Method and apparatus for determining imaging quality control of fetal ultrasound images

Abstract

A method and apparatus for determining imaging quality control of a fetal ultrasound image, the method including: obtaining parameters of the fetal ultrasound image for determining the imaging quality of the fetal ultrasound image (101); determining an imaging score value of the fetal ultrasound image based on the parameters of the fetal ultrasound image (102); and determining the imaging quality of the fetal ultrasound image based on the imaging score value of the fetal ultrasound image (103). The method automatically determines the imaging quality of the fetal ultrasound image based on the determined imaging score value of the fetal ultrasound image, thereby enabling quick and accurate determination of the imaging quality of the fetal ultrasound image, thereby realizing precise and rapid control of the imaging quality of the fetal ultrasound image, further contributing to obtaining high-quality fetal ultrasound images and accurately capturing fetal growth and development status. The determined imaging quality of the fetal ultrasound image can further inform practitioners of the standardization of their fetal ultrasound image detection process.

Description

[Technical Field]

[0001] The present invention relates to the technical field of image processing, and in particular to a method and apparatus for determining imaging quality control of fetal ultrasound images. [Background technology]

[0002] With the progress of society and people's increasing awareness of the importance of having a healthy newborn, more and more pregnant women are now undergoing regular prenatal checkups at hospitals in accordance with prenatal checkup schedules to learn about the growth and development status of their fetuses.

[0003] In practical applications, to clearly and accurately determine the growth and development status of the fetus, it is necessary to obtain high-quality fetal ultrasound images. However, to obtain high-quality fetal ultrasound images, it is necessary to control the quality of the fetal ultrasound images. Currently, the quality control method for fetal ultrasound images mainly involves medical staff with relevant experience quantitatively evaluating the fetal ultrasound images by determining whether important structures exist in the fetal ultrasound images and whether the geometric shapes of the important structures are standard, thereby achieving quality control of the fetal ultrasound images. However, in reality, medical staff have a certain degree of subjectivity and are easily fatigued due to long working hours, which easily leads to a decrease in the accuracy of quality control of fetal ultrasound images. Summary of the Invention [Problem to be solved by the invention]

[0004] The technical problem to be solved by the present invention is to provide a method and apparatus for determining imaging quality control of fetal ultrasound images, which can improve the accuracy of quality control of fetal ultrasound images. [Means for solving the problem]

[0005] In order to solve the above technical problem, a first aspect of the present invention discloses a method for determining imaging quality control of fetal ultrasound images, the method comprising: obtaining parameters of the fetal ultrasound image for determining an imaging quality of the fetal ultrasound image; Determining an imaging score value for the fetal ultrasound image based on parameters of the fetal ultrasound image, and determining an imaging quality of the fetal ultrasound image based on the imaging score value of the fetal ultrasound image.

[0006] In an optional embodiment, in the first aspect of the present invention, acquiring parameters of the fetal ultrasound image comprises: A fetal ultrasound image is input into the determined parameter determination model for analysis, and the analysis results output from the parameter determination model are obtained as parameters of the fetal ultrasound image, wherein the parameter determination model includes a feature determination model and / or a cross section determination model, and when the parameter determination model is the feature determination model, the parameters of the fetal ultrasound image include feature parameters of the fetal ultrasound image, and the feature parameters of the fetal ultrasound image include regional feature parameters and / or structural feature parameters of the fetal ultrasound image, and when the parameter determination model is the cross section determination model, the parameters of the fetal ultrasound image include cross section parameters of the fetal ultrasound image, and the cross section parameters of the fetal ultrasound image include cross section score values ​​of standard cross sections of the fetal ultrasound image, and / or The method includes receiving parameters of the fetal ultrasound image sent by the determined terminal device and / or input by an authorized person as parameters of the fetal ultrasound image, wherein the parameters of the fetal ultrasound image include feature parameters and / or cross-section parameters of the fetal ultrasound image, the feature parameters of the fetal ultrasound image include region feature parameters and / or structure feature parameters of the fetal ultrasound image, and the cross-section parameters of the fetal ultrasound image include cross-section score values ​​of standard cross-sections of the fetal ultrasound image.

[0007] In an optional embodiment, in a first aspect of the present invention, the fetal ultrasound image is composed of a plurality of consecutive frames of sub-fetal ultrasound images, determining an imaging score value for the fetal ultrasound image based on parameters of the fetal ultrasound image; performing a chapter division operation on the fetal ultrasound image to obtain at least one target chapter, each of the target chapters including a number of consecutive frames of the sub-fetal ultrasound images, and all the sub-fetal ultrasound images included in each of the target chapters are different from each other, and the total number of all the sub-fetal ultrasound images included in each of the target chapters is equal to the total number of all the sub-fetal ultrasound images included in the fetal ultrasound image; Calculating a score value for each target chapter based on parameters of target features of the sub-fetal ultrasound image of each frame included in each target chapter, wherein the target features of the sub-fetal ultrasound image of each frame include at least one of regional features, structural features, and standard cross sections of the sub-fetal ultrasound image; and determining score values ​​of all the target chapters as imaging score values ​​of the fetal ultrasound image.

[0008] As an optional embodiment, in the first aspect of the present invention, the fetal ultrasound image corresponds to at least one target class, the target class includes a feature class or a cross-section class, and the number of target features corresponding to each of the target classes is one or more; When the target class is the feature class, the target feature includes a structure feature or a part feature; when the target class is the cross-section class, the target feature includes a standard cross-section; Each of the target classes corresponds to at least one frame of the sub-fetal ultrasound image, and all of the sub-fetal ultrasound images corresponding to each of the target classes are different from each other, and all of the sub-fetal ultrasound images corresponding to all of the target classes constitute the fetal ultrasound image.

[0009] In an optional embodiment, in a first aspect of the present invention, performing a chapter division operation on the fetal ultrasound image to obtain at least one target chapter includes: determining a location of a sub-fetal ultrasound image of a start frame corresponding to each of the target classes included in the fetal ultrasound image and a location of a sub-fetal ultrasound image of an end frame corresponding to the target class; determining, as target chapters corresponding to each of the target classes, a sub-fetal ultrasound image of a start frame corresponding to each of the target classes, a sub-fetal ultrasound image of an end frame corresponding to each of the target classes, and all sub-fetal ultrasound images between the determined location of the sub-fetal ultrasound image of the start frame corresponding to each of the target classes and the location of the sub-fetal ultrasound image of the end frame corresponding to each of the target classes; The location of the sub-fetal ultrasound image of the start frame corresponding to each of the target classes is the location where a sub-fetal ultrasound image containing target features of the target class first appears in the fetal ultrasound image, and the location of the sub-fetal ultrasound image of the end frame corresponding to each of the target classes is the location where a sub-fetal ultrasound image containing target features of the target class last appears in the fetal ultrasound image, or the location of a sub-fetal ultrasound image that appears a predetermined number of frames consecutively from the sub-fetal ultrasound image of the start frame containing target features of the target class in the fetal ultrasound image.

[0010] As an optional embodiment, in the first aspect of the present invention, calculating a score value of each target chapter based on parameters of target features of the sub-fetal ultrasound image of each frame included in each target chapter includes: If the target feature of the sub-fetal ultrasound image of each frame is a regional feature of the sub-fetal ultrasound image, calculating the sum of the regional feature score values ​​of the regional features of the sub-fetal ultrasound image of each frame included in each target chapter as the score value of the target chapter; If the target features of the sub-fetal ultrasound image of each frame are structural features of the sub-fetal ultrasound image, calculating a score value of the target chapter based on the class probability of the structural features of the sub-fetal ultrasound image of each frame included in each target chapter, the position probability of the structural features, and the weight value of the structural features; When the target feature of the sub-fetal ultrasound image of each frame is a standard cross section of the sub-fetal ultrasound image, calculating the sum of the cross section score values ​​of the standard cross sections of the sub-fetal ultrasound image of each frame included in each of the target chapters as the score value of the target chapter.

[0011] As an optional embodiment, in a first aspect of the present invention, after performing a chapter division operation on the fetal ultrasound image to obtain at least one target chapter, the method further comprises: determining a total number of frames of all the sub-fetal ultrasound images included in each of the target chapters; Then, after calculating the score value of each target chapter based on the parameters of the target features of the sub-fetal ultrasound image of each frame included in each target chapter, the method further includes: Dividing the score value of each target chapter by the total number of frames of all the sub-fetal ultrasound images included in the target chapter to obtain a target score value of the target chapter; and triggering the execution of the operation of updating the score value of each of the target chapters to the target score value of the target chapter and determining the score values ​​of all of the target chapters as imaging score values ​​of the fetal ultrasound image.

[0012] In an optional embodiment, in the first aspect of the present invention, determining an imaging score value for the fetal ultrasound image based on parameters of the fetal ultrasound image comprises: If the parameters of the fetal ultrasound image are regional feature parameters of the fetal ultrasound image, the regional feature parameters of the fetal ultrasound image include regional feature score values ​​of the fetal ultrasound image, and the regional feature score values ​​of the fetal ultrasound image are determined as the imaging score values ​​of the fetal ultrasound image; and / or If the parameters of the fetal ultrasound image are structural feature parameters of the fetal ultrasound image, the structural feature parameters of the fetal ultrasound image include class probabilities of structural features of the fetal ultrasound image, location probabilities of the structural features, and weight values ​​of the structural features; Calculating a structural feature score value of the structural feature of the fetal ultrasound image based on the class probability of the structural feature, the location probability of the structural feature, and the weight value of the structural feature, and determining the structural feature score value as an imaging score value of the fetal ultrasound image; and / or When the parameters of the fetal ultrasound image are feature parameters of the fetal ultrasound image, the structural feature parameters of the fetal ultrasound image include class probabilities of structural features of the fetal ultrasound image, position probabilities of the structural features, and weight values ​​of the structural features, and the regional feature parameters of the fetal ultrasound image include class probabilities of regional features of the fetal ultrasound image; Calculating a structural feature score value of the structural feature based on the class probability of the regional feature of the fetal ultrasound image, the class probability of the structural feature of the fetal ultrasound image, the position probability of the structural feature, and the weight value of the structural feature, and determining the structural feature score value as an imaging score value of the fetal ultrasound image; and / or determining a standard cross section of the fetal ultrasound image based on the class probability of the regional feature of the fetal ultrasound image and the class probability of the structural feature of the fetal ultrasound image, and calculating a cross section score value of the standard cross section of the fetal ultrasound image as an imaging score value of the fetal ultrasound image based on parameters of the structural feature in the standard cross section of the fetal ultrasound image, wherein the structural feature parameters of the fetal ultrasound image include parameters of the structural feature in the standard cross section of the fetal ultrasound image.

[0013] In an optional embodiment, in the first aspect of the present invention, before determining the imaging quality of the fetal ultrasound image based on the imaging score value of the fetal ultrasound image, the method further comprises: determining a detection result corresponding to the fetal ultrasound image, the detection result corresponding to the fetal ultrasound image being for determining the imaging quality of the fetal ultrasound image, and including at least one of a feature detection result, a biological pathway detection result, and a Doppler blood flow spectrum detection result, and the feature detection result including at least one of a region feature detection result, a structure feature detection result, and a standard cross section detection result; and determining an imaging quality of the fetal ultrasound image based on an imaging score value of the fetal ultrasound image, Determining an imaging quality of the fetal ultrasound image based on an imaging score value of the fetal ultrasound image and feature results corresponding to the fetal ultrasound image. A second aspect of the present invention discloses an apparatus for determining imaging quality control of fetal ultrasound images, the apparatus comprising: an acquisition module for acquiring parameters of the fetal ultrasound image for determining an imaging quality of the fetal ultrasound image; a first determination module for determining an imaging score value of the fetal ultrasound image based on parameters of the fetal ultrasound image; and a second determination module for determining an imaging quality of the fetal ultrasound image based on an imaging score value of the fetal ultrasound image.

