Ultrasonic Image Interception Method, Device, Terminal Device and Storage Medium

Abstract

The present application provides a method, apparatus, terminal device, and storage medium for ultrasonic image capture. The method includes: obtaining an ultrasonic scan video; obtaining a target capture method corresponding to the ultrasonic scan video, where the target capture method includes a plurality of capture nodes, and each capture node corresponds to a reference description information; performing image recognition on the ultrasonic scan video to determine the description information corresponding to each video frame in the ultrasonic scan video; and capturing the ultrasonic scan video according to the description information and the reference description information corresponding to each capture node in the target capture method. The ultrasonic image capture method provided by the present application captures the ultrasonic scan video according to the target capture method, removes the unnecessary video frames in the ultrasonic scan video, so that when the doctor views the captured ultrasonic scan video, there is no need to view the unnecessary video frames, reducing the burden on the doctor.

Description

Technical Field

[0001] This application relates to the technical field of medical image processing, and particularly relates to a method, device, terminal device, and computer-readable storage medium for intercepting ultrasound images. Background Art

[0002] Ultrasound scanning is a relatively common imaging method in AI medicine. Generally, during ultrasound scanning, an operator uses an ultrasound device to scan a target area of the human body to obtain an ultrasound video image. Then, the ultrasound scanning video obtained through ultrasound scanning is provided to a doctor.

[0003] Usually, after obtaining the ultrasound scanning video, a doctor needs to play or view the ultrasound scanning video multiple times to find the information required by the doctor himself. However, repeatedly viewing the ultrasound scanning video is time-consuming. Summary of the Invention

[0004] The ultrasound image interception method provided by this application intercepts the ultrasound scanning video according to the target interception method, avoiding the doctor from viewing the entire ultrasound scanning video.

[0005] In a first aspect, this application provides an ultrasound image interception method, which includes:

[0006] Obtain an ultrasound scanning video;

[0007] Obtain the target interception method corresponding to the ultrasound scanning video, where the target interception method includes multiple interception nodes, and each interception node corresponds to a reference description information;

[0008] Perform image recognition on the ultrasound scanning video to determine the description information corresponding to each video frame in the ultrasound scanning video;

[0009] Intercept the ultrasound scanning video according to the description information and the reference description information corresponding to each interception node in the target interception method.

[0010] In some embodiments of this application, the obtaining of the target interception method corresponding to the ultrasound scanning video includes:

[0011] Perform anomaly detection on the ultrasound scanning video according to a preset anomaly detection model to obtain the anomaly information of the ultrasound scanning video;

[0012] Obtain the target interception method from a preset database according to the anomaly information, where each anomaly information corresponding interception method is stored in the database.

[0013] In some embodiments of the present application, the image recognition of the ultrasound scan video to determine the description information corresponding to each video frame in the ultrasound scan video includes:

[0014] Perform object image recognition on the ultrasound scan video to obtain the corresponding object type in the ultrasound scan video;

[0015] According to the object type, obtain a target three-dimensional model matching the object type from a preset database;

[0016] Determine the three-dimensional position information corresponding to each video frame in the ultrasound scan video in the target three-dimensional model;

[0017] Determine that the three-dimensional position information is the description information of the video frame.

[0018] In some embodiments of the present application, the image recognition of the ultrasound scan video to determine the description information corresponding to each video frame in the ultrasound scan video includes:

[0019] Obtain the target scan path corresponding to the ultrasound scan video;

[0020] Determine the scan path points of each video frame in the ultrasound scan video on the target scan path;

[0021] According to the scan path points of each video frame on the target scan path, obtain the description information of each video frame.

[0022] In some embodiments of the present application, the image recognition of the ultrasound scan video to determine the description information corresponding to each video frame in the ultrasound scan video includes:

[0023] Perform frame-by-frame image recognition on the ultrasound scan video to obtain the sign information of each video frame in the ultrasound scan video, and the description information corresponding to each video frame in the ultrasound scan video includes the sign information.

[0024] In some embodiments of the present application, the intercepting of the ultrasound scan video according to the description information and the reference description information corresponding to each intercepting node in the target intercepting method includes:

[0025] Match the reference description information corresponding to each intercepting node with the description information corresponding to each video frame in the ultrasound scan video respectively to obtain the video frames matching the reference description information corresponding to each intercepting node;

[0026] Intercept the matching video frames from the ultrasound scan video to obtain target video frames.

[0027] In some embodiments of the present application, the step of matching the reference description information corresponding to each of the intercepted nodes with the description information corresponding to each video frame in the ultrasonic scan video to obtain the video frames that match the reference description information corresponding to each of the intercepted nodes includes:

[0028] Matching the three-dimensional positions in each reference description information with the three-dimensional position information corresponding to each video frame to obtain the video frames that match each reference description information.

