Tire direction identification method, electronic equipment and storage medium

Abstract

The invention discloses a tire orientation identification method. The method comprises the following steps: in response to a scanning instruction, acquiring scanning information corresponding to the scanning instruction from an ultrasonic probe; corresponding ultrasonic data collected by the ultrasonic probe through scanning according to the scanning information are obtained, feature classification is carried out on the corresponding ultrasonic data so as to identify corresponding target features, and feature classification is a classification model obtained through training based on corresponding ultrasonic images; and based on the corresponding target features, determining a corresponding tire orientation. The invention further discloses electronic equipment and a storage medium. The corresponding target features are obtained in response to the scanning instruction, the corresponding fetal orientation is determined, the difficulty and technical threshold of ultrasonic diagnosis of the fetal orientation are reduced, and the diagnosis efficiency and objectivity are improved.

Description

Technical Field

[0001] The disclosed embodiments of the present application relate to the technical field of fetal position diagnosis, and more specifically, to a method for identifying fetal position, an electronic device, and a storage medium. Background Art

[0002] The currently commonly used ultrasound fetal position diagnosis technology is not automatic. It requires clinicians to map the abdomen, find specific features such as the spine and eye sockets, and rely on the doctor's clinical experience to analyze the ultrasound image to ultimately determine the fetal position. However, such an ultrasound fetal position diagnosis process is very dependent on the clinician's clinical experience and ultrasound reading ability, so it places high demands on clinicians. Ultrasound fetal position diagnosis is difficult and has a high technical threshold, which reduces the efficiency of fetal position diagnosis. Summary of the invention

[0003] According to the embodiments of the present application, the present application proposes a method for identifying fetal position, an electronic device and a storage medium to improve the efficiency and objectivity of fetal position diagnosis.

[0004] The first aspect of the present application discloses a method for identifying fetal position, comprising: in response to a scanning instruction, obtaining scanning information corresponding to the scanning instruction from an ultrasound probe; obtaining corresponding ultrasound data collected by the ultrasound probe according to the scanning information, and performing feature classification on the corresponding ultrasound data to identify corresponding target features, wherein the feature classification is a classification model obtained by training based on corresponding ultrasound images; and determining the corresponding fetal position based on the corresponding target features.

[0005] The second aspect of the present application discloses an ultrasound system, including an ultrasound probe, a memory and a processor, wherein the ultrasound probe is used to acquire ultrasound data, and the processor is coupled to the memory and is used to execute program instructions stored in the memory to implement the method for identifying the fetal position described in the first aspect.

[0006] The third aspect of the present application discloses a non-volatile computer-readable storage medium having program instructions stored thereon, and when the program instructions are executed by a processor, the method for identifying the fetal position described in the first aspect is implemented.

[0007] The beneficial effects of the present application include: in response to a scanning instruction, obtaining scanning information corresponding to the scanning instruction from the ultrasound probe, obtaining corresponding ultrasound data collected by the ultrasound probe according to the scanning information, and performing feature classification on the corresponding ultrasound data to identify corresponding target features, wherein the feature classification is based on a classification model obtained by training corresponding ultrasound images, and then the corresponding target features, to determine the corresponding fetal position, thereby reducing the difficulty and technical threshold of ultrasonic diagnosis of fetal position and improving the efficiency and objectivity of diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The present application will be further described below in conjunction with the accompanying drawings and implementation methods, in which:

[0009] Figure 1 is a schematic diagram of the fetal position of an embodiment of the present application;

[0010] Figure 2 is a schematic diagram of an electronic device system interface according to an embodiment of the present application;

[0011] Figure 3 is a schematic diagram of an electronic device system interface according to another embodiment of the present application;

[0012] Figure 4 is a flow chart of a method for identifying a fetal position according to an embodiment of the present application;

[0013] Figure 5 is a schematic diagram of longitudinal ultrasound scanning of the abdomen in an embodiment of the present application;

[0014] Figure 6 is a schematic structural diagram of an ultrasound system according to an embodiment of the present application;

[0015] Figure 7 It is a schematic diagram of the structure of the non-volatile computer-readable storage medium of an embodiment of the present application. DETAILED DESCRIPTION

[0016] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0017] The term "and / or" in this application is only a description of the association relationship of associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the objects associated before and after are in an "or" relationship. In addition, "many" in this article means two or more than two. In addition, the term "at least one" in this article means any combination of at least two of any one or more of a plurality of, for example, including at least one of A, B, and C, and can mean including any one or more elements selected from the set consisting of A, B, and C. In addition, the terms "first", "second", and "third" in this application are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features.

[0018] Monitoring of fetal position during the delivery phase is of great significance for the diagnosis and intervention of obstetricians. According to the "ISUOG Practice Guidelines: intrapartum ultrasound" published by the International Society of Gynecology and Obstetrics ISOUG in 2018: Generally, the determination of fetal position during the delivery phase is mainly based on transabdominal ultrasound in the "sagittal (i.e. longitudinal)" and "axial (i.e. transverse)" imaging for evaluation. The fetal position can be described as a circle like a clock, such as Figure 1 As shown, Figure 1 It is a schematic diagram of the fetal position of an embodiment of the present application, wherein ≥2.30h and ≤3.30h are left occipital transverse position (LOT), ≥8.30h and ≤9.30h are right occipital transverse position (ROT), >3.30h and <8.30h are occipital posterior position (OP), and >9.30h and <2.30h are occipital anterior position (OA). Generally, when the probe is placed on the "sagittal position of the abdomen" of the parturient, and then the ultrasound probe is moved downward and rotated to the "axial position of the abdomen", when the two eye sockets of the fetus are displayed in the ultrasound imaging, it indicates a posterior occipital position, and if the midline of the brain appears in the ultrasound image, it indicates a transverse occipital position. Therefore, the fetal position can be comprehensively judged based on the features in the ultrasound image and the position and posture of the probe scan. In practice, the state of the fetus may be more complicated than the above theoretical description, so more features and scanning positions need to be considered.

