Output control method, device and system for detecting results of fetal ultrasound images

Through the intelligent detection system, the fetal ultrasound image is analyzed and output feature identification is solved, and the problem of inaccurate fetal ultrasound image detection results in the prior art is achieved, and rapid and accurate determination of fetal growth and development is achieved.

CN112215806BActive Publication Date: 2024-11-19GUANGZHOU AIYUNJI INFORMATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202011016791.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-09-24
Publication Date
2024-11-19
Estimated Expiration
2040-09-24

AI Technical Summary

Technical Problem

In the prior art, the accuracy of fetal ultrasound imaging detection results is affected by factors such as staff's limited experience and fatigue, which makes it impossible to accurately determine the growth and development of the fetus.

Method used

Using an intelligent detection system, fetal ultrasound image is input into the image analysis model for analysis, obtain detection results, and output detection marks of features through the output terminal, including characteristics to be detected, detected, normal, suspected and abnormal, to reduce feature missed detection and improve Detection accuracy.

Benefits of technology

It realizes the rapid acquisition of accurate detection results of fetal ultrasound images, reduces feature missed detection, and improves the accurate determination of fetal growth and development.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112215806B_ABST
    Figure CN112215806B_ABST
Patent Text Reader

Abstract

The present invention discloses an output control method, device and system for the detection results of fetal ultrasound images. The method includes inputting the received fetal ultrasound image into a determined image analysis model for analysis, and obtaining the analysis result output by the image analysis model as the detection result of the fetal ultrasound image, and controlling the output terminal to output the detection result. The detection result includes the detection result of each feature of the fetal ultrasound image, including the detection identifier of the feature. The detection identifier corresponding to each feature is used to indicate that the feature is one of a feature to be detected, a detected and normal feature, a detected and suspected feature, and a detected and abnormal feature. The detected and suspected feature is a feature that has been detected and has an uncertain category, and the detected and abnormal feature is a feature that has been detected and has abnormal structural features. It can be seen that the implementation of the present invention can quickly obtain accurate detection results of the features of the fetal ultrasound image, which is conducive to accurately determining the growth and development of the fetus.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to an output control method, device and system for detecting results of fetal ultrasound images. Background Art

[0002] With the progress of society and the strengthening of people's awareness of obtaining healthy newborns, more and more pregnant women are obtaining information about the growth and development of their fetuses through regular prenatal examinations.

[0003] The current method for obtaining the growth and development of the fetus is to use the principle of ultrasound to collect echoes, display the fetal tomographic image on the screen, and after obtaining the dynamic image of the fetus, the staff with relevant experience will analyze the test results of the fetal ultrasound image based on their own experience to determine the growth and development of the fetus. However, it has been found in practice that due to the limited experience and / or fatigue of the staff, it is easy to fail to obtain high-accuracy fetal ultrasound image test results, and thus fail to accurately determine the growth and development of the fetus. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide an output control method, device and system for fetal ultrasound image detection results, which can obtain accurate fetal ultrasound image detection results to accurately determine the growth and development of the fetus.

[0005] In order to solve the above technical problems, the first aspect of the present invention discloses a method for controlling the output of detection results of fetal ultrasound images, which is applied in an intelligent detection system and comprises:

[0006] The intelligent detection system inputs the received fetal ultrasound image into the determined image analysis model for analysis, and obtains the analysis result output by the image analysis model as the detection result of the fetal ultrasound image;

[0007] The intelligent detection system controls an output terminal corresponding to the intelligent detection system to output the detection result;

[0008] Among them, the detection results include detection results of multiple features of the fetal ultrasound image, and the detection result of each feature includes a detection identifier of the feature. The detection identifier corresponding to each feature is used to indicate that the feature is one of the features to be detected, the detected and normal feature, the detected and suspected feature, and the detected and abnormal feature. The detected and suspected feature is a feature that has been detected and the category is uncertain, and the detected and abnormal feature is a feature that has been detected and has abnormal structural features.

[0009] As an optional embodiment, in the first aspect of the present invention, the method further comprises:

[0010] The intelligent detection system determines whether there is a determined key detection feature among all the features according to the target information of all the features included in the fetal ultrasound image;

[0011] When it is determined that at least one of the key detection features exists among all the features included in the fetal ultrasound image, the intelligent detection system controls the output terminal to output a cross-sectional schematic diagram corresponding to each of the key detection features, wherein the cross-sectional schematic diagram corresponding to each of the key detection features includes an output identifier of each structural feature in the standard cross-sectional diagram corresponding to the key detection feature;

[0012] The intelligent detection system determines the detection status of the structural feature corresponding to the output identifier according to the change status of each output identifier included in the cross-section schematic diagram corresponding to each key detection feature;

[0013] Among them, for any of the key detection features, when the change of each of the output identifiers included in the cross-section schematic diagram corresponding to the key detection feature is used to indicate that the output identifier changes from a first state to a second state, the detection status of the structural feature corresponding to each of the output identifiers is used to indicate that the structural feature is detected in the corresponding standard cross-section.

[0014] As an optional embodiment, in the first aspect of the present invention, the output interface of the output terminal includes a first area and a second area, the first area is used to output the detection result, and the second area is used to output a list of features to be checked and a list of checked features corresponding to the fetal ultrasound image, the list of features to be checked is used to store multiple features to be checked of the fetal ultrasound image, and the list of checked features is used to store multiple checked features of the fetal ultrasound image, and the categories of all features to be checked included in the list of features to be checked include the categories of all checked features included in the list of checked features, and the categories of the multiple features included in the fetal ultrasound image include the categories of all features to be checked included in the list of features to be checked.

[0015] As an optional implementation, in the first aspect of the present invention, all of the features included in the fetal ultrasound image include multiple structural features of the fetal ultrasound image, the detection result of each of the features also includes a feature parameter of the feature, and the feature parameter of each of the features includes category information of the feature;

[0016] Furthermore, after the intelligent detection system obtains the analysis result output by the image analysis model as the detection result of the fetal ultrasound image, the method further includes:

[0017] The intelligent detection system determines the part feature of the frame of the fetal ultrasound image where each of the structural features included in the fetal ultrasound image is located, and determines the feature parameter of each of the part features, wherein the feature parameter of each of the part features includes the category information of the part feature;

[0018] The intelligent detection system determines the standard section of each feature according to the category information of each feature and the category information of the part feature corresponding to the feature, and the detection result of each feature also includes the detection result of the standard section of the feature.

[0019] As an optional implementation, in the first aspect of the present invention, after the intelligent detection system obtains the analysis result output by the image analysis model as the detection result of the fetal ultrasound image, the method further includes:

[0020] The intelligent detection system determines whether a playback request triggered for a fetal ultrasound image corresponding to a certain target feature category is detected, the playback request is used to request the playback of the fetal ultrasound image corresponding to the target feature category, and the fetal ultrasound image corresponding to the target feature category includes at least one of an optimal frame fetal ultrasound image corresponding to the target feature category, fetal ultrasound images of all standard sections corresponding to the target feature category, and fetal ultrasound images of all chapters corresponding to the target feature category, the fetal ultrasound image includes the fetal ultrasound image corresponding to the target feature category, the target feature category includes a target structural feature category and / or a target standard section category, and the category of the standard section of each fetal ultrasound image included in each chapter is the same;

[0021] When the judgment result is yes, the intelligent detection system determines the fetal ultrasound image corresponding to the target feature category according to the playback request, and controls the output terminal to play back the fetal ultrasound image corresponding to the target feature category.

[0022] As an optional implementation, in the first aspect of the present invention, the intelligent detection system determines the fetal ultrasound image corresponding to the target feature category according to the playback request, including:

[0023] When the fetal ultrasound image corresponding to the target feature category is the optimal frame fetal ultrasound image corresponding to the target feature category, the intelligent detection system determines a section score of each of the standard sections among all the standard sections corresponding to the target feature category;

[0024] The intelligent detection system determines, based on the section score of each of the standard sections among all the standard sections corresponding to the target feature category, a frame fetal ultrasound image corresponding to the standard section with the highest section score from all the standard sections as the optimal frame fetal ultrasound image corresponding to the target feature category.

[0025] As an optional implementation, in the first aspect of the present invention, the intelligent detection system determines, according to the section score of each of the standard sections in all the standard sections corresponding to the target feature category, a frame fetal ultrasound image corresponding to the standard section corresponding to the highest section score from all the standard sections as the optimal frame fetal ultrasound image corresponding to the target feature category, before the method further includes:

[0026] When the target feature category is the target structural feature category, the intelligent detection system determines whether the target feature category corresponds to at least two matching feature categories, and the at least two matching feature categories include at least two matching standard section categories or at least two matching chapter categories;

[0027] When the judgment result is no, triggering the execution of the operation of determining, according to the section score of each of the standard sections among all the standard sections corresponding to the target feature category, a frame fetal ultrasound image corresponding to the standard section corresponding to the highest section score from all the standard sections as the optimal frame fetal ultrasound image corresponding to the target feature category;

[0028] When the judgment result is yes, the intelligent detection system determines the section score of each of the standard sections among all the standard sections corresponding to each of the matching feature categories corresponding to the target feature category, and according to the section score of each of the standard sections corresponding to each of the matching feature categories, screens the frame fetal ultrasound image corresponding to the highest section score from all the standard sections, and determines the frame fetal ultrasound image corresponding to all the matching feature categories as the optimal frame fetal ultrasound image corresponding to the target feature category, and the number of optimal frame fetal ultrasound images corresponding to the target feature category is greater than 1.

[0029] As an optional implementation, in the first aspect of the present invention, after the intelligent detection system obtains the analysis result output by the image analysis model as the detection result of the fetal ultrasound image, the method further includes:

[0030] The intelligent detection system determines whether there is an abnormal feature among all the features included in the fetal ultrasound image, and when the determination result is yes, screens all the abnormal features from all the features included in the fetal ultrasound image;

[0031] The intelligent detection system sorts all the abnormal features according to the determined sorting method to obtain all the sorted abnormal features, and controls the output terminal to output all the sorted abnormal features.

