Ultrasonic image acquisition method, device, computer equipment and storage medium

Abstract

The present application provides an ultrasound image acquisition method, device, medical imaging equipment and storage medium. The method acquires an ultrasound image video segment, which includes a target object, identifies a target area of ​​the target object from a video frame of the ultrasound image video segment, and then extracts image feature information of the target area in the video frame. Based on the image feature information, the target ultrasound image is screened from the video frame of the ultrasound image video segment. After the ultrasound image video segment is acquired, based on the area to be observed of the target object in each video frame, that is, the image feature information of the target area, the target ultrasound image with good imaging quality and easy observation in the area to be observed is quickly screened from the ultrasound image video segment, thereby reducing the time consumption of ultrasound image acquisition and improving the efficiency of ultrasound image acquisition.

Description

Technical Field

[0001] The present application relates to the field of image processing, and in particular to an ultrasound image acquisition method, device, computer equipment and storage medium. Background Art

[0002] Ultrasound imaging has become a common method for assisting disease diagnosis. Ultrasound scanning equipment is used to scan the target part of the human body to obtain an ultrasound video of the target part so that medical staff can observe the lesion in the target part. However, during the observation process, medical staff often need to spend a lot of time looking for an ultrasound image with a clear and easy-to-observe lesion in the huge amount of ultrasound video data, which results in a long and inefficient ultrasound image acquisition process. Summary of the invention

[0003] Based on this, it is necessary to provide an ultrasound image acquisition method, device, computer equipment and storage medium to address the above technical problems.

[0004] In a first aspect, the present application provides a method for acquiring an ultrasound image, the method comprising:

[0005] Acquire an ultrasound image video segment, wherein the ultrasound image video segment includes a target object;

[0006] identifying a target region of a target object from a video frame of the ultrasound image video segment;

[0007] The image feature information of the target area in the video frame is extracted, and the target ultrasound image is screened from the video frame of the ultrasound image video segment based on the image feature information.

[0008] In some embodiments of the present application, the image feature information includes morphological feature information of the target area;

[0009] Extracting image feature information of a target area in a video frame, and screening a target ultrasound image from a video frame of an ultrasound image video segment based on the image feature information, including:

[0010] Inputting the image data of the video frame into the morphological feature recognition model to obtain the morphological feature information of the target area;

[0011] Obtaining the similarity between the morphological feature information and the standard morphological feature information corresponding to the target area;

[0012] The video frames whose similarity is greater than a preset similarity threshold are determined as the target ultrasound images in the ultrasound image video segment.

[0013] In some embodiments of the present application, the image feature information includes the number of pixels;

[0014] Extracting image feature information of a target area in a video frame, and screening a target ultrasound image from a video frame of an ultrasound image video segment based on the image feature information, including:

[0015] Get the number of pixels in the target area of ​​the video frame;

[0016] A video frame whose number of pixels is greater than a preset pixel threshold is determined as a target ultrasound image in the ultrasound image video segment.

[0017] In some embodiments of the present application, the image feature information includes a grayscale contrast value;

[0018] Extracting image feature information of a target area in a video frame, and screening a target ultrasound image from a video frame of an ultrasound image video segment based on the image feature information, including:

[0019] determining, from the video frame, an associated region corresponding to the target region;

[0020] Obtaining a grayscale contrast value according to the image grayscale value of the target area and the image grayscale value of the associated area;

[0021] The video frame whose grayscale contrast value is greater than a preset grayscale threshold is determined as the target ultrasound image in the ultrasound image video segment.

[0022] In some embodiments of the present application, the image feature information includes a noise value;

[0023] Extracting image feature information of a target area in a video frame, and screening a target ultrasound image from a video frame of an ultrasound image video segment based on the image feature information, including:

[0024] Obtain the noise pixel points in the target area;

[0025] Calculate the noise value of the target area in the video frame based on the noise pixel points;

[0026] A video frame whose noise value is less than a preset noise threshold is determined as a target ultrasound image in the ultrasound image video segment.

[0027] In some embodiments of the present application, obtaining an ultrasound image video segment further includes:

[0028] Acquire the ultrasound image video source to be processed;

[0029] Acquire a reference ultrasound image matching the standard section from a video frame of an ultrasound image video source;

[0030] Based on the reference ultrasound image, an ultrasound image video segment to be processed is determined from an ultrasound image video source.

[0031] In some embodiments of the present application, identifying a target area of ​​a target object from a video frame of an ultrasound image video segment includes:

[0032] Inputting video frames of the ultrasound image video segment into an object recognition model to obtain an object type of a target object in the ultrasound image video segment;

[0033] A target region segmentation model corresponding to the object type is determined, and a video frame in the ultrasound image video segment is input into the target region segmentation model to obtain a target region of the target object.

[0034] In a second aspect, the present application provides an ultrasonic image acquisition device, the device comprising:

[0035] An image video acquisition module is used to acquire an ultrasound image video segment, wherein the ultrasound image video segment includes a target object;

[0036] A target region determination module, used for identifying a target region of a target object from a video frame of an ultrasound image video segment;

[0037] The ultrasonic image screening module is used to extract the image feature information of the target area in the video frame, and screen the target ultrasonic image from the video frame of the ultrasonic image video segment based on the image feature information.