[0014] As an optional embodiment, in the second aspect of the present invention, the manner in which the acquisition module acquires parameters of the fetal ultrasound image is specifically as follows: A fetal ultrasound image is input into the determined parameter determination model for analysis, and the analysis results output from the parameter determination model are obtained as parameters of the fetal ultrasound image, wherein the parameter determination model includes a feature determination model and / or a cross section determination model, and when the parameter determination model is the feature determination model, the parameters of the fetal ultrasound image include feature parameters of the fetal ultrasound image, and the feature parameters of the fetal ultrasound image include regional feature parameters and / or structural feature parameters of the fetal ultrasound image, and when the parameter determination model is the cross section determination model, the parameters of the fetal ultrasound image include cross section parameters of the fetal ultrasound image, and the cross section parameters of the fetal ultrasound image include cross section score values ​​of standard cross sections of the fetal ultrasound image, and / or Parameters of the fetal ultrasound image sent by the determined terminal device and / or input by an authorized person are received as parameters of the fetal ultrasound image, the parameters of the fetal ultrasound image including feature parameters and / or cross-section parameters of the fetal ultrasound image, the feature parameters of the fetal ultrasound image including region feature parameters and / or structure feature parameters of the fetal ultrasound image, and the cross-section parameters of the fetal ultrasound image including cross-section score values ​​of standard cross-sections of the fetal ultrasound image.

[0015] In an optional embodiment, in a second aspect of the present invention, the fetal ultrasound image is comprised of a plurality of consecutive frames of sub-fetal ultrasound images, And the first determination module: a division sub-module for performing a chapter division operation on the fetal ultrasound image to obtain at least one target chapter, each of the target chapters including a number of consecutive frames of the sub-fetal ultrasound images, and all the sub-fetal ultrasound images included in each of the target chapters are different from each other, and the total number of all the sub-fetal ultrasound images included in each of the target chapters is equal to the total number of all the sub-fetal ultrasound images included in the fetal ultrasound image; a calculation submodule for calculating a score value of each of the target chapters based on parameters of target features of the subfetal ultrasound image of each frame included in each of the target chapters, the target features of the subfetal ultrasound image of each frame including at least one of regional features, structural features, and standard cross sections of the subfetal ultrasound image; and a determination sub-module for determining score values ​​of all the target chapters as imaging score values ​​of the fetal ultrasound image.

[0016] As an optional embodiment, in a second aspect of the present invention, the fetal ultrasound image corresponds to at least one target class, the target class includes a feature class or a cross-section class, and the number of target features corresponding to each of the target classes is one or more; When the target class is the feature class, the target feature includes a structure feature or a part feature; when the target class is the cross-section class, the target feature includes a standard cross-section; Each of the target classes corresponds to at least one frame of the sub-fetal ultrasound image, and all of the sub-fetal ultrasound images corresponding to each of the target classes are different from each other, and all of the sub-fetal ultrasound images corresponding to all of the target classes constitute the fetal ultrasound image.

[0017] As an optional embodiment, in the second aspect of the present invention, the manner in which the segmentation sub-module performs a chapter segmentation operation on the fetal ultrasound image to obtain at least one target chapter is specifically as follows: determining a location of a sub-fetal ultrasound image of a start frame corresponding to each of the target classes included in the fetal ultrasound image and a location of a sub-fetal ultrasound image of an end frame corresponding to the target class; determining, as target chapters corresponding to each of the target classes, a sub-fetal ultrasound image of a start frame corresponding to each of the target classes, a sub-fetal ultrasound image of an end frame corresponding to each of the target classes, and all sub-fetal ultrasound images between the determined location of the sub-fetal ultrasound image of the start frame corresponding to each of the target classes and the location of the sub-fetal ultrasound image of the end frame corresponding to each of the target classes; The location of the sub-fetal ultrasound image of the start frame corresponding to each of the target classes is the location where a sub-fetal ultrasound image containing target features of the target class first appears in the fetal ultrasound image, and the location of the sub-fetal ultrasound image of the end frame corresponding to each of the target classes is the location where a sub-fetal ultrasound image containing target features of the target class last appears in the fetal ultrasound image, or the location of a sub-fetal ultrasound image that appears a predetermined number of frames consecutively from the sub-fetal ultrasound image of the start frame containing target features of the target class in the fetal ultrasound image.

[0018] As an optional embodiment, in the second aspect of the present invention, the calculation submodule calculates the score value of each target chapter based on the parameters of the target features of the sub-fetal ultrasound images of each frame included in each target chapter, specifically as follows: If the target feature of the sub-fetal ultrasound image of each frame is a regional feature of the sub-fetal ultrasound image, calculate the sum of the regional feature score values ​​of the regional features of the sub-fetal ultrasound image of each frame included in each target chapter as the score value of the target chapter; If the target features of the sub-fetal ultrasound images of each frame are structural features of the sub-fetal ultrasound images, calculate a score value of the target chapter based on the class probability of the structural features of the sub-fetal ultrasound images of each frame included in each target chapter, the position probability of the structural features, and the weight value of the structural features; If the target feature of the sub-fetal ultrasound image of each frame is a standard cross section of the sub-fetal ultrasound image, the sum of the cross section score values ​​of the standard cross sections of the sub-fetal ultrasound image of each frame included in each target chapter is calculated as the score value of the target chapter. As an optional embodiment, in a second aspect of the present invention, the determination submodule is further configured to determine a total number of frames of all the sub-fetal ultrasound images included in each target chapter after the division submodule performs a chapter division operation on the fetal ultrasound images to obtain at least one target chapter; And the device further comprises: a calculation module for dividing the score value of each target chapter by the total number of frames of all the sub-fetal ultrasound images included in each target chapter after the first determination module calculates the score value of the target chapter based on the parameters of the target features of the sub-fetal ultrasound images of each frame included in each target chapter to obtain the target score value of the target chapter; and an update module for updating the score value of each of the target chapters to the target score value of the target chapter, and triggering the second determination module to perform the operation of determining the score values ​​of all of the target chapters as imaging score values ​​of the fetal ultrasound image.

[0019] As an optional embodiment, in the second aspect of the present invention, the manner in which the first determination module determines the imaging score value of the fetal ultrasound image based on the parameters of the fetal ultrasound image is specifically: If the parameters of the fetal ultrasound image are regional feature parameters of the fetal ultrasound image, the regional feature parameters of the fetal ultrasound image include regional feature score values ​​of the fetal ultrasound image, and the regional feature score values ​​of the fetal ultrasound image are determined as the imaging score values ​​of the fetal ultrasound image; and / or When the parameters of the fetal ultrasound image are structural feature parameters of the fetal ultrasound image, the structural feature parameters of the fetal ultrasound image include class probabilities of structural features of the fetal ultrasound image, location probabilities of the structural features, and weight values ​​of the structural features; Calculating a structural feature score value of the structural feature of the fetal ultrasound image based on the class probability of the structural feature, the location probability of the structural feature, and the weight value of the structural feature, and determining the structural feature score value as an imaging score value of the fetal ultrasound image; and / or When the parameters of the fetal ultrasound image are feature parameters of the fetal ultrasound image, the structural feature parameters of the fetal ultrasound image include class probabilities of structural features of the fetal ultrasound image, position probabilities of the structural features, and weight values ​​of the structural features, and the regional feature parameters of the fetal ultrasound image include class probabilities of regional features of the fetal ultrasound image; Calculate a structural feature score value of the structural feature based on the class probability of the regional feature of the fetal ultrasound image, the class probability of the structural feature of the fetal ultrasound image, the position probability of the structural feature, and the weight value of the structural feature, and determine the structural feature score value as an imaging score value of the fetal ultrasound image; and / or determine a standard slice of the fetal ultrasound image based on the class probability of the regional feature of the fetal ultrasound image and the class probability of the structural feature of the fetal ultrasound image, and calculate a slice score value of the standard slice of the fetal ultrasound image as an imaging score value of the fetal ultrasound image based on parameters of the structural feature in the standard slice of the fetal ultrasound image, wherein the structural feature parameters of the fetal ultrasound image include parameters of the structural feature in the standard slice of the fetal ultrasound image.

[0020] In an alternative embodiment, in the second aspect of the invention, the apparatus further comprises a third determination module: The third determination module is for determining a detection result corresponding to the fetal ultrasound image before the second determination module determines the imaging quality of the fetal ultrasound image based on the imaging score value of the fetal ultrasound image, and the detection result corresponding to the fetal ultrasound image is for determining the imaging quality of the fetal ultrasound image, and includes at least one of a feature detection result, a biological pathway detection result, and a Doppler blood flow spectrum detection result, and the feature detection result includes at least one of a region feature detection result, a structure feature detection result, and a standard cross section detection result; The second determination module determines the imaging quality of the fetal ultrasound image based on the imaging score of the fetal ultrasound image in a manner as follows: An imaging quality of the fetal ultrasound image is determined based on an imaging score value of the fetal ultrasound image and feature results corresponding to the fetal ultrasound image.

[0021] A third aspect of the present invention discloses another apparatus for determining imaging quality control of fetal ultrasound images, the apparatus comprising: a memory in which executable program code is stored; a processor coupled to the memory; The processor invokes the executable program code stored in the memory to execute the method for determining imaging quality control of fetal ultrasound images disclosed in the first aspect of the present invention. A fourth aspect of the present invention discloses a computer storage medium having stored thereon computer instructions which, when invoked, are for performing the method for determining imaging quality control of fetal ultrasound images disclosed in the first aspect of the present invention. [Effects of the Invention]

[0022] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: In an embodiment of the present invention, a method and apparatus for determining imaging quality control of a fetal ultrasound image is provided, the method including: obtaining parameters of the fetal ultrasound image for determining the imaging quality of the fetal ultrasound image; determining an imaging score value of the fetal ultrasound image based on the parameters of the fetal ultrasound image; and determining the imaging quality of the fetal ultrasound image based on the imaging score value of the fetal ultrasound image. As can be seen from the above, by implementing the present invention, the imaging quality of the fetal ultrasound image can be quickly and accurately determined by automatically determining the imaging quality of the fetal ultrasound image based on the determined imaging score value of the fetal ultrasound image, thereby realizing precise and rapid control of the imaging quality of the fetal ultrasound image, further contributing to obtaining high-quality fetal ultrasound images and accurately capturing the growth and development status of the fetus. The determined imaging quality of the fetal ultrasound image can also help practitioners standardize the detection process of the fetal ultrasound image and know whether the detection of items that need to be detected for the fetus has been completed. [Brief explanation of the drawings]

[0023] In order to more clearly describe the technical solutions of the embodiments of the present invention, the following briefly describes the drawings necessary for describing the embodiments. Obviously, the drawings described below are examples of the embodiments of the present invention, and those skilled in the art can further obtain other drawings based on these drawings without any creative efforts. [Figure 1] FIG. 1 is a flowchart of a method for determining imaging quality control of fetal ultrasound images disclosed in an embodiment of the present invention. [Figure 2] FIG. 2 is a flowchart of another method for determining imaging quality control of fetal ultrasound images disclosed in an embodiment of the present invention. [Figure 3] FIG. 3 is a structural schematic diagram of the imaging quality control determination device for fetal ultrasound images disclosed in an embodiment of the present invention. [Figure 4] FIG. 4 is a structural schematic diagram of another fetal ultrasound image imaging quality control determination device disclosed in an embodiment of the present invention. [Figure 5]FIG. 5 is a structural schematic diagram of another fetal ultrasound image imaging quality control determination device disclosed in an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0024] In order to allow those skilled in the art to better understand the inventive solution, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the drawings of the embodiments of the present invention. Of course, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments that those skilled in the art can obtain without inventive efforts fall within the protection scope of the present invention.