[0032] The second aspect of the present invention discloses an output control device for detecting results of fetal ultrasound images, the device is applied in an intelligent detection system, and the device comprises:

[0033] An analysis module, used for inputting the received fetal ultrasound image into the determined image analysis model for analysis;

[0034] An acquisition module, used for acquiring the analysis result output by the image analysis model as the detection result of the fetal ultrasound image;

[0035] A control module, used to control an output terminal corresponding to the intelligent detection system to output the detection result;

[0036] Among them, the detection results include detection results of multiple features of the fetal ultrasound image, and the detection result of each feature includes a detection identifier of the feature. The detection identifier corresponding to each feature is used to indicate that the feature is one of the features to be detected, the detected and normal feature, the detected and suspected feature, and the detected and abnormal feature. The detected and suspected feature is a feature that has been detected and the category is uncertain, and the detected and abnormal feature is a feature that has been detected and has abnormal structural features.

[0037] As an optional implementation, in the second aspect of the present invention, the device further includes:

[0038] A first judgment module is used to judge whether there is a determined key detection feature among all the features according to the target information of all the features included in the fetal ultrasound image;

[0039] The control module is further configured to control the output terminal to output a cross-sectional schematic diagram corresponding to each of the key detection features when the first judgment module judges that at least one of the key detection features exists among all of the features included in the fetal ultrasound image, wherein the cross-sectional schematic diagram corresponding to each of the key detection features includes an output identifier of each structural feature in the standard cross-sectional diagram corresponding to the key detection feature;

[0040] A first determination module, configured to determine the detection status of the structural feature corresponding to the output identifier according to the change status of each output identifier included in the cross-sectional schematic diagram corresponding to each key detection feature;

[0041] Among them, for any of the key detection features, when the change of each of the output identifiers included in the cross-section schematic diagram corresponding to the key detection feature is used to indicate that the output identifier changes from a first state to a second state, the detection status of the structural feature corresponding to each of the output identifiers is used to indicate that the structural feature is detected in the corresponding standard cross-section.

[0042] As an optional embodiment, in the second aspect of the present invention, the output interface of the output terminal includes a first area and a second area, the first area is used to output the detection result, and the second area is used to output a list of features to be checked and a list of checked features corresponding to the fetal ultrasound image, the list of features to be checked is used to store multiple features to be checked of the fetal ultrasound image, and the list of checked features is used to store multiple checked features of the fetal ultrasound image, and the categories of all features to be checked included in the list of features to be checked include the categories of all checked features included in the list of checked features, and the categories of the multiple features included in the fetal ultrasound image include the categories of all features to be checked included in the list of features to be checked.

[0043] As an optional implementation, in the second aspect of the present invention, all of the features included in the fetal ultrasound image include multiple structural features of the fetal ultrasound image, the detection result of each of the features also includes a feature parameter of the feature, and the feature parameter of each of the features includes category information of the feature;

[0044] And, the device further comprises:

[0045] The acquisition module is further used to determine the part feature of the frame of the fetal ultrasound image where each structural feature included in the fetal ultrasound image is located after acquiring the analysis result output by the image analysis model as the detection result of the fetal ultrasound image;

[0046] A second determination module is used to determine a characteristic parameter of each of the part features, wherein the characteristic parameter of each of the part features includes category information of the part feature;

[0047] The second determination module is further used to determine the standard section of each feature according to the category information of each feature and the category information of the part feature corresponding to the feature, and the detection result of each feature also includes the detection result of the standard section of the feature.

[0048] As an optional implementation, in the second aspect of the present invention, the device further includes:

[0049] a second judgment module, configured to judge whether a playback request triggered for a fetal ultrasound image corresponding to a certain target feature category is detected after the acquisition module acquires the analysis result output by the image analysis model as the detection result of the fetal ultrasound image, the playback request being used to request playback of the fetal ultrasound image corresponding to the target feature category, and the fetal ultrasound image corresponding to the target feature category includes at least one of an optimal frame fetal ultrasound image corresponding to the target feature category, fetal ultrasound images of all standard sections corresponding to the target feature category, and fetal ultrasound images of all chapters corresponding to the target feature category, the fetal ultrasound image includes the fetal ultrasound image corresponding to the target feature category, the target feature category includes a target structural feature category and / or a target standard section category, and the category of the standard section of each fetal ultrasound image included in each chapter is the same;

[0050] a third determination module, configured to determine, when the determination result of the second determination module is yes, the fetal ultrasound image corresponding to the target feature category according to the playback request;

[0051] The control module is further used to control the output terminal to play back the fetal ultrasound image corresponding to the target feature category.

[0052] As an optional implementation manner, in the second aspect of the present invention, the third determination module includes:

[0053] a determination submodule, configured to determine a section score of each of the standard sections among all the standard sections corresponding to the target feature category when the fetal ultrasound image corresponding to the target feature category is the optimal frame fetal ultrasound image corresponding to the target feature category;

[0054] The determination submodule is also used to determine, based on the section score of each of the standard sections among all the standard sections corresponding to the target feature category, a frame fetal ultrasound image corresponding to the standard section corresponding to the highest section score from all the standard sections, as the optimal frame fetal ultrasound image corresponding to the target feature category.

[0055] As an optional implementation manner, in the second aspect of the present invention, the third determining module further includes:

[0056] a judging submodule, used for, before the determining submodule determines, according to the section score of each of the standard sections among all the standard sections corresponding to the target feature category, a frame fetal ultrasound image corresponding to the standard section with the highest section score from among all the standard sections as the optimal frame fetal ultrasound image corresponding to the target feature category, when the target feature category is the target structure feature category, determining whether the target feature category corresponds to at least two matching feature categories, the at least two matching feature categories including at least two matching standard section categories or at least two matching chapter categories; when the judgment result is no, triggering the determining submodule to execute the operation of determining, according to the section score of each of the standard sections among all the standard sections corresponding to the target feature category, a frame fetal ultrasound image corresponding to the standard section with the highest section score from among all the standard sections as the optimal frame fetal ultrasound image corresponding to the target feature category;

[0057] The determination submodule is further configured to determine the section score of each standard section among all standard sections corresponding to each matching feature category corresponding to the target feature category when the judgment result of the judgment submodule is yes;

[0058] A screening submodule, configured to screen, according to the section score of each standard section corresponding to each matching feature category, a frame of fetal ultrasound image corresponding to the highest section score from all the standard sections;

[0059] The determination submodule is further used to determine all the frame fetal ultrasound images corresponding to the matching feature categories as the optimal frame fetal ultrasound images corresponding to the target feature category, and the number of the optimal frame fetal ultrasound images corresponding to the target feature category is greater than 1.

[0060] As an optional implementation, in the second aspect of the present invention, the device further includes:

[0061] A third judgment module is used to judge whether there is an abnormal feature among all the features included in the fetal ultrasound image after the acquisition module acquires the analysis result output by the image analysis model as the detection result of the fetal ultrasound image;

[0062] a screening module, configured to screen all the abnormal features from all the features included in the fetal ultrasound image when the third judging module determines that the abnormal features are yes;

[0063] A sorting module, used for sorting all the abnormal features according to the determined sorting method to obtain all the abnormal features after sorting;

[0064] The control module is used to control the output terminal to output all the abnormal features after sorting.

[0065] The third aspect of the present invention discloses another output control device for detecting results of fetal ultrasound images, the device is applied in an intelligent detection system, and the device comprises:

[0066] A memory storing executable program code;

[0067] a processor coupled to the memory;

[0068] The processor calls the executable program code stored in the memory to execute the output control method of the detection result of the fetal ultrasound image disclosed in the first aspect of the present invention.

[0069] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute the output control method of the fetal ultrasound image detection results disclosed in the first aspect of the present invention.

[0070] The fifth aspect of the present invention discloses an intelligent detection system for executing the output control method of the detection result of the fetal ultrasound image disclosed in the first aspect of the present invention.

[0071] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0072] In an embodiment of the present invention, the intelligent detection system inputs the received fetal ultrasound image into the determined image analysis model for analysis, and obtains the analysis result output by the image analysis model as the detection result of the fetal ultrasound image, and controls the output terminal corresponding to the intelligent detection system to output the detection result, wherein the detection result includes the detection results of multiple features of the fetal ultrasound image, and the detection result of each feature includes the detection identification of the feature, and the detection identification corresponding to each feature is used to indicate that the feature is one of the features to be detected, the detected and normal features, the detected and suspected features, and the detected and abnormal features. The detected and suspected features are features that are detected and have uncertain categories, and the detected and abnormal features are features that have been detected and have abnormal structural features. It can be seen that the implementation of the present invention can quickly obtain accurate detection results of each feature (e.g., structural features, cut surfaces) of the fetal ultrasound image by automatically analyzing the fetal ultrasound image, such as abnormal, normal, suspected, detected, and undetected, which is conducive to accurately determining the growth and development of the fetus; and by identifying each feature of the fetal ultrasound image, it can reduce the occurrence of feature omissions, so as to increase the possibility of successfully detecting the required detection features, thereby further facilitating the accurate determination of the growth and development of the fetus. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0074] Figure 1 It is a flow chart of a method for controlling output of detection results of fetal ultrasound images disclosed in an embodiment of the present invention;

[0075] Figure 2 It is a flow chart of another method for controlling the output of the detection results of fetal ultrasound images disclosed in an embodiment of the present invention;

[0076] Figure 3 It is a structural schematic diagram of a device for outputting control of detection results of fetal ultrasound images disclosed in an embodiment of the present invention;

[0077] Figure 4 It is a structural schematic diagram of another output control device for detecting results of fetal ultrasound images disclosed in an embodiment of the present invention;

[0078] Figure 5 It is a structural schematic diagram of another output control device for detecting results of fetal ultrasound images disclosed in an embodiment of the present invention;

[0079] Figure 6 It is a structural schematic diagram of an intelligent detection system disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0080] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0081] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.

[0082] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0083] The present invention discloses an output control method, device and system for the detection results of fetal ultrasound images, which can automatically analyze the fetal ultrasound images and quickly obtain accurate detection results of each feature (e.g., structural features, sections) of the fetal ultrasound images, such as abnormal, normal, suspected, tested, and untested, which is conducive to accurately determining the growth and development of the fetus; and by marking each feature of the fetal ultrasound image, it is possible to reduce the occurrence of feature omissions, thereby increasing the possibility of successfully detecting the required detection features, and further facilitating accurate determination of the growth and development of the fetus. The following are detailed descriptions.