[0038] In a third aspect, the present application further provides a medical imaging device, the medical imaging device comprising:

[0039] one or more processors;

[0040] Memory; and

[0041] One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the ultrasound image acquisition method.

[0042] In a fourth aspect, the present application also provides a computer-readable storage medium on which a computer program is stored, and the computer program is loaded by a processor to execute the steps in the ultrasound image acquisition method.

[0043] In a fifth aspect, an embodiment of the present application provides a computer program product or a computer program, the computer program product or the computer program including computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method provided in the first aspect above.

[0044] The above-mentioned ultrasonic image acquisition method, device, computer equipment and storage medium obtain an ultrasonic image video segment, which includes a target object, identifies a target area of ​​the target object from a video frame of the ultrasonic image video segment, and then extracts image feature information of the target area in the video frame, and screens the target ultrasonic image from the video frame of the ultrasonic image video segment based on the image feature information. After the ultrasonic image video segment is acquired, based on the area to be observed of the target object in each video frame, that is, the image feature information of the target area, the target ultrasonic image with good imaging quality and easy observation in the area to be observed is quickly screened from the ultrasonic image video segment, thereby reducing the time consumption of ultrasonic image acquisition and improving the efficiency of ultrasonic image acquisition. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0046] Figure 1 is a schematic diagram of a scene of an ultrasound image acquisition method in an embodiment of the present application;

[0047] Figure 2 is a flow chart of the ultrasound image acquisition method in an embodiment of the present application;

[0048] Figure 3 It is a flowchart of the steps of obtaining ultrasound image video segments in an embodiment of the present application;

[0049] Figure 4 is a flow chart of the target area acquisition step in the embodiment of the present application;

[0050] Figure 5 is a schematic diagram of the structure of an ultrasonic image acquisition device in an embodiment of the present application;

[0051] Figure 6 It is a schematic diagram of the structure of a computer device in an embodiment of the present application. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0053] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0054] In the description of the present application, the word "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0055] At present, the use of ultrasound images to assist disease diagnosis is becoming more and more popular. Generally, when performing ultrasound image scanning, the human body organs or physiological tissues are often scanned at different angles by ultrasound scanning equipment to obtain multiple ultrasound image videos. When watching ultrasound image videos, medical staff need to play and watch them one by one, so as to find ultrasound images with good imaging quality and meeting the observation requirements in multiple ultrasound image videos to assist diagnosis, but the process of finding ultrasound images with good imaging quality and meeting the observation requirements requires a lot of time, which affects the overall diagnosis and treatment progress. In the prior art, the standard sections of different body organs or physiological tissues are usually saved in the database first, and when scanning the body organs or physiological tissues of the human body, the medical staff are guided to find video frames matching the standard sections based on the standard sections; or, after obtaining the ultrasound image video, the corresponding standard section is retrieved from the database, and then the video frame matching the standard section is found in the ultrasound image video as the best ultrasound image for auxiliary diagnosis. The best ultrasound image obtained by existing technology only matches the theoretical standard section. Although it can present the overall situation of the body's organs or physiological tissues, the diseased tissues that actually need to be observed, such as lesions, in the body's organs or physiological tissues often have problems such as low clarity and small area, and cannot present the diseased tissues well. The ultrasound image is difficult to meet the observation requirements of the diseased area, and it is difficult for medical staff to observe the diseased tissue to be observed from the ultrasound image.

[0056] Figure 1FIG. 1 is an application environment diagram of an ultrasonic image acquisition method in an embodiment. The ultrasonic image acquisition method can be applied to a computer device, which can be a server or a terminal. Figure 1 As shown, taking the computer device as a medical imaging device 100 as an example, the medical imaging device 100 can scan and obtain an ultrasound image video segment 101 through a scanning device, and the ultrasound image video segment 101 includes a target object; after obtaining the ultrasound image video segment 101, a target area of ​​the target object is identified from the video frame of the ultrasound image video segment 101, and then image feature information of the target area in the video frame is extracted, and a target ultrasound image 102 is screened from the video frame of the ultrasound image video segment 101 based on the image feature information, so that after obtaining the ultrasound image video segment, based on the area to be observed of the target object in each video frame, that is, the image feature information of the target area, a target ultrasound image with good imaging quality and easy to observe in the area to be observed is quickly screened from the ultrasound image video segment, thereby reducing the time consumption of ultrasound image acquisition and improving the efficiency of ultrasound image acquisition.

[0057] Those skilled in the art will understand that Figure 1 The application environment shown in the figure is only one application scenario of the present application solution and does not constitute a limitation on the application scenario of the present application solution. Other application environments may also include Figure 1 More or less computer equipment as shown in Figure 1 Only one computer device is shown in FIG. 1 . It is understandable that the abnormal code processing system may also include one or more other servers, which are not specifically limited here. Figure 1 The application scenario shown may also include a memory for storing data, such as standard sections, ultrasound image video segments, etc.

[0058] It should also be noted that Figure 1 The scenario diagram of the exception code processing system shown is only an example. The exception code processing system and scenario described in the embodiment of the present invention are intended to more clearly illustrate the technical solution of the embodiment of the present invention, and do not constitute a limitation on the technical solution provided by the embodiment of the present invention. Ordinary technicians in this field can know that with the evolution of the exception code processing system and the emergence of new business scenarios, the technical solution provided by the embodiment of the present invention is also applicable to similar technical problems.