[0025] The terms "first," "second," etc. in the present specification and claims, as well as in the drawings, are intended to distinguish different objects, not to describe a particular order. Furthermore, the terms "comprise," "have," and any variations thereof are intended to include a non-exclusive inclusion. For example, a process, method, apparatus, product, or equipment that includes a series of steps or units is not limited to the listed steps or units, but may also include unlisted steps or units as alternatives, or may also include other steps or units inherent in the process, method, product, or equipment as alternatives.

[0026] The term "embodiment" as used herein means that a particular feature, structure, or characteristic described with reference to the embodiment may be included in at least one embodiment of the present invention. Appearances of the term in various places in the specification do not necessarily refer to the same embodiment, nor are they exclusive, independent, or alternative embodiments to other embodiments. As will be understood by those skilled in the art, either explicitly or implicitly, the embodiments described herein may be combined with other embodiments.

[0027] The present invention discloses a method and apparatus for determining the imaging quality control of fetal ultrasound images, which automatically determines the imaging quality of a fetal ultrasound image based on the determined imaging score value of the fetal ultrasound image, thereby enabling the imaging quality of the fetal ultrasound image to be determined quickly and accurately, thereby realizing precise and rapid control of the imaging quality of the fetal ultrasound image, further contributing to obtaining high-quality fetal ultrasound images and accurately capturing the growth and development status of the fetus. The determined imaging quality of the fetal ultrasound image also allows practitioners to standardize the detection process of the fetal ultrasound image and know whether the detection of items that need to be detected by the fetus has been completed. Each will be described in detail below.

[0028] Example 1 Referring to Figure 1, Figure 1 is a flowchart of a method for determining imaging quality control of fetal ultrasound images disclosed in an embodiment of the present invention. The method for determining imaging quality control of fetal ultrasound images described in Figure 1 may be applied to an imaging quality determination server (service device), which may include a local imaging quality determination server or a cloud imaging quality determination server, and the embodiment of the present invention is not limited thereto. As shown in Figure 1, the method for determining imaging quality control of fetal ultrasound images may include the following operations: 101. Obtaining parameters of the fetal ultrasound image for determining the imaging quality of the fetal ultrasound image.

[0029] In an embodiment of the present invention, the fetal ultrasound image is any one of the fetal ultrasound images whose imaging quality needs to be determined. Furthermore, the fetal ultrasound image may be a single-frame image or a moving image. If the fetal ultrasound image is a single-frame image, the parameters of the fetal ultrasound image may include parameters of the single-frame fetal ultrasound image and may also include parameters corresponding to the fetal ultrasound video corresponding to the fetal ultrasound image, and the embodiments of the present invention are not limited thereto. In this case, the imaging quality of the fetal ultrasound image may indicate the imaging quality of the single-frame fetal ultrasound image or the imaging quality corresponding to the fetal ultrasound video in which the fetal ultrasound image is located, and the embodiments of the present invention are not limited thereto.

[0030] In an embodiment of the present invention, as an optional embodiment, acquiring parameters of a fetal ultrasound image comprises: The method may include inputting a fetal ultrasound image into the determined parameter determination model for analysis, and obtaining the analysis results output from the parameter determination model as parameters of the fetal ultrasound image.

[0031] In an embodiment of the present invention, as a further option, if the fetal ultrasound image is a single-frame image, the fetal ultrasound images may be continuously input into the parameter determination model at a predetermined frame rate (e.g., 30 frames / second) for analysis, and the analysis results sequentially output from the parameter determination model may be obtained as parameters for the fetal ultrasound image for each frame. Inputting multiple consecutive frames of fetal ultrasound images into the parameter determination model for analysis in this manner helps reduce the occurrence of situations in which the imaging quality of the fetal ultrasound image cannot be determined because a single-frame fetal ultrasound image contains too little feature information, resulting in too few or no parameters for the acquired fetal ultrasound image, and contributes to quickly obtaining parameters for the fetal ultrasound image. Alternatively, if the fetal ultrasound image is a dynamic image, the parameter determination model may further perform a frame division operation on the fetal ultrasound image to obtain multiple frames of sub-fetal ultrasound images, and then analyze each of the multiple frames of sub-fetal ultrasound images to obtain parameters for the multiple frames of sub-fetal ultrasound images. In this way, performing processing operations on static or dynamic fetal ultrasound images improves the fetal ultrasound image parameter obtainability.

[0032] In an embodiment of the present invention, as a further option, each fetal ultrasound image has a corresponding unique frame number. By assigning a unique frame number to each frame of the fetal ultrasound image, the fetal ultrasound image can be clearly distinguished from each other in the process of determining the imaging quality of the fetal ultrasound image, and this contributes to managing related information of the fetal ultrasound image (e.g., imaging score value).

[0033] In an embodiment of the present invention, the parameter determination model includes a feature determination model and / or a cross-section determination model, where the feature determination model is a model capable of determining feature parameters of a fetal ultrasound image, and the cross-section determination model is a model capable of determining feature parameters of a fetal ultrasound image. The parameter determination model may include at least one of models capable of obtaining parameters of a fetal ultrasound image, such as a target detection model, an instance segmentation model, and a semantic segmentation model, and the embodiment of the present invention is not limited thereto.

[0034] In an embodiment of the present invention, when the parameter determination model is a feature determination model, the parameters of the fetal ultrasound image include feature parameters of the fetal ultrasound image, and the feature parameters of the fetal ultrasound image include regional feature parameters and / or structural feature parameters of the fetal ultrasound image.

[0035] In an embodiment of the present invention, the regional feature parameters of the fetal ultrasound image include the class of the regional feature of the fetal ultrasound image and the class probability (also called confidence) of the regional feature of the fetal ultrasound image. Furthermore, the regional feature parameters of the fetal ultrasound image may further include the geometric coordinates of the regional feature of the fetal ultrasound image.

[0036] In an embodiment of the present invention, the structural feature parameters of the fetal ultrasound image include the class of the structural feature of the fetal ultrasound image and the class probability (also called reliability) of the structural feature of the fetal ultrasound image. Furthermore, the structural feature parameters of the fetal ultrasound image further include at least one of the geometric coordinates, size, and position probability of the structural feature of the fetal ultrasound image, and the embodiment of the present invention is not limited thereto. Furthermore, the feature information of the fetal ultrasound image further includes polygonal contour information of the structural feature of the fetal ultrasound image, for example, polygonal contour coordinates. Thus, the more information included in the structural feature parameters of the fetal ultrasound image, the more it contributes to improving the accuracy and efficiency of determining the imaging quality of the fetal ultrasound image.

[0037] In an embodiment of the present invention, the geometric coordinates of the above-mentioned site features or structural features may include polygonal coordinates or elliptical coordinates, and the polygonal coordinates may include odd-numbered polygonal coordinates or even-numbered polygonal coordinates, such as pentagonal coordinates or rectangular coordinates, and the selection of polygonal coordinates is determined according to the shape of the site features or structural features, thereby improving the accuracy of obtaining the coordinates of the site features and structural features.

[0038] In an embodiment of the present invention, when the parameter determination model is a plane determination model, the parameters of the fetal ultrasound image include plane parameters of the fetal ultrasound image, and the plane parameters of the fetal ultrasound image include plane score values ​​of the standard planes of the fetal ultrasound image. Furthermore, the plane parameters of the fetal ultrasound image further include plane classes of the standard planes of the fetal ultrasound image. In this way, the plane determination model automatically obtains the plane parameters of the fetal ultrasound image, thereby improving the efficiency and accuracy of obtaining the plane parameters of the fetal ultrasound image.

[0039] As can be seen from the above, an embodiment of the present invention can further input fetal ultrasound images into a parameter determination model for analysis, thereby quickly realizing automatic acquisition of fetal ultrasound image parameters, without the need for human intervention, and improving the accuracy and reliability of fetal ultrasound image parameter acquisition, thereby improving the accuracy and efficiency of determining the imaging score value of fetal ultrasound images.

[0040] In another alternative embodiment of the present invention, acquiring parameters of the fetal ultrasound image may include: The method may include receiving parameters of the fetal ultrasound image transmitted by the determined terminal device and / or input by an authorized person as parameters of the fetal ultrasound image.

[0041] In an embodiment of the present invention, the parameters of the fetal ultrasound image include feature parameters and / or cross-section parameters of the fetal ultrasound image, the feature parameters of the fetal ultrasound image include region feature parameters and / or structure feature parameters of the fetal ultrasound image, and the cross-section parameters of the fetal ultrasound image include cross-section score values ​​of standard cross-sections of the fetal ultrasound image.

[0042] In the embodiment of the present invention, for other explanations of the parameters of fetal ultrasound images, please refer to the detailed explanation of the parameters of fetal ultrasound images in the above embodiment, and detailed explanations will be omitted in the optional embodiment.

[0043] In this alternative method, the terminal device pre-establishes communication with an imaging quality determination server (service device).

[0044] As can be seen from the above, an embodiment of the present invention can further acquire parameters of fetal ultrasound images by sending them from a terminal device and / or input by an authorized person, thereby enriching the acquisition methods of parameters of fetal ultrasound images.

[0045] In addition, in an embodiment of the present invention, the parameters of the fetal ultrasound image may be obtained by any of the above methods. In this way, the means for obtaining the parameters of the fetal ultrasound image can be enriched, thereby improving the possibility of obtaining the parameters of the fetal ultrasound image. Furthermore, the imaging score value of the fetal ultrasound image can be obtained by referring to the feature parameters and cross-sectional parameters of the fetal ultrasound image, thereby improving the accuracy of obtaining the imaging score value of the fetal ultrasound image.

[0046] 102, determining an imaging score value for the fetal ultrasound image based on the parameters of the fetal ultrasound image.

[0047] In an embodiment of the present invention, the fetal ultrasound image is composed of a plurality of consecutive frames of sub-fetal ultrasound images, and as an optional embodiment, determining an imaging score value of the fetal ultrasound image based on parameters of the fetal ultrasound image includes: performing a chapter splitting operation on the fetal ultrasound image to obtain at least one target chapter; This may include calculating a score value for each target chapter based on parameters of the target features of the sub-fetal ultrasound image of each frame included in the target chapter, and determining the score values ​​of all target chapters as imaging score values ​​of the fetal ultrasound image.

[0048] In an embodiment of the present invention, the target features of the sub-fetal ultrasound image of each frame optionally include at least one of a region feature, a structure feature, and a standard cross section of the sub-fetal ultrasound image.

[0049] In an embodiment of the present invention, the regional features of the sub-fetal ultrasound image include, but are not limited to, abdominal features, craniocerebral features, lung features, arm features, toe features, and heart features.

[0050] In an embodiment of the present invention, the structural features of the sub-fetal ultrasound image include, but are not limited to, a gastric bubble structural feature, an umbilical vein structural feature, a cavity of the septum pellucidum structural feature, a thalamus structural feature, a lateral ventricle liver structural feature, a descending aorta structural feature, a rib structural feature, and an inferior vena cava structural feature.