[0019] In order to enable those skilled in the art to better understand the technical solution of the present application, the technical solution of the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0020] To facilitate understanding of the present application, the electronic device of the following embodiments of the present application is first described in detail.

[0021] In some embodiments, the electronic device includes a memory and a processor coupled to each other, the processor is used to execute program instructions stored in the memory, and at least one instruction control is set through a system interface, wherein the at least one instruction control is used to receive at least one scanning instruction, and the electronic device can be an ultrasonic inspector, etc. Figure 2 As shown, Figure 22 is a schematic diagram of an electronic device system interface of an embodiment of the present application. The electronic device is provided with at least one command control, such as a control 210, through a system interface 200. The at least one command control is used to receive at least one scanning command. The control 210 may be displayed on the interface 200 in the form of an icon, or may be located at a certain position of the electronic device in the form of a button. The specific form is not limited in the present application. For example, the control 210 may be a button or a soft key. The soft key is provided on the screen or on the touch screen or on the ultrasound probe. The soft key is touched or clicked a preset number of times to receive different scanning commands. Instructions, for example, after one touch, multiple options pop up in the system interface, such as "transverse position data (up -> down)", "longitudinal position data (middle -> left)", "longitudinal position data (middle -> right)", etc., at this time, you can touch or click the button again to select the option, that is, button multiplexing; or, the control 210 can be a plurality of buttons or soft keys, which are arranged on the screen or on the touch screen or on the ultrasound probe, and some prompt texts can be marked on the control, such as "transverse position data (up -> down)", "longitudinal position data (middle -> left)", "longitudinal position data (middle -> right)", etc.

[0022] Furthermore, in some embodiments, the electronic device is provided with at least one prompt control through the system interface 200, such as Figure 3 As shown, Figure 3 3 is a schematic diagram of the system interface of an electronic device of another embodiment of the present application. The electronic device is provided with at least one instruction control, such as control 311, control 312 and control 313, on the system interface 300, and at least one prompt control, such as control 321, control 322 and control 323, is provided on the system interface 300. In response to at least one instruction control being triggered, at least one prompt control is displayed on the system interface, and at least one prompt control is used to prompt when the ultrasound probe scans the corresponding ultrasound data collected according to at least one scanning information. In response to at least one instruction control being triggered, at least one prompt control is displayed on the system interface, for example, after control 311 is triggered, control 321 is displayed in the system, and control 321 is used to prompt when the ultrasound probe scans the corresponding ultrasound data collected according to at least one scanning information, for example, after pressing control 311, control 321 lights up to prompt the operator to move the ultrasound probe in a direction to collect the corresponding ultrasound data.

[0023] See also Figure 4 , Figure 4 The method can be executed by an electronic device with computing functions, such as a microcomputer, a server, and a mobile device such as a laptop computer or a tablet computer.

[0024] It should be noted that if there are substantially the same results, the method of the present application is not limited to Figure 2 The process sequence shown is limited.

[0025] In some possible implementations, the method may be implemented by a processor calling computer-readable instructions stored in a memory, such as Figure 1 As shown, the method may include the following steps:

[0026] S41: In response to the scanning instruction, scanning information corresponding to the scanning information instruction is obtained from the ultrasound probe.

[0027] In response to a scanning instruction, for example, in response to at least one instruction control being triggered, wherein the scanning instruction includes a transverse position data acquisition instruction from top to bottom, a longitudinal position data acquisition instruction from center to left, and a longitudinal position data acquisition instruction from center to right. The scanning information in response to the scanning information instruction is obtained from the ultrasound probe, with the abdomen of the pregnant woman as the scanning object, for example, the instruction control of the scanning instruction A is pressed, at this time, at least one scanning information of the ultrasound probe is obtained, including the position of the pregnant woman's body where the probe is located, the scanning direction, and the section type of the probe scanning surface, wherein the position of the probe can be all positions within the range of the pregnant woman's abdomen, etc., the scanning direction can be from top to bottom, left to right, right to left, etc., and the section type can be a transverse section or a longitudinal section.

[0028] S42: Obtain corresponding ultrasound data collected by the ultrasound probe according to the scanning information, and perform feature classification on the corresponding ultrasound data to identify corresponding target features, wherein the feature classification is a classification model obtained by training based on the corresponding ultrasound image.

[0029] The ultrasound probe scans the abdomen of the pregnant woman according to the scanning information, and the corresponding ultrasound data collected may be at least one frame of the abdominal ultrasound image. The corresponding ultrasound data is feature classified, for example, the feature classification algorithm is used to perform feature recognition on the corresponding ultrasound data to identify the target feature, that is, while scanning, the feature classification algorithm is used to perform feature recognition on the ultrasound image to obtain the target feature, wherein the target feature includes spinal features, eye frame features, and brain midline features.

[0030] Feature classification is a classification model obtained by training based on corresponding ultrasound images, for example, a classification model for feature classification algorithm is obtained, wherein the feature classification algorithm can adopt an image classification algorithm based on deep learning. A large number of ultrasound images of the production stage are collected using ultrasound equipment, mainly from the abdomen. The collection method can be to respond to at least one scanning instruction, obtain at least one scanning information of the ultrasound probe, and the ultrasound probe scans the corresponding ultrasound data collected according to at least one scanning information. The main collected data include cross-sectional images of the spine, eye frames, and brain midline features. Specifically, the collected data is used to make a data set, and the configuration ratio of each type of data in the data set is as follows: spine: eye frames: brain midline: other = 1:1:1:1, and each type of image data needs to be sufficient. Based on the collected images, a data set is made, and a classification network is trained. The classification network model includes but is not limited to Alexnet, VGG, mobilenet, etc., to obtain a trained classification network model. Among them, the fetal position feature classification algorithm includes but is not limited to the above-mentioned artificial intelligence algorithm, and can also be other algorithms based on image processing.