[0059] See also Figure 2 The present application embodiment provides an ultrasonic image acquisition method, which is mainly applied to the above Figure 1 Taking the server in the example as an example, the method includes steps S210 to S230, which are as follows:

[0060] S210: Acquire an ultrasound image video segment, where the ultrasound image video segment includes a target object.

[0061] The ultrasound image video segment refers to an image video captured by a medical imaging device. It can be understood that the ultrasound image video segment includes multiple video frames, and each video frame is an ultrasound image of a target object.

[0062] The target object refers to the scanned object of the ultrasound image video segment. In actual application scenarios, the target object can be, but is not limited to, an organ or physiological tissue of the body; for example, the target object can be the heart, liver, breast tissue, bone, etc., which are not limited here.

[0063] Specifically, the physiological tissue or body organ to be detected can be scanned by an ultrasonic scanning device, and multiple video frames can be obtained by scanning at different scanning positions to form an ultrasonic image video segment.

[0064] Furthermore, after scanning the physiological tissue or body organ to be detected by an ultrasonic scanning device and obtaining a plurality of video frames, the obtained video frames can be screened according to the standard sections. Specifically, in one embodiment, Figure 3 As shown, obtaining ultrasound image video segments specifically includes:

[0065] S310, obtaining an ultrasound image video source to be processed;

[0066] S320, acquiring a reference ultrasound image matching the standard section from a video frame of an ultrasound image video source;

[0067] S330: Determine an ultrasound image video segment to be processed from an ultrasound image video source based on the reference ultrasound image.

[0068] The ultrasound image video source may be an initial ultrasound image video obtained by scanning the physiological tissue or body organ to be detected by an ultrasound scanning device; and the ultrasound image video segment may be a segment of ultrasound image video captured from the ultrasound image video source.

[0069] Among them, standard sections refer to ultrasound images that can display all characteristic information of organs or physiological tissues of the body; for example, for the heart, its standard sections include parasternal left ventricular long axis section, aortic short axis section, and apical four-chamber and five-chamber heart section. The reference ultrasound image refers to a video frame in the ultrasound image video source that is similar to the standard section.

[0070] Specifically, standard sections of different body organs or physiological tissues can be first obtained and saved in a database; after obtaining the ultrasound image video source, the standard section corresponding to the target object (i.e., the physiological tissue or body organ to be detected) is obtained from the database; then, the video frames in the ultrasound image video source are used as target video frames in turn, and the matching degree between the target video frame and the standard section is calculated. If the matching degree is greater than a preset matching threshold, the target video frame is determined as a reference ultrasound image.

[0071] After determining the reference ultrasound image, determine the ultrasound image video segment to be processed from the ultrasound image video source. Specifically, the ultrasound image video segment can be determined from the ultrasound image video source based on the frame sequence of the reference ultrasound image. For example, if the frame sequence of the reference ultrasound image is t, then the video frames with a frame sequence of (t-5) to (t+5) in the ultrasound image video source can be determined as the ultrasound image video segment.

[0072] Ultrasound image video segments are screened based on standard sections, so that the ultrasound image video frames that can see the target object most clearly are used as subsequent data processing objects, thereby improving the observability of the target object in the subsequent data processing objects, improving the accuracy of target ultrasound image screening, and reducing the amount of subsequent image processing, thereby improving the efficiency of obtaining the target ultrasound image.

[0073] S220: Identify a target area of ​​the target object from video frames of the ultrasound image video segment.

[0074] The target area refers to an area that can characterize the characteristic information of the target object. In actual application scenarios, taking the target object as an organ or physiological tissue, the target area refers to the area where the diseased tissue in the organ or physiological tissue is located, wherein the diseased tissue is an abnormal tissue existing inside or near the organ or physiological tissue. After acquiring the ultrasound image video segment, for each video frame in the ultrasound image video segment, the target area of ​​the target object in the video frame is identified.

[0075] Specifically, the target area of ​​the target object in the video frame can be identified by inputting the video frame into a deep learning model for identifying the target area in the target object, and identifying the target area of ​​the target object in the video frame through the deep learning model. The deep learning model is a trained deep learning model, such as a convolutional neural network, a deconvolutional neural network, a deep neural network, etc., which is not limited here.

[0076] More specifically, in one embodiment, Figure 4 As shown, step S220 locates the target area where the target object is located from the video frame of the ultrasound image video segment, including:

[0077] S410, inputting a video frame of the ultrasound image video segment into an object recognition model to obtain an object type of a target object in the ultrasound image video segment;

[0078] S420, determining a target region segmentation model corresponding to the object type, inputting the video frames in the ultrasound image video segment into the target region segmentation model, and obtaining a target region of the target object.

[0079] The object recognition model refers to a deep learning model for identifying the object type of a target object, such as a convolutional neural network, a deconvolutional neural network, a deep neural network, etc., which is not limited here. It can be understood that the object recognition model here is a trained model.

[0080] Among them, the target region segmentation model refers to a deep learning model used to identify the target region in the positioning mark object, such as a convolutional neural network, a deconvolutional neural network, a deep neural network, etc., which is not limited here. It can be understood that for different object types, target region segmentation models corresponding to different object types can be trained accordingly. After the object type of the target object is obtained, the video frame is input into the target region segmentation model corresponding to the object type of the target object to obtain the target region of the target object in the video frame.