[0051] In an embodiment of the present invention, the standard sections of the sub-fetal ultrasound image include a crown-rump length measurement section, a bivertex diameter measurement section, a NT measurement section, a facial midline section, a forehead-maxillary angle measurement section, a humerus length measurement section, a femur length measurement section, both upper limb sections, both lower limb sections, a fetal heart rate measurement section, a tricuspid valve spectrum measurement section, a venous catheter spectrum measurement section, a gastric bubble section, a urinary bladder section, both umbilical arteries sections, a gender indication section, a nasal bone measurement section, an intestinal diameter measurement section, a ulnar-radial long diameter section, a middle cerebral artery section, a gallbladder umbilical vein section, a ductus arteriosus arch section, a section of the pulmonary vein entering the left atrium, an abdominal circumference section, an anal section, a humerus long diameter section, a cervix measurement section, a femur long diameter section, a coronary sinus section, a specific section of the conus medullaris, a coronary spine section, a spinal column section, These include, but are not limited to, spinal column cross section, tibiofibular long diameter cross section, NF measurement cross section, bladder + both umbilical arteries cross section, umbilical artery spectrum measurement cross section, umbilical cord inserted into the placenta cross section, umbilical cord wrapped around the neck cross section, umbilical cord inlet cross section, three-vessel tracheal cross section, superior and inferior vena cava cross section entering the right atrium cross section, superior alveolar process cross section, kidney long diameter measurement cross section, esophagus-tracheal cross section, hand cross section, biapical diameter cross section, both kidney cross section, four-chambered heart cross section, placenta cross section, midline skull cross section, transvaginal skull cross section, cerebellum cross section, gender indication cross section, chest-abdominal cross section, facial surface image cross section, interpupillary distance measurement cross section, amniotic fluid cross section, right ventricular outflow tract cross section, aortic arch cross section / foot cross section, left innominate vein joining the right superior cavity cross section, left ventricular outflow tract cross section, left and right pulmonary artery bifurcation cross section, and ear cross section.

[0052] In an embodiment of the present invention, the target features of the sub-fetal ultrasound image of each frame include at least one standard cross section in one direction, including a coronal direction, a sagittal direction, and a horizontal direction. For example, the abdominal features include a horizontal abdominal feature, a sagittal abdominal feature, and a coronal abdominal feature, the abdominal circumference cross sections include a horizontal abdominal circumference cross section, a sagittal abdominal circumference cross section, and a coronal abdominal circumference cross section, and the stomach bubble structure features include a horizontal stomach bubble structure feature, a sagittal stomach bubble structure feature, and a coronal stomach bubble structure feature.

[0053] In an embodiment of the present invention, each target chapter includes a number of consecutive frames of sub-fetal ultrasound images, and all the sub-fetal ultrasound images included in each target chapter are different from each other, and the total number of all the sub-fetal ultrasound images included in each target chapter is equal to the total number of all the sub-fetal ultrasound images included in the fetal ultrasound images.

[0054] In an embodiment of the present invention, the fetal ultrasound images may be divided into chapters in real time. That is, a plurality of consecutive frames of sub-fetal ultrasound images of the fetal ultrasound images are sequentially input into the parameter determination model for analysis, and the analysis results sequentially output from the parameter determination model are obtained as parameters for the sub-fetal ultrasound images of each frame, and all sub-fetal ultrasound images are divided into chapters. The fetal ultrasound images may be divided into chapters after the parameters for all sub-fetal ultrasound images are obtained, and the embodiment of the present invention is not limited thereto.

[0055] In an embodiment of the present invention, as a further option, the fetal ultrasound image corresponds to at least one target class, the target class including a feature class or a cross-section class, and the number of target features corresponding to each target class is 1 or more. If the target class is a feature class, the target feature includes a structure feature or a region feature; if the target class is a cross-section class, the target feature includes a standard cross-section; each target class corresponds to at least one frame of sub-fetal ultrasound image, and all the sub-fetal ultrasound images corresponding to each target class are different from each other, and all the sub-fetal ultrasound images corresponding to all the target classes constitute a fetal ultrasound image.

[0056] As can be seen from the above, the embodiment of the present invention can further automatically divide the fetal ultrasound image into chapters of different classes, and the calculated score value of each chapter can be used as the imaging score value of the fetal ultrasound image, thereby improving the accuracy and efficiency of obtaining the imaging score value of the fetal ultrasound image, thereby contributing to improving the accuracy and reliability of determining the imaging quality of the fetal ultrasound image, realizing precise and rapid control of the imaging quality of the fetal ultrasound image, contributing to obtaining higher quality fetal ultrasound images, and contributing to improving the accuracy and reliability of determining the growth and development status of the fetus.

[0057] In the alternative embodiment, further optionally, performing a chapter splitting operation on the fetal ultrasound image to obtain at least one target chapter includes: determining a location of a sub-fetal ultrasound image of a start frame corresponding to each target class included in the fetal ultrasound image and a location of a sub-fetal ultrasound image of an end frame corresponding to the target class; This may include determining, as target chapters corresponding to each target class, a sub-fetal ultrasound image of a start frame corresponding to each target class, a sub-fetal ultrasound image of an end frame corresponding to the target class, and all sub-fetal ultrasound images between the determined location of the sub-fetal ultrasound image of the start frame corresponding to the target class and the location of the sub-fetal ultrasound image of the end frame corresponding to the target class.

[0058] In an embodiment of the present invention, the location of the sub-fetal ultrasound image of the start frame corresponding to each target class is the location where a sub-fetal ultrasound image containing target features of the target class first appears in the fetal ultrasound image, and the location of the sub-fetal ultrasound image of the end frame corresponding to each target class is the location where a sub-fetal ultrasound image containing target features of the target class last appears in the fetal ultrasound image, or the location of a sub-fetal ultrasound image a predetermined number of frames after the sub-fetal ultrasound image of the start frame that contains target features of the target class in the fetal ultrasound image, which contributes to improving the accuracy of determining the location of the fetal ultrasound image of the end frame corresponding to each target class, thereby improving the accuracy of determining the target chapter for each target class and thereby improving the accuracy of determining the score value of the target chapter. Note that the situation where the location of the sub-fetal ultrasound image of the end frame corresponding to each target class is the location of a sub-fetal ultrasound image a predetermined number of frames after the sub-fetal ultrasound image of the start frame that contains target features of the target class in the fetal ultrasound image, is applicable to situations where fetal ultrasound images are divided into chapters in real time.

[0059] For example, the target class is a stomach bubble structure feature class, and the fetal ultrasound images are composed of 100 frames of sub-fetal ultrasound images. The stomach bubble structure feature first appears at the position of the sub-fetal ultrasound image in the 5th frame and last appears at the position of the sub-fetal ultrasound image in the 50th frame. In this case, the position of the sub-fetal ultrasound image in the start frame corresponding to the stomach bubble structure feature class is the position of the sub-fetal ultrasound image in the 5th frame, and the position of the sub-fetal ultrasound image in the end frame is the position of the sub-fetal ultrasound image in the 50th frame. Alternatively, the predetermined number of frames corresponding to the stomach bubble structure feature class is 30 frames. In this case, the position of the sub-fetal ultrasound image in the 34th frame, which appears consecutively from the position of the sub-fetal ultrasound image in the 5th frame, is the position of the sub-fetal ultrasound image in the end frame corresponding to the stomach bubble structure feature class. To further illustrate, the target class is an abdominal circumference standard cross section, and the fetal ultrasound images are composed of 100 frames of sub-fetal ultrasound images. The abdominal circumference standard cross section class first appears at the position of the sub-fetal ultrasound image in the 5th frame and last appears at the position of the sub-fetal ultrasound image in the 50th frame. In this case, the position of the sub-fetal ultrasound image in the start frame corresponding to the abdominal circumference standard cross section class is the position of the sub-fetal ultrasound image in the 5th frame, and the position of the fetal ultrasound image in the end frame is the position of the fetal ultrasound image in the 50th frame. Alternatively, the predetermined number of frames corresponding to the abdominal circumference standard cross section class is 30 frames. In this case, the position of the sub-fetal ultrasound image in the 34th frame, which appears consecutively from the position of the sub-fetal ultrasound image in the 5th frame, is the position of the sub-fetal ultrasound image in the end frame corresponding to the abdominal circumference standard cross section class.

[0060] In an embodiment of the present invention, all sub-fetal ultrasound images included in a target chapter corresponding to each target class include fetal ultrasound images that include at least target features of the target class, and the number of target features of the target class included in a target chapter corresponding to each target class is one or more. Furthermore, all sub-fetal ultrasound images included in a target chapter corresponding to each target class further include sub-fetal ultrasound images that do not include target features of the target class. For example, a chapter corresponding to a stomach bubble structure feature class includes 50 frames of fetal ultrasound images, of which 45 frames of sub-fetal ultrasound images correspond to the stomach bubble structure feature class, and the structural features included in the remaining 5 frames of sub-fetal ultrasound images are finger structure features.

[0061] As can be seen from the above, embodiments of the present invention can further realize automatic determination of chapters corresponding to various types of regional features, structural features, or standard cross sections by automatically determining the location of the fetal ultrasound image of the start frame and the location of the fetal ultrasound image of the end frame of each type of regional feature, structural feature, or standard cross section, which contributes to improving the efficiency and accuracy of determining each chapter, and thereby contributing to improving the efficiency and accuracy of calculating the score value of each chapter.

[0062] In the alternative embodiment, as a further option, calculating a score value of each target chapter based on parameters of target features of the sub-fetal ultrasound image of each frame included in each target chapter includes: When the target feature of the sub-fetal ultrasound image of each frame is a regional feature of the sub-fetal ultrasound image, calculating the sum of the regional feature score values ​​of the regional features of the sub-fetal ultrasound image of each frame included in each target chapter as the score value of the target chapter; If the target features of the sub-fetal ultrasound image of each frame are structural features of the sub-fetal ultrasound image, calculate a score value of the target chapter based on the class probability of the structural features of the sub-fetal ultrasound image of each frame included in each target chapter, the position probability of the structural features, and the weight value of the structural features; When the target feature of the sub-fetal ultrasound image of each frame is a standard cross section of the sub-fetal ultrasound image, calculating the sum of the cross section score values ​​of the standard cross sections of the sub-fetal ultrasound image of each frame included in each target chapter as the score value of the target chapter.

[0063] In an embodiment of the present invention, when the target feature of the sub-fetal ultrasound image of each frame is the structural feature of the sub-fetal ultrasound image, the calculation formula for the score value of the target chapter corresponding to each feature class is: JPEG0007779907000001.jpg21170JPEG0007779907000002.jpg55170

[0064] In an embodiment of the present invention, the parameters of the structural features of the sub-fetal ultrasound images of each frame included in each target chapter further include the location probability of the structural feature. At this time, the structural feature score calculation formula of the i-th structural feature corresponding to the feature class in the target chapter is: JPEG0007779907000003.jpg 13170JPEG0007779907000004.jpg 8170. In this way, the more parameters of a structural feature, the more it contributes to improving the accuracy of calculating the structural feature score value of the structural feature, which in turn contributes to further improving the accuracy of the score value of the chapter corresponding to the structural feature, thereby further improving the accuracy of determining the imaging quality of fetal ultrasound images.

[0065] In the alternative embodiment, when the target feature of the sub-fetal ultrasound image of each frame is a standard cross section of the sub-fetal ultrasound image, the calculation formula of the target chapter corresponding to each cross section class is: JPEG0007779907000005.jpg18170JPEG0007779907000006.jpg26170

[0066] In the alternative embodiment, when the target feature of the sub-fetal ultrasound image of each frame is the region feature of the sub-fetal ultrasound image, the calculation formula of the target chapter corresponding to each region class is: JPEG0007779907000007.jpg16170JPEG0007779907000008.jpg27170

[0067] In an embodiment of the present invention, as a further option, since the target features of each frame of the sub-fetal ultrasound image all include one or more features in the horizontal, sagittal, and coronal directions, the score value of each target chapter may include an average value of score values ​​corresponding to at least one of the three directions of the target features of the corresponding target class. For example, if the structural features included in Chapter A are gastric bubble structural features corresponding to the gastric bubble structural feature class, the structural feature score values ​​corresponding to the three directions of the horizontal, sagittal, and coronal directions of each gastric bubble structural feature in Chapter A are calculated, and the average value of the structural feature score values ​​corresponding to the three directions of all gastric bubble structural features is calculated as the score value of Chapter A. The method of calculating the average value of score values ​​in multiple directions of region features and standard cross sections is the same as that of the average value of score values ​​in multiple directions of structural features, and therefore a detailed description thereof will be omitted here. In this way, by calculating the average score values ​​of structural features, regional features, and standard cross sections in multiple directions as the chapter score value, the accuracy of calculating the chapter score value can be further improved, thereby further improving the accuracy of determining the imaging quality of fetal ultrasound images and contributing to obtaining even higher quality fetal ultrasound images.

