structures in the three-dimensional volume data are identified, the number of fetuses can be counted according to the key structures. Statistics of the number of fetuses at the early pregnancy stage can be determined by the number of identified gestational sacs and embryos; the number of fetuses can be determined during the early pregnancy stage based on the number of identified critical anatomical structures such as the cranium, trunk, femur, spine, etc.

The system identifies an anatomical structure to determine the number of fetuses, for example, 1 fetal cranium is detected in the three-dimensional volume data, which indicates that there are only 1 fetus in the three-dimensional volume data. However, any detection algorithm has a certain false detection rate, and in order to improve the identification accuracy, in the embodiment of the present invention, a plurality of key anatomical structures can be identified at the same time, and then the final fetal number counting stage is determined by using a voting strategy of the number of the plurality of key anatomical structures, for example, the system detects 5 anatomical structures in total, 2 fetuses in three-dimensional volume data can be inferred by 4 anatomical structures, only 1 probe in the volume data can be inferred by another structure, and 2 fetuses in the three-dimensional volume data can be inferred finally according to the voting principle.

And finally displaying the statistical number of the fetus on an image interface. Meanwhile, the reliability of the structure can be output, errors exist in structure identification possibly for some volume data with poor images, and a low reliability value can be used for reminding a doctor to pay attention to recheck.

The key points of the embodiment are as follows: a method for determining the number of fetuses in the uterus by identifying key anatomical structures or entire embryo structures in the three-dimensional volume data of the uterus. A volume data acquisition step for acquiring three-dimensional volume data; an anatomical structure identification step of identifying an anatomical structure in the volume data; and determining the number of the fetuses, wherein the number of the fetuses is determined and is displayed on an image interface.

Fig. 6 is a schematic structural diagram of an ultrasound imaging apparatus according to an embodiment of the present invention, and according to another aspect of the embodiment of the present invention, there is also provided an ultrasound imaging apparatus including: the probe 602, the transmit circuitry 604, the receive circuitry 606, the processor 608, and the display 610, which are described in more detail below.

A probe 602; a transmitting circuit 604 connected to the probe 602, the transmitting circuit exciting the probe to transmit ultrasonic waves to the uterus; a receiving circuit 606 connected to the probe 602, the receiving circuit receiving the ultrasound echo returned from the uterus via the probe to obtain an ultrasound echo signal; a processor 608 connected to the receiving circuit 606, for processing the ultrasonic echo signal to obtain three-dimensional data of the uterus; a display 610 connected to the processor 608, the display displaying the three-dimensional volume data; wherein, the processor 608 further executes the following steps: identifying key anatomical structures from the three-dimensional volumetric data; and determining the number of fetuses in the uterus based on the critical anatomical structures.

In one embodiment, the display 610 is further configured to display at least one of: key anatomical structures, number of fetuses in uterus, and pregnancy period in which the uterus is located.

According to another aspect of the embodiments of the present invention, there is also provided a storage medium including a stored program, wherein when the program is executed, an apparatus in which the storage medium is located is controlled to execute the ultrasound imaging method according to any one of the above.

According to another aspect of the embodiments of the present invention, there is also provided a processor for executing a program, wherein the program is executed to perform the ultrasound imaging method of any one of the above.

According to another aspect of the embodiments of the present invention, there is also provided a computer device, including: a memory and a processor, the memory storing a computer program; a processor for executing a computer program stored in the memory, the computer program when running executing the ultrasound imaging method of any of the above.

The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.

In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.

The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.

Claims

An ultrasound imaging method, comprising:

transmitting ultrasonic waves to the uterus in a mode of covering the whole uterus area, and receiving ultrasonic echoes to obtain ultrasonic echo signals;

obtaining three-dimensional volume data of the uterus according to the ultrasonic echo signals;

determining the pregnancy period in which the uterus is;

identifying key anatomical structures of a fetus corresponding to the pregnancy from the three-dimensional volumetric data;

determining the number of fetuses in the uterus based on the critical anatomical structures.
The method of claim 1, wherein the pregnancy period comprises: an early pregnancy period with a week of pregnancy less than a predetermined number of weeks, or an early-intermediate pregnancy period with a week of pregnancy greater than a predetermined number of weeks.
The method of claim 2, wherein the critical anatomical structures corresponding to the early pregnancy period comprise at least one of: gestational sac, yolk sac and embryo; the critical anatomical structures corresponding to the early pregnancy include at least one of: cranium, trunk, femur, spine, and limbs.
The method of claim 1, wherein identifying key anatomical structures of a fetus corresponding to the pregnancy from the three-dimensional volumetric data comprises:

obtaining features that enable discrimination between critical anatomical structures;

identifying at least one region from the three-dimensional volume data according to the feature;

determining a target region from the at least one region, wherein the target region is determined to have the highest probability of being the key anatomical structure;