[0084] Embodiment 1

[0085] See also Figure 1 , Figure 1 1 is a flow chart of a method for controlling the output of fetal ultrasound image detection results disclosed in an embodiment of the present invention. Figure 1 The output control method of the detection result of the fetal ultrasound image described above can be applied to an intelligent detection system (intelligent detection device / intelligent detection server, wherein the intelligent detection server may include a local intelligent detection server or a cloud intelligent detection server, which is not limited in the embodiment of the present invention). Figure 1 As shown, the output control method of the detection result of the fetal ultrasound image may include the following operations:

[0086] 101. The intelligent detection system inputs the received fetal ultrasound image into the determined image analysis model for analysis, and obtains the analysis result output by the image analysis model as the detection result of the fetal ultrasound image.

[0087] In an embodiment of the present invention, optionally, the fetal ultrasound image may be an image sent from a physical terminal device and / or a virtual terminal device that establishes a communication connection with the intelligent detection system. The physical terminal device may include an ultrasound image acquisition device and other terminal devices that have a communication connection with the ultrasound image acquisition device, such as a computer. The virtual terminal device may be a network disk and / or a cloud service terminal device, etc. Further, the physical terminal device may also include a pluggable storage device, such as a USB flash drive, etc. Further, the fetal ultrasound image may be a real-time image or a non-real-time image. When the fetal ultrasound image is a real-time image, the physical terminal device is preferably an ultrasound image acquisition device.

[0088] In an embodiment of the present invention, optionally, the detection result of the fetal ultrasound image includes the detection results of multiple features of the fetal ultrasound image. Further optionally, the detection result of the fetal ultrasound image can be a real-time analysis result of the fetal ultrasound image, or it can be an analysis result output after the analysis of the fetal ultrasound image is completed. Still further optionally, the multiple features of the fetal ultrasound image include multiple structural features and / or multiple standard sections of the fetal ultrasound image. Still further, the multiple features of the fetal ultrasound image can also include multiple part features. In this way, by outputting the detection results of structural features, sections, and part features, more accurate ultrasound image detection results can be obtained, thereby more accurately knowing the growth and development of the fetus.

[0089] In an embodiment of the present invention, optionally, the detection result of each feature includes a detection identifier of the feature, and the detection identifier corresponding to each feature is used to indicate that the feature is one of a feature to be detected, a detected and normal feature, a detected and suspected feature, and a detected and abnormal feature. Among them, the detected and suspected feature is a feature that has been detected and has an uncertain category, and the detected and abnormal feature is a feature that has been detected and has an abnormal structural feature. Specifically, when all the features included in the fetal ultrasound image are multiple structural features of the fetal ultrasound image, the detected and suspected feature is a feature that has been detected and its confidence (also known as the probability of the feature category) is less than or equal to a preset confidence threshold and / or matches the determined suspected feature, and the detected and abnormal feature is a feature that has been detected and has an abnormality. For example: If the structural feature A is a midline cerebral sac structural feature, and the midline cerebral sac structural feature is not accompanied by other structural features (for example: thalamic structural features, etc.), then the structural feature A is a suspected midline cerebral sac structural feature. When all the features included in the fetal ultrasound image are multiple standard sections of the fetal ultrasound image, the detected and suspected features are features that include key structural features that match the features and do not include other structural features, and the detected and abnormal features are features that have been detected and have abnormal structural features. For example: if the B standard section includes gastric bubble structural features and umbilical vein structural features, then the B standard section is a suspected abdominal circumference standard section; if the B standard section includes gastric bubble structural features and umbilical vein structural features, and also includes other structural features of the liver, descending aorta, ribs, and inferior vena cava, then the B standard section is a normal abdominal circumference standard section; if the B standard section includes abnormal gastric bubble structural features, then the B standard section is an abnormal abdominal circumference standard section. Further optionally, different detection results of the same feature correspond to different detection identifiers. Among them, the detection identifier can include at least one of a graphic identifier, a text identifier, and a pattern identifier. For example: when the detection result of the C structural feature is a normal gastric bubble structure feature, the detection mark of the C structural feature is a green box; when the detection result of the C structural feature is an undetected structural feature, the detection mark of the C structural feature is a gray box; when the detection result of the C structural feature is a suspected gastric bubble structure feature, the detection mark of the C structural feature is a yellow box; when the detection result of the C structural feature is an abnormal gastric bubble structure feature, the detection mark of the C structural feature is a red box, and the box is used to select the C structural feature. In this way, by marking different detection results of the same feature with different detection marks, the detection results of the corresponding features can be accurately and intuitively known, thereby knowing the growth and development of the fetus, such as abnormal development, normal development, unknown development, etc.

[0090] In an embodiment of the present invention, the image analysis model may include at least one of the determined target analysis model, instance segmentation model, and semantic segmentation model that can analyze fetal ultrasound images, and the embodiment of the present invention is not limited thereto.

[0091] 102. The intelligent detection system controls the output terminal corresponding to the intelligent detection system to output the above detection result.

[0092] In the embodiment of the present invention, optionally, the output terminal corresponding to the intelligent detection system includes an output terminal integrated with the intelligent detection system and / or an output terminal independent of the intelligent detection system and having a communication connection with the intelligent detection system. Further optionally, the output terminal includes a display terminal and / or a voice terminal, preferably a display terminal with a voice function.

[0093] In an embodiment of the present invention, the output interface of the output terminal includes a first area and a second area, the first area is used to output the above-mentioned detection results, and the second area is used to output a list of features to be checked and a list of checked features corresponding to the fetal ultrasound image, the list of features to be checked is used to store multiple features to be checked of the determined fetal ultrasound image, the list of checked features is used to store multiple checked features of the fetal ultrasound image, and the categories of all features to be checked included in the list of features to be checked include the categories of all checked features included in the list of checked features, and the categories of multiple features included in the fetal ultrasound image include the categories of all features to be checked included in the list of features to be checked. Furthermore, when the feature to be checked corresponding to a certain feature category to be checked in the list of features to be checked has been detected, the certain feature category to be checked can be cleared from the list of features to be checked. It should be noted that the above-mentioned detection results also include a list of features to be checked and a list of checked features corresponding to the fetal ultrasound image. Further, the output interface of the output terminal is provided with a side navigation bar, and the side navigation bar includes a list of features to be detected and / or a list of features that have been detected. Further, the side navigation bar also includes the retention status of the detected features, wherein the retention status of the detected features is used to indicate that when the detected feature needs to be output, the output terminal is controlled to output the detected feature, and when the detected feature does not need to be output, the detected feature is hidden. In this way, by controlling the output terminal to output features or hide features according to the situation where the features need to be output, the output flexibility of the features can be improved and the occurrence of feature distinction errors or even indistinguishability caused by too much content output from the output interface of the output terminal can be reduced. Further, different detection items correspond to different side navigation bars, wherein the detection items include at least one of mid-to-late pregnancy detection, early pregnancy detection, and gynecological detection. When a certain detection item needs to be detected, it is switched to the corresponding side navigation bar.

[0094] In an optional embodiment, the output control method of the detection result of the fetal ultrasound image may also include the following operations:

[0095] The intelligent detection system determines whether the key detection features are determined in all the features according to the target information of all the features included in the fetal ultrasound image;

[0096] When it is determined that there is at least one key detection feature among all the features included in the fetal ultrasound image, the intelligent detection system controls the output terminal to output a cross-sectional schematic diagram corresponding to each key detection feature, wherein the cross-sectional schematic diagram corresponding to each key detection feature includes an output identifier of each structural feature in the standard cross-sectional diagram corresponding to the key detection feature;

[0097] The intelligent detection system determines the detection status of the structural feature corresponding to the output identifier according to the change status of each output identifier included in the cross-section schematic diagram corresponding to each key detection feature;

[0098] Among them, for any key detection feature, when the change of each output identifier included in the cross-section schematic diagram corresponding to the key detection feature is used to indicate that the output identifier changes from a first state to a second state, the detection status of the structural feature corresponding to each output identifier is used to indicate that the structural feature is detected in the corresponding standard cross-section.

[0099] In this optional embodiment, the target information of each feature included in the fetal ultrasound image includes at least one of the category of the feature, the position of the feature in the fetus corresponding to the fetal ultrasound image, and the complexity of the feature. The intelligent detection system determines whether there is a determined key detection feature in all features, specifically: when it is determined that the category of at least one feature of all features included in the fetal ultrasound image is the category of the determined key detection feature, and / or, when it is determined that the position of at least one feature of all features included in the fetal ultrasound image in the fetal ultrasound image is the determined key position (for example: heart), and / or, when it is determined that the level of complexity of at least one feature of all features included in the fetal ultrasound image is greater than or equal to the level threshold of the determined complexity, it is determined that there is at least one key detection feature in all features included in the fetal ultrasound image. In this way, by determining the presence of a key detection feature in all features included in the fetal ultrasound image through multiple methods such as the category of the feature, the position of the feature in the fetus corresponding to the fetal ultrasound image, and / or the complexity of the feature, the efficiency and accuracy of determining the presence of a key detection feature in all features included in the fetal ultrasound image can be improved, thereby improving the output accuracy and confidence rate of the corresponding cross-sectional schematic diagram, and thus facilitating the relevant personnel to intuitively know the situation of the key detection feature.

[0100] In this optional embodiment, the key detection features include features whose importance level is greater than or equal to the determined importance level (for example: level 3, the higher the level, the more important) and / or features whose number of structural features contained in the standard section is greater than or equal to the determined number of structural features (for example: 5).

[0101] In this optional embodiment, the key detection features may include key structural features and / or key standard sections. Further, after the output mark changes from the first state to the second state, the second state may be maintained, so that it can be clearly distinguished whether the structural feature corresponding to the output mark is detected, thereby improving the accuracy of determining whether the key structural feature detection is completed, and further improving the accuracy of determining the growth and development of the fetus.

[0102] In this optional embodiment, when it is determined that there are no key detection features among all the features included in the fetal ultrasound image, the intelligent detection system directly ends the process.

[0103] It can be seen that this optional embodiment determines whether there is a key detection feature among all the features included in the fetal ultrasound image. If so, it outputs a cross-sectional schematic diagram corresponding to the key detection feature, which is helpful to clearly determine that all structural features included in the corresponding standard cross-section have been detected, and reduce the situation where it is impossible to clearly confirm whether the structural features required to be detected in the standard cross-section have been detected due to too many structural features included in the cross-section, and it is convenient for relevant personnel to know the feature detection status of important detection features, which is further beneficial to improve the accuracy of determining the growth and development of the fetus.

