Ultrasonic video processing method, device and computer equipment

Abstract

The present application relates to a method, device, computer equipment, storage medium and computer program product for processing ultrasound video. The method comprises: obtaining ultrasound video stream segments, determining the detection part type, the anatomical section and the standard condition of the anatomical section involved in each ultrasound video image frame of the ultrasound video stream segment; if the ultrasound video segment includes at least one most standard section of an anatomical section type, then obtaining the video stream segment of the most standard section based on the ultrasound video image frames related to the anatomical section type in the ultrasound video segment. By using this method, the ultrasound video image frames of the most standard section and those related to the most standard section are displayed to the doctor, providing the doctor with ultrasound video dynamic information.

Description

Technical Field

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

[0002] Prenatal ultrasound examination is the preferred detection method for secondary prevention of birth defects. It is a crucial imaging examination for fetal anatomical structure examination. Fetal abnormalities found and diagnosed by prenatal ultrasound are an important basis for clinical treatment and decision-making. The advancement of prenatal ultrasound examination technology can enable more fetal abnormalities to be discovered, which is of great significance to improving the efficiency and quality of prenatal screening.

[0003] Prenatal ultrasound examinations in my country are currently facing challenges such as low standardization, low efficiency, and talent shortages: Each prenatal ultrasound examination includes 30-50 standard sections, which takes more than 30-50 minutes. Each ultrasound anatomical section requires the doctor to make subjective judgments and manually obtain it, and the saved anatomical section images are not standard and are often single-frame static images, from which doctors can obtain less information. The most important advantage of ultrasound is real-time dynamic images. How to preserve and automatically obtain dynamic short videos of standard sections is currently a difficult problem. Summary of the invention

[0004] Based on this, it is necessary to provide an ultrasound video processing method, device, computer equipment, computer-readable storage medium and computer program product that can increase the amount of ultrasound video image information in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for processing an ultrasound video, the method comprising:

[0006] Obtaining ultrasound video stream segments;

[0007] Determining the detection part type involved in each ultrasound video image frame of the ultrasound video stream segment, the anatomical structure section to which it belongs, and the standard condition of the anatomical structure section;

[0008] If the ultrasound video segment includes at least one most standard slice of an anatomical structure slice type, a video stream segment of the most standard slice is obtained according to ultrasound video image frames related to the anatomical structure slice type in the ultrasound video segment.

[0009] In one embodiment, the step of determining the detection part type, the anatomical structure section, and the standard condition of the anatomical structure section involved in each ultrasound video image frame of the ultrasound video stream segment includes:

[0010] Identifying the detection part type involved in each ultrasound video image frame of the ultrasound video stream segment frame by frame;

[0011] Each of the ultrasound video image frames is input into an anatomical structure recognition model of a corresponding detection part type to obtain the anatomical structure section to which the ultrasound video image frame belongs and a standard condition of the anatomical structure section.

[0012] In one of the embodiments, the method further includes: generating an ultrasound video stream queue corresponding to the ultrasound video stream segment, wherein the ultrasound video stream queue records the detection part type, the anatomical structure section and the standard condition of the anatomical structure section involved in each of the ultrasound video image frames of the ultrasound video stream segment.

[0013] In one embodiment, the standard condition of the anatomical structure section includes whether the section is a standard section and a score of the section; and the method of determining whether the ultrasound video segment includes the most standard section of at least one anatomical structure section type includes:

[0014] If the ultrasound video segment includes at least one standard section of an anatomical section type, the score of the standard section of the anatomical section type included in the ultrasound video segment is compared with the score of the current most standard section of the anatomical section type; if the score of the standard section of the anatomical section type included in the ultrasound video segment is greater than the score of the current most standard section of the anatomical section type, the standard section of the anatomical section type included in the ultrasound video segment is marked as the current most standard section of the anatomical section type.

[0015] In one of the embodiments, after the step of obtaining the video stream segment of the most standard section, the method further includes:

[0016] Output a video stream segment of the most standard slice of at least one anatomical structure slice type currently detected.

[0017] In one embodiment, the method further comprises:

[0018] storing the most standard slices of each anatomical structure slice type detected through all current ultrasound video stream segments;

[0019] After the ultrasonic examination is completed, the most standard section of each anatomical structure section type and the video stream segment of the most standard section are obtained.

[0020] In one embodiment, obtaining the video stream segment of the most standard section according to the ultrasound video image frame related to the anatomical structure section type in the ultrasound video segment includes:

[0021] The ultrasound video image frame of the most standard section is used as the tail of the first ultrasound video stream queue and the head of the second ultrasound video stream queue;

[0022] Ultrasound video image frames of the same anatomical structure section type as the ultrasound video image frames of the most standard section are selected from the first ultrasound video stream queue and the second ultrasound video stream queue, and combined into a video stream segment of the most standard section.

[0023] In a second aspect, the present application provides an ultrasound video processing device, the device comprising:

[0024] An image acquisition module, used for acquiring ultrasound video stream segments;

[0025] An image frame determination module, used to determine the detection part type involved in each ultrasound video image frame of the ultrasound video stream segment, the anatomical structure section to which it belongs, and the standard condition of the anatomical structure section;

[0026] The output module is used to obtain a video stream segment of the most standard section according to the ultrasound video image frames related to the anatomical structure section type in the ultrasound video segment if the ultrasound video segment includes at least one most standard section of the anatomical structure section type.

[0027] In a third aspect, the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method described in the above embodiments when executing the computer program.

[0028] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method described in the above embodiments are implemented.

[0029] In a fifth aspect, the present application provides a computer program product, including a computer program, which implements the steps of the methods described in the above embodiments when executed by a processor.