[0068] As can be seen from the above, the embodiments of the present invention can not only realize the determination of chapter score values ​​by calculating structural feature score values ​​corresponding to each type of structural feature, or cross-section score values ​​corresponding to each type of cross-section, or region feature score values ​​corresponding to each type of region feature, but also enrich the methods of determining chapter score values, thereby improving the accuracy and reliability of determining chapter score values. Furthermore, the chapter score values ​​obtained by the structural feature score values, the chapter score values ​​obtained by the region feature score values, together with the chapter score values ​​obtained by the cross-section score values, can determine the imaging quality of fetal ultrasound images, thereby further improving the accuracy and reliability of determining the imaging quality of fetal ultrasound images, and thereby further contributing to obtaining higher quality fetal ultrasound images.

[0069] In an embodiment of the present invention, since each standard cross section includes at least one structural feature, the cross section score value of each standard cross section can be obtained by at least one of the following methods: direct transmission by the terminal device, input by an authorized person, and output by the cross section determination model, and can also be calculated and obtained based on the structural feature score value of each structural feature included in the standard cross section. That is, the cross section score value of each type of standard cross section is calculated based on the structural feature score value of each structural feature included in each standard cross section of each type of standard cross section, and the score value of the chapter corresponding to the standard cross section of each class is calculated and obtained based on the cross section score value of the standard cross section of the class, and the score value of the chapter is then calculated as the average of the score value of the chapter obtained by the calculated cross section score value of each type of standard cross section and the score value of the chapter obtained by the directly obtained cross section score value of the standard cross section of the class. For example, if Chapter B corresponds to the abdominal section class of the target class, and Chapter B includes five abdominal sections, each with a section score value of 10, 8, 9, 9.5, and 8.6, the score value of Chapter B calculated based on the section score value of the abdominal section is 45.1. The structural features of the abdominal sections include a stomach bubble structural feature, an umbilical vein structural feature, and a liver structural feature. The structural feature score value corresponding to the stomach bubble structural feature included in each abdominal section in Chapter B is 14.5, the structural feature score value corresponding to the umbilical vein structural feature is 16, and the structural feature score value corresponding to the liver structural feature is 15.5. Therefore, the score value of Chapter B calculated based on the structural feature score values ​​corresponding to the structural features is 46, and the average value of 46 and 45.1, 45.55, is taken as the final score value of Chapter B. In this way, by obtaining the average value of the score values ​​of a chapter obtained by different means as the score value of that chapter, i.e., the imaging score value of the fetal ultrasound image, the accuracy of determining the imaging score value of the fetal ultrasound image can be further improved, thereby further improving the accuracy of determining the imaging quality of the fetal ultrasound image.

[0070] In further embodiments of the present invention, since the region features include multiple standard cross sections, and the standard cross sections include multiple structural features, when calculating the score value of a chapter corresponding to a region feature, the final score value of the chapter can be the average value of the chapter score value obtained by calculation using the cross section score values ​​of the multiple standard cross sections and the score value of the chapter corresponding to the region feature. To explain by way of example, please refer to the detailed explanation of the score value relationship between the standard cross sections and the structural features included in the standard cross sections in the previous example, and detailed explanation will be omitted here.

[0071] In one alternative embodiment, after performing a chapter division operation on the fetal ultrasound image to obtain at least one target chapter, the method further includes: determining the total number of frames of all sub-fetal ultrasound images included in each target chapter; Then, after calculating the score value of each target chapter based on the parameters of the target features of the sub-fetal ultrasound images of each frame included in each target chapter, the method further comprises: Dividing the score value of each target chapter by the total number of frames of all sub-fetal ultrasound images included in the target chapter to obtain a target score value of the target chapter; updating the score value of each target chapter to the target score value of the target chapter, and triggering the execution of step 103.

[0072] For example, if the number of fetal ultrasound images included in the chapter corresponding to the gastric bubble structure feature class is 100 frames and the score value of the chapter corresponding to the gastric bubble structure feature class is 180, 180 is divided by 100 to obtain 1.8 as the score value of the chapter, and then the score value of the chapter corresponding to the gastric bubble structure feature class is updated to 1.8.

[0073] As can be seen from the above, after obtaining the score value of a chapter, this optional embodiment further obtains a new score value for the chapter based on the score value of the chapter and the total number of frames of the chapter, and updates the imaging score value of the fetal ultrasound image to the new score value, which can further improve the accuracy of determining the imaging score value of the fetal ultrasound image, and further contributes to improving the accuracy of determining the imaging quality of the fetal ultrasound image.

[0074] In another optional embodiment of the present invention, determining an imaging score value for the fetal ultrasound image based on the parameters of the fetal ultrasound image may include: If the parameters of the fetal ultrasound image are regional feature parameters of the fetal ultrasound image, the regional feature parameters of the fetal ultrasound image include regional feature score values ​​of the fetal ultrasound image, and the regional feature score values ​​of the fetal ultrasound image are determined as the imaging score values ​​of the fetal ultrasound image; and / or If the parameters of the fetal ultrasound image are structural feature parameters of the fetal ultrasound image, the structural feature parameters of the fetal ultrasound image include class probabilities of structural features of the fetal ultrasound image, location probabilities of the structural features, and weight values ​​of the structural features; Calculate a structural feature score value of the structural feature of the fetal ultrasound image based on the class probability of the structural feature, the location probability of the structural feature, and the weight value of the structural feature, and determine the structural feature score value as an imaging score value of the fetal ultrasound image; and / or When the parameters of the fetal ultrasound image are feature parameters of the fetal ultrasound image, the structural feature parameters of the fetal ultrasound image include class probabilities of the structural features of the fetal ultrasound image, position probabilities of the structural features, and weight values ​​of the structural features, and the regional feature parameters of the fetal ultrasound image include class probabilities of the regional features of the fetal ultrasound image; Calculating a structural feature score value of the structural feature based on the class probability of the regional feature of the fetal ultrasound image, the class probability of the structural feature of the fetal ultrasound image, the position probability of the structural feature, and the weight value of the structural feature, and determining the structural feature score value as an imaging score value of the fetal ultrasound image; and / or determining a standard cross section of the fetal ultrasound image based on the class probability of the regional feature of the fetal ultrasound image and the class probability of the structural feature of the fetal ultrasound image, and calculating a cross section score value of the standard cross section of the fetal ultrasound image as an imaging score value of the fetal ultrasound image based on parameters of the structural feature in the standard cross section of the fetal ultrasound image, wherein the structural feature parameters of the fetal ultrasound image include parameters of the structural feature in the standard cross section of the fetal ultrasound image.

[0075] As can be seen from the above, the embodiments of the present invention can further realize the calculation of the score value of the fetal ultrasound image by respectively calculating the regional feature score value, the structural feature score value, and the standard cross-section score value of the fetal ultrasound image, which not only enriches the method of determining the score value of the fetal ultrasound image, but also improves the accuracy of determining the imaging quality of the fetal ultrasound image, thereby further realizing the accurate and rapid control of the imaging quality of the fetal ultrasound image.

[0076] 103, determining the imaging quality of the fetal ultrasound image based on the imaging score value of the fetal ultrasound image.

[0077] In an embodiment of the present invention, as a further option, the imaging score value of the fetal ultrasound image is stored, thereby contributing to optimizing the imaging quality determination server based on the imaging score value, and further contributing to obtaining higher quality fetal ultrasound images.

[0078] In an embodiment of the present invention, the structural features of the standard slice of the fetal ultrasound image include at least the important structural features of the standard slice, and may further include other structural features. After obtaining the standard slice of the fetal ultrasound image, it is determined whether the standard slice is a normal standard slice or a pseudo-standard slice based on the structural features included in the standard slice. For example, in the case of an abdominal standard slice, if the important structural features are the stomach bubble and umbilical vein, and the other structural features are the liver, descending aorta, ribs, and inferior vena cava, and the abdominal standard slice not only includes the important structural features of the stomach bubble and umbilical vein but also includes other structural features of the liver, descending aorta, ribs, and inferior vena cava, the abdominal standard slice is determined to be a normal standard slice. On the other hand, if the abdominal standard slice includes the important structural features of the stomach bubble and umbilical vein but does not include at least one structural feature of the liver, descending aorta, ribs, and inferior vena cava, the abdominal standard slice is determined to be a pseudo-standard slice.

[0079] As can be seen from the above, by implementing the determination method for controlling the imaging quality of fetal ultrasound images described in Figure 1, the imaging quality of the fetal ultrasound image can be determined quickly and accurately by automatically determining the imaging quality of the fetal ultrasound image based on the determined imaging score value of the fetal ultrasound image, thereby realizing precise and quick control of the imaging quality of the fetal ultrasound image, and further contributing to obtaining high-quality fetal ultrasound images and accurately capturing the growth and development status of the fetus. The determined imaging quality of the fetal ultrasound image can also help practitioners to know whether the standardization of the fetal ultrasound image detection process and the detection of items that need to detect the fetus have been completed.

[0080] Example 2 Referring to Figure 2, Figure 2 is a flowchart of another method for determining imaging quality control of fetal ultrasound images disclosed in an embodiment of the present invention. The method for determining imaging quality control of fetal ultrasound images described in Figure 2 may be applied to an imaging quality determination server (service device), which may include a local imaging quality determination server or a cloud imaging quality determination server, and the embodiment of the present invention is not limited thereto. As shown in Figure 2, the method for determining imaging quality control of fetal ultrasound images may include the following operations: 201, obtaining parameters of the fetal ultrasound image for determining the imaging quality of the fetal ultrasound image; 202, determining an imaging score value for the fetal ultrasound image based on the parameters of the fetal ultrasound image. 203, determining a detection result corresponding to the fetal ultrasound image.

[0081] In an embodiment of the present invention, the detection results corresponding to the fetal ultrasound image are used to determine the imaging quality of the fetal ultrasound image, and include at least one of feature detection results, biological pathway detection results, and Doppler blood flow spectrum detection results, and the feature detection results include at least one of region feature detection results, structural feature detection results, and standard cross-section detection results, and the embodiments of the present invention are not limited.

[0082] In an embodiment of the present invention, the feature detection result indicates whether the detection of the features to be detected is complete, i.e., whether the detection of at least one of the site features, structural features, and standard cross sections to be detected is complete.

[0083] In one alternative embodiment, after performing step 203, the method further comprises: determining whether the determined detection requirement is met based on the detection result corresponding to the fetal ultrasound image; If the determination result is YES, triggering step 204 to be executed; If the determination result is NO, generating a detection presentation of the fetal ultrasound image and outputting the detection presentation. In the alternative embodiment, the detection indication is for indicating at least one of the presence of an undetected feature (e.g., the humerus long axis cross section is not detected), the biological pathway of the fetal ultrasound image is not detected, and the Doppler blood flow spectrum of the fetal ultrasound image is not detected, and the detection indication is for presenting to a person authorized to detect the undetected content.

[0084] In the alternative embodiment, step 204 may optionally be triggered to be performed after outputting the detection suggestion.