[0081] Taking the case where the target object is physiological tissue and the target area refers to the area where the diseased tissue in the physiological tissue is located as an example, the video frames of the ultrasound image video segment are input into the object recognition model to obtain the part type of the physiological tissue in the ultrasound image video; determine the target area segmentation model corresponding to the part type, input the video frames in the ultrasound image video segment into the target area segmentation model, and obtain the target area where the diseased tissue in the physiological tissue is located.

[0082] By first confirming the object type of the target object in the video frame and then segmenting the target area of ​​the video frame based on a target area segmentation model corresponding to the object type, the positioning speed of the target area can be improved.

[0083] S230, extracting image feature information of the target area in the video frame, and screening the target ultrasound image from the video frame of the ultrasound image video segment based on the image feature information.

[0084] Among them, image feature information refers to feature information extracted from the image data of the target area, especially observable characteristic information, such as shape features, texture features, etc.; specifically, image feature information includes but is not limited to morphological feature information, number of pixels, grayscale information, noise information, etc. of the target area.

[0085] The target ultrasound image is selected from the video frames of the ultrasound image video segment based on the image feature information, and specifically, the video frame with more image feature information in the target area or a higher feature value corresponding to the image feature information is selected as the target ultrasound image. Since the image feature information of the target area can reflect the observable characteristic information of the target area in the video frame, when further data processing is performed based on the target ultrasound image, the accuracy of the subsequent processing results can be improved based on the target ultrasound image with more feature information or a higher feature value in the feature information.

[0086] Still taking the example that the target object is the physiological tissue and the target area refers to the area where the diseased tissue is located in the physiological tissue, based on the image feature information of the area where the diseased tissue is located in each video frame, the video frames with more feature information or higher feature values ​​in the feature information in the area where the diseased tissue is located are screened as target ultrasound images. When the diseased tissue is subsequently classified based on the target ultrasound images, the target ultrasound images with more feature information or higher feature values ​​in the feature information can improve the accuracy of the subsequent diseased tissue classification.

[0087] Specifically, in one embodiment, the image feature information includes morphological feature information of the target area; step S230 includes: inputting the image data of the video frame into a morphological feature recognition model to obtain the morphological feature information of the target area; obtaining the similarity between the morphological feature information and the standard morphological feature information corresponding to the target area; and determining the video frame whose similarity is greater than a preset similarity threshold as the target ultrasound image in the ultrasound image video segment.

[0088] Among them, the morphological feature information of the target area includes but is not limited to the edge features, texture features, shape features, etc. of the target area; for example, edge features include smooth edges and calcified edges, etc., texture features include echo textures and anechoic textures, etc., and shape features include regular shapes and irregular shapes, etc.

[0089] The standard morphological feature information refers to the morphological feature information of a target region when the target region is a region where a diseased tissue in a physiological tissue is located.

[0090] Specifically, after determining the target area in the video frame, the image data is input into the morphological feature recognition model, and the morphological feature information of the target area is obtained through the morphological feature recognition model. The morphological feature recognition model is a deep learning model for morphological recognition of the target area, such as a convolutional neural network, a deconvolutional neural network, a deep neural network, etc., which is not limited here.

[0091] It can be understood that the morphological feature recognition model here is a trained model; for example, ultrasound image samples of the target object and annotation information of the ultrasound image samples can be obtained in advance, wherein the annotation information includes the position of the target area in the target object and different morphological features of the target area, and then the pre-constructed morphological feature recognition model is trained based on the ultrasound image samples and the annotation information corresponding to the ultrasound image samples, so that the morphological feature recognition model can recognize the morphological features of the target area in the input image.

[0092] Taking the case where the target object is a physiological tissue, the target area is an area where the diseased tissue in the physiological tissue is located, and the morphological features include edge features, texture features, and shape features as an example, the area where the diseased tissue is located and the morphological features of the area where the diseased tissue is located are marked in the ultrasound image sample. Specifically, if the edge feature of the area where the diseased tissue is located in the ultrasound image sample is a smooth edge, it is marked as "10", and if it is a calcified edge, it is marked as "11"; if the texture feature of the area where the diseased tissue is located in the ultrasound image sample is an echo texture, it is marked as "20", and if it is an echo-free texture, it is marked as "21"; if the shape feature of the area where the diseased tissue is located in the ultrasound image sample is a regular shape, it is marked as "30", and if it is an irregular shape, it is marked as "31". After training the pre-constructed morphological feature recognition model based on the ultrasound image samples and the annotation information corresponding to the ultrasound image samples, the video frame in the ultrasound image video segment (the area where the diseased tissue is located in the video frame has been determined) is input into the morphological feature recognition model, and the edge feature category (i.e., smooth edge or calcified edge), texture feature category (i.e., echo texture or anechoic texture) and shape feature category (i.e., regular shape or irregular shape) of the area where the diseased tissue is located can be obtained.

[0093] After obtaining the morphological feature information of the target area, the morphological feature information is compared with the standard morphological feature information to calculate the similarity between the two; then, the video frame with a similarity greater than a preset similarity threshold is determined as the target ultrasound image in the ultrasound image video segment, so that the video frame that can display more morphological feature information of the target area is used as the target ultrasound image.