[0029] In some embodiments of the present application, the step of matching the reference description information corresponding to each of the intercepted nodes with the description information corresponding to each video frame in the ultrasonic scan video to obtain the video frames that match the reference description information corresponding to each of the intercepted nodes includes:

[0030] Matching the scan path points in each reference description information with the scan path points corresponding to each video frame to determine the video frames that match each reference description information.

[0031] In some embodiments of the present application, the step of matching the reference description information corresponding to each of the intercepted nodes with the description information corresponding to each video frame in the ultrasonic scan video to obtain the video frames that match the reference description information corresponding to each of the intercepted nodes includes:

[0032] Matching the reference sign information in each reference description information with the sign information of each video frame to obtain the video frames that match each reference description information.

[0033] In a second aspect, the present application further provides an ultrasonic image interception device, and the device includes:

[0034] A first acquisition module, configured to acquire an ultrasonic scan video;

[0035] A second acquisition module, configured to acquire a target interception method corresponding to the ultrasonic scan video, where the target interception method includes a plurality of intercepted nodes, and each intercepted node corresponds to a reference description information;

[0036] A determination module, configured to perform image recognition on the ultrasonic scan video to determine the description information corresponding to each video frame in the ultrasonic scan video;

[0037] An interception module, configured to intercept the ultrasonic scan video according to the description information and the reference description information corresponding to each intercepted node in the target interception method.

[0038] In some embodiments of the present application, the second acquisition module is specifically configured to:

[0039] According to a preset anomaly detection model, anomaly detection is performed on the ultrasound scanning video to obtain abnormal information of the ultrasound scanning video;

[0040] According to the abnormal information, a target interception method is obtained from a preset database, and the database stores an interception method corresponding to each abnormal information.

[0041] In some implementations of the present application, the determination module is specifically used to:

[0042] Performing object image recognition on the ultrasonic scanning video to obtain a corresponding object type in the ultrasonic scanning video;

[0043] According to the object type, obtaining a target three-dimensional model matching the object type from a preset database;

[0044] Determine and obtain the three-dimensional position information corresponding to each video frame in the ultrasonic scanning video in the target three-dimensional model;

[0045] The three-dimensional position information is determined as description information of the video frame.

[0046] In some implementations of the present application, the determination module is further specifically used for:

[0047] Acquire a target scanning path corresponding to the ultrasonic scanning video;

[0048] Determine a scan path point of each video frame in the ultrasound scan video on the target scan path;

[0049] The description information of each video frame is obtained according to the scanning path points of each video frame on the target scanning path.

[0050] In some implementations of the present application, the determination module is further specifically used for:

[0051] Image recognition is performed frame by frame on the ultrasound scanning video to obtain sign information of each video frame in the ultrasound scanning video, and the description information corresponding to each video frame in the ultrasound scanning video includes the sign information.

[0052] In some embodiments of the present application, the interception module is specifically used for:

[0053] Matching the reference description information corresponding to each interception node with the description information corresponding to each video frame in the ultrasound scanning video, respectively, to obtain video frames matching the reference description information corresponding to each interception node;

[0054] The matched video frame is intercepted from the ultrasound scanning video to obtain a target video frame.

[0055] In some embodiments of the present application, the intercepting module is further specifically configured to:

[0056] Match the three-dimensional positions in each reference description information with the three-dimensional position information corresponding to each video frame respectively, to obtain the video frames that match the respective reference description information.

[0057] In some embodiments of the present application, the intercepting module is further specifically configured to:

[0058] Match the scanning path points in the respective reference description information with the scanning path points corresponding to each video frame respectively, to determine the video frames that match the respective reference description information.

[0059] In some embodiments of the present application, the intercepting module is further specifically configured to:

[0060] Match the reference sign information in each reference description information with the sign information of each video frame respectively, to obtain the video frames that match the respective reference description information.

[0061] In a third aspect, the present application further provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to implement the steps in any one of the ultrasonic image intercepting methods described above.

[0062] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and the computer program is executed by a processor to implement the steps in any one of the ultrasonic image intercepting methods described above.

[0063] The ultrasonic image intercepting method provided by the present application intercepts an ultrasonic scanning video according to a target intercepting method, and removes the unnecessary video frames in the ultrasonic scanning video, so that when a doctor views the intercepted ultrasonic scanning video, there is no need to view the unnecessary video frames anymore. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention, and those skilled in the art can obtain other drawings without creative efforts based on these drawings.

[0065] Figure 1 is a schematic diagram of the scenario of the ultrasonic image intercepting system provided in the embodiment of the present application;

[0066] Figure 2It is a schematic flowchart of an embodiment of the ultrasonic image capture method in an embodiment of the present application;

[0067] Figure 3 It is a schematic diagram of a functional module of the ultrasonic image capture device in an embodiment of the present application;

[0068] Figure 4 It is a schematic structural diagram of a terminal device in an embodiment of the present application. Detailed implementation manners

[0069] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of the present application.

[0070] In the description of the present application, it should be understood that the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present application, "a plurality" means two or more unless otherwise specifically defined.