[0085] As can be seen from the above, in this optional embodiment, when detecting the acquired fetal ultrasound image, first determine whether the detection result meets the detection requirements; if YES, perform the subsequent operation of determining the imaging quality of the fetal ultrasound image; if NO, output a detection presentation of the fetal ultrasound image, which can be presented to the authorized person if there is undetected content and can be presented to the authorized person to supervise the operating behavior of the authorized person, making it easier for the authorized person to detect the undetected content, thereby contributing to obtaining an accurate imaging score value of the fetal super-live image, further improving the accuracy of determining the imaging quality of the fetal super-live image, and further realizing accurate and rapid control of the imaging quality of the fetal ultrasound image.

[0086] As can be seen from the above, embodiments of the present invention can further improve the accuracy of determining the imaging quality of fetal ultrasound images by obtaining the detection results of fetal ultrasound images, for example, detecting all standard cross sections that need to be detected and combining the imaging score value of the fetal ultrasound image with the detection results to determine whether the imaging quality of the fetal ultrasound image is determined, thereby further realizing accurate and rapid control of the imaging quality of fetal ultrasound images, further obtaining higher quality fetal ultrasound images, and contributing to obtaining accurate fetal growth and development status.

[0087] In another alternative embodiment, the method further comprises: After obtaining the target feature of the fetal ultrasound image, it is detected whether there is an abnormal feature in the target feature of the fetal ultrasound image. If it is detected that there is an abnormal feature, the chapter at the location of the abnormal feature is determined as the abnormal feature location, and the location includes at least one of a chapter, a standard cross section, and a region.

[0088] The alternative embodiment further optionally includes, after determining the location of the anomaly feature, outputting the location of the anomaly feature to an authorized person.

[0089] For example, if an abnormality of the lateral ventricle (such as cerebral edema) is detected, the chapter in which the lateral ventricle is located is determined as an abnormal chapter, and the abnormal characteristic chapter is output to an authorized person.

[0090] In this selectable embodiment, when there are multiple types of abnormal features, an optimal abnormal feature location, for example, an optimal abnormal feature chapter, is selected from the abnormal feature locations corresponding to the multiple types of abnormal features. Furthermore, when an abnormal feature appears, the score value corresponding to the abnormal feature location is multiplied by a determined coefficient (for example, 10) to obtain a score value corresponding to the abnormal feature location, and the abnormal feature location with the highest score value is obtained as the optimal abnormal feature location.

[0091] In this alternative embodiment, the relevant description of the target features of the fetal ultrasound image may refer to the detailed description of the relevant content in the first embodiment, and the detailed description will be omitted here.

[0092] As can be seen from the above, after detecting the presence of an abnormal feature in a target feature of a fetal ultrasound image, the optional embodiment determines the location of the abnormal feature, for example, the optimal abnormal feature chapter, and outputs the location to an authorized person, facilitating the authorized person to quickly confirm and identify the abnormal feature.

[0093] 204, determining the imaging quality of the fetal ultrasound image based on the imaging score value of the fetal ultrasound image and the feature results corresponding to the fetal ultrasound image.

[0094] In the embodiment of the present invention, for other explanations of steps 201, 202 and 204, refer to the detailed explanation of steps 101 to 103 in the first embodiment, and detailed explanations will be omitted in the embodiment of the present invention.

[0095] As can be seen from the above, when the method for determining imaging quality control of a fetal ultrasound image described in Figure 2 is implemented, the imaging quality of the fetal ultrasound image can be determined quickly and accurately by automatically determining the imaging quality of the fetal ultrasound image based on the determined imaging score value of the fetal ultrasound image, thereby realizing accurate and rapid control of the imaging quality of the fetal ultrasound image and further contributing to obtaining a high-quality fetal ultrasound image and accurately capturing the growth and development status of the fetus. The determined imaging quality of the fetal ultrasound image can also be used to determine whether the practitioner has completed the standardization of the fetal ultrasound image detection process and the detection of items that need to be detected by the fetus. Furthermore, the imaging score value of the fetal ultrasound image can also be combined with the detection result to automatically determine the imaging quality of the fetal ultrasound image, further improving the accuracy of determination of imaging quality control of the fetal ultrasound image, thereby further realizing accurate and rapid control of the imaging quality of the fetal ultrasound image.

[0096] Example 3 An embodiment of the present invention discloses a method for determining an imaging score value of a fetal ultrasound image. The method may be applied to an imaging quality determination server, and the imaging quality determination server may include a local imaging quality determination server or a cloud imaging quality determination server, and the embodiment of the present invention is not limited thereto. The method for determining an imaging score value of a fetal ultrasound image may include the following operations:

[0097] Step 1: Perform a chapter division operation on a fetal ultrasound image to obtain at least one target chapter.

[0098] In an embodiment of the present invention, a fetal ultrasound image is composed of multiple consecutive frames of sub-fetal ultrasound images.

[0099] In an embodiment of the present invention, each target chapter includes a number of consecutive frames of sub-fetal ultrasound images, and all the sub-fetal ultrasound images included in each target chapter are different from each other, and the total number of all the sub-fetal ultrasound images included in each target chapter is equal to the total number of all the sub-fetal ultrasound images included in the fetal ultrasound images.

[0100] Step 2: Calculate the score value of each target chapter based on the target feature parameters of the sub-fetal ultrasound image of each frame included in the target chapter. In an embodiment of the present invention, the target features of the sub-fetal ultrasound image of each frame include at least one of a region feature, a structure feature, and a standard cross section of the sub-fetal ultrasound image.

[0101] Step 3: Determine the score values ​​of all target chapters as the imaging score values ​​of the fetal ultrasound image.

[0102] For other related explanations of steps 1 to 3, please refer to the detailed explanations of the first and second embodiments, and detailed explanations will be omitted in the embodiments of the present invention.

[0103] As can be seen from the above, by implementing this method for determining the imaging score value of a fetal ultrasound image, the fetal ultrasound image can be automatically divided into chapters of different classes, and the calculated score value of each chapter can be used as the imaging score value of the fetal ultrasound image, thereby improving the accuracy and efficiency of obtaining the imaging score value of the fetal ultrasound image, thereby improving the accuracy and reliability of determining the imaging quality of the fetal ultrasound image, contributing to realizing accurate and rapid control of the imaging quality of the fetal ultrasound image, further contributing to obtaining high-quality fetal ultrasound images, and contributing to improving the accuracy and reliability of determining the growth and development status of the fetus.

[0104] Example 4 Referring to Figure 3, Figure 3 is a structural schematic diagram of a determination device for imaging quality control of fetal ultrasound images disclosed in an embodiment of the present invention. The determination device for imaging quality control of fetal ultrasound images described in Figure 3 may be applied to an imaging quality determination server (service device), which may include a local imaging quality determination server or a cloud imaging quality determination server, and the embodiment of the present invention is not limited thereto. As shown in Figure 3, the determination device for imaging quality control of fetal ultrasound images may include an acquisition module 301, a first determination module 302, and a second determination module 303.

[0105] The acquisition module 301 is for acquiring parameters of a fetal ultrasound image for determining the imaging quality of the fetal ultrasound image.

[0106] The first determination module 302 is for determining an imaging score value of the fetal ultrasound image based on parameters of the fetal ultrasound image.

[0107] The second determination module 303 is for determining the imaging quality of the fetal ultrasound image based on the imaging score value of the fetal ultrasound image.

[0108] As can be seen from the above, by implementing the determination device for controlling the imaging quality of fetal ultrasound images described in Figure 3, the imaging quality of the fetal ultrasound image can be determined quickly and accurately by automatically determining the imaging quality of the fetal ultrasound image based on the determined imaging score value of the fetal ultrasound image, thereby realizing precise and quick control of the imaging quality of the fetal ultrasound image, and further contributing to obtaining high-quality fetal ultrasound images and accurately capturing the growth and development status of the fetus. The determined imaging quality of the fetal ultrasound image can also help practitioners to know whether the standardization of the fetal ultrasound image detection process and the detection of items that need to be detected by the fetus have been completed.

[0109] In one alternative embodiment, the manner in which the acquisition module 301 acquires the parameters of the fetal ultrasound image is specifically as follows: A fetal ultrasound image is input into the determined parameter determination model for analysis, and the analysis result output from the parameter determination model is obtained as parameters of the fetal ultrasound image, wherein the parameter determination model includes a feature determination model and / or a cross-section determination model, and if the parameter determination model is a feature determination model, the parameters of the fetal ultrasound image include feature parameters of the fetal ultrasound image, and the feature parameters of the fetal ultrasound image include region feature parameters and / or structure feature parameters of the fetal ultrasound image, and if the parameter determination model is a cross-section determination model, the parameters of the fetal ultrasound image include cross-section parameters of the fetal ultrasound image, and the cross-section parameters of the fetal ultrasound image include cross-section score values ​​of standard cross-sections of the fetal ultrasound image, and / or Parameters of the fetal ultrasound image sent by the determined terminal device and / or input by an authorized person are received as parameters of the fetal ultrasound image, the parameters of the fetal ultrasound image including feature parameters and / or cross-section parameters of the fetal ultrasound image, the feature parameters of the fetal ultrasound image including region feature parameters and / or structure feature parameters of the fetal ultrasound image, and the cross-section parameters of the fetal ultrasound image including cross-section score values ​​of standard cross-sections of the fetal ultrasound image.

[0110] As can be seen from the above, by implementing the determination device described in Figure 3, the fetal ultrasound image can be further input into the parameter determination model for analysis, thereby quickly realizing automatic acquisition of the parameters of the fetal ultrasound image, and improving the accuracy and reliability of parameter acquisition of the fetal ultrasound image without the need for human intervention, thereby improving the accuracy and efficiency of determining the imaging score value of the fetal ultrasound image, and the parameters of the fetal ultrasound image can be acquired by being transmitted by the terminal device and / or input by an authorized person, thereby enriching the methods of acquiring parameters of the fetal ultrasound image.

[0111] In another alternative embodiment, the fetal ultrasound image is composed of a plurality of consecutive frames of sub-fetal ultrasound images, and as shown in Figure 4, the first determination module 302 may include a division sub-module 3021, a calculation sub-module 3022 and a determination sub-module 3023; The division sub-module 3021 is for performing a chapter division operation on the fetal ultrasound image to obtain at least one target chapter, where each target chapter includes a number of consecutive frames of sub-fetal ultrasound images, and all the sub-fetal ultrasound images included in each target chapter are different from each other, and the total number of all the sub-fetal ultrasound images included in each target chapter is equal to the total number of all the sub-fetal ultrasound images included in the fetal ultrasound image.

[0112] The calculation sub-module 3022 is for calculating a score value of each target chapter based on parameters of the target features of the sub-fetal ultrasound image of each frame included in each target chapter, and the target features of the sub-fetal ultrasound image of each frame include at least one of regional features, structural features and standard cross sections of the sub-fetal ultrasound image.

[0113] The determining sub-module 3023 is for determining the score values ​​of all the target chapters as the imaging score values ​​of the fetal ultrasound image.

[0114] In this alternative embodiment, the fetal ultrasound image corresponds to at least one target class, the target class including a feature class or a cross-section class, and the number of target features corresponding to each target class is one or more. If the target class is a feature class, the target feature includes a structure feature or a region feature, and if the target class is a cross-section class, the target feature includes a standard cross-section. Each target class corresponds to at least one frame of sub-fetal ultrasound image, and all the sub-fetal ultrasound images corresponding to each target class are different from each other, and all the sub-fetal ultrasound images corresponding to all the target classes constitute a fetal ultrasound image.

[0115] As can be seen from the above, by implementing the determination device described in Figure 4, the fetal ultrasound image can be automatically divided into chapters of different classes, and the calculated score value of each chapter can be used as the imaging score value of the fetal ultrasound image, thereby improving the accuracy and efficiency of obtaining the imaging score value of the fetal ultrasound image, thereby contributing to improving the accuracy and reliability of determining the imaging quality of the fetal ultrasound image, and further contributing to obtaining high-quality fetal ultrasound images.