[0104] In another optional embodiment, all the features included in the fetal ultrasound image include multiple structural features of the fetal ultrasound image, and the detection result of each feature also includes a feature parameter of the feature, and the feature parameter of each feature includes category information of the feature. And, after executing step 101, the output control method of the detection result of the fetal ultrasound image may also include the following operations:

[0105] The intelligent detection system determines the part feature of the frame of the fetal ultrasound image where each structural feature included in the fetal ultrasound image is located, and determines the feature parameter of each part feature, wherein the feature parameter of each part feature includes the category information of the part feature;

[0106] The intelligent detection system determines the standard section of each feature according to the category information of each feature and the category information of the part feature corresponding to the feature. The detection result of each feature also includes the detection result of the standard section of the feature.

[0107] It can be seen that this optional embodiment can improve the accuracy and reliability of determining the standard section of the fetus by determining the standard section of the structural features based on the category information of the structural features and the category information of the position features of the fetal ultrasound image in the frame, thereby further improving the accuracy and reliability of the detection results of the fetal ultrasound image.

[0108] In yet another optional embodiment, after executing step 101, the output control method of the detection result of the fetal ultrasound image may further include the following operations:

[0109] The intelligent detection system determines whether there are abnormal features among all the features included in the fetal ultrasound image, and when the determination result is yes, all the abnormal features are screened out from all the features included in the fetal ultrasound image;

[0110] The intelligent detection system sorts all abnormal features according to the determined sorting method to obtain all sorted abnormal features, and controls the output terminal to output all sorted abnormal features.

[0111] In this optional embodiment, the abnormal features may include abnormal structural features and / or abnormal standard sections.

[0112] In this optional embodiment, the determined sorting method includes at least one of feature importance, feature appearance duration, and feature appearance times, wherein the higher the feature importance of a certain feature, the more abnormal the fetal growth and development corresponding to the fetal ultrasound image; the feature appearance duration includes the duration of a single appearance or the total duration of the total number of appearances. In this way, by improving multiple sorting methods, the accuracy of sorting abnormal features can be improved, thereby further improving the accuracy of relevant personnel knowing the growth and development of the fetus clearly.

[0113] In this optional embodiment, when it is determined that there are features among all the features of the fetal ultrasound image that do not match its normal features, the intelligent detection system determines that there are abnormal features among all the features included in the fetal ultrasound image, and the abnormal features of the fetal ultrasound image include features that do not match its normal features.

[0114] In this optional embodiment, the intelligent detection system determines whether there are abnormal features among all the features included in the fetal ultrasound image, which may include:

[0115] When all features included in the fetal ultrasound image are standard sections, the intelligent detection system obtains information about each structural feature of each standard section included in the fetal ultrasound image, and the information about each structural feature is used to determine whether the standard section where the structural feature is located is an abnormal standard section;

[0116] The intelligent detection system determines whether each structural feature matches the standard section according to the information of each structural feature of each standard section;

[0117] When it is determined that there is a non-matching structural feature among all the structural features that does not match the standard section in which it is located, the intelligent detection system determines that there is an abnormal standard section whose structural feature is an abnormal structural feature among all the standard sections, and the abnormal standard section is the standard section where the non-matching structural feature is located, that is, there is an abnormal feature among all the features included in the fetal ultrasound image.

[0118] It can be seen that this optional embodiment can determine the presence of abnormal features in fetal ultrasound images by acquiring information on each structural feature of a standard section and judging whether each structural feature matches the corresponding standard section based on the information on each structural feature.

[0119] In another optional embodiment, judging whether each structural feature matches the standard section according to the information of each structural feature of each standard section may include:

[0120] Determine, according to the information of each structural feature of each standard section, a representation type corresponding to each structural feature, the representation type including a numerical representation type and / or a feature morphology representation type, and the information of each structural feature including a feature category of the structural feature;

[0121] When the representation type of the structural feature is a numerical representation type, a target geometric parameter value corresponding to the structural feature is obtained, and it is determined whether the target geometric parameter value corresponding to the structural feature is within a predetermined normal parameter value range. When the judgment result is no, it is determined that the structural feature does not match the standard section where it is located;

[0122] When the representation type of the structural feature is the feature morphology representation type, it is determined whether the structural feature is located in the detection area of ​​the part feature corresponding to the structural feature. When it is determined that it is not in the detection area, it is determined that the structural feature does not match the standard section.

[0123] In this optional embodiment, the detection area of ​​each part feature can be selected by using a detection frame, such as a polygonal frame or an elliptical frame.

[0124] In this optional embodiment, the target geometric parameter value corresponding to each structural feature includes the transverse diameter corresponding to the structural feature and / or the circumference corresponding to the structural feature, so that the more content the geometric parameter value includes, the more conducive it is to improve the accuracy of judging whether the structural feature matches the standard section in which it is located. Among them, different structural features have corresponding normal parameter value ranges, wherein the normal parameter value ranges corresponding to different structural features can be the same or different. Further, different geometric parameter values ​​of the same structural feature correspond to different normal parameter value ranges. Further, the geometric parameter value corresponding to each structural feature may include proportional size and / or actual size. Specifically, after judging that the proportional size corresponding to the structural feature is within the predetermined normal parameter value range, the actual size corresponding to the structural feature is further obtained, and it is judged whether the actual size is within the predetermined normal size range. When the judgment result is no, it is determined that the structural feature does not match the standard section in which it is located. In this way, by comparing the proportional size and actual size of the structural feature with their respective normal values ​​at the same time, the accuracy of determining whether the structural feature matches the standard section in which it is located can be improved, thereby reducing the occurrence of erroneous correction of the section score of abnormal standard sections and improving the correction accuracy and reliability of the section score of abnormal standard sections.

[0125] In this optional embodiment, when it is determined that the structural feature is located in the detection area of ​​the part feature corresponding to the structural feature, it is determined whether the structural feature exists in multiple frames of fetal ultrasound images. When the judgment result is yes, it is determined that the structural feature does not match the standard section where it is located. Among them, the multiple frames of fetal ultrasound images can be fetal ultrasound images that appear continuously or intermittently after the fetal ultrasound image where the structural feature is located is the first frame of the fetal ultrasound image. In this way, when it is determined that the structural feature is in the detection area of ​​the corresponding part feature, it is further determined whether there are multiple frames of fetal ultrasound images that contain the structural feature. If so, it is determined that the structural feature does not match the standard section where it is located, which can improve the accuracy of determining whether the structural feature matches the standard section where it is located, thereby reducing the occurrence of erroneous correction of the section score of the abnormal standard section, and improving the correction accuracy and reliability of the section score of the abnormal standard section.

[0126] It can be seen that when this optional embodiment determines that a structural feature appears in a fetal ultrasound image, it determines whether the structural feature matches the standard section by obtaining the geometric parameter value of the structural feature, or determines whether the structural feature is located within the detection area of ​​the corresponding part feature to achieve the determination of whether the structural feature matches the standard section. This can improve the possibility, accuracy and efficiency of determining whether the structural feature matches the standard section.

[0127] In this optional embodiment, all the abnormal features after sorting can be located in the above-mentioned unchecked feature list, or in the above-mentioned checked feature list, or a new abnormal feature list can be created for all abnormal features, that is, the sorted abnormal features are located in the abnormal feature list. Furthermore, whether they are located in the unchecked feature list or in the checked feature list, all the abnormal features after sorting can be sorted in the front position in the corresponding list. In this way, by placing the abnormal features in the front position in the list, it is helpful for relevant personnel to know the abnormal features of the fetal ultrasound image more clearly and quickly, so as to further quickly and clearly know that abnormalities have occurred in the growth and development of the fetus.

[0128] In this optional embodiment, when it is determined that there are no abnormal features among all the features included in the fetal ultrasound image, the process is terminated.

[0129] In this optional embodiment, the detection result in step 102 may also include all the abnormal features after sorting, that is, the action of the intelligent detection system controlling the output terminal to output all the abnormal features after sorting may occur simultaneously with step 102 .

[0130] It can be seen that this optional embodiment, after detecting the presence of abnormal features in all features in the fetal ultrasound image, further sorts all abnormal features and outputs the sorted abnormal features, which helps relevant personnel quickly know the abnormal features of the fetal ultrasound image, and thus further quickly and clearly know that abnormalities have occurred in the growth and development of the fetus.

[0131] In yet another optional embodiment, the output control method of the detection result of the fetal ultrasound image may further include the following operations:

[0132] The intelligent detection system determines whether there are any features that have been detected among all the features to be detected in the above-mentioned list of features to be detected. When the judgment result is yes, the output terminal is controlled to output prompt information to relevant personnel.

[0133] In this optional embodiment, it should be noted that the prompt information may be output only after all the features to be inspected in the list of features to be inspected have been inspected, and this optional embodiment does not limit this.

[0134] In this optional embodiment, the output method of the prompt information includes a graphic display output method and / or a voice output method (for example, a "ding" sound indicates that the abdominal circumference section detection is completed, etc.), and the detection results of the above-mentioned features include prompt information.

[0135] It can be seen that this optional embodiment automatically outputs prompt information to relevant personnel after detecting that the detection of the feature to be inspected is completed, without the need for relevant personnel to monitor in real time which features have been detected and which have not been detected, so that relevant personnel can quickly, clearly and accurately know the completion status of feature detection.

[0136] It can be seen that implementation Figure 1 The output control method of the detection results of the described fetal ultrasound image can automatically analyze the fetal ultrasound image to quickly obtain accurate detection results of each feature of the fetal ultrasound image (for example: structural features, cross-sections), such as: abnormal, normal, suspected, tested, and untested, which is conducive to accurately determining the growth and development of the fetus; and by marking each feature of the fetal ultrasound image, it can reduce the occurrence of feature omissions, thereby increasing the possibility of successfully detecting the required detection features, which is further conducive to accurately determining the growth and development of the fetus.

[0137] Embodiment 2

[0138] See also Figure 2 , Figure 2 FIG. 1 is a flow chart of another method for controlling the output of fetal ultrasound image detection results disclosed in an embodiment of the present invention. Figure 2 The output control method of the detection result of the fetal ultrasound image described above can be applied to an intelligent detection system (intelligent detection device / intelligent detection server, wherein the intelligent detection server may include a local intelligent detection server or a cloud intelligent detection server, which is not limited in the embodiment of the present invention). Figure 2 As shown, the output control method of the detection result of the fetal ultrasound image may include the following operations:

[0139] 201. The intelligent detection system inputs the received fetal ultrasound image into the determined image analysis model for analysis, and obtains the analysis result output by the image analysis model as the detection result of the fetal ultrasound image.