[0071] In the present application, the term "exemplary" is used to mean "serving as an example, illustration, or description". Any embodiment described as "exemplary" in the present application is not necessarily construed as being more preferred or having more advantages than other embodiments. In order for any person skilled in the art to implement and use the present application, the following description is given. In the following description, details are set forth for the purpose of explanation. It should be understood by those skilled in the art that the present application can be implemented without these specific details. In other instances, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present application with unnecessary details. Therefore, the present application is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed in the present application.

[0072] The present application provides an ultrasonic image capture method, device, terminal device, and storage medium, which will be described in detail below.

[0073] Please refer to Figure 1 , Figure 1 which is a schematic diagram of the scenario of the ultrasonic image capture system provided by the embodiment of the present application. The ultrasonic image capture system may include a terminal device 100 and a storage device 200, and the storage device 200 can transmit data to the terminal device 100. As Figure 1The terminal device 100 therein can obtain the ultrasound scan video pre-stored in the storage device 200 to execute the ultrasound image capture method in this application.

[0074] In the embodiments of this application, the terminal device 100 may include, but is not limited to, a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, an embedded device, etc.

[0075] In the embodiments of this application, communication between the terminal device 100 and the storage device 200 can be achieved through any communication method, including but not limited to mobile communication based on the 3rd Generation Partnership Project (3GPP), Long Term Evolution (LTE), Worldwide Interoperability for Microwave Access (WiMAX), or computer network communication based on the TCP / IP protocol suite (TCP / IP), User Datagram Protocol (UDP), etc.

[0076] It should be noted that Figure 1 The scene schematic diagram of the ultrasound image capture system shown is only an example. The ultrasound image capture system and the scene described in the embodiments of this application are for more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. Those of ordinary skill in the art know that with the evolution of the ultrasound image capture system and the emergence of new business scenarios, the technical solutions provided by the embodiments of this application are equally applicable to similar technical problems.

[0077] As Figure 2 shown, Figure 2 is a schematic flowchart of an embodiment of the ultrasound image capture method in the embodiments of this application. The ultrasound image capture method may include the following steps 201 to 204:

[0078] 201. Obtain the ultrasound scan video.

[0079] In the embodiments of this application, the ultrasound scan video may be an ultrasound scan video obtained by an operating user through methods such as 2D ultrasound scanning and 4D ultrasound scanning of an object. Among them, multiple ultrasound scan videos may be stored in the relevant storage device, and the multiple ultrasound scan videos may be ultrasound scan videos at different times, different angles, and different regions.

[0080] In addition, to obtain the ultrasound scan video, the processing device for ultrasound images can be connected to the storage device storing the multiple ultrasound scan videos. When it is necessary to process the multiple ultrasound scan videos, the multiple ultrasound scan videos in the storage device can be directly read.

[0081] 202. Obtain the target extraction method corresponding to the ultrasound scan video. The target extraction method includes multiple extraction nodes, and each extraction node corresponds to a reference description information.

[0082] According to the background art, doctors often need to repeatedly watch ultrasound scan videos. Therefore, in order to reduce the burden on doctors when watching ultrasound scan videos, the method adopted in this embodiment is to extract the ultrasound scan videos. For example, if an ultrasound scan video includes 100 video frames, 50 video frames are extracted through the extraction method. In this way, when doctors watch the ultrasound scan video, even if they watch it repeatedly, the content they need to watch is reduced, thus reducing the burden on doctors.

[0083] Among them, the target extraction method can be the extraction method specified by the doctor according to his own habits or experience. Since the ultrasound scan video includes multiple video frames, and doctors will not only view a certain frame of the video when viewing the ultrasound scan video, the target extraction method provided by the doctor usually includes multiple extractions, that is, one extraction can be regarded as an extraction node. At the same time, in order to inform the terminal device how to extract, when the doctor sets the relevant extraction method, a reference description information needs to be set for each extraction node. For example, the reference description information can include an image or a text description. When the terminal device extracts the ultrasound scan video according to the extraction node, it can refer to the image or the relevant text description in the reference description information and select the video frame in the ultrasound scan video that matches the reference description information for extraction.

[0084] Among them, when selecting the target extraction method corresponding to the ultrasound scan video, the doctor corresponding to the ultrasound scan video can be determined, and then it can be detected whether the doctor has provided a relevant target extraction method. For example, in a hospital system, whether it is an outpatient patient or an inpatient, there is a corresponding doctor in charge, and the corresponding doctor in charge can be queried in the hospital system. Therefore, when the operating user performs an ultrasound scan on a relevant patient, the doctor in charge corresponding to the patient can be determined according to the information recorded in the hospital system, and then the target extraction method provided by the corresponding doctor in charge can be selected.

[0085] In order to better implement the embodiment of the present application, in an embodiment of the present application, obtaining the target extraction method corresponding to the ultrasound scan video includes:

[0086] Perform anomaly detection on the ultrasound scan video according to a preset anomaly detection model to obtain the anomaly information of the ultrasound scan video; according to the anomaly information, obtain the target interception method from a preset database, where the interception methods corresponding to each anomaly information are stored in the database.