[0116] In another optional embodiment, as shown in FIG. 4, the manner in which the division sub-module 3021 performs the chapter division operation on the fetal ultrasound image to obtain at least one target chapter is specifically as follows: determining the location of a sub-fetal ultrasound image of a start frame corresponding to each target class included in the fetal ultrasound image and the location of a sub-fetal ultrasound image of an end frame corresponding to the target class; determining, as target chapters corresponding to each target class, a sub-fetal ultrasound image of a start frame corresponding to each target class, a sub-fetal ultrasound image of an end frame corresponding to the target class, and all sub-fetal ultrasound images between the determined location of the sub-fetal ultrasound image of the start frame corresponding to the target class and the location of the sub-fetal ultrasound image of the end frame corresponding to the target class; The location of the sub-fetal ultrasound image of the start frame corresponding to each target class is the location where a sub-fetal ultrasound image containing target features of that target class first appears in the fetal ultrasound image, and the location of the sub-fetal ultrasound image of the end frame corresponding to each target class is the location where a sub-fetal ultrasound image containing target features of that target class last appears in the fetal ultrasound image, or the location of a sub-fetal ultrasound image that appears a predetermined number of frames consecutively from the sub-fetal ultrasound image of the start frame containing target features of that target class in the fetal ultrasound image.

[0117] As can be seen from the above, by implementing the determination device described in Figure 4, it is possible to automatically determine the location of the fetal ultrasound image of the start frame and the location of the fetal ultrasound image of the end frame of each type of regional feature or structural feature or standard cross section, thereby realizing automatic determination of the chapters corresponding to each type of regional feature or structural feature or standard cross section, which contributes to improving the efficiency and accuracy of determining each chapter, and thereby contributing to improving the efficiency and accuracy of calculating the score value of each chapter.

[0118] In another alternative embodiment, as shown in FIG. 4 , the calculation submodule 3022 calculates the score value of each target chapter based on the target feature parameters of the sub-fetal ultrasound image of each frame included in the target chapter, specifically as follows: If the target feature of the sub-fetal ultrasound image of each frame is a regional feature of the sub-fetal ultrasound image, calculate the sum of the regional feature score values ​​of the regional features of the sub-fetal ultrasound image of each frame included in each target chapter as the score value of the target chapter; If the target features of the sub-fetal ultrasound image of each frame are structural features of the sub-fetal ultrasound image, calculate a score value of the target chapter based on the class probability of the structural features of the sub-fetal ultrasound image of each frame included in each target chapter, the position probability of the structural features, and the weight value of the structural features; When the target feature of the sub-fetal ultrasound image of each frame is a standard cross section of the sub-fetal ultrasound image, the sum of the cross section score values ​​of the standard cross sections of the sub-fetal ultrasound image of each frame included in each target chapter is calculated as the score value of the target chapter.

[0119] As can be seen from the above, by implementing the determination device described in Figure 4, it is possible to not only determine the chapter score values ​​by calculating the structural feature score values ​​corresponding to each type of structural feature, or the cross-section score values ​​corresponding to each type of cross-section, or the region feature score values ​​corresponding to each type of region feature, but also to enrich the methods for determining the chapter score values, thereby improving the accuracy and reliability of determining the chapter score values. Furthermore, the chapter score values ​​obtained by the structural feature score values, the chapter score values ​​obtained by the region feature score values, together with the chapter score values ​​obtained by the cross-section score values, determine the imaging quality of the fetal ultrasound image, thereby further improving the accuracy and reliability of determining the imaging quality of the fetal ultrasound image, thereby further contributing to obtaining higher quality fetal ultrasound images.

[0120] In another alternative embodiment, as shown in FIG. 4, the device further comprises a calculation module 304 and an update module 305; The determining sub-module 3023 is further for determining the total number of frames of all sub-fetal ultrasound images included in each target chapter after the dividing sub-module 3021 performs the chapter dividing operation on the fetal ultrasound images to obtain at least one target chapter; The calculation module 304 is for, after the first determination module 302 calculates the score value of each target chapter based on the parameters of the target features of the sub-fetal ultrasound images of each frame included in each target chapter, dividing the score value of each target chapter by the total number of frames of all sub-fetal ultrasound images included in the target chapter to obtain the target score value of the target chapter.

[0121] The update module 305 is for updating the score value of each target chapter to the target score value of the target chapter, and triggering the second determination module 303 to perform the above operation of determining the score values ​​of all target chapters as the imaging score values ​​of the fetal ultrasound image.

[0122] In this optional embodiment, after the division sub-module 3021 performs a chapter division operation on the fetal ultrasound image to obtain at least one target chapter, the determination sub-module 3023 may be triggered to perform the above operation of determining the total number of frames of all sub-fetal ultrasound images included in each target chapter.

[0123] As can be seen from the above, by implementing the determination device described in Figure 4, after obtaining the score value of the chapter, a new score value of the chapter is obtained based on the score value of the chapter and the total number of frames of the chapter, and the imaging score value of the fetal ultrasound image is updated to the new score value, thereby further improving the accuracy of determining the imaging score value of the fetal ultrasound image, and further contributing to improving the accuracy of determining the imaging quality of the fetal ultrasound image.

[0124] In another optional embodiment, as shown in FIG. 4 , the manner in which the first determination module 302 determines the imaging score value of the fetal ultrasound image based on the parameters of the fetal ultrasound image is specifically: If the parameters of the fetal ultrasound image are regional feature parameters of the fetal ultrasound image, the regional feature parameters of the fetal ultrasound image include regional feature score values ​​of the fetal ultrasound image, and the regional feature score values ​​of the fetal ultrasound image are determined as the imaging score values ​​of the fetal ultrasound image; and / or When the parameters of the fetal ultrasound image are structural feature parameters of the fetal ultrasound image, the structural feature parameters of the fetal ultrasound image include: a class probability of the structural feature of the fetal ultrasound image, a location probability of the structural feature, and a weight value of the structural feature; Calculate a structural feature score value of the structural feature of the fetal ultrasound image based on the class probability of the structural feature, the location probability of the structural feature, and the weight value of the structural feature, and determine the structural feature score value as an imaging score value of the fetal ultrasound image; and / or When the parameters of the fetal ultrasound image are feature parameters of the fetal ultrasound image, the structural feature parameters of the fetal ultrasound image include class probabilities of the structural features of the fetal ultrasound image, position probabilities of the structural features, and weight values ​​of the structural features, and the regional feature parameters of the fetal ultrasound image include class probabilities of the regional features of the fetal ultrasound image; A structural feature score value of the structural feature is calculated based on the class probability of the regional feature of the fetal ultrasound image, the class probability of the structural feature of the fetal ultrasound image, the position probability of the structural feature, and the weight value of the structural feature, and the structural feature score value is determined as an imaging score value of the fetal ultrasound image; and / or a standard cross section of the fetal ultrasound image is determined based on the class probability of the regional feature of the fetal ultrasound image and the class probability of the structural feature of the fetal ultrasound image, and a cross section score value of the standard cross section of the fetal ultrasound image is calculated as an imaging score value of the fetal ultrasound image based on parameters of the structural feature in the standard cross section of the fetal ultrasound image, and the structural feature parameters of the fetal ultrasound image include parameters of the structural feature in the standard cross section of the fetal ultrasound image.

[0125] As can be seen from the above, by implementing the determination device described in Figure 4, the score value of the fetal ultrasound image can be calculated by further calculating the regional feature score value, structural feature score value, and standard cross-section score value of the fetal ultrasound image, which not only enriches the method of determining the score value of the fetal ultrasound image, but also improves the accuracy of determining the imaging quality of the fetal ultrasound image, thereby further realizing accurate and rapid control of the imaging quality of the fetal ultrasound image.

[0126] In another alternative embodiment, as shown in FIG. 4, the device further comprises a third determination module 306, the third determination module 306 is for determining a detection result corresponding to the fetal ultrasound image for determining the imaging quality of the fetal ultrasound image before the second determination module 302 determines the imaging quality of the fetal ultrasound image based on the imaging score value of the fetal ultrasound image, and the detection result corresponding to the fetal ultrasound image includes at least one of a feature detection result, a biological pathway detection result, and a Doppler blood flow spectrum detection result, and the feature detection result includes at least one of a region feature detection result, a structure feature detection result, and a standard cross section detection result; The second determination module 302 determines the imaging quality of the fetal ultrasound image based on the imaging score of the fetal ultrasound image in the following manner: The imaging quality of the fetal ultrasound image is determined based on the imaging score value of the fetal ultrasound image and the feature results corresponding to the fetal ultrasound image. As can be seen from the above, by implementing the determination device described in Figure 4, the detection results of the fetal ultrasound image, for example, whether all standard cross sections that should be detected are detected, can be further obtained, and the imaging score value of the fetal ultrasound image can be combined with the detection results to determine the imaging quality of the fetal ultrasound image, thereby further improving the accuracy of determining the imaging quality of the fetal ultrasound image, thereby further realizing accurate and rapid control of the imaging quality of the fetal ultrasound image, further obtaining higher quality fetal ultrasound images, and contributing to obtaining accurate fetal growth and development status.

[0127] Example 5 Referring to Figure 5, Figure 5 is a diagram illustrating another device for determining imaging quality control of fetal ultrasound images disclosed in an embodiment of the present invention. The method for determining imaging quality control of fetal ultrasound images described in Figure 5 can be applied to an imaging quality determination server (service device), which can include a local imaging quality determination server or a cloud imaging quality determination server, and the embodiment of the present invention is not limited thereto. As shown in Figure 5, the device for determining imaging quality control of fetal ultrasound images includes: a memory 501 in which executable program code is stored; a processor 502 coupled to the memory 501; The system may further include an input interface 503 and an output interface 504 coupled to the processor 502; The processor 502 is configured to call executable program code stored in the memory 501 to execute some or all of the steps in the method for determining the imaging quality control of fetal ultrasound images described in Example 1 or Example 2.

[0128] Example 6 An embodiment of the present invention discloses a computer-readable storage medium, on which a computer program for electronic data exchange is stored, and the computer program causes a computer to perform some or all of the steps in the method for determining imaging quality control of fetal ultrasound images described in Example 1 or Example 2.

[0129] Example 7 An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium on which a computer program is stored, and by operating the computer program, a computer can perform some or all of the steps in the method for determining imaging quality control of fetal ultrasound images described in Example 1 or Example 2.

[0130] The above-described device embodiments are merely schematic, and the modules described as separate components may or may not be physically separated, and the components represented as modules may or may not be physical modules. That is, they may be located in one place or may be arranged in multiple network modules. Depending on actual needs, some or all of the modules may be selected to achieve the purpose of the solution of this embodiment. Those skilled in the art can understand and implement this without any creative effort.

[0131] From the specific description of the above examples, those skilled in the art can clearly understand that each embodiment may be realized in the form of software plus a required general-purpose hardware platform, and of course, may also be realized in the form of hardware. Based on this understanding, the essential aspects of the above technical solutions or the parts that contribute to the prior art may be embodied in the form of a software product, and the computer software product may be stored in a computer-readable storage medium, including a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a programmable read-only memory (PROM, Programmable Read-Only Memory), an erasable programmable read-only memory (EPROM, Erasable Programmable Read-Only Memory), a one-time programmable read-only memory (OTPROM, One-time Programmable Read-Only Memory), an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc memory, a magnetic disc memory, a magnetic tape memory, or any other computer-readable medium for carrying or storing data.