[0140] 202. The intelligent detection system determines whether a playback request triggered by a fetal ultrasound image corresponding to a certain target feature category is detected. If the judgment result is yes, step 203 is triggered; if the judgment result is no, this process can be terminated and step 205 can be triggered.

[0141] In an embodiment of the present invention, a playback request is used to request playback of a fetal ultrasound image corresponding to a target feature category, and the fetal ultrasound image corresponding to the target feature category includes at least one of an optimal frame fetal ultrasound image corresponding to the target feature category, fetal ultrasound images of all standard sections corresponding to the target feature category, and fetal ultrasound images of all chapters corresponding to the target feature category. The above-mentioned fetal ultrasound image includes the fetal ultrasound image corresponding to the target feature category, and the category of the standard section of each fetal ultrasound image included in each chapter is the same. The target feature category includes a target structural feature category and / or a target standard section category.

[0142] In an embodiment of the present invention, the number of target feature categories is greater than or equal to 1, that is, more than two types of fetal ultrasound images can be requested to be replayed at one time, for example: the optimal frame fetal ultrasound image corresponding to the standard section of the abdominal circumference and the optimal frame fetal ultrasound image corresponding to the standard section of the thalamus.

[0143] In an embodiment of the present invention, when the sound pickup device of the intelligent detection system collects keywords for the target feature category (e.g., abdominal circumference), it is determined that a playback request triggered by the fetal ultrasound image corresponding to the target feature category is detected; when the display device of the intelligent detection system receives keywords for the target feature category (e.g., abdominal circumference), it is determined that a playback request triggered by the fetal ultrasound image corresponding to the target feature category is detected; when the intelligent detection system receives keywords for the target feature category (e.g., abdominal circumference) sent by a terminal device (e.g., computer, mobile phone) that establishes a connection and communication with the intelligent detection system, it is determined that a playback request triggered by the fetal ultrasound image corresponding to the target feature category is detected. Further, multiple playback request gestures (e.g., gestures) for fetal ultrasound images corresponding to the feature categories are pre-set. At this time, when the display device of the intelligent detection system receives a gesture for the target feature category, it is determined that a playback request triggered by the fetal ultrasound image corresponding to the target feature category is detected. In this way, by providing a variety of detection methods for the playback of fetal ultrasound images corresponding to structural features and / or standard sections, the possibility of detecting the playback request of fetal ultrasound images corresponding to structural features and / or standard sections can be improved, thereby improving the probability of playback of fetal ultrasound images corresponding to structural features and / or standard sections. Furthermore, the playback request gestures of the optimal frame fetal ultrasound image corresponding to each target feature category, the fetal ultrasound images of all standard sections corresponding to the target feature category, and the fetal ultrasound images of all chapters corresponding to the target feature category are also different. In this way, by setting different playback request gestures for images of the same structural feature category and different standard section categories, the playback accuracy and efficiency of fetal ultrasound images corresponding to structural features and / or standard sections can be further improved.

[0144] 203. The intelligent detection system determines the fetal ultrasound image corresponding to the target feature category according to the playback request.

[0145] 204. The intelligent detection system controls the output terminal to play back the fetal ultrasound image corresponding to the target feature category.

[0146] In an embodiment of the present invention, when the fetal ultrasound image corresponding to the target feature category is the fetal ultrasound image of all standard sections corresponding to the target feature category, the intelligent detection system can play back the fetal ultrasound images of all standard sections corresponding to the target feature category frame by frame; when the fetal ultrasound image corresponding to the target feature category is the fetal ultrasound image of all chapters corresponding to the target feature category, the intelligent detection system can play back the fetal ultrasound images of all chapters corresponding to the target feature category chapter by chapter. When the fetal ultrasound image corresponding to the target feature category is the optimal frame fetal ultrasound image corresponding to the target feature category, the intelligent detection system can directly play back the optimal frame fetal ultrasound image corresponding to the target feature category, or after playing back the fetal ultrasound image corresponding to the target feature category frame by frame or chapter by chapter, the intelligent detection system can play back the optimal frame fetal ultrasound image corresponding to the target feature category. In this way, by playing back the fetal ultrasound images frame by frame or chapter by chapter, it is helpful for relevant personnel to clearly understand the growth and development of the fetus through the fetal ultrasound images; and by directly playing back the optimal frame fetal ultrasound image or by positioning and playing back the optimal frame fetal ultrasound image after playing back the fetal ultrasound image frame by frame / chapter by chapter, while ensuring the playback efficiency of the optimal frame fetal ultrasound image, the playback method of the optimal frame fetal ultrasound image is enriched.

[0147] It can be seen that after obtaining the detection results of the fetal ultrasound image, the embodiment of the present invention further determines whether a playback request for a fetal ultrasound image of a certain target feature category is detected. If detected, the output terminal is controlled to play back the fetal ultrasound image of the target feature category, which can facilitate relevant personnel to review the fetal ultrasound image again. In particular, when there are abnormalities in the growth and development of the fetus corresponding to the fetal ultrasound image, playing back the fetal ultrasound image helps to accurately determine the abnormalities in the growth and development of the fetus.

[0148] 205. The intelligent detection system controls the output terminal corresponding to the intelligent detection system to output the detection result.

[0149] It should be noted that, since the detection result of the fetal ultrasound image is the real-time analysis result of the fetal ultrasound image or the analysis result of the completed fetal ultrasound image analysis (for specific description, please refer to the relevant description in Example 1), the playback request triggered for the fetal ultrasound image corresponding to the target feature category can be triggered in real time or triggered when the fetal ultrasound image analysis is completed, that is, the fetal ultrasound image corresponding to the target feature category can be real-time or the final fetal ultrasound image of the target feature category in the fetal ultrasound image.

[0150] It should be further explained that step 204 can occur simultaneously with step 205, that is, the detection result in step 205 can also include the optimal frame fetal ultrasound image corresponding to a certain target feature category. It should be further explained that step 202 can also occur after step 205. When step 202 and step 205 occur simultaneously, step 204 occurs after step 205.

[0151] In the embodiment of the present invention, for other descriptions of step 201 and step 205, please refer to the detailed description of step 101-step 102 in embodiment 1, which will not be repeated in the embodiment of the present invention.

[0152] As an optional implementation, the intelligent detection system determines the fetal ultrasound image corresponding to the target feature category according to the playback request, including:

[0153] When the fetal ultrasound image corresponding to the target feature category is the optimal frame fetal ultrasound image corresponding to the target feature category, the intelligent detection system determines the section score of each standard section among all standard sections corresponding to the target feature category, and based on the section score of each standard section among all standard sections corresponding to the target feature category, determines the frame fetal ultrasound image corresponding to the standard section corresponding to the highest section score from all the standard sections as the optimal frame fetal ultrasound image corresponding to the target feature category.

[0154] In this optional implementation, further optionally, based on the weight value corresponding to each structural feature of each standard section and the characteristic parameters of the structural feature, the section score of each standard section is calculated. Specifically: based on the determined weight value corresponding to each structural feature of each standard section, the category probability of the structural feature and the position probability of the structural feature, the structural score corresponding to each structural feature of each standard section is calculated; the sum of the structural scores corresponding to all structural features of each standard section is calculated as the section score of the standard section. Each standard section corresponds to a frame of fetal ultrasound image. The weight value corresponding to each structural feature of each standard section is used to represent the expression level of the structural feature in the standard section. The higher the weight value corresponding to the structural feature, the higher the corresponding expression level, that is, the higher the proportion of the structural feature in the corresponding standard section.

[0155] In this optional implementation, the characteristic parameters of each structural feature of each standard section include the category probability of the structural feature and the position probability of the structural feature.

[0156] In this optional implementation, the calculation formula for the section score of the standard section of each frame of the fetal ultrasound image is as follows:

[0157]

[0158] Hi =P i ×Q i ×O i ;

[0159]

[0160] Where S is the section score of each standard section, H i is the structural score of the i-th structural feature in each standard section, M is the total number of structural features in each standard section, and P i is the category probability (also known as confidence) of the i-th structural feature in each standard section, Q i is the position probability of the i-th structural feature in each standard section, O i is the weight value of the i-th structural feature in each standard section, N is the total number of key weight value influencing factors of the i-th structural feature, O ij It is the sub-weight value corresponding to the jth key weight value influencing factor in the i-th structural feature in each standard section.

[0161] In this optional implementation, further, the parameters included in the structural features in each standard section also include the probability of the location where the structural feature is located. In this case, the calculation formula for the structural score of the i-th structural feature in each standard section is:

[0162] H i =P i ×Q i ×O i ×C i ;

[0163] In the formula, C i The parameters included for the structural features in each standard section also include the probability of the location of the structural feature. In this way, the more parameters of the structural features, the more accurate the calculation of the structural score of the structural features, thereby improving the accuracy of the calculation of the section score of the standard section, and further helping to improve the accuracy and reliability of determining the optimal standard section.

[0164] In this way, by calculating the structural score corresponding to each structural feature of the standard section respectively, the section score of the standard section can be calculated, which is conducive to improving the accuracy and efficiency of the section score calculation of the standard section; and according to different structural features, different parameters are selected to improve the calculation accuracy and efficiency of the structural score corresponding to the structural feature, thereby further improving the accuracy and efficiency of the section score calculation of the standard section.

[0165] It can be seen that this optional implementation method can improve the accuracy and efficiency of determining the optimal frame fetal ultrasound image by taking the frame fetal ultrasound image corresponding to the standard section corresponding to the highest section score as the optimal frame fetal ultrasound image, thereby improving the accuracy and efficiency of outputting the optimal frame fetal ultrasound image.

[0166] In an optional embodiment, the intelligent detection system determines the frame fetal ultrasound image corresponding to the standard section corresponding to the highest section score from all the standard sections according to the section score of each standard section corresponding to the target feature category, and uses it as the optimal frame fetal ultrasound image corresponding to the target feature category. The output control method of the detection result of the fetal ultrasound image may also include the following operations:

[0167] When the target feature category is a target structural feature category, the intelligent detection system determines whether the target feature category corresponds to at least two matching feature categories, the at least two matching feature categories including at least two matching standard section categories or at least two matching chapter categories;

[0168] When the judgment result is no, the intelligent detection system triggers the execution of the above-mentioned operation of determining, according to the section score of each standard section among all the standard sections corresponding to the target feature category, the frame fetal ultrasound image corresponding to the standard section corresponding to the highest section score from all the standard sections as the optimal frame fetal ultrasound image corresponding to the target feature category;

[0169] When the judgment result is yes, the intelligent detection system determines the section score of each standard section among all standard sections corresponding to each matching feature category corresponding to the target feature category, and according to the section score of each standard section corresponding to each matching feature category, screens the frame fetal ultrasound image corresponding to the highest section score from all the standard sections, and determines the frame fetal ultrasound image corresponding to all matching feature categories as the optimal frame fetal ultrasound image corresponding to the target feature category, and the number of optimal frame fetal ultrasound images corresponding to the target feature category is greater than 1.