[0094] For example, the similarity between the morphological feature information and the standard morphological feature information can be calculated, and when the similarity reaches a preset similarity threshold (such as 80%), the video frame is determined as the target ultrasound image; for another example, the standard morphological feature information includes 5 morphological feature information, and the morphological feature information of the target area of ​​a certain video frame includes 4 morphological feature information, and the preset similarity threshold of 80% is reached, then the video frame is determined as the target ultrasound image, and the ultrasound image taken at a certain angle or at a certain time and showing the most complete morphology of the diseased tissue or the most morphological features of the diseased tissue is taken as the best frame.

[0095] Taking the case where the target object is a physiological tissue and the target area refers to the area where the diseased tissue in the physiological tissue is located as an example, based on the morphological feature information of the area where the diseased tissue is located in each video frame, the video frames that can show more pathological morphologies in the area where the diseased tissue is located are screened as target ultrasound images. It can be understood that compared with other ultrasound images in the ultrasound video segment, the target area in the target ultrasound image has the largest area and can express more feature information. When further data processing is performed based on the target ultrasound image, the accuracy of subsequent processing results can be improved. For example, when the diseased tissue is subsequently classified based on the target ultrasound image, since the area where the diseased tissue is located in the target ultrasound image is larger, more disease information can be provided, effectively improving the accuracy of subsequent diseased tissue classification.

[0096] In one embodiment, the image feature information includes the number of pixels; extracting the image feature information of the target area in the video frame, and screening the target ultrasound image from the video frame of the ultrasound image video segment based on the image feature information, including: obtaining the number of pixels in the target area in the video frame; and determining the video frame whose number of pixels is greater than a preset pixel threshold as the target ultrasound image in the ultrasound image video segment.

[0097] The number of pixels in the target area can represent the area size of the target area. By obtaining the number of pixels in the target area in each video frame, the area size of the target area in each video can be obtained.

[0098] The preset pixel threshold can be set according to actual conditions. Specifically, by determining the video frame with a number of pixels greater than the preset pixel threshold as the ultrasound image video segment, the video frame with the largest target area is used as the target ultrasound image.

[0099] Still taking the example that the target object is the physiological tissue and the target area refers to the area where the diseased tissue is located in the physiological tissue, based on the number of pixels in the area where the diseased tissue is located in each video frame, the video frame with the largest area (i.e., the largest number of pixels) in the area where the diseased tissue is located is selected as the target ultrasound image.

[0100] It is understandable that, compared with other ultrasound images in the ultrasound video segment, the target area in the target ultrasound image is the largest, that is, it has more feature information, and when further data processing is performed based on the target ultrasound image, the accuracy of subsequent processing results can be improved. For example, when lesion tissue is subsequently classified based on the target ultrasound image, since the target ultrasound image has a larger area where the lesion tissue is located, it can provide more lesion information, effectively improving the accuracy of subsequent lesion tissue classification.

[0101] In one embodiment, the image feature information includes a grayscale contrast value; extracting the image feature information of the target area in the video frame, and screening the target ultrasound image from the video frame of the ultrasound image video segment based on the image feature information, including: determining the associated area corresponding to the target area from the video frame; obtaining the grayscale contrast value according to the image grayscale value of the target area and the image grayscale value of the associated area; and determining the video frame whose grayscale contrast value is greater than a preset grayscale threshold as the target ultrasound image in the ultrasound image video segment.

[0102] The associated area refers to the surrounding area of ​​the target area, and the associated area surrounds the target area; for example, the boundary pixel point of the target area can be used as the starting point, and a certain number of pixels can be expanded to the surrounding area, and the area obtained by the expansion is determined as the associated area.

[0103] After the associated region is obtained, the grayscale contrast value between the target region and the associated region can be calculated, wherein the grayscale contrast value can be used to reflect the clarity of the boundary between the target region and the associated region. By determining the video frame whose grayscale contrast value is greater than the preset grayscale threshold as the ultrasound image video segment, the video frame with the clearest boundary is used as the target ultrasound image.

[0104] Still taking the example that the target object is the physiological tissue and the target area refers to the area where the diseased tissue is located in the physiological tissue, based on the grayscale contrast value between the area where the diseased tissue is located and the associated area in each video frame, the video frame with the clearest boundary of the area where the diseased tissue is located is selected as the target ultrasound image.

[0105] It can be understood that, compared with other ultrasound images in the ultrasound video segment, the grayscale contrast value between the target area and the associated area in the target ultrasound image is the largest, that is, the boundary of the target area is the clearest, and when further data processing is performed based on the target ultrasound image, the accuracy of the subsequent processing results can be improved. For example, when the target ultrasound image is used to segment the area where the diseased tissue is located, since the boundary of the target ultrasound image where the diseased tissue is located is clearer, more boundary information can be provided, which effectively improves the accuracy of the subsequent diseased tissue segmentation.

[0106] In one embodiment, the image feature information includes a noise value; extracting the image feature information of the target area in the video frame, and screening the target ultrasound image from the video frame of the ultrasound image video segment based on the image feature information, including: obtaining noise pixels in the target area; calculating the noise value of the target area in the video frame based on the noise pixels; and determining the video frame whose noise value is less than a preset noise threshold as the target ultrasound image in the ultrasound image video segment.