[0031] The number of feature categories to be identified includes but is not limited to the above three features, and this application does not make specific restrictions on this. The more feature categories there are, the faster the recognition efficiency is, the more section categories there are, and the more detailed the fetal position description is.

[0032] S43: Determine the corresponding fetal position based on the corresponding target features.

[0033] Based on the corresponding target features, that is, based on the pregnant woman's body position where the probe is located, the scanning direction, the section type of the probe scanning surface, and the target features identified by the feature classification algorithm, the corresponding fetal position is determined, where the fetal position includes but is not limited to occiput posterior position, occiput anterior position, occiput left transverse position, and occiput right transverse position.

[0034] In this embodiment, in response to a scanning instruction, scanning information corresponding to the scanning instruction is acquired from the ultrasound probe, corresponding ultrasound data collected by the ultrasound probe according to the scanning information is acquired, and feature classification is performed on the corresponding ultrasound data to identify corresponding target features, wherein the feature classification can be based on a classification model trained on corresponding ultrasound images, and then the corresponding fetal position can be determined through the corresponding target features, thereby reducing the difficulty and technical threshold of ultrasonic diagnosis of fetal position and improving the efficiency and objectivity of diagnosis.

[0035] In some embodiments, the scanning instruction is one of a first scanning instruction, a second scanning instruction, and a third scanning instruction, wherein the first scanning instruction, the second scanning instruction, and the third scanning instruction are different and correspond to different scanning information, the first scanning instruction corresponds to the first scanning information, the second scanning instruction corresponds to the second scanning information, and the third scanning instruction corresponds to the third scanning information; the corresponding ultrasonic data collected by scanning according to the first scanning information is the first ultrasonic data, the corresponding ultrasonic data collected by scanning according to the second scanning information is the second ultrasonic data, and the corresponding ultrasonic data collected by scanning according to the third scanning information is the third ultrasonic data.

[0036] The scanning instructions include a transverse position data acquisition instruction from top to bottom, a longitudinal position data acquisition instruction from center to left, and a longitudinal position data acquisition instruction from center to right, wherein the first scanning instruction may be any one of the transverse position data acquisition instruction from top to bottom, the longitudinal position data acquisition instruction from center to left, and the longitudinal position data acquisition instruction from center to right, the second scanning instruction may be any one of the other two of the transverse position data acquisition instruction from top to bottom, the longitudinal position data acquisition instruction from center to left, and the longitudinal position data acquisition instruction from center to right, and the third scanning instruction may be the other of the other two. The first scanning instruction, the second scanning instruction, and the third scanning instruction are different and correspond to different scanning information, the first scanning instruction corresponds to the first scanning information, the second scanning instruction corresponds to the second scanning information, and the third scanning instruction corresponds to the third scanning information.

[0037] At this time, the corresponding ultrasonic data collected by scanning according to the first scanning information is the first ultrasonic data, that is, in response to the first scanning instruction, the first scanning information of the ultrasonic probe can be obtained, and then the corresponding ultrasonic data collected by the ultrasonic probe according to the first scanning information is obtained. The corresponding ultrasonic data collected by scanning according to the second scanning information is the second ultrasonic data, that is, in response to the second scanning instruction, the second scanning information of the ultrasonic probe can be obtained, and then the corresponding ultrasonic data collected by the ultrasonic probe according to the second scanning information is obtained. The corresponding ultrasonic data collected by scanning according to the third scanning information is the third ultrasonic data, that is, in response to the third scanning instruction, the third scanning information of the ultrasonic probe can be obtained, and then the corresponding ultrasonic data collected by the ultrasonic probe according to the third scanning information is obtained.

[0038] In some embodiments, the scanning instruction is a first scanning instruction, and the corresponding target feature is the first target feature; in response to not identifying the first target feature from the first ultrasound data, receiving a second scanning instruction and obtaining second scanning information in response to the second scanning instruction; obtaining second ultrasound data, and performing feature classification on the second ultrasound data to identify the corresponding second target feature; and determining the corresponding fetal position based on the second target feature.

[0039] When the scanning instruction is the first scanning instruction, the target feature corresponding to the first scanning instruction is the first target feature. For example, if the first scanning instruction is a transverse position data top-to-bottom acquisition instruction, the target feature corresponding to the transverse position data top-to-bottom acquisition instruction is the first target feature. In response to the first scanning instruction, the first scanning information of the ultrasound probe can be obtained, and then the corresponding ultrasound data collected by the ultrasound probe according to the first scanning information is obtained. In response to the failure to identify the first target feature from the first ultrasound data, a second scanning instruction is received and responded to, for example, the second scanning instruction can be a longitudinal position data center-to-left acquisition instruction, and then the second ultrasound data corresponding to the second scanning information is obtained, and the second ultrasound data is feature classified to identify the corresponding second target feature, and the corresponding fetal position is determined based on the second target feature.

[0040] Further, in some embodiments, in response to not identifying the second target feature from the second ultrasound data, a third scanning instruction is received and responded to, for example, the third scanning instruction may be a center-to-right acquisition instruction for longitudinal cutting data, to obtain third scanning information; the third ultrasound data is obtained, and feature classification is performed on the third ultrasound data to identify a corresponding third target feature; and the corresponding fetal position is determined based on the third target feature.