[0087] In the above embodiment, a method for obtaining the target interception method corresponding to the ultrasound scan video according to different doctors is provided. This embodiment also provides a solution for obtaining the corresponding interception method based on the content of the video itself.

[0088] Since the scanned parts corresponding to the ultrasound scan video include multiple types, and the structures of different scanned parts are also different, the video content in the presented ultrasound scan video is also different. For example: there are lung anomalies in some ultrasound scan videos, and liver anomalies in some ultrasound scan videos, etc., and for different anomaly situations, the interception methods are also different. Therefore, it is necessary to identify the specific anomaly situation so as to select the target interception method corresponding to the specific anomaly situation.

[0089] Among them, the anomaly detection model in this embodiment can be a pre-trained anomaly detection model. When training this anomaly detection model, different anomaly situation images can be input into the untrained anomaly detection model to complete the training of this anomaly detection model. It should be noted that the model structure of this anomaly detection model is not limited in this application.

[0090] After the anomaly detection model identifies the specific anomaly situation, for example: when a liver tumor is identified, the interception method matching the liver tumor can be selected from the preset database, so that the ultrasound scan video can be intercepted by the interception method matching the liver tumor.

[0091] 203. Perform image recognition on the ultrasound scan video to determine the description information corresponding to each video frame in the ultrasound scan video.

[0092] According to the above embodiment, after the target interception method is selected, that is, when the terminal device already knows the content to be intercepted, it is also necessary to determine what content each video frame in the ultrasound scan video specifically expresses, so that when intercepting, the video frames matching the target interception method can be intercepted. Therefore, to solve this problem, it is also necessary to determine the description information of each video frame in this ultrasound scan video, that is, to determine what content each video frame expresses.

[0093] Among them, in order to identify the respective description information of each video frame in the ultrasound scan video, the respective description information of each video frame in the ultrasound scan video can be identified through a pre-trained video recognition model. For example: after identifying the specific video content, the description information corresponding to the specific video content can be output. Similar to the above embodiment, the video recognition model is also a pre-trained video recognition model. The specific training method is the same as that in the above embodiment, which will not be elaborated here, and the present application does not limit the model structure of the video recognition model either.

[0094] In order to better implement the embodiments of the present application, in one embodiment of the present application, image recognition is performed on the ultrasound scan video to determine the description information corresponding to each video frame in the ultrasound scan video, including:

[0095] Performing object image recognition on the ultrasound scan video to obtain the corresponding object type in the ultrasound scan video; according to the object type, obtaining a target three-dimensional model that matches the object type from a preset database; determining the corresponding three-dimensional position information of each video frame in the ultrasound scan video in the target three-dimensional model; determining the three-dimensional position information as the description information of the video frame.

[0096] In the above embodiment, a method for determining the description information corresponding to each video frame in the ultrasound scan video through a model is provided. However, in order to improve the accuracy and diversity of determining the description information. The embodiments of the present application can express the description information in the form of a three-dimensional model.

[0097] For example: after obtaining the ultrasound scan video, by recognizing the feature information in the ultrasound scan video, such as detecting the feature information of the coronary artery, it can be determined that the scanned object corresponding to the ultrasound scan video is the heart. Therefore, a three-dimensional model corresponding to the scanned object can be selected from the database, that is, a three-dimensional model of the heart is obtained.

[0098] In the preset three-dimensional model, relevant position identification information can be added. For example, if the three-dimensional model is still a three-dimensional model of the heart, a label A can be added to the coronary artery. Therefore, when recognizing each video frame in the ultrasound scan video and recognizing the feature information including the coronary artery, it can be determined that the video frame including the coronary artery corresponds to the label A in the three-dimensional model of the heart. By analogy, when there are multiple identification information in the three-dimensional model of the heart, the video frames including the heart feature information in the ultrasound scan video can be respectively corresponded to the three-dimensional model of the heart, and the video frames without heart feature information correspond to no description information, so as to obtain the three-dimensional position description information corresponding to each video frame in the ultrasound scan video.

[0099] In order to better implement the embodiments of the present application, in one embodiment of the present application, image recognition is performed on the ultrasonic scanning video to determine the description information corresponding to each video frame in the ultrasonic scanning video, including:

[0100] Obtain the target scanning path corresponding to the ultrasonic scanning video; determine the scanning path points of each video frame in the ultrasonic scanning video on the target scanning path; and obtain the description information of each video frame according to the scanning path points of each video frame on the target scanning path.

[0101] In the above embodiment, a solution for intercepting an ultrasonic scanning video through a three-dimensional model as a medium is provided. The present application also provides a solution for intercepting an ultrasonic scanning video according to the scanning path of the ultrasonic scanning video as a medium.