[0107] Among them, noise pixel points refer to black points in the target area; specifically, each pixel point in the target area can be traversed, and the grayscale value of each pixel point can be obtained; if the grayscale value of the pixel point is greater than or equal to the preset grayscale value threshold, the pixel point is determined as a black area pixel point, and then it is determined whether each black area pixel point is a separate pixel point. If so, the black area pixel point is determined as a noise pixel point.

[0108] After obtaining the noise pixel points in the target area, the noise value of the target area can be determined according to the number of noise pixel points, and the video frame with a noise value less than a preset noise threshold can be determined as the target ultrasound image. By determining the video frame with a noise value of the target area less than the preset noise threshold as the target ultrasound image in the ultrasound image video segment, the video frame with less noise can be used as the target ultrasound image.

[0109] Still taking the example that the target object is the physiological tissue and the target area refers to the area where the diseased tissue is located in the physiological tissue, based on the noise value of the area where the diseased tissue is located in each video frame, the video frame with the least noise information in the area where the diseased tissue is located is selected as the target ultrasound image.

[0110] It is understandable that, compared with other ultrasound images in the ultrasound video segment, the target area in the target ultrasound image has the least noise information, and when further data processing is performed based on the target ultrasound image, the accuracy of the subsequent processing results can be improved. For example, when the target ultrasound image is used to classify the area where the diseased tissue is located, the target ultrasound image contains less noise and more useful information, which effectively improves the accuracy of the subsequent classification of the diseased tissue.

[0111] The above-mentioned ultrasonic image acquisition method obtains an ultrasonic image video segment, which includes a target object, identifies a target area of ​​the target object from a video frame of the ultrasonic image video segment, and then extracts image feature information of the target area in the video frame, and screens the target ultrasonic image from the video frame of the ultrasonic image video segment based on the image feature information. After the ultrasonic image video segment is acquired, based on the area to be observed of the target object in each video frame, that is, the image feature information of the target area, the target ultrasonic image with good imaging quality and easy observation in the area to be observed is quickly screened from the ultrasonic image video segment, thereby reducing the time consumption of ultrasonic image acquisition and improving the efficiency of ultrasonic image acquisition.

[0112] Further, as mentioned above, the image feature information includes but is not limited to at least one of the morphological feature information of the target area, the number of pixels in the target area, the grayscale contrast value between the target area and the associated area, and the noise value of the target area; therefore, in one embodiment, the target ultrasound image can also be screened from the video frames of the ultrasound image video segment based on any two or more of the above-mentioned image feature information.

[0113] For example, the target ultrasound image can be screened from the video frame of the ultrasound image video segment based on the morphological feature information and the number of pixels of the target area. Specifically, the image data of the video frame is first input into the morphological feature recognition model to obtain the morphological feature information of the target area, and the similarity between the morphological feature information and the standard morphological feature information corresponding to the target area is obtained, and the number of pixels of the target area in the video frame is obtained at the same time; after obtaining the similarity between the morphological feature information of the target area and the standard morphological feature information corresponding to the target area, and the number of pixels of the target area, the video frame with a similarity greater than a preset similarity threshold and a number of pixels greater than a preset pixel threshold can be determined as the target ultrasound image in the ultrasound image video segment; the video frame with a similarity greater than a preset similarity threshold can be first determined as the preliminary screening ultrasound image in the ultrasound image video segment, and then the video frame with a number of pixels greater than the preset pixel threshold in the preliminary screening ultrasound image can be determined as the target ultrasound image; the video frame with a number of pixels greater than the preset pixel threshold can also be first determined as the preliminary screening ultrasound image in the ultrasound image video segment, and the video frame with a similarity greater than the preset similarity threshold can be determined as the target ultrasound image in the preliminary screening ultrasound image.

[0114] For another example, the target ultrasound image may be screened from the video frames of the ultrasound image video segment based on the morphological feature information of the target area and the grayscale contrast value between the target area and the associated area. Specifically, the image data of the video frame is first input into the morphological feature recognition model to obtain the morphological feature information of the target area, and the similarity between the morphological feature information and the standard morphological feature information corresponding to the target area is obtained. At the same time, the associated area corresponding to the target area is determined from the video frame, and the grayscale contrast value is obtained according to the image grayscale value of the target area and the image grayscale value of the associated area. After obtaining the similarity between the morphological feature information of the target area and the standard morphological feature information corresponding to the target area, and the grayscale contrast value between the target area and the associated area, the video frame whose similarity is greater than a preset similarity threshold and whose grayscale contrast value is greater than a preset grayscale threshold can be determined as the target ultrasound image in the ultrasound image video segment; the video frame whose grayscale contrast value is greater than the preset grayscale threshold can also be first determined as the preliminary screening ultrasound image in the ultrasound image video segment, and then the video frame whose similarity is greater than the preset similarity threshold can be determined as the target ultrasound image in the preliminary screening ultrasound image; the video frame whose similarity is greater than the preset similarity threshold can also be first determined as the preliminary screening ultrasound image in the ultrasound image video segment, and the video frame whose grayscale contrast value is greater than the preset grayscale threshold can be determined as the target ultrasound image in the preliminary screening ultrasound image.