[0041] It can be understood that the scanning instruction includes a first scanning instruction, wherein the first scanning instruction can be any one of a transverse position data acquisition instruction from top to bottom, a longitudinal position data acquisition instruction from center to left, and a longitudinal position data acquisition instruction from center to right, and the scanning information includes the first scanning information, that is, the ultrasonic data acquired by the probe under the first instruction.

[0042] Taking the system interface 300 of the above-mentioned electronic device as an example for explanation, in response to the first scanning instruction, for example, in response to any one of the control 311 being triggered, the control 312 being triggered, and the control 313 being triggered, the first scanning information of the ultrasound probe is obtained. For example, the first instruction is a transverse position data acquisition instruction from top to bottom, that is, in response to the control 311 being triggered, the first scanning information of the ultrasound probe is obtained. At this time, the first scanning information includes the position of the pregnant woman's body where the probe is located, the scanning direction, and the type of section of the probe scanning surface. For example, the ultrasound probe moves uniformly from top to bottom in the transverse position of the abdomen to perform continuous ultrasound scanning data. Specifically, after the operator manually clicks the "Transverse Position Data (Top to Bottom)" button, that is, the control 311, the probe is placed in the transverse position, as shown in the figure. Figure 3 Follow the direction of the prompt light as shown and manually scan the abdomen from top to bottom at a constant speed in real time.

[0043] Acquire first ultrasound data collected by the ultrasound probe according to the first scanning information, and use a feature classification algorithm to perform feature recognition on the first ultrasound data, that is, transmit each frame of data in the scanning process to a trained section classification algorithm for feature section classification, and in response to recognizing a first target feature from the first ultrasound data, use the first target feature as a target feature. For example, when the probe scan reaches the lower edge of the abdomen or the classification algorithm recognizes the first target feature, stop scanning, and then determine the corresponding fetal position based on the first target feature.

[0044] Further, the scanning instruction includes a second scanning instruction, wherein the first scanning instruction can be any one of a transverse position data acquisition instruction from top to bottom, a longitudinal position data acquisition instruction from center to left, and a longitudinal position data acquisition instruction from center to right, and the second scanning instruction can be any one of the other two of a transverse position data acquisition instruction from top to bottom, a longitudinal position data acquisition instruction from center to left, and a longitudinal position data acquisition instruction from center to right, and the scanning information includes the second scanning information, that is, the ultrasonic data acquired by the probe under the second instruction, and the second scanning information is different from the first scanning information.

[0045] Taking the system interface 300 of the above-mentioned electronic device as an example for explanation, in response to the failure to identify the first target feature from the first ultrasound data, a second scanning instruction is received and responded to the second scanning instruction. For example, in response to the failure to identify the first target feature from the first ultrasound data, in response to the other two of control 311 being triggered, control 312 being triggered, and control 313 being triggered, the second scanning information of the ultrasound probe is obtained. For example, the second instruction is a longitudinal section data center to left acquisition instruction, that is, in response to control 312 being triggered, the second scanning information of the ultrasound probe is obtained. At this time, the second scanning information includes the position of the pregnant woman's body where the probe is located, the scanning direction, and the type of section of the probe scanning surface. For example, the probe moves evenly from the "median longitudinal section" in the abdomen to the left side of the pregnant woman to perform continuous ultrasound scanning data. Specifically, after the operator manually clicks the "Longitudinal Section Data (center to left)" button, that is, control 312, the probe is placed in the "median longitudinal section" of the abdomen, and the following steps are performed. Figure 3 Following the direction indicated by the indicator light, manually scan the abdomen from the "median longitudinal section" at a constant speed toward the left side of the pregnant woman.

[0046] Acquire second ultrasound data collected by the ultrasound probe according to the second scanning information, and use a feature classification algorithm to perform feature recognition on the second ultrasound data, that is, transmit each frame of data in the scanning process to a trained section classification algorithm for feature section classification, and in response to recognizing a second target feature from the second ultrasound data, use the second target feature as a target feature. For example, when the probe scan reaches the horizontal position on the left side of the mother's abdomen or the classification algorithm recognizes the second target feature, stop scanning, and then determine the corresponding fetal position based on the second target feature.

[0047] Further, the scanning instruction includes a third scanning instruction, wherein the first scanning instruction can be any one of a transverse position data acquisition instruction from top to bottom, a longitudinal position data acquisition instruction from center to left, and a longitudinal position data acquisition instruction from center to right, and the second scanning instruction can be any one of the other two of a transverse position data acquisition instruction from top to bottom, a longitudinal position data acquisition instruction from center to left, and a longitudinal position data acquisition instruction from center to right, and the third scanning instruction can be the other of the other two, and at least one scanning information includes the third scanning information, that is, the ultrasonic data collected by the probe under the third instruction, and the second scanning information is different from the first scanning information and the second scanning information.

[0048] Continuing to use the system interface 300 of the above-mentioned electronic device as an example for explanation, in response to the failure to identify the second target feature from the second ultrasonic data, a third scanning instruction is received and responded to the third scanning instruction. For example, in response to the failure to identify the second target feature from the second ultrasonic data, in response to the other of the two of control 311 being triggered, control 312 being triggered, and control 313 being triggered, the third scanning information of the ultrasonic probe is obtained. For example, the third instruction is a longitudinal section data center to right acquisition instruction, that is, in response to control 313 being triggered, the third scanning information of the ultrasonic probe is obtained. At this time, the third scanning information includes the position of the pregnant woman's body where the probe is located, the scanning direction, and the type of section of the probe scanning surface. For example, the probe moves uniformly from the "median longitudinal section" in the abdomen to the right side of the pregnant woman to perform continuous ultrasonic scanning data. Specifically, after the operator manually clicks the "Longitudinal Section Data (center to right)" button, that is, control 313, the probe is placed in the "median longitudinal section" of the abdomen, as shown in the following figure. Figure 3 Following the direction indicated by the indicator light, manually scan the abdomen from the "median longitudinal section" at a constant speed toward the right side of the pregnant woman.