[0170] For example, it is necessary to determine the optimal frame fetal ultrasound image corresponding to the gastric bubble structure feature. Since the standard sections corresponding to the gastric bubble structure feature include the abdominal circumference standard section and the gallbladder umbilical vein section, the optimal frame fetal ultrasound image corresponding to the gastric bubble structure feature includes the optimal frame fetal ultrasound image corresponding to the abdominal circumference standard section and the optimal frame fetal ultrasound image corresponding to the gallbladder umbilical vein section, that is, the number of optimal frame fetal ultrasound images corresponding to the gastric bubble structure feature is 2.

[0171] It can be seen that this optional embodiment first determines whether there are multiple standard section categories and / or chapter categories corresponding to the structural feature. If not, it directly determines the optimal frame fetal ultrasound image corresponding to the structural feature, which can improve the efficiency and accuracy of determining the optimal frame fetal ultrasound image corresponding to the structural feature; if so, it separately determines the optimal frame fetal ultrasound images corresponding to different standard section categories and / or chapter categories, thereby further improving the accuracy of determining the optimal frame fetal ultrasound image.

[0172] It can be seen that implementation Figure 2 The output control method of the detection results of the described fetal ultrasound image can automatically analyze the fetal ultrasound image to quickly obtain accurate detection results of each feature of the fetal ultrasound image (for example: structural features, cross-sections), such as: abnormal, normal, suspected, tested, and untested, which is conducive to accurately determining the growth and development of the fetus; and by marking each feature of the fetal ultrasound image, it can reduce the occurrence of feature omissions, thereby increasing the possibility of successfully detecting the required detection features, which is further conducive to accurately determining the growth and development of the fetus.

[0173] Embodiment 3

[0174] See also Figure 3 , Figure 3 1 is a schematic diagram of a structure of a control device for outputting detection results of fetal ultrasound images disclosed in an embodiment of the present invention. Figure 3 The output control device for detecting the result of fetal ultrasound imaging described above can be applied to an intelligent detection system (intelligent detection device / intelligent detection server, wherein the intelligent detection server may include a local intelligent detection server or a cloud intelligent detection server, which is not limited in the embodiment of the present invention). Figure 3 As shown, the output control device for the detection result of the fetal ultrasound image may include an analysis module 301, an acquisition module 302 and a control module 303, wherein:

[0175] The analysis module 301 is used to input the received fetal ultrasound image into the determined image analysis model for analysis.

[0176] The acquisition module 302 is used to acquire the analysis result output by the image analysis model as the detection result of the fetal ultrasound image.

[0177] The control module 303 is used to control the output terminal corresponding to the intelligent detection system to output the detection result.

[0178] In an embodiment of the present invention, the detection result of the fetal ultrasound image includes the detection results of multiple features of the fetal ultrasound image, and the detection result of each feature includes the detection identifier of the feature. The detection identifier corresponding to each feature is used to indicate that the feature is one of the features to be detected, the detected and normal feature, the detected and suspected feature, and the detected and abnormal feature. The detected and suspected feature is a feature that has been detected and the category is uncertain, and the detected and abnormal feature is a feature that has been detected and has abnormal structural features.

[0179] In an embodiment of the present invention, further optionally, the output interface of the output terminal includes a first area and a second area, the first area is used to output the detection results, and the second area is used to output a list of features to be tested and a list of tested features corresponding to the fetal ultrasound image, the list of features to be tested is used to store multiple features to be tested of the determined fetal ultrasound image, the list of tested features is used to store multiple tested features of the fetal ultrasound image, and the categories of all features to be tested included in the list of features to be tested include the categories of all tested features included in the list of tested features, and the categories of the multiple features included in the fetal ultrasound image include the categories of all features to be tested included in the list of features to be tested.

[0180] It can be seen that implementation Figure 3 The output control device for the detection results of the described fetal ultrasound image can automatically analyze the fetal ultrasound image to quickly obtain accurate detection results of each feature of the fetal ultrasound image (for example, structural features, cross-sections), such as abnormal, normal, suspected, tested, and untested, which is conducive to accurately determining the growth and development of the fetus; and by marking each feature of the fetal ultrasound image, it can reduce the occurrence of feature omissions, thereby increasing the possibility of successfully detecting the required detection features, which is further conducive to accurately determining the growth and development of the fetus.

[0181] In an optional embodiment, if Figure 4 As shown, the device also includes a first judging module 304 and a first determining module 305, wherein:

[0182] The first judgment module 304 is used to judge whether there is a determined key detection feature in all features according to the target information of all features included in the fetal ultrasound image.

[0183] The control module 303 is also used to control the output terminal to output a cross-sectional schematic diagram corresponding to each key detection feature when the first judgment module 304 determines that there is at least one key detection feature among all the features included in the fetal ultrasound image. The cross-sectional schematic diagram corresponding to each key detection feature includes the output identifier of each structural feature in the standard cross-sectional diagram corresponding to the key detection feature.

[0184] The first determination module 305 is used to determine the detection status of the structural feature corresponding to each output identifier according to the change status of each output identifier included in the cross-section schematic diagram corresponding to each key detection feature.

[0185] Among them, for any key detection feature, when the change of each output identifier included in the cross-section schematic diagram corresponding to the key detection feature is used to indicate that the output identifier changes from a first state to a second state, the detection status of the structural feature corresponding to each output identifier is used to indicate that the structural feature is detected in the corresponding standard cross-section.

[0186] It can be seen that implementation Figure 4 The output control device for the detection results of the described fetal ultrasound image determines whether there is a key detection feature among all the features included in the fetal ultrasound image. If so, it outputs a cross-sectional schematic diagram corresponding to the key detection feature, which is conducive to clearly determining that all structural features included in the corresponding standard cross-section have been detected, and reducing the situation where it is impossible to clearly confirm whether the structural features required to be detected on the standard cross-section have been detected due to too many structural features included in the cross-section, and it is facilitating relevant personnel to know the feature detection status of important detection features, thereby further helping to improve the accuracy of determining the growth and development of the fetus.

[0187] In another optional embodiment, all the features included in the fetal ultrasound image include multiple structural features of the fetal ultrasound image, and the detection result of each feature also includes a feature parameter of the feature, and the feature parameter of each feature includes category information of the feature. Figure 4 As shown, the device also includes a second determining module 306, wherein:

[0188] The acquisition module 302 is further used to determine the location feature of the frame of the fetal ultrasound image where each structural feature included in the fetal ultrasound image is located after acquiring the analysis result output by the image analysis model as the detection result of the fetal ultrasound image.

[0189] The second determination module 306 is used to determine the characteristic parameters of each part feature, and the characteristic parameters of each part feature include category information of the part feature.

[0190] The second determination module 306 is further used to determine the standard section of each feature according to the category information of each feature and the category information of the part feature corresponding to the feature, and the detection result of each feature also includes the detection result of the standard section of the feature.

[0191] It can be seen that implementation Figure 4The output control device for the detection results of the described fetal ultrasound image can improve the accuracy and reliability of determining the standard section of the fetus by determining the standard section of the structural features based on the category information of the structural features and the category information of the part features of the fetal ultrasound image in the frame, thereby further improving the accuracy and reliability of the detection results of the fetal ultrasound image.

[0192] In yet another optional embodiment, Figure 5 As shown, the device may further include a second judging module 307 and a third determining module 308, wherein:

[0193] The second judgment module 307 is used to determine whether a playback request triggered for a fetal ultrasound image corresponding to a certain target feature category is detected after the acquisition module 302 acquires the analysis result output by the image analysis model as the detection result of the fetal ultrasound image, and the playback request is used to request the playback of the fetal ultrasound image corresponding to the target feature category, and the fetal ultrasound image corresponding to the target feature category includes at least one of the optimal frame fetal ultrasound image corresponding to the target feature category, the fetal ultrasound images of all standard sections corresponding to the target feature category, and the fetal ultrasound images of all chapters corresponding to the target feature category, the fetal ultrasound image includes the fetal ultrasound image corresponding to the target feature category, the target feature category includes the target structural feature category and / or the target standard section category, and the category of the standard section of each fetal ultrasound image included in each chapter is the same.

[0194] The third determination module 308 is configured to determine the fetal ultrasound image corresponding to the target feature category according to the playback request when the determination result of the second determination module 307 is yes.

[0195] The control module 303 is also used to control the output terminal to play back the fetal ultrasound image corresponding to the target feature category.

[0196] It can be seen that implementation Figure 4 The output control device for the detection results of the described fetal ultrasound images further determines whether a playback request for a fetal ultrasound image of a certain target feature category is detected after obtaining the detection results of the fetal ultrasound images. If detected, the output terminal is controlled to play back the fetal ultrasound image of the target feature category, which can facilitate relevant personnel to review the fetal ultrasound image. In particular, when there are abnormalities in the growth and development of the fetus corresponding to the stored fetal ultrasound image, playing back the fetal ultrasound image helps to accurately determine the abnormalities in the growth and development of the fetus.

[0197] In yet another optional embodiment, Figure 4 As shown, the third determination module 308 may include a determination submodule 3081, wherein:

[0198] The determination submodule 3081 is used to determine the slice score of each standard slice among all standard slices corresponding to the target feature category when the fetal ultrasound image corresponding to the target feature category is the optimal frame fetal ultrasound image corresponding to the target feature category.

[0199] The determination submodule 3081 is also used to determine, based on the slice score of each standard slice among all standard slices corresponding to the marked feature category, the frame fetal ultrasound image corresponding to the standard slice corresponding to the highest slice score from all standard slices, as the optimal frame fetal ultrasound image corresponding to the target feature category.

[0200] It can be seen that implementation Figure 4 The output control device for the detection results of the described fetal ultrasound images can improve the accuracy and efficiency of determining the optimal frame fetal ultrasound image by taking the frame fetal ultrasound image corresponding to the standard section corresponding to the highest section score as the optimal frame fetal ultrasound image, thereby improving the accuracy and efficiency of outputting the optimal frame fetal ultrasound image.