[0115] It can be understood that based on any two or more of the image feature information including the morphological feature information of the target area, the number of pixels in the target area, the grayscale contrast value between the target area and the associated area, and the noise value of the target area, the target ultrasound image can be screened from the video frames of the ultrasound image video segment. The target ultrasound image can be screened according to the above examples, which will not be elaborated here.

[0116] Furthermore, in addition to screening the target ultrasound image based on the image feature information of the target area in the target object, the target ultrasound image can also be screened based on the image data of the video frame. In one embodiment, the ultrasound image acquisition method includes: acquiring an ultrasound image video segment, the ultrasound image video segment includes the target object; acquiring a black area in the video frame of the ultrasound image video segment; counting the number of pixels in the black area in each video frame, and determining the video frame with a number of pixels less than a preset pixel threshold as the target ultrasound image.

[0117] In this embodiment, the specific definition of the step of obtaining the ultrasound image video segment can refer to the definition of obtaining the ultrasound image video segment in the above text, which will not be repeated here.

[0118] The black area refers to an area in the video frame composed of pixels whose grayscale value is greater than a preset grayscale value. Specifically, after obtaining the black area in the video frame, the pixels in the black area are counted, and the video frame with a pixel count less than a preset pixel threshold is determined as the target ultrasound image.

[0119] It can be understood that the black area refers to an area in the video frame without any valid image information. The larger the black area, the less valid image information in the corresponding video frame, and the smaller the black area, the more valid image information in the corresponding video frame. Therefore, by screening the video frames whose pixels in the black area are less than the preset pixel threshold as the target ultrasound image, the amount of image information in the subsequent ultrasound image processing can be effectively guaranteed to improve the efficiency or accuracy of image processing.

[0120] In order to better implement the ultrasonic image acquisition method provided in the embodiment of the present application, on the basis of the ultrasonic image acquisition method provided in the embodiment of the present application, an ultrasonic image acquisition device is also provided in the embodiment of the present application, such as Figure 5 As shown, the ultrasound image acquisition device 500 includes:

[0121] An image video acquisition module 510 is used to acquire an ultrasound image video segment, wherein the ultrasound image video segment includes a target object;

[0122] A target region determination module 520 is used to identify a target region of a target object from a video frame of an ultrasound image video segment;

[0123] The ultrasound image screening module 530 is used to extract image feature information of a target area in a video frame, and screen a target ultrasound image from the video frame of the ultrasound image video segment based on the image feature information.

[0124] In some embodiments of the present application, the image feature information includes morphological feature information of the target area; the ultrasound image screening module 530 is specifically used to input the image data of the video frame into the morphological feature recognition model to obtain the morphological feature information of the target area; obtain the similarity between the morphological feature information and the standard morphological feature information corresponding to the target area; and determine the video frame whose similarity is greater than a preset similarity threshold as the target ultrasound image in the ultrasound image video segment.

[0125] In some embodiments of the present application, the image feature information includes the number of pixels; the ultrasound image screening module 530 is specifically used to obtain the number of pixels in the target area in the video frame; and the video frame with a number of pixels greater than a preset pixel threshold is determined as the target ultrasound image in the ultrasound image video segment.

[0126] In some embodiments of the present application, image feature information includes grayscale contrast value; the ultrasound image screening module 530 is specifically used to determine the associated area corresponding to the target area from the video frame; obtain the grayscale contrast value according to the image grayscale value of the target area and the image grayscale value of the associated area; and determine the video frame whose grayscale contrast value is greater than the preset grayscale threshold as the target ultrasound image in the ultrasound image video segment.

[0127] In some embodiments of the present application, image feature information includes noise value; the ultrasound image screening module 530 is specifically used to obtain noise pixel points in the target area; calculate the noise value of the target area in the video frame based on the noise pixel points; and determine the video frame with a noise value less than a preset noise threshold as the target ultrasound image in the ultrasound image video segment.

[0128] In some embodiments of the present application, the image video acquisition module 510 is specifically used to obtain an ultrasound image video source to be processed; obtain a reference ultrasound image matching a standard section from a video frame of the ultrasound image video source; and determine an ultrasound image video segment to be processed from the ultrasound image video source based on the reference ultrasound image.

[0129] In some embodiments of the present application, the target area determination module 530 is used to input the video frames of the ultrasound image video segment into the object recognition model to obtain the object type of the target object in the ultrasound image video segment; determine the target area segmentation model corresponding to the object type, input the video frames in the ultrasound image video segment into the target area segmentation model, and obtain the target area of ​​the target object.

[0130] For the specific definition of the ultrasonic image acquisition device, please refer to the definition of the ultrasonic image acquisition method above, which will not be repeated here. Each module in the above-mentioned ultrasonic image acquisition device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0131] In some embodiments of the present application, the ultrasound image acquisition device 500 may be implemented in the form of a computer program. The computer program may be implemented in a computer program such as Figure 6 The computer device shown in the figure is run on the computer device. The memory of the computer device can store various program modules constituting the ultrasound image acquisition device 500, for example, Figure 5 The video acquisition module 510, the target area determination module 520 and the ultrasound image screening module 530 are shown. The computer program composed of various program modules enables the processor to execute the steps of the ultrasound image acquisition method of each embodiment of the present application described in this specification.