[0049] Acquire third ultrasound data collected by the ultrasound probe according to the third scanning information, and use a feature classification algorithm to perform feature recognition on the third ultrasound data, that is, transmit each frame of data in the scanning process to a trained section classification algorithm for feature section classification; in response to recognizing a third target feature from the third ultrasound data, use the third target feature as a target feature. For example, when the probe scan reaches the horizontal position on the right side of the maternal abdomen or the classification algorithm recognizes the second target feature, stop scanning and determine the corresponding fetal position based on the third target feature.

[0050] In some embodiments, the scanning information includes a scanning direction; scanning is performed according to the scanning information to collect corresponding ultrasound data, including: in response to the scanning direction being from top to bottom, collecting transverse ultrasound data; in response to the scanning direction being from middle to left, collecting first longitudinal ultrasound data; in response to the scanning direction being from middle to right, collecting second longitudinal ultrasound data.

[0051] In response to the scanning instruction, scanning information corresponding to the scanning instruction is obtained from the ultrasound probe, and the scanning information includes the scanning direction, that is, the scanning direction of the ultrasound probe. In response to the scanning direction being from top to bottom, transverse ultrasound data is collected, for example, after the operator manually clicks the "Transverse Data (Top to Bottom)" button, the probe is placed in the transverse position, and the abdomen is evenly moved downward from the top to perform continuous ultrasound scanning data in the transverse position according to the direction indicated by the prompt light; in response to the scanning direction being from center to left, the first longitudinal ultrasound data is collected, for example, after the operator manually clicks the "Longitudinal Data (Central to Left)" button, the probe is placed in the "median longitudinal position" of the abdomen, and the abdomen is evenly moved from the "median longitudinal position" to the left side of the pregnant woman to perform continuous ultrasound scanning data; in response to the scanning direction being from center to right, the second longitudinal ultrasound data is collected, for example, after the operator manually clicks the "Longitudinal Data (Central to Right)" button, the probe is placed in the "median longitudinal position" of the abdomen, and the abdomen is evenly moved to the right side of the pregnant woman from the "median longitudinal position" to perform continuous ultrasound scanning data, such as Figure 5 As shown, Figure 5 It is a schematic diagram of longitudinal abdominal ultrasound scanning in an embodiment of the present application.

[0052] In some embodiments, the target feature includes at least one of a double eye frame feature, a brain midline feature, and a spinal feature, wherein the double eye frame feature and the brain midline feature are respectively identified from the transverse ultrasound data, and the spinal feature is identified from the first longitudinal ultrasound data or the second longitudinal ultrasound data; based on the corresponding target feature, the corresponding fetal position is determined, including: when the scanning direction is from top to bottom, if the target feature is the double eye frame feature, the corresponding fetal position is determined to be occipital posterior position; if the target feature is the brain midline feature, the corresponding fetal position is determined to be occipital transverse position; when the scanning direction is from center to left, if the target feature is the spinal feature, the corresponding fetal position is determined to be one of occipital left transverse position and occipital anterior position; when the scanning direction is from center to right, if the target feature is the spinal feature, the corresponding fetal position is determined to be one of occipital left transverse position and occipital anterior position.

[0053] Continuing to use the system interface 300 of the above electronic device as an example, for example, the first instruction is a transverse position data top-to-bottom acquisition instruction, that is, after the operator manually clicks the "transverse position data (top-to-bottom)" button, that is, the control 311, the probe is placed in the transverse position, and the following steps are performed: Figure 3 Following the direction of the prompt light shown, the abdomen is manually scanned downward at a constant speed in real time to collect transverse ultrasound data. At the same time, the feature classification algorithm is used to perform feature recognition on the transverse ultrasound data. If the double eye frame feature is recognized as the target feature, the corresponding fetal position is determined to be occipital posterior position; if the brain midline feature is recognized as the target feature, the corresponding fetal position is determined to be occipital transverse position.

[0054] In response to the fact that the eye frame feature and the brain midline feature are not identified from the transverse ultrasound data, the ultrasound probe is obtained to scan according to the second scanning information. For example, the second instruction is the longitudinal data center to left acquisition instruction, that is, the operator manually clicks the "longitudinal data (center to left)" button, that is, the control 312, and places the probe in the "median longitudinal position" of the abdomen. Figure 3 Following the direction of the prompt light shown, manually move from the "median longitudinal position" to the left side of the pregnant woman at a constant speed to scan the abdomen to collect the first longitudinal position ultrasound data, and use the feature classification algorithm to perform feature recognition on the first longitudinal position ultrasound data, recognize the spinal feature as the target feature, and determine the corresponding fetal position as one of the left occipital transverse position and the occipital anterior position.

[0055] In response to the fact that no spinal feature is identified from the first longitudinal ultrasound data, the ultrasound probe is scanned according to the third scanning information. For example, the third instruction is a longitudinal data middle to right acquisition instruction, that is, after the operator manually clicks the "longitudinal data (middle to right)" button, that is, control 313, the probe is placed in the "median longitudinal position" of the abdomen, and the scanning is performed according to the following steps: Figure 3 Following the direction of the prompt light shown, manually move from the "median longitudinal section" to the right side of the pregnant woman at a constant speed to scan the abdomen to collect the second longitudinal section ultrasound data, and use the feature classification algorithm to perform feature recognition on the second longitudinal section ultrasound data, recognize the spinal feature as the target feature, and determine the corresponding fetal position as one of the right occipital transverse position and occipital anterior position.