determining the target region as the critical anatomical structure.
The method of claim 4, wherein the characteristics comprise at least one of: two-dimensional features and three-dimensional features.
The method of claim 5, wherein obtaining features that can distinguish whether a critical anatomical structure is present comprises:

collecting positive samples determined to be the critical anatomical structure and negative samples determined not to be the critical anatomical structure;

training the positive and negative examples based on machine learning to obtain features that can distinguish whether a critical anatomical structure is present.
The method of claim 1, wherein identifying key anatomical structures of a fetus corresponding to the pregnancy from the three-dimensional volumetric data comprises:

classifying pixel points in the image of the three-dimensional volume data to obtain a classification result;

and identifying key anatomical structures according to the classification result.
The method of claim 1, wherein identifying key anatomical structures of a fetus corresponding to the pregnancy from the three-dimensional volumetric data comprises:

determining a structure template, wherein the structure template comprises a plurality of real key anatomical structures;

identifying a target region from the three-dimensional volume data according to the structure template, wherein the target region is a region with the highest matching degree with a key anatomical structure in the structure template;

determining the target region as the critical anatomical structure.
The method of any one of claims 1 to 8, wherein identifying key anatomical structures of a fetus corresponding to the pregnancy from the three-dimensional volumetric data comprises:

identifying a pending critical anatomical structure from the three-dimensional volumetric data;

and adjusting the undetermined key anatomical structure in a mode of receiving input operation to obtain the key anatomical structure.
The method of any one of claims 1 to 8, wherein determining the number of fetuses within the uterus based on the critical anatomical structures comprises:

acquiring the number of fetuses in the uterus, which is determined according to a plurality of key anatomical structures respectively, under the condition that the number of the key anatomical structures is multiple;

determining the number of fetuses in the uterus that is the highest in consistency.
An ultrasound imaging method, comprising:

displaying three-dimensional volume data of the uterus, wherein the three-dimensional volume data is obtained after scanning the uterus in a mode of covering the whole uterus area through ultrasound;

displaying a pregnancy in which the uterus is located, and displaying key anatomical structures of a fetus corresponding to the pregnancy;

displaying the number of fetuses in the uterus determined from the key anatomical structures.
The method of claim 11, wherein displaying key anatomical structures of the fetus corresponding to the pregnancy comprises:

displaying features that can distinguish whether a critical anatomical structure is present;

displaying at least one region identified from the three-dimensional volume data according to the feature;

highlighting a target region, wherein the target region is determined to have the highest probability of being the critical anatomical structure.
The method of claim 11, wherein displaying key anatomical structures of the fetus corresponding to the pregnancy comprises:

and displaying a pixel contour obtained after classifying the pixel points in the image of the three-dimensional volume data, wherein the pixel contour is used for distinguishing a key anatomical structure from a non-key anatomical structure.
The method of claim 11, wherein displaying key anatomical structures of the fetus corresponding to the pregnancy comprises:

displaying key anatomical structures in a structure template, wherein the structure template comprises a plurality of real key anatomical structures;

and displaying a target region identified from the three-dimensional volume data according to the structure template, wherein the target region is a region with the highest matching degree with a key anatomical structure in the structure template.
The method of any one of claims 11 to 14, wherein displaying key anatomical structures of the fetus corresponding to the pregnancy comprises:

displaying pending critical anatomical structures identified from the three-dimensional volumetric data;

displaying the input operation;

and displaying the key anatomical structure obtained after the undetermined key anatomical structure is adjusted according to the operation.
An ultrasound imaging method, comprising:

acquiring three-dimensional volume data of a uterus, wherein the three-dimensional volume data is obtained by scanning the uterus through ultrasound;

identifying key anatomical structures from the three-dimensional volumetric data;

determining the number of fetuses in the uterus based on the critical anatomical structures.
An ultrasound imaging apparatus, comprising:

a probe;

a transmitting circuit, wherein the transmitting circuit stimulates the probe to transmit ultrasonic waves to the uterus;

a receiving circuit that receives an ultrasound echo returned from the uterus by the probe to obtain an ultrasound echo signal;

a processor that processes the ultrasound echo signals to obtain three-dimensional volumetric data of the uterus;

a display that displays the three-dimensional volume data;

wherein the processor further performs the steps of: identifying key anatomical structures from the three-dimensional volumetric data; and determining the number of fetuses in the uterus based on the critical anatomical structures.
The apparatus of claim 17,

the display is further used for displaying at least one of the following: the critical anatomy, the number of fetuses in the uterus, the pregnancy period in which the uterus is located.
A storage medium comprising a stored program, wherein the program, when executed, controls an apparatus in which the storage medium is located to perform the ultrasound imaging method of any of claims 1 to 17.
A processor for running a program, wherein the program is run to perform the ultrasound imaging method of any of claims 1 to 16.
A computer device, comprising: a memory and a processor, wherein the processor is capable of,

the memory stores a computer program;

the processor for executing a computer program stored in the memory, the computer program when running performing the ultrasound imaging method of any of claims 1 to 16.