[0102] Among them, to obtain the target scanning path corresponding to the ultrasonic scanning video, a displacement sensor can be installed on the ultrasonic scanning probe of the terminal device for ultrasonic scanning, and the displacement trajectory of the scanning probe can be obtained through the displacement sensor, so as to obtain the scanning path corresponding to the ultrasonic scanning video. At the same time, since a scanned image, that is, a certain video frame in the ultrasonic scanning video, is obtained each time the scanning probe moves, the video frame obtained each time the scanning probe moves can be corresponded to this movement. Moreover, the movement trajectory of the scanning probe is the scanning path, so each video frame can be corresponded to each path point in the scanning path, thereby determining the path description information corresponding to each video frame.

[0103] In order to better implement the embodiments of the present application, in one embodiment of the present application, image recognition is performed on the ultrasonic scanning video to determine the description information corresponding to each video frame in the ultrasonic scanning video, including:

[0104] Perform frame-by-frame image recognition on the ultrasonic scanning video to obtain the sign information of each video frame in the ultrasonic scanning video. The description information corresponding to each video frame in the ultrasonic scanning video includes sign information.

[0105] In the above embodiment, a factual method for intercepting an ultrasonic scanning video through a path medium or a model medium is provided. This embodiment provides a method for intercepting an ultrasonic scanning video without passing through other additional media.

[0106] The specific method includes: identifying the sign information expressed by each video frame in the ultrasonic scanning video through a relevant sign recognition model. Among them, the sign information is information that can reflect the characteristics of an object. For example: the shape of the coronary artery or the specific abnormal conditions of the coronary artery. At this time, there is no need to establish an additional medium as the carrier of the sign information.

[0107] 204. Intercept the ultrasound scan video according to the description information and the reference description information corresponding to each interception node in the target interception method.

[0108] When, according to the above embodiments, the reference description information in each interception node in the target interception method and the description information expressed by each video frame in the ultrasound scan video are respectively determined, the ultrasound scan video can be intercepted. For example: Suppose the target interception method includes three interception nodes. At this time, the first interception node can be selected first, and the reference description information in the first interception node is matched with the description information corresponding to each video frame, and the video frames that match the reference description information of the first interception node are intercepted. Similarly, the second interception node and the third interception node can be intercepted in the same way.

[0109] In addition, when the reference description information is image information, the image information of the reference description information will be traversed one by one through each video frame of the ultrasound scan video in turn, so as to obtain the video frames that match the reference description information, and then intercept them.

[0110] In order to better implement the embodiments of the present application, in one embodiment of the present application, intercepting the ultrasound scan video according to the description information and the reference description information corresponding to each interception node in the target interception method includes:

[0111] Match the reference description information corresponding to each interception node with the description information corresponding to each video frame in the ultrasound scan video respectively to obtain the video frames that match the reference description information corresponding to each interception node; intercept the matched video frames from the ultrasound scan video to obtain the target video frames.

[0112] The above embodiments provide an interception method that matches the video frames in the ultrasound scan video one by one according to multiple interception nodes in the target interception method. In this embodiment, matching can be performed simultaneously. For example: Suppose the target interception method still includes three interception nodes. At this time, the reference description information corresponding to the three interception nodes can be matched with the description information corresponding to each video frame at the same time. The advantage of this method is that it reduces the matching time.

[0113] In order to better implement the embodiments of the present application, in one embodiment of the present application, matching the reference description information corresponding to each interception node with the description information corresponding to each video frame in the ultrasound scan video respectively to obtain the video frames that match the reference description information corresponding to each interception node includes:

[0114] Match the three-dimensional positions in each reference description information with the three-dimensional position information corresponding to each video frame respectively to obtain the video frames that match each reference description information.

[0115] According to the above embodiments, each video frame including three-dimensional position description information can be obtained. Therefore, on this basis, when the reference description information in each intercept node is matched with each video frame, the ultrasonic scan video can be intercepted through the three-dimensional model as a medium.

[0116] Among them, according to the above embodiments, the reference description information can be text information. Therefore, when the reference description information is "image of coronary artery", the reference description information can be matched with the identifier A of the coronary artery in the three-dimensional model of the heart at this time. And so on, each reference description information can be associated with each position of the three-dimensional model respectively.

[0117] After each reference description information is associated with each position of the three-dimensional model respectively, since each video frame is also associated with each position of the three-dimensional model, each reference description information can be corresponding to each video frame. At this time, interception can be performed according to the corresponding relationship.

[0118] In order to better implement the embodiments of the present application, in one embodiment of the present application, the reference description information corresponding to each intercept node is respectively matched with the description information corresponding to each video frame in the ultrasonic scan video to obtain the video frames matching the reference description information corresponding to each intercept node, including:

[0119] The scan path points in each reference description information are respectively matched with the scan path points corresponding to each video frame to determine the video frames matching each reference description information.