[0056] It should be noted that the present application does not limit the order of scanning directions. For example, any one of the three directions of upward and downward, middle to left, and middle to right can be selected as the start. It is not limited to scanning in every direction. For example, scanning can be stopped when the target feature is identified.

[0057] In some embodiments, when the scanning direction is center to left, if the target feature is a spinal feature, the corresponding fetal position is determined to be one of occipital left transverse position and occipital anterior position, including: calculating the first fetal position boundary value based on the scanning frame rate, the number of frames corresponding to the spinal feature, and the scanning time; determining whether the first fetal position boundary value is greater than a preset value; in response to the first fetal position boundary value being greater than or equal to the preset value, determining the corresponding fetal position to be occipital left transverse position; in response to the first fetal position boundary value being less than the preset value, determining the corresponding fetal position to be occipital anterior position.

[0058] Based on the scanning frame rate, the number of frames corresponding to the spine features, and the scanning time, the first fetal position demarcation value is calculated. For example, after the operator manually clicks the "longitudinal position data (center to left)" button, the probe is placed in the "median longitudinal position" of the abdomen, and the abdomen is moved uniformly from the "median longitudinal position" to the left side of the pregnant woman for continuous ultrasound scanning to obtain the first longitudinal position ultrasound data. For example, the frame rate of the ultrasound scan is k frames / s, and the category C to which each frame image belongs is recorded. i And the corresponding frame number fi , where C is one of "spine, eye frame, brain midline, other"; i represents the frame number, i = 1, 2, 3, 4... When the probe scan reaches the horizontal position on the left side of the mother's abdomen, the scan stops and the system records the time T of the process 1 Then calculate the first fetal position cutoff value, for example, by calculating the formula Where T = T 1 If the first fetal position demarcation value is less than the preset value in response to the target fetal position being determined to be an occipital anterior position, for example, when the spinal feature is identified in the f-th frame image, when Threshold<5 / 6, the fetal position is "occipital anterior position"; if the first fetal position demarcation value is greater than or equal to the preset value, the target fetal position is determined to be an occipital left transverse position, that is, when Threshold>=5 / 6, the fetal position is "occipital left transverse position".

[0059] When the scanning direction is from center to right, if the target feature is a spinal feature, the corresponding fetal position is determined to be one of occipital left transverse position and occipital anterior position, including: calculating the second fetal position boundary value based on the scanning frame rate, the number of frames corresponding to the spinal feature, and the scanning time; judging whether the second fetal position boundary value is greater than a preset value; in response to the second fetal position boundary value being greater than or equal to the preset value, determining the corresponding fetal position to be occipital right transverse position; in response to the second fetal position boundary value being less than the preset value, determining the corresponding fetal position to be occipital anterior position.

[0060] Based on the scanning frame rate, the number of frames corresponding to the spine features, and the scanning time, the second fetal position demarcation value is calculated. For example, after the operator manually clicks the "longitudinal position data (center to right)" button, the probe is placed in the "median longitudinal position" of the abdomen, and the abdomen is evenly moved from the "median longitudinal position" to the right side of the pregnant woman for continuous ultrasound scanning to obtain the second longitudinal position ultrasound data. For example, the frame rate of the ultrasound scan is k frames / s, and the category C to which each frame image belongs is recorded. i And the corresponding frame number f i , where C is one of "spine, eye frame, brain midline, other"; i represents the frame number, i = 1, 2, 3, 4... When the probe scan reaches the horizontal position on the right side of the mother's abdomen, the scan stops and the system records the time T of the process 2 Then calculate the first fetal position cutoff value, for example, by calculating the formula Where T = T 2 If the first fetal position demarcation value is less than the preset value in response to the target fetal position being determined to be an occipital anterior position, for example, when the spinal feature is identified in the f-th frame image, when Threshold<5 / 6, the fetal position is "occipital anterior position"; if the first fetal position demarcation value is greater than or equal to the preset value, the target fetal position is determined to be an occipital transverse position, that is, when Threshold>=5 / 6, the fetal position is "occipital transverse position".

[0061] Those skilled in the art will appreciate that, in the above method of specific implementation, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0062] See also Figure 6 , Figure 6 6 is a schematic diagram of the structure of the ultrasound system of the embodiment of the present application. The ultrasound system 600 includes an ultrasound probe 610, a memory 624 and a processor 616. The ultrasound probe 610 is used to obtain ultrasound information. The processor 616 and the memory 624 are coupled to each other. The processor 62 is used to execute the program instructions stored in the memory 624 to implement the steps of the above-mentioned fetal position recognition method embodiment.

[0063] Specifically, the ultrasound system 600 includes an ultrasound probe 610, a transmitting circuit 612, a receiving circuit 614, a processor 616, and a display 618. Further, the ultrasound system may also include a transmit / receive selection switch 120 and a beamforming module 622, and the transmitting circuit 612 and the receiving circuit 614 may be connected to the ultrasound probe 610 through the transmit / receive selection switch 120.

[0064] The ultrasonic probe 610 is used to generate ultrasonic waves that propagate in the target tissue of the target object; the transmitting circuit 612 is used to stimulate the ultrasonic probe 610 to transmit ultrasonic waves to the target tissue; and the receiving circuit 614 is used to control the ultrasonic probe 610 to receive ultrasonic echoes returned by the target tissue.

[0065] The ultrasonic probe 610 includes a transducer (not shown) composed of a plurality of array elements arranged in an array. The array element is used to transmit ultrasonic waves according to an excitation electrical signal, or to convert received ultrasonic waves into electrical signals. Therefore, each array element can be used to realize the mutual conversion between electrical pulse signals and ultrasonic waves, thereby transmitting ultrasonic waves to the biological tissue of the target object, and can also be used to receive the echo of ultrasonic waves reflected back by the tissue.