[0132] It should be noted that the methods and apparatuses for determining imaging quality control of fetal ultrasound images according to the embodiments of the present invention are only preferred embodiments of the present invention, and are intended to describe the technical solutions of the present invention but are not intended to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art will understand that the technical solutions described in the above embodiments may still be modified or some of the technical features therein may be equivalently replaced, but these modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. 1. A method for determining imaging quality control for fetal ultrasound images, comprising: obtaining parameters of the fetal ultrasound image for determining imaging quality of the fetal ultrasound image, the fetal ultrasound image being composed of a plurality of consecutive frames of sub-fetal ultrasound images; determining an imaging score value for the fetal ultrasound image based on parameters of the fetal ultrasound image, and determining an imaging quality of the fetal ultrasound image based on the imaging score value of the fetal ultrasound image; determining an imaging score value for the fetal ultrasound image based on parameters of the fetal ultrasound image; performing a chapter division operation on the fetal ultrasound images to obtain at least one target chapter, each of the target chapters including a number of consecutive frames of the sub-fetal ultrasound images, and all of the sub-fetal ultrasound images included in each of the target chapters being different from each other; the target feature of the sub-fetal ultrasound image of each frame includes at least one of a region feature, a structure feature, and a standard cross section of the sub-fetal ultrasound image; The parameters of the fetal ultrasound images all include parameters of target features of the sub-fetal ultrasound images, and the parameters of the target features of the sub-fetal ultrasound images of each frame include at least one of regional feature parameters, structural feature parameters, and standard cross-sectional parameters of the sub-fetal ultrasound images; Calculating a score value for each target chapter based on parameters of target features of the sub-fetal ultrasound image of each frame included in the target chapter; When determining the score value of each chapter, (a) The cross-sectional score obtained by directly acquiring the standard cross-section; (b) determining the final score of the chapter by at least one of summing or averaging the structural feature score values ​​of the structural features included in the standard cross section; A method for determining imaging quality control of a fetal ultrasound image, characterized in that score values ​​of all the target chapters are determined as imaging score values ​​of the fetal ultrasound image.

2. Obtaining parameters of fetal ultrasound images is A fetal ultrasound image is input into the determined parameter determination model for analysis, and the analysis results output from the parameter determination model are obtained as parameters of the fetal ultrasound image, wherein the parameter determination model includes a feature determination model and / or a cross section determination model, and when the parameter determination model is the feature determination model, the parameters of the fetal ultrasound image include feature parameters of the fetal ultrasound image, and the feature parameters of the fetal ultrasound image include region feature parameters and / or structure feature parameters of the fetal ultrasound image, and when the parameter determination model is the cross section determination model, the parameters of the fetal ultrasound image include cross section parameters of the fetal ultrasound image, and the cross section parameters of the fetal ultrasound image include cross section score values ​​of standard cross sections of the fetal ultrasound image, and / or The method for determining imaging quality control of a fetal ultrasound image, as described in claim 1, further comprising receiving parameters of a fetal ultrasound image sent by a determined terminal device and / or input by an authorized person as parameters of the fetal ultrasound image, the parameters of the fetal ultrasound image including feature parameters and / or cross-sectional parameters of the fetal ultrasound image, the feature parameters of the fetal ultrasound image including region feature parameters and / or structure feature parameters of the fetal ultrasound image, and the cross-sectional parameters of the fetal ultrasound image including cross-sectional score values ​​of standard cross-sections of the fetal ultrasound image.

3. The fetal ultrasound image corresponds to at least one target class, the target class including a feature class or a cross-section class, and the number of target features corresponding to each target class is one or more; When the target class is the feature class, the target feature includes a structure feature or a part feature; when the target class is the cross-section class, the target feature includes a standard cross-section; A method for determining the imaging quality control of fetal ultrasound images, as described in claim 1 or 2, characterized in that each of the target classes corresponds to at least one frame of the sub-fetal ultrasound image, and all of the sub-fetal ultrasound images corresponding to each of the target classes are different from each other, and all of the sub-fetal ultrasound images corresponding to all of the target classes constitute the fetal ultrasound image.

4. performing a chapter division operation on the fetal ultrasound image to obtain at least one target chapter; determining a location of a sub-fetal ultrasound image of a start frame corresponding to each of the target classes included in the fetal ultrasound image and a location of a sub-fetal ultrasound image of an end frame corresponding to the target class; determining, as target chapters corresponding to each of the target classes, a sub-fetal ultrasound image of a start frame corresponding to each of the target classes, a sub-fetal ultrasound image of an end frame corresponding to each of the target classes, and all sub-fetal ultrasound images between the determined location of the sub-fetal ultrasound image of the start frame corresponding to each of the target classes and the location of the sub-fetal ultrasound image of the end frame corresponding to each of the target classes; The method for determining imaging quality control of fetal ultrasound images described in claim 3, characterized in that the location of the sub-fetal ultrasound image of the start frame corresponding to each of the target classes is the location where a sub-fetal ultrasound image containing target features of the target class first appears in the fetal ultrasound image, and the location of the sub-fetal ultrasound image of the end frame corresponding to each of the target classes is the location where a sub-fetal ultrasound image containing target features of the target class last appears in the fetal ultrasound image, or the location of a sub-fetal ultrasound image that appears a predetermined number of frames consecutively from the sub-fetal ultrasound image of the start frame containing target features of the target class in the fetal ultrasound image.

5. Calculating a score value of each target chapter based on parameters of target features of the sub-fetal ultrasound image of each frame included in the target chapter includes: If the target feature of the sub-fetal ultrasound image of each frame is a regional feature of the sub-fetal ultrasound image, calculating the sum of the regional feature score values ​​of the regional features of the sub-fetal ultrasound image of each frame included in each target chapter as the score value of the target chapter; If the target features of the sub-fetal ultrasound image of each frame are structural features of the sub-fetal ultrasound image, calculating a score value of the target chapter based on the class probability of the structural features of the sub-fetal ultrasound image of each frame included in each target chapter, the position probability of the structural features, and the weight value of the structural features; A method for determining imaging quality control of fetal ultrasound images as described in claim 1 or 2, characterized in that when the target feature of the sub-fetal ultrasound image of each frame is a standard cross-section of the sub-fetal ultrasound image, the sum of the cross-section score values ​​of the standard cross-sections of the sub-fetal ultrasound image of each frame included in each target chapter is calculated as the score value of the target chapter.

6. After performing a chapter division operation on the fetal ultrasound image to obtain at least one target chapter, the determining method further includes: determining a total number of frames of all the sub-fetal ultrasound images included in each of the target chapters; Then, after calculating the score value of each target chapter based on the parameters of the target features of the sub-fetal ultrasound images of each frame included in each target chapter, the determination method further includes: Dividing the score value of each target chapter by the total number of frames of all the sub-fetal ultrasound images included in the target chapter to obtain a target score value of the target chapter; A method for determining imaging quality control of a fetal ultrasound image as described in claim 1 or 2, characterized in that it includes triggering to execute the division operation, which updates the score value of each target chapter to the target score value of the target chapter and determines the score values ​​of all the target chapters as imaging score values ​​of the fetal ultrasound image.

7. determining an imaging score value for the fetal ultrasound image based on parameters of the fetal ultrasound image; If the parameters of the fetal ultrasound image are regional feature parameters of the fetal ultrasound image, the regional feature parameters of the fetal ultrasound image include regional feature score values ​​of the fetal ultrasound image, and the regional feature score values ​​of the fetal ultrasound image are determined as the imaging score values ​​of the fetal ultrasound image; and / or If the parameters of the fetal ultrasound image are structural feature parameters of the fetal ultrasound image, the structural feature parameters of the fetal ultrasound image include class probabilities of structural features of the fetal ultrasound image, location probabilities of the structural features, and weight values ​​of the structural features; Calculating a structural feature score value of the structural feature of the fetal ultrasound image based on the class probability of the structural feature, the location probability of the structural feature, and the weight value of the structural feature, and determining the structural feature score value as an imaging score value of the fetal ultrasound image; and / or When the parameters of the fetal ultrasound image are feature parameters of the fetal ultrasound image, the structural feature parameters of the fetal ultrasound image include class probabilities of structural features of the fetal ultrasound image, position probabilities of the structural features, and weight values ​​of the structural features, and the regional feature parameters of the fetal ultrasound image include class probabilities of regional features of the fetal ultrasound image; 3. The method for determining imaging quality control of a fetal ultrasound image according to claim 2, further comprising: calculating a structural feature score value of the structural feature based on the class probability of the regional feature of the fetal ultrasound image, the class probability of the structural feature of the fetal ultrasound image, the position probability of the structural feature, and the weight value of the structural feature; and determining the structural feature score value as the imaging score value of the fetal ultrasound image; and / or determining a standard slice of the fetal ultrasound image based on the class probability of the regional feature of the fetal ultrasound image and the class probability of the structural feature of the fetal ultrasound image; and calculating a slice score value of the standard slice of the fetal ultrasound image as the imaging score value of the fetal ultrasound image based on parameters of the structural feature in the standard slice of the fetal ultrasound image, wherein the structural feature parameters of the fetal ultrasound image include parameters of the structural feature in the standard slice of the fetal ultrasound image.

8. Before determining the imaging quality of the fetal ultrasound image based on the imaging score value of the fetal ultrasound image, the method further comprises: determining a detection result corresponding to the fetal ultrasound image, the detection result corresponding to the fetal ultrasound image being for determining an imaging quality of the fetal ultrasound image, the detection result including at least one of a feature detection result, a biological pathway detection result, and a Doppler blood flow spectrum detection result, and the feature detection result including at least one of a region feature detection result, a structure feature detection result, and a standard plane detection result; and determining an imaging quality of the fetal ultrasound image based on an imaging score value of the fetal ultrasound image, A method for determining imaging quality control of a fetal ultrasound image, as described in any one of claims 1, 2, 4 and 7, characterized in that it includes determining the imaging quality of the fetal ultrasound image based on an imaging score value of the fetal ultrasound image and feature results corresponding to the fetal ultrasound image.

9. 1. An apparatus for determining imaging quality control of fetal ultrasound images, comprising: an acquisition module for acquiring parameters of the fetal ultrasound image for determining imaging quality of the fetal ultrasound image, the fetal ultrasound image being composed of a plurality of consecutive frames of sub-fetal ultrasound images; a first determination module for determining an imaging score value of the fetal ultrasound image based on parameters of the fetal ultrasound image; a second determination module for determining an imaging quality of the fetal ultrasound image based on an imaging score value of the fetal ultrasound image; The first determination module: a division sub-module for performing a chapter division operation on the fetal ultrasound images to obtain at least one target chapter, each of the target chapters including a number of consecutive frames of the sub-fetal ultrasound images, and all the sub-fetal ultrasound images included in each of the target chapters being different from each other; and calculating a score value for each of the target chapters based on parameters of target features of the sub-fetal ultrasound image of each frame included in each of the target chapters, wherein the target features of the sub-fetal ultrasound image of each frame include at least one of regional features, structural features, and standard cross sections of the sub-fetal ultrasound image; a calculation sub-module, wherein the parameters of the fetal ultrasound images all include parameters of target features of the sub-fetal ultrasound images, and the parameters of the target features of the sub-fetal ultrasound images of each frame include at least one of regional feature parameters, structural feature parameters, and standard cross-sectional parameters of the sub-fetal ultrasound images; The calculation sub-module, when determining the score value of each chapter, (a) the cross-section score obtained by directly acquiring the standard cross-section; and (b) the sum or average of the structural feature scores of the structural features included in said standard cross section; a determination submodule for determining the score values ​​of all the target chapters as imaging score values ​​of the fetal ultrasound image, the determination device for imaging quality control of fetal ultrasound images comprising: a determination submodule for determining the final score of the chapter based on at least one of the above; and

Images