[0120] According to the above embodiments, the reference description information can be text information. Assuming that the reference description information is still "image of coronary artery", it can be determined that the reference description information needs to intercept the image of the coronary artery position. Since the scan path is obtained and each scan path point in the scan path is corresponding to each video frame, the path points corresponding to the coronary artery can be known. After knowing the path points corresponding to the coronary artery, the relevant path points can be corresponding to the reference description information, so that when intercepting the ultrasonic scan video according to the reference description information, the corresponding scan path points can be found first through the relationship between the reference description information and the corresponding path points, and then the video frame corresponding to the scan path point can be found according to the path description information in the above embodiments. After finding the corresponding video frame, the ultrasonic scan video can be intercepted.

[0121] In order to better implement the embodiments of the present application, in one embodiment of the present application, the reference description information corresponding to each intercept node is respectively matched with the description information corresponding to each video frame in the ultrasonic scan video to obtain the video frames that match the reference description information corresponding to each intercept node, including:

[0122] The reference sign information in each reference description information is respectively matched with the sign information of each video frame to obtain the video frames that match each reference description information.

[0123] According to the above embodiments, after obtaining the sign information corresponding to each video frame respectively, since the reference description information can be text information, the reference description information can be directly matched with the sign information. For example: when the sign information is the coronary artery and the reference description information is also an image of the coronary artery, at this time, the two are matched and corresponding, and the video frames with the sign information of the coronary artery can be directly intercepted.

[0124] The ultrasonic image interception method provided by the present application intercepts the ultrasonic scan video according to the target interception method, removes the unnecessary video frames in the ultrasonic scan video, so that when the doctor views the intercepted ultrasonic scan video, there is no need to view the unnecessary video frames, reducing the burden on the doctor.

[0125] In order to better implement the ultrasonic image interception method in the embodiments of the present application, on the basis of the ultrasonic image interception method, the embodiments of the present application also provide an ultrasonic image interception device, as Figure 3 shown, the device 300 includes:

[0126] A first acquisition module 301, configured to acquire an ultrasonic scan video;

[0127] A second acquisition module 302, configured to acquire a target interception method corresponding to the ultrasonic scan video, where the target interception method includes a plurality of intercept nodes, and each intercept node corresponds to a reference description information;

[0128] A determination module 303, configured to perform image recognition on the ultrasonic scan video to determine the description information corresponding to each video frame in the ultrasonic scan video;

[0129] An interception module 304, configured to intercept the ultrasonic scan video according to the description information and the reference description information corresponding to each intercept node in the target interception method.

[0130] The ultrasonic image capture device provided by this application acquires an ultrasonic scanning video through the first acquisition module 301, then acquires a target capture method matching the ultrasonic scanning video through the second acquisition module 302, then determines the description information corresponding to each video frame through the determination module 303, and finally intercepts the ultrasonic scanning video according to the target capture method and the description information through the capture module 304, removing the unnecessary video frames in the ultrasonic scanning video, so that when a doctor views the captured ultrasonic scanning video, there is no need to view the unnecessary video frames, reducing the burden on the doctor.

[0131] In some embodiments of this application, the second acquisition module 302 is specifically configured to:

[0132] Perform anomaly detection on the ultrasonic scanning video according to a preset anomaly detection model to obtain the anomaly information of the ultrasonic scanning video;

[0133] According to the anomaly information, obtain the target capture method from a preset database, and the capture methods corresponding to each anomaly information are stored in the database.

[0134] In some embodiments of this application, the determination module 303 is specifically configured to:

[0135] Perform object image recognition on the ultrasonic scanning video to obtain the corresponding object type in the ultrasonic scanning video;

[0136] According to the object type, obtain a target three-dimensional model matching the object type from a preset database;

[0137] Determine the three-dimensional position information corresponding to each video frame in the ultrasonic scanning video in the target three-dimensional model;

[0138] Determine that the three-dimensional position information is the description information of the video frame.

[0139] In some embodiments of this application, the determination module 303 is specifically further configured to:

[0140] Obtain the target scanning path corresponding to the ultrasonic scanning video;

[0141] Determine the scanning path points of each video frame in the ultrasonic scanning video on the target scanning path;

[0142] According to the scanning path points of each video frame on the target scanning path, obtain the description information of each video frame.

[0143] In some embodiments of this application, the determination module 303 is specifically further configured to:

[0144] Perform frame-by-frame image recognition on the ultrasound scan video to obtain the sign information of each video frame in the ultrasound scan video. The description information corresponding to each video frame in the ultrasound scan video includes the sign information.

[0145] In some embodiments of the present application, the intercepting module 304 is specifically configured to:

[0146] Match the reference description information corresponding to each intercepting node with the description information corresponding to each video frame in the ultrasound scan video to obtain the video frames that match the reference description information corresponding to each intercepting node;

[0147] Intercept the matched video frames from the ultrasound scan video to obtain the target video frames.

[0148] In some embodiments of the present application, the intercepting module 304 is specifically further configured to:

[0149] Match the three-dimensional positions in each reference description information with the three-dimensional position information corresponding to each video frame to obtain the video frames that match each reference description information.