[0066] The transmitting circuit 612 is used to control the ultrasonic probe 610 to transmit ultrasonic waves, for example, according to the control of the processor 616, stimulate the ultrasonic probe 610 to transmit ultrasonic waves toward the target object.

[0067] The receiving circuit 614 is used to control the ultrasonic probe 610 to receive ultrasonic echoes, for example, to receive ultrasonic echoes returned from the target object through the ultrasonic probe 610 to obtain ultrasonic echo signals, and can also process the ultrasonic echo signals. The receiving circuit 614 may include one or more amplifiers, analog-to-digital converters (ADCs), etc.

[0068] The display 618 is used for display or human-computer interaction, such as outputting visual information and receiving user input. The display 618 includes an input device and at least one display screen. The input device is used to receive user input, which can be a keyboard, operation button, mouse, trackball, touch pad, etc., or a touch screen integrated with the display screen.

[0069] The memory 624 is used to store various types of data.

[0070] The ultrasonic imaging device may also include a beamforming module 612. The beamforming module 612 is connected to the receiving circuit 614 signal, and is used to perform corresponding delay and weighted summing beamforming processing on the echo signal. Since the distances from the ultrasonic receiving point in the measured tissue to the receiving array element are different, the channel data of the same receiving point output by different receiving array elements have delay differences, and delay processing is required to align the phases and perform weighted summing on the different channel data of the same receiving point to obtain the ultrasonic image data after beamforming. The ultrasonic image data output by the beamforming module 612 is also called radio frequency data (RF data). The beamforming module 122 performs focusing delay, weighting and channel summing on the ultrasonic echo data, and then sends it to the processor 616. The processor 616 performs signal detection, signal enhancement, data conversion, logarithmic compression and other processing on the ultrasonic echo signal to form an ultrasonic image. The ultrasonic image obtained by the processor 616 can be displayed on the display 618 or stored in the memory 624.

[0071] The processor 616 may be implemented as software, hardware, firmware or any combination thereof, and may use a single or multiple application specific integrated circuits (ASICs), a single or multiple general purpose integrated circuits, a single or multiple microprocessors, a single or multiple programmable logic devices, or any combination of the aforementioned circuits and / or devices, or other suitable circuits or devices. Furthermore, the processor 616 may control other components in the ultrasound system 600 to perform corresponding steps of the methods in various embodiments of the present specification.

[0072] The display 618 is connected to the processor 616, and the display 618 may be a touch screen, a liquid crystal display, etc.; or, the display 618 may be an independent display such as a liquid crystal display, a television, etc., which is independent of the ultrasound system 600; or, the display 618 may be a display screen of an electronic device such as a smart phone or a tablet computer, etc. The number of the display 618 may be one or more;

[0073] The display 618 can display the ultrasound image obtained by the processor 616. In addition, while displaying the ultrasound image, the display 618 can also provide the user with a graphical interface for human-computer interaction, set one or more controlled objects on the graphical interface, and provide the user with a human-computer interaction device to input operation instructions to control these controlled objects, thereby performing corresponding control operations. For example, an icon is displayed on the graphical interface, and the icon can be operated using the human-computer interaction device to perform a specific function, such as drawing a region of interest box on the ultrasound image.

[0074] Optionally, the ultrasound system 600 may further include other human-machine interaction devices in addition to the display 618, which are connected to the processor 616. For example, the processor 616 may be connected to the human-machine interaction device via an external input / output port, and the external input / output port may be a wireless communication module, or a wired communication module, or a combination of the two. The external input / output port may also be implemented based on USB, bus protocols such as CAN, and / or wired network protocols.

[0075] The human-computer interaction device may include an input device for detecting user input information, which may be, for example, a control instruction for ultrasonic transmission / reception timing, an operation input instruction for drawing points, lines or frames on an ultrasonic image, or other instruction types. The input device may include a keyboard, a mouse, a scroll wheel, a trackball, a mobile input device (such as a mobile device with a touch screen, a mobile phone, etc.), a multi-function knob, etc., or a combination of multiple thereof. The human-computer interaction device may also include an output device such as a printer.

[0076] The ultrasound system 600 may further include a memory 624 for storing instructions executed by the processor, storing received ultrasound echoes, storing ultrasound images, etc. The memory may be a flash memory card, a solid-state memory, a hard disk, etc. It may be a volatile memory and / or a non-volatile memory, a removable memory and / or a non-removable memory, etc.

[0077] In some embodiments, the processor is further used to execute program instructions stored in the memory to set at least one instruction control through the system interface, wherein the at least one instruction control is used to receive at least one scanning instruction.

[0078] In some embodiments, the processor is also used to execute program instructions stored in the memory to set at least one prompt control through the system interface, wherein in response to at least one instruction control being triggered, at least one prompt control is displayed on the system interface, and the at least one prompt control is used to prompt when the ultrasound probe scans corresponding ultrasound data collected according to at least one scanning information.

[0079] See also Figure 7 , Figure 7 Schematic diagram of the structure of a non-volatile computer-readable storage medium according to an embodiment of the present application. The non-volatile computer-readable storage medium 70 is used to store a computer program 701. When the computer program 701 is executed by a processor, for example, Figure 6 When the processor 616 in the embodiment is executed, it is used to implement the steps of the above-mentioned embodiment of the method for identifying the fetal position.

[0080] The above description of various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other, and for the sake of brevity, they will not be repeated herein.

[0081] In the several embodiments provided in the present application, it should be understood that the disclosed methods and related devices can be implemented in other ways. For example, the above-described related device implementations are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication disconnection shown or discussed can be through some interfaces, indirect coupling or communication disconnection of devices or units, which can be electrical, mechanical or other forms.