[0201] In yet another optional embodiment, Figure 4 As shown, the third determination module 308 also includes a judgment submodule 3082 and a screening submodule 3083, wherein:

[0202] The judgment submodule 3082 is used for determining, before the determination submodule 3081 determines, based on the slice score of each standard slice among all the standard slices corresponding to the target feature category, a frame fetal ultrasound image corresponding to the standard slice with the highest slice score from all the standard slices as the optimal frame fetal ultrasound image corresponding to the target feature category, and when the target feature category is the target structure feature category, determining whether the target feature category corresponds to at least two matching feature categories, the at least two matching feature categories including at least two matching standard slice categories or at least two matching chapter categories; when the judgment result is no, triggering the determination submodule 3081 to perform the above-mentioned operation of determining, based on the slice score of each standard slice among all the standard slices corresponding to the target feature category, a frame fetal ultrasound image corresponding to the standard slice with the highest slice score from all the standard slices as the optimal frame fetal ultrasound image corresponding to the target feature category.

[0203] The determination submodule 3081 is further used to determine the section score of each standard section among all standard sections corresponding to each matching feature category corresponding to the target feature category when the judgment result of the judgment submodule 3082 is yes.

[0204] A screening submodule 3083 is used to screen the fetal ultrasound image frame corresponding to the highest section score from all the standard sections according to the section score of each standard section corresponding to each matching feature category;

[0205] The determination submodule 3081 is further used to determine the frame fetal ultrasound images corresponding to all matching feature categories as the optimal frame fetal ultrasound images corresponding to the target feature category, and the number of the optimal frame fetal ultrasound images corresponding to the target feature category is greater than 1.

[0206] It can be seen that implementation Figure 4 The output control device for the detection results of the described fetal ultrasound image first determines whether there are multiple standard section categories and / or chapter categories corresponding to the structural feature. If not, it directly determines the optimal frame fetal ultrasound image corresponding to the structural feature, which can improve the efficiency and accuracy of determining the optimal frame fetal ultrasound image corresponding to the structural feature; if so, it separately determines the optimal frame fetal ultrasound images corresponding to different standard section categories and / or chapter categories, thereby further improving the accuracy of determining the optimal frame fetal ultrasound image.

[0207] In yet another optional embodiment, Figure 4 As shown, the device further includes a third judgment module 309, a screening module 310 and a sorting module 311, wherein:

[0208] The third judgment module 309 is used to judge whether there is an abnormal feature among all the features included in the fetal ultrasound image after the acquisition module 302 acquires the analysis result output by the image analysis model as the detection result of the fetal ultrasound image.

[0209] The screening module 310 is used to screen all abnormal features from all features included in the fetal ultrasound image when the third judging module 309 judges that the result is yes.

[0210] The sorting module 311 is used to sort all abnormal features according to the determined sorting method to obtain all sorted abnormal features.

[0211] The control module 303 is used to control the output terminal to output all the abnormal features after sorting.

[0212] It can be seen that implementation Figure 4 The output control device for the detection results of the described fetal ultrasound image further sorts all the abnormal features after detecting the presence of abnormal features in all the features in the fetal ultrasound image, and outputs the sorted abnormal features, which is conducive to relevant personnel quickly knowing the abnormal features of the fetal ultrasound image, and thus further quickly and clearly knowing that abnormalities have occurred in the growth and development of the fetus.

[0213] Embodiment 4

[0214] See also Figure 5 , Figure 5 It is another output control device for detecting results of fetal ultrasound images disclosed in an embodiment of the present invention. Figure 5The output control device for detecting the result of fetal ultrasound imaging described above can be applied to an intelligent detection system (intelligent detection device / intelligent detection server, wherein the intelligent detection server may include a local intelligent detection server or a cloud intelligent detection server, which is not limited in the embodiment of the present invention). Figure 5 As shown, the output control device of the detection result of the fetal ultrasound image may include:

[0215] A memory 501 storing executable program codes;

[0216] a processor 502 coupled to the memory 501;

[0217] Furthermore, it may also include an input interface 503 and an output interface 504 coupled to the processor 502;

[0218] The processor 502 calls the executable program code stored in the memory 501 to execute part or all of the steps in the output control method of the detection result of the fetal ultrasound image described in the first or second embodiment.

[0219] Embodiment 5

[0220] See also Figure 6 , Figure 6 Schematic diagram of the structure of an intelligent detection system disclosed in an embodiment of the present invention. Figure 6 As shown, the intelligent detection system may include an output control device for detecting the detection result of the fetal ultrasound image, and is used to realize Figure 1 or Figure 2 The output control method of the fetal ultrasound image detection result described in the embodiment. Optionally, the output control device of the fetal ultrasound image detection result can be Figure 3 or Figure 4 The output control device for detecting the result of fetal ultrasound imaging described in any one of the items is not limited in the embodiments of the present invention.

[0221] Embodiment 6

[0222] An embodiment of the present invention discloses a computer-readable storage medium that stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute some or all of the steps in the output control method of the detection results of fetal ultrasound images described in Embodiment 1 or Embodiment 2.

[0223] Embodiment 7

[0224] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute some or all of the steps in the output control method of the detection results of fetal ultrasound images described in Example 1 or Example 2.

[0225] The device embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components output by the modules may or may not be physical modules, i.e., they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0226] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or partly contributed to the prior art in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0227] Finally, it should be noted that the output control method, device and system of the fetal ultrasound image detection results disclosed in the embodiments of the present invention are only preferred embodiments of the present invention, which are only used to illustrate the technical scheme of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical schemes described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical schemes from the spirit and scope of the technical schemes of the embodiments of the present invention.

Claims

1. A method for controlling the output of detection results of fetal ultrasound images, characterized in that: The method is applied to an intelligent detection system, and the method comprises: The intelligent detection system inputs the received fetal ultrasound image into the determined image analysis model for analysis, and obtains the analysis result output by the image analysis model as the detection result of the fetal ultrasound image; The intelligent detection system controls an output terminal corresponding to the intelligent detection system to output the detection result; The detection result includes detection results of multiple features of the fetal ultrasound image, and the detection result of each feature includes a detection identifier of the feature. The detection identifier corresponding to each feature is used to indicate that the feature is one of a feature to be detected, a detected and normal feature, a detected and suspected feature, and a detected and abnormal feature. The detected and suspected feature is a feature that has been detected and the category is uncertain, and the detected and abnormal feature is a feature that has been detected and has abnormal structural features. Furthermore, after the intelligent detection system obtains the analysis result output by the image analysis model as the detection result of the fetal ultrasound image, the method further includes: The intelligent detection system determines whether a playback request triggered for a fetal ultrasound image corresponding to a certain target feature category is detected, the playback request is used to request the playback of the fetal ultrasound image corresponding to the target feature category, and the fetal ultrasound image corresponding to the target feature category includes at least one of an optimal frame fetal ultrasound image corresponding to the target feature category, fetal ultrasound images of all standard sections corresponding to the target feature category, and fetal ultrasound images of all chapters corresponding to the target feature category, the fetal ultrasound image includes the fetal ultrasound image corresponding to the target feature category, the target feature category includes a target structural feature category and / or a target standard section category, and the category of the standard section of each fetal ultrasound image included in each chapter is the same; When the judgment result is yes, the intelligent detection system determines the fetal ultrasound image corresponding to the target feature category according to the playback request, and controls the output terminal to play back the fetal ultrasound image corresponding to the target feature category; The intelligent detection system determines the fetal ultrasound image corresponding to the target feature category according to the playback request, including: When the fetal ultrasound image corresponding to the target feature category is the optimal frame fetal ultrasound image corresponding to the target feature category, the intelligent detection system determines a section score of each of the standard sections among all the standard sections corresponding to the target feature category; The intelligent detection system determines, according to the section score of each standard section among all the standard sections corresponding to the target feature category, a frame fetal ultrasound image corresponding to the standard section corresponding to the highest section score from among all the standard sections as the optimal frame fetal ultrasound image corresponding to the target feature category; Wherein, before the intelligent detection system determines, according to the section score of each of the standard sections among all the standard sections corresponding to the target feature category, a frame fetal ultrasound image corresponding to the standard section corresponding to the highest section score from all the standard sections as the optimal frame fetal ultrasound image corresponding to the target feature category, the method further comprises: When the target feature category is the target structural feature category, the intelligent detection system determines whether the target feature category corresponds to at least two matching feature categories, and the at least two matching feature categories include at least two matching standard section categories or at least two matching chapter categories; When the judgment result is no, triggering the execution of the operation of determining, according to the section score of each of the standard sections among all the standard sections corresponding to the target feature category, a frame fetal ultrasound image corresponding to the standard section corresponding to the highest section score from all the standard sections as the optimal frame fetal ultrasound image corresponding to the target feature category; When the judgment result is yes, the intelligent detection system determines the section score of each of the standard sections in all the standard sections corresponding to each of the matching feature categories corresponding to the target feature category, and according to the section score of each of the standard sections corresponding to each of the matching feature categories, screens the frame fetal ultrasound image corresponding to the highest section score from all the standard sections, and determines the frame fetal ultrasound images corresponding to all the matching feature categories as the optimal frame fetal ultrasound images corresponding to the target feature category, and the number of the optimal frame fetal ultrasound images corresponding to the target feature category is greater than 1; Furthermore, after the intelligent detection system obtains the analysis result output by the image analysis model as the detection result of the fetal ultrasound image, the method further includes: The intelligent detection system determines whether there is an abnormal feature among all the features included in the fetal ultrasound image, and when the determination result is yes, screens all the abnormal features from all the features included in the fetal ultrasound image; The intelligent detection system sorts all the abnormal features according to the determined sorting method to obtain all the sorted abnormal features, and controls the output terminal to output all the sorted abnormal features; The intelligent detection system determines whether there are any abnormal features among all the features included in the fetal ultrasound image, including: When all the features included in the fetal ultrasound image are the standard sections, the intelligent detection system obtains information about each structural feature of each standard section included in the fetal ultrasound image, and the information about each structural feature is used to determine whether the standard section where the structural feature is located is an abnormal standard section; The intelligent detection system determines whether each structural feature matches the standard section according to the information of each structural feature of each standard section; When it is determined that there is a non-matching structural feature that does not match the standard section in which it is located among all the structural features, the intelligent detection system determines that there is an abnormal standard section in which the structural feature is an abnormal structural feature among all the standard sections, and the abnormal standard section is the standard section where the non-matching structural feature is located, that is, there is an abnormal feature in all the features included in the fetal ultrasound image; The intelligent detection system determines whether each structural feature matches the standard section according to the information of each structural feature of each standard section, including: Determine, according to the information of each structural feature of each standard section, a representation type corresponding to each structural feature, wherein the representation type includes a numerical representation type and / or a feature morphology representation type, and the information of each structural feature includes a feature category of the structural feature; When the representation type of the structural feature is the numerical representation type, obtaining a target geometric parameter value corresponding to the structural feature, and judging whether the target geometric parameter value corresponding to the structural feature is within a predetermined normal parameter value range, and when the judgment result is no, judging that the structural feature does not match the standard section; When the representation type of the structural feature is the feature morphology representation type, determining whether the structural feature is located in the detection area of ​​the part feature corresponding to the structural feature, and when it is determined that the structural feature is not located in the detection area of ​​the part feature corresponding to the structural feature, determining that the structural feature does not match the standard section where it is located; When it is determined that the structural feature is located in the detection area of ​​the part feature corresponding to the structural feature, it is determined whether the structural feature exists in multiple frames of fetal ultrasound images. When the judgment result is yes, it is determined that the structural feature does not match the standard section where it is located; wherein the multiple frames of fetal ultrasound images are fetal ultrasound images that appear continuously or intermittently after the fetal ultrasound image where the structural feature is located is the first frame of the fetal ultrasound image.