[0150] In some embodiments of the present application, the intercepting module 304 is specifically further configured to:

[0151] Match the scan path points in each reference description information with the scan path points corresponding to each video frame to determine the video frames that match each reference description information.

[0152] In some embodiments of the present application, the intercepting module is specifically further configured to:

[0153] Match the reference sign information in each reference description information with the sign information of each video frame to obtain the video frames that match each reference description information.

[0154] The embodiments of the present application further provide a terminal device, which includes a processor, a memory, and a computer program stored in the memory and executable on the processor. The processor executes the computer program to implement the steps in any one of the ultrasound image intercepting methods in the embodiments of the present application. Among them, this terminal device integrates any one of the ultrasound image intercepting methods provided by the embodiments of the present application. As Figure 4 shown, it shows a schematic structural diagram of the terminal device involved in the embodiments of the present application. Specifically:

[0155] This terminal device may include a processor 401 with one or more processing cores, a memory 402 of one or more computer-readable storage media, a power supply 403, an input unit 404 and other components. Those skilled in the art can understand that Figure 4The terminal device structure shown does not limit the terminal device, which may include more or fewer components than shown, or combine certain components, or have different component arrangements. Among them:

[0156] The processor 401 is the control center of the terminal device, connecting various parts of the entire terminal device through various interfaces and lines. By running or executing software programs and / or modules stored in the memory 402, and calling data stored in the memory 402, it executes various functions of the terminal device and processes data, thereby monitoring the terminal device as a whole. Optionally, the processor 401 may include one or more processing cores; the processor 401 may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. Preferably, the processor 401 may integrate an application processor and a modem processor. Among them, the application processor mainly processes the operating system, user interface and application programs, etc., and the modem processor mainly processes wireless communication. It can be understood that the above modem processor may not be integrated into the processor 401 either.

[0157] The memory 402 can be used to store software programs and modules. The processor 401 executes various functional applications and data processing by running the software programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area. Among them, the program storage area may store the operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 402 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices. Correspondingly, the memory 402 may also include a memory controller to provide the processor 401 with access to the memory 402.

[0158] The terminal device further includes a power supply 403 for powering each component. Preferably, the power supply 403 can be logically connected to the processor 401 through a power management system, so as to manage functions such as charging, discharging, and power consumption management through the power management system. The power supply 403 can also include any components such as one or more DC or AC power supplies, a recharge system, a power failure detection circuit, a power converter or inverter, and a power status indicator.

[0159] The terminal device may further include an input unit 404, which can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function controls.

[0160] Although not shown, the terminal device may further include a display unit, etc., which will not be elaborated here. Specifically, in this embodiment, the processor 401 in the terminal device will load the executable files corresponding to the processes of one or more application programs into the memory 402 according to the following instructions, and the processor 401 will run the application programs stored in the memory 402 to implement various functions, such as:

[0161] Obtain an ultrasound scan video;

[0162] Obtain a target interception method corresponding to the ultrasound scan video, where the target interception method includes multiple interception nodes, and each interception node corresponds to a reference description information;

[0163] Perform image recognition on the ultrasound scan video to determine the description information corresponding to each video frame in the ultrasound scan video;

[0164] Intercept the ultrasound scan video according to the description information and the reference description information corresponding to each interception node in the target interception method.

[0165] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed through instructions, or through instructions to control relevant hardware. The instructions can be stored in a computer-readable storage medium and loaded and executed by the processor.

[0166] Therefore, the embodiments of the present application provide a computer-readable storage medium, which may include: read-only memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), a magnetic disk or an optical disc, etc. A computer program is stored thereon, and the computer program is loaded by the processor to execute the steps in any of the ultrasound image interception methods provided by the embodiments of the present application. For example, when the computer program is loaded by the processor, it can execute the following steps:

[0167] Obtain an ultrasound scan video;

[0168] Obtain a target intercepting method corresponding to the ultrasound scan video, where the target intercepting method includes multiple intercepting nodes, and each intercepting node corresponds to a reference description information;

[0169] Perform image recognition on the ultrasound scan video to determine the description information corresponding to each video frame in the ultrasound scan video;

[0170] Intercept the ultrasound scan video according to the description information and the reference description information corresponding to each intercepting node in the target intercepting method.

[0171] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference may be made to the detailed descriptions of other embodiments above, which will not be elaborated here.

[0172] In specific implementation, the above-mentioned each unit or structure can be implemented as an independent entity, or can be combined arbitrarily to be implemented as the same or several entities. For the specific implementation of the above-mentioned each unit or structure, reference may be made to the method embodiments above, which will not be elaborated here.

[0173] For the specific implementation of the above-mentioned each operation, reference may be made to the previous embodiments, which will not be elaborated here.