[0132] For example, Figure 6 The computer device shown in FIG. 5 can perform step S210 through the image video acquisition module 510 in the ultrasonic image acquisition device 900 shown in FIG. 5. The computer device can perform step S220 through the target area determination module 520. The computer device can perform step S230 through the ultrasonic image screening module 530. The computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external computer device through a network connection. When the computer program is executed by the processor, an ultrasonic image acquisition method is implemented.

[0133] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0134] In some embodiments of the present application, a medical imaging device is provided, comprising one or more processors; a memory; and one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor in the steps of the ultrasound image acquisition method. The steps of the ultrasound image acquisition method here may be the steps of the ultrasound image acquisition method in each of the above embodiments.

[0135] In some embodiments of the present application, a computer-readable storage medium is provided, which stores a computer program, and the computer program is loaded by a processor, so that the processor executes the steps of the ultrasound image acquisition method. The steps of the ultrasound image acquisition method here can be the steps in the ultrasound image acquisition method of each of the above embodiments.

[0136] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Any reference to memory, storage, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0137] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0138] The above is a detailed introduction to an ultrasonic image acquisition method, device, medical imaging equipment and storage medium provided in the embodiments of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for acquiring an ultrasonic image, characterized in that: include: Acquire an ultrasound image video segment, wherein the ultrasound image video segment includes a target object; identifying a target area of ​​the target object from a video frame of the ultrasound image video segment; Extracting image feature information of a target area in the video frame, and screening a target ultrasound image from the video frame of the ultrasound image video segment based on the image feature information; the image feature information includes at least one of morphological feature information, number of pixels, grayscale contrast value, and noise value of the target area; The step of identifying a target area of ​​the target object from a video frame of the ultrasound image video segment includes: Inputting the video frame of the ultrasound image video segment into an object recognition model to obtain the object type of the target object in the ultrasound image video segment; A target region segmentation model corresponding to the object type is determined, and the video frames in the ultrasound image video segment are input into the target region segmentation model to obtain the target region of the target object.

2. The method according to claim 1, characterized in that The step of extracting image feature information of the target area in the video frame, and screening the target ultrasound image from the video frame of the ultrasound image video segment based on the image feature information, comprises: Inputting the image data of the video frame into a morphological feature recognition model to obtain morphological feature information of the target area; Acquire the similarity between the morphological feature information and the standard morphological feature information corresponding to the target area; The video frame whose similarity is greater than a preset similarity threshold is determined as the target ultrasound image in the ultrasound image video segment.

3. The method according to claim 1, characterized in that The step of extracting image feature information of the target area in the video frame, and screening the target ultrasound image from the video frame of the ultrasound image video segment based on the image feature information, comprises: Obtaining the number of pixels in the target area of ​​the video frame; A video frame whose number of pixels is greater than a preset pixel threshold is determined as a target ultrasound image in the ultrasound image video segment.

4. The method according to claim 1, characterized in that: The step of extracting image feature information of the target area in the video frame, and screening the target ultrasound image from the video frame of the ultrasound image video segment based on the image feature information, comprises: Determining an associated area corresponding to the target area from the video frame; Obtaining a grayscale contrast value according to the image grayscale value of the target area and the image grayscale value of the associated area; The video frame whose grayscale contrast value is greater than a preset grayscale threshold is determined as the target ultrasound image in the ultrasound image video segment.

5. The method according to claim 1, characterized in that The step of extracting image feature information of the target area in the video frame, and screening the target ultrasound image from the video frame of the ultrasound image video segment based on the image feature information, comprises: Obtain the noise pixel points in the target area; Calculating the noise value of the target area in the video frame according to the noise pixel points; A video frame whose noise value is less than a preset noise threshold is determined as a target ultrasound image in the ultrasound image video segment.

6. The method according to any one of claims 1 to 5, characterized in that: The step of acquiring the ultrasound image video segment further includes: Obtaining an ultrasound image video source to be processed; Acquire a reference ultrasound image matching a standard section from a video frame of the ultrasound image video source; Based on the reference ultrasound image, an ultrasound image video segment to be processed is determined from the ultrasound image video source.

7. An ultrasonic image acquisition device, characterized in that: The device comprises: An image video acquisition module, used to acquire an ultrasound image video segment, wherein the ultrasound image video segment includes a target object; A target region determination module, configured to identify a target region of the target object from a video frame of the ultrasound image video segment; an ultrasonic image screening module, configured to extract image feature information of a target area in the video frame, and screen a target ultrasonic image from the video frame of the ultrasonic image video segment based on the image feature information; the image feature information includes at least one of morphological feature information, number of pixels, grayscale contrast value, and noise value of the target area; The target area determination module is further used for: Inputting the video frame of the ultrasound image video segment into an object recognition model to obtain the object type of the target object in the ultrasound image video segment; A target region segmentation model corresponding to the object type is determined, and the video frames in the ultrasound image video segment are input into the target region segmentation model to obtain the target region of the target object.

8. A medical imaging device, characterized in that: The medical imaging equipment includes: one or more processors; Memory; and One or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the processor to implement the ultrasound image acquisition method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and the computer program is loaded by a processor to execute the steps in the ultrasound image acquisition method according to any one of claims 1 to 6.

Images