[0082] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0083] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of each implementation method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.

[0084] It is easy for a person skilled in the art to know that many modifications and changes can be made to the device and method while maintaining the teaching content of the present application. Therefore, the above disclosure should be considered as limited only by the scope of the appended claims.

Claims

1. A method for identifying fetal position, characterized in that: include: In response to the scanning instruction, acquiring scanning information corresponding to the scanning instruction from the ultrasound probe; Acquire corresponding ultrasound data collected by the ultrasound probe according to the scanning information, and perform feature classification on the corresponding ultrasound data to identify corresponding target features, wherein the feature classification is a classification model obtained by training based on corresponding ultrasound images; Based on the corresponding target features, a corresponding fetal position is determined.

2. The method according to claim 1, characterized in that The scanning instruction is one of a first scanning instruction, a second scanning instruction, and a third scanning instruction, wherein the first scanning instruction, the second scanning instruction, and the third scanning instruction are different and correspond to different scanning information, the first scanning instruction corresponds to the first scanning information, the second scanning instruction corresponds to the second scanning information, and the third scanning instruction corresponds to the third scanning information; The corresponding ultrasonic data collected by scanning according to the first scanning information is the first ultrasonic data, the corresponding ultrasonic data collected by scanning according to the second scanning information is the second ultrasonic data, and the corresponding ultrasonic data collected by scanning according to the third scanning information is the third ultrasonic data.

3. The method according to claim 2, characterized in that The scanning instruction is a first scanning instruction, and the corresponding target feature is a first target feature; The method further comprises: In response to not identifying the first target feature from the first ultrasound data, receiving the second scanning instruction and acquiring the second scanning information in response to the second scanning instruction; Acquiring the second ultrasonic data, and performing feature classification on the second ultrasonic data to identify corresponding second target features; Based on the second target feature, the corresponding fetal position is determined.

4. The method according to claim 3, characterized in that The method further comprises: In response to not identifying the second target feature from the second ultrasound data, receiving the third scanning instruction and acquiring the third scanning information in response to the third scanning instruction; Acquiring the third ultrasonic data, and performing feature classification on the third ultrasonic data to identify corresponding third target features; Based on the third target feature, the corresponding fetal position is determined.

5. The method according to claim 1, characterized in that: The scanning information includes a scanning direction; Scanning is performed according to the scanning information to collect corresponding ultrasound data, including: In response to the scanning direction being from top to bottom, collecting transverse ultrasound data; In response to the scanning direction being from center to left, acquiring first longitudinal ultrasound data; In response to the scanning direction being from center to right, second longitudinal section ultrasound data is acquired.

6. The method according to claim 5, characterized in that The target feature includes at least one of a binocular frame feature, a brain midline feature, and a spinal column feature, wherein the binocular frame feature and the brain midline feature are respectively identified from the transverse ultrasound data, and the spinal column feature is identified from the first longitudinal ultrasound data or the second longitudinal ultrasound data; The determining the corresponding fetal position based on the corresponding target feature includes: When the scanning direction is from top to bottom, if the target feature is the double eye frame feature, the corresponding fetal position is determined to be occipital posterior position; if the target feature is the brain midline feature, the corresponding fetal position is determined to be occipital transverse position; When the scanning direction is from center to left, if the target feature is the spinal feature, determining the corresponding fetal position to be one of occipital left transverse position and occipital anterior position; When the scanning direction is from center to right, if the target feature is the spinal feature, the corresponding fetal position is determined to be one of the left occipital transverse position and the occipital anterior position.

7. The method according to claim 6, characterized in that When the scanning direction is from center to left, if the target feature is the spinal feature, determining the corresponding fetal position as one of occipital left transverse position and occipital anterior position includes: Calculating a first fetal position cutoff value based on a scanning frame rate, a number of frames corresponding to the spinal feature, and a scanning time; Determining whether the first tire position boundary value is greater than a preset value; In response to the first fetal position demarcation value being greater than or equal to the preset value, determining that the corresponding fetal position is occipital left transverse position; In response to the first fetal position demarcation value being less than the preset value, determining that the corresponding fetal position is an occipital anterior position; When the scanning direction is from center to right, if the target feature is the spinal feature, determining the corresponding fetal position as one of the left occipital transverse position and the occipital anterior position includes: Calculating a second fetal position cutoff value based on the scanning frame rate, the number of frames corresponding to the spinal feature, and the scanning time; Determining whether the second tire position boundary value is greater than the preset value; In response to the second fetal position demarcation value being greater than or equal to the preset value, determining that the corresponding fetal position is occipital right transverse position; In response to the second fetal position boundary value being less than the preset value, the corresponding fetal position is determined to be an occiput anterior position.

8. An ultrasound system, characterized in that: It comprises an ultrasound probe, a memory and a processor, wherein the ultrasound probe is used to acquire ultrasound data, and the processor is coupled to the memory and is used to execute program instructions stored in the memory to implement the method for identifying the fetal position as described in any one of claims 1 to 7.

9. The ultrasound system according to claim 8, characterized in that The processor is also used to execute program instructions stored in the memory so as to be provided with an instruction control through a system interface, wherein the instruction control is used to receive a scanning instruction.

10. The ultrasound system according to claim 9, characterized in that The processor is also used to execute program instructions stored in the memory to set a prompt control through the system interface, wherein in response to the instruction control being triggered, the prompt control is displayed on the system interface, and the prompt control is used to prompt when the ultrasound probe scans the corresponding ultrasound data collected according to the scanning information.

11. A non-volatile computer-readable storage medium having program instructions stored thereon, characterized in that: When the program instructions are executed by a processor, the method for identifying the fetal position according to any one of claims 1 to 7 is implemented.

Images