[0174] The above has introduced in detail a method and device for intercepting ultrasound images provided by the embodiments of the present application. Specific examples are used in this article to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those skilled in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. An ultrasonic image capture method, characterized in that, The method includes: Obtaining an ultrasonic scan video; Obtaining a target intercepting manner corresponding to the ultrasonic scan video, where the target intercepting manner includes multiple intercepting nodes, and each intercepting node corresponds to a reference description information; the reference description information includes an image or relevant text description; Performing image recognition on the ultrasonic scan video to determine the description information corresponding to each video frame in the ultrasonic scan video; Intercepting the ultrasonic scan video according to the description information and the reference description information corresponding to each intercepting node in the target intercepting manner; The intercepting the ultrasonic scan video according to the description information and the reference description information corresponding to each intercepting node in the target intercepting manner includes: Obtaining a target scan path corresponding to the ultrasonic scan video; Determining the scan path points of each video frame in the ultrasonic scan video on the target scan path; Obtaining the description information of each video frame according to the scan path points of each video frame on the target scan path; and Matching the scan path points in the respective reference description information with the scan path points corresponding to each video frame to determine the video frames matching the respective reference description information.

2. The ultrasonic image capture method according to claim 1, wherein The obtaining the target intercepting manner corresponding to the ultrasonic scan video includes: Performing anomaly detection on the ultrasonic scan video according to a preset anomaly detection model to obtain the anomaly information of the ultrasonic scan video; Obtaining a target intercepting manner from a preset database according to the anomaly information, where the database stores the intercepting manner corresponding to each anomaly information.

3. The ultrasonic image capture method according to claim 1, wherein The performing image recognition on the ultrasonic scan video to determine the description information corresponding to each video frame in the ultrasonic scan video includes: Performing object image recognition on the ultrasonic scan video to obtain the corresponding object type in the ultrasonic scan video; Obtaining a target three-dimensional model matching the object type from a preset database according to the object type; Determining the three-dimensional position information corresponding to each video frame in the ultrasonic scan video in the target three-dimensional model; Determining the three-dimensional position information as the description information of the video frame.

4. The ultrasonic image capture method according to claim 1, characterized in that The performing image recognition on the ultrasonic scan video to determine the description information corresponding to each video frame in the ultrasonic scan video includes: Performing frame-by-frame image recognition on the ultrasonic scan video to obtain the sign information of each video frame in the ultrasonic scan video, and the description information corresponding to each video frame in the ultrasonic scan video includes the sign information.

5. The ultrasonic image capture method according to any one of claims 1-4, characterized in that, The intercepting the ultrasonic scan video according to the description information and the reference description information corresponding to each intercepting node in the target intercepting manner includes: Matching the reference description information corresponding to each intercepting node with the description information corresponding to each video frame in the ultrasonic scan video respectively to obtain the video frames matching the reference description information corresponding to each intercepting node; Intercepting the matching video frames from the ultrasonic scan video to obtain target video frames.

6. The ultrasonic image capture method according to claim 5, wherein Matching the reference description information corresponding to each of the intercepted nodes with the description information corresponding to each video frame in the ultrasound scan video respectively to obtain video frames that match the reference description information corresponding to each of the intercepted nodes, includes: Matching the three-dimensional positions in each of the reference description information with the three-dimensional position information corresponding to each video frame respectively to obtain video frames that match each of the reference description information.

7. The ultrasonic image capture method according to claim 5, characterized in that Matching the reference description information corresponding to each of the intercepted nodes with the description information corresponding to each video frame in the ultrasound scan video respectively to obtain video frames that match the reference description information corresponding to each of the intercepted nodes, includes: Matching the reference sign information in each of the reference description information with the sign information of each of the video frames respectively to obtain video frames that match each of the reference description information.

8. An ultrasonic image capturing device, characterized in that, The apparatus includes: A first acquisition module, configured to acquire an ultrasound scan video; A second acquisition module, configured to acquire a target interception method corresponding to the ultrasound scan video, where the target interception method includes a plurality of intercepted nodes, and each intercepted node corresponds to a reference description information; the reference description information includes an image or related text description; A determination module, configured to perform image recognition on the ultrasound scan video to determine the description information corresponding to each video frame in the ultrasound scan video; An interception module, configured to intercept the ultrasound scan video according to the description information and the reference description information corresponding to each intercepted node in the target interception method; Intercepting the ultrasound scan video according to the description information and the reference description information corresponding to each intercepted node in the target interception method, includes: Obtaining a target scan path corresponding to the ultrasound scan video; Determining the scan path points of each video frame in the ultrasound scan video on the target scan path; Obtaining the description information of each video frame according to the scan path points of each video frame on the target scan path; and Matching the scan path points in each of the reference description information with the scan path points corresponding to each video frame respectively to determine video frames that match each of the reference description information.

9. A terminal device, characterized in that, The terminal device includes a processor, a memory, and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to implement the steps in the ultrasound image interception method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, A computer program is stored on a computer-readable storage medium, and the computer program is executed by a processor to implement the steps in the ultrasound image interception method according to any one of claims 1 to 7.

Images