2. The method for controlling the output of the detection result of fetal ultrasound image according to claim 1, characterized in that: The method further comprises: The intelligent detection system determines whether there is a determined key detection feature among all the features according to the target information of all the features included in the fetal ultrasound image; When it is determined that at least one of the key detection features exists among all the features included in the fetal ultrasound image, the intelligent detection system controls the output terminal to output a cross-sectional schematic diagram corresponding to each of the key detection features, wherein the cross-sectional schematic diagram corresponding to each of the key detection features includes an output identifier of each structural feature in the standard cross-sectional diagram corresponding to the key detection feature; The intelligent detection system determines the detection status of the structural feature corresponding to the output identifier according to the change status of each output identifier included in the cross-section schematic diagram corresponding to each key detection feature; Among them, for any of the key detection features, when the change of each of the output identifiers included in the cross-section schematic diagram corresponding to the key detection feature is used to indicate that the output identifier changes from a first state to a second state, the detection status of the structural feature corresponding to each of the output identifiers is used to indicate that the structural feature is detected in the corresponding standard cross-section.

3. The method for controlling the output of the detection result of fetal ultrasound image according to claim 1 or 2, characterized in that: The output interface of the output terminal includes a first area and a second area, the first area is used to output the detection result, and the second area is used to output a list of features to be checked and a list of checked features corresponding to the fetal ultrasound image, the list of features to be checked is used to store multiple features to be checked of the fetal ultrasound image, and the list of checked features is used to store multiple checked features of the fetal ultrasound image, and the categories of all features to be checked included in the list of features to be checked include the categories of all checked features included in the list of checked features, and the categories of the multiple features included in the fetal ultrasound image include the categories of all features to be checked included in the list of features to be checked.

4. The method for controlling the output of the detection result of fetal ultrasound image according to any one of claims 1 to 3, characterized in that: All of the features included in the fetal ultrasound image include multiple structural features of the fetal ultrasound image, the detection result of each feature also includes a feature parameter of the feature, and the feature parameter of each feature includes category information of the feature; Furthermore, after the intelligent detection system obtains the analysis result output by the image analysis model as the detection result of the fetal ultrasound image, the method further includes: The intelligent detection system determines the part feature of the frame of the fetal ultrasound image where each of the structural features included in the fetal ultrasound image is located, and determines the feature parameter of each of the part features, wherein the feature parameter of each of the part features includes the category information of the part feature; The intelligent detection system determines the standard section of each feature according to the category information of each feature and the category information of the part feature corresponding to the feature, and the detection result of each feature also includes the detection result of the standard section of the feature.

5. A device for controlling the output of detection results of fetal ultrasound images, characterized in that: The device is applied in an intelligent detection system, and the device comprises: An analysis module, used for inputting the received fetal ultrasound image into the determined image analysis model for analysis; An acquisition module, used for acquiring the analysis result output by the image analysis model as the detection result of the fetal ultrasound image; A control module, used to control an output terminal corresponding to the intelligent detection system to output the detection result; The detection result includes detection results of multiple features of the fetal ultrasound image, and the detection result of each feature includes a detection identifier of the feature. The detection identifier corresponding to each feature is used to indicate that the feature is one of a feature to be detected, a detected and normal feature, a detected and suspected feature, and a detected and abnormal feature. The detected and suspected feature is a feature that has been detected and the category is uncertain, and the detected and abnormal feature is a feature that has been detected and has abnormal structural features. And, the device also includes: a second judgment module, configured to judge whether a playback request triggered for a fetal ultrasound image corresponding to a certain target feature category is detected after the acquisition module acquires the analysis result output by the image analysis model as the detection result of the fetal ultrasound image, the playback request being used to request playback of the fetal ultrasound image corresponding to the target feature category, and the fetal ultrasound image corresponding to the target feature category includes at least one of an optimal frame fetal ultrasound image corresponding to the target feature category, fetal ultrasound images of all standard sections corresponding to the target feature category, and fetal ultrasound images of all chapters corresponding to the target feature category, the fetal ultrasound image includes the fetal ultrasound image corresponding to the target feature category, the target feature category includes a target structural feature category and / or a target standard section category, and the category of the standard section of each fetal ultrasound image included in each chapter is the same; a third determination module, configured to determine, when the determination result of the second determination module is yes, the fetal ultrasound image corresponding to the target feature category according to the playback request; The control module is further used to control the output terminal to play back the fetal ultrasound image corresponding to the target feature category; Wherein, the third determination module includes: a determination submodule, configured to determine a section score of each of the standard sections among all the standard sections corresponding to the target feature category when the fetal ultrasound image corresponding to the target feature category is the optimal frame fetal ultrasound image corresponding to the target feature category; The determination submodule is further configured to determine, according to the section score of each of the standard sections among all the standard sections corresponding to the target feature category, a frame fetal ultrasound image corresponding to the standard section corresponding to the highest section score from among all the standard sections, as the optimal frame fetal ultrasound image corresponding to the target feature category; Wherein, the third determination module further includes: a judging submodule, used for, before the determining submodule determines, according to the section score of each of the standard sections among all the standard sections corresponding to the target feature category, a frame fetal ultrasound image corresponding to the standard section with the highest section score from among all the standard sections as the optimal frame fetal ultrasound image corresponding to the target feature category, when the target feature category is the target structure feature category, determining whether the target feature category corresponds to at least two matching feature categories, the at least two matching feature categories including at least two matching standard section categories or at least two matching chapter categories; when the judgment result is no, triggering the determining submodule to execute the operation of determining, according to the section score of each of the standard sections among all the standard sections corresponding to the target feature category, a frame fetal ultrasound image corresponding to the standard section with the highest section score from among all the standard sections as the optimal frame fetal ultrasound image corresponding to the target feature category; The determination submodule is further configured to determine the section score of each standard section among all standard sections corresponding to each matching feature category corresponding to the target feature category when the judgment result of the judgment submodule is yes; A screening submodule, configured to screen, according to the section score of each standard section corresponding to each matching feature category, a frame of fetal ultrasound image corresponding to the highest section score from all the standard sections; The determination submodule is further configured to determine all the frame fetal ultrasound images corresponding to the matching feature categories as the optimal frame fetal ultrasound images corresponding to the target feature category, and the number of the optimal frame fetal ultrasound images corresponding to the target feature category is greater than 1; And, the device also includes: A third judgment module is used to judge whether there is an abnormal feature among all the features included in the fetal ultrasound image after the acquisition module acquires the analysis result output by the image analysis model as the detection result of the fetal ultrasound image; a screening module, configured to screen all the abnormal features from all the features included in the fetal ultrasound image when the third judging module determines that the abnormal features are yes; A sorting module, used for sorting all the abnormal features according to the determined sorting method to obtain all the abnormal features after sorting; The control module is used to control the output terminal to output all the abnormal features after sorting; The specific manner in which the third judgment module judges whether there is an abnormal feature among all the features included in the fetal ultrasound image includes: When all the features included in the fetal ultrasound image are the standard sections, obtaining information of each structural feature of each standard section included in the fetal ultrasound image, and the information of each structural feature is used to determine whether the standard section where the structural feature is located is an abnormal standard section; According to the information of each structural feature of each standard section, determining whether each structural feature matches the standard section; When it is determined that there is a non-matching structural feature that does not match the standard section in which it is located among all the structural features, the intelligent detection system determines that there is an abnormal standard section in which the structural feature is an abnormal structural feature among all the standard sections, and the abnormal standard section is the standard section where the non-matching structural feature is located, that is, there is an abnormal feature in all the features included in the fetal ultrasound image; The specific manner in which the third judgment module judges whether each structural feature matches the standard section according to the information of each structural feature of each standard section includes: Determine, according to the information of each structural feature of each standard section, a representation type corresponding to each structural feature, wherein the representation type includes a numerical representation type and / or a feature morphology representation type, and the information of each structural feature includes a feature category of the structural feature; When the representation type of the structural feature is the numerical representation type, obtaining a target geometric parameter value corresponding to the structural feature, and judging whether the target geometric parameter value corresponding to the structural feature is within a predetermined normal parameter value range, and when the judgment result is no, judging that the structural feature does not match the standard section; When the representation type of the structural feature is the feature morphology representation type, determining whether the structural feature is located in the detection area of ​​the part feature corresponding to the structural feature, and when it is determined that the structural feature is not located in the detection area of ​​the part feature corresponding to the structural feature, determining that the structural feature does not match the standard section where it is located; When it is determined that the structural feature is located in the detection area of ​​the part feature corresponding to the structural feature, it is determined whether the structural feature exists in multiple frames of fetal ultrasound images. When the judgment result is yes, it is determined that the structural feature does not match the standard section where it is located; wherein the multiple frames of fetal ultrasound images are fetal ultrasound images that appear continuously or intermittently after the fetal ultrasound image where the structural feature is located is the first frame of the fetal ultrasound image.

6. An intelligent detection system, characterized in that: The intelligent detection system is used to execute the output control method of the detection results of fetal ultrasound images as described in any one of claims 1-4.