[0030] The above-mentioned ultrasound video processing method, device, computer equipment, storage medium and computer program product obtain ultrasound video stream segments, determine the detection part type involved in each ultrasound video image frame of the ultrasound video stream segment, the anatomical structure section to which it belongs, and the standard situation of the anatomical structure section, and if the ultrasound video segment includes at least one most standard section of the anatomical structure section type, then according to the ultrasound video image frame related to the anatomical structure section type in the ultrasound video segment, obtain the video stream segment of the most standard section. In this way, the ultrasound video image frames of the most standard section and those related to the most standard section are displayed to the doctor, providing the doctor with ultrasound video dynamic information. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 is an application environment diagram of an ultrasound video processing method in one embodiment;

[0032] Figure 2 is a schematic flow chart of a method for processing ultrasound video in one embodiment;

[0033] Figure 3 A schematic diagram of a flow chart of a step of determining the most standard ultrasound video image frame in one embodiment;

[0034] Figure 4 A schematic diagram of a flow chart of a method for real-time recognition and capture of standard video stream segments in one embodiment;

[0035] Figure 5 is a structural block diagram of an ultrasonic video processing device in one embodiment;

[0036] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0038] In modern medicine, ultrasound has become a common, routine, and indispensable imaging examination method. Ultrasound imaging is a method of using ultrasound to obtain visible images of objects. Since ultrasound can penetrate many opaque objects, it is possible to obtain information about the acoustic properties of the internal structure of these objects using ultrasound. Ultrasound imaging technology turns this information into images visible to the human eye.

[0039] At present, the existing automatic recognition method of the standard section of the fetus in the ultrasound video image can only obtain a single frame of the standard section image, and cannot obtain the continuous segment of the standard section.

[0040] On the one hand, due to the uncertain position of the fetus in the mother's body, the mother's physical condition, the doctor's examination technique and other factors, the various anatomical structures of the fetus change dynamically in the ultrasound video image, and the doctor cannot determine whether the various anatomical structures in the ultrasound video image of the fetus are normal; on the other hand, due to the low refresh rate of the ultrasound detector, a certain standard section of the fetus often flashes when the ultrasound video of the fetus is detected. The doctor has no time to analyze the dynamic changes of the section before and after, and it is difficult for the doctor to scan the section again due to factors such as fetal movement; on the other hand, if the doctor wants to obtain the dynamic change fragments of the standard sections of all fetal sections for diagnosis, he can only save the complete ultrasound video and then manually capture it. This will not only consume a lot of human and physical resources and fail to meet the real-time standards, but will also be affected by the doctor's level of cognition of the standard sections, resulting in inconsistent results.

[0041] In view of this, the ultrasonic video processing method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown.

[0042] The doctor scans the fetus by using the probe of the ultrasound instrument 102 to obtain ultrasound video stream segments; the processor 100 collects the ultrasound video stream segments in the ultrasound instrument 102 through the acquisition card, and the processor 100 determines the detection part type involved in each ultrasound video image frame of the ultrasound video stream segment, the anatomical structure section to which it belongs, and the standard condition of the anatomical structure section; if the ultrasound video segment includes at least one most standard section of the anatomical structure section type, then according to the ultrasound video image frames related to the anatomical structure section type in the ultrasound video segment, a video stream segment of the most standard section is obtained, and the processor 100 returns the video stream segment of the most standard section to the ultrasound instrument 102 and presents it on the display device of the ultrasound instrument 102.

[0043] The processor 100 may be, but is not limited to, various personal computers, laptop computers, etc. The processor 100 has an image acquisition function and has a certain graphics processing capability.

[0044] In one embodiment, Figure 2 As shown, a method for processing ultrasound video is provided, and the method is applied to Figure 1 The processor in the example is used to illustrate, including the following steps:

[0045] S200: Acquire an ultrasound video stream segment.

[0046] Among them, obtaining the ultrasound video stream fragment includes: obtaining the ultrasound video stream image obtained by the ultrasound instrument for ultrasonic detection, the processor samples the ultrasound video stream image according to a preset frequency, and the ultrasound video stream fragment with a suitable frame rate can be obtained by adjusting the preset sampling frequency of the acquisition card in the processor.

[0047] Specifically, a driver is written into the ultrasound instrument. When a doctor performs an ultrasound examination on a pregnant woman, the ultrasound instrument acquires ultrasound video stream images in real time, and the processor samples the ultrasound video stream images at a frequency of 2 frames per second to obtain ultrasound video stream segments.

[0048] It can be understood that the processor can store the received ultrasound video stream segment or ultrasound video stream image in a cache table, in which information such as an identity document (ID) representing the ultrasound video stream segment or ultrasound video stream image, gestational period, and storage location can also be registered.

[0049] Among them, the cache table is obtained based on the Remote Dictionary Server (Redis) technology. The Remote Dictionary Server is an open source log-type, Key-Value database written in ANSI language, supporting the network, memory-based and persistent, and can provide APIs in multiple languages. Among them, ANSI is the standard for C language released by the American National Standards Institute (ANSI).

[0050] S202: Determine the detection part type, the anatomical structure section, and the standard condition of the anatomical structure section involved in each ultrasound video image frame of the ultrasound video stream segment.

[0051] The ultrasound video stream segment includes a plurality of ultrasound video image frames, and the inspection part type involved in the ultrasound video image frame refers to a coarse classification result of the image features of the ultrasound video image frame.

[0052] Specifically, the method for coarsely classifying the ultrasound video image frames can be to adopt a pre-trained swin transformer model, use the swin transformer model to classify the image features of the ultrasound video image frames, and match them by comparing the image features of the ultrasound video stream image frames with the standard image features in the image feature library. If the matching result is higher than a threshold, the inspection part type corresponding to the standard image feature is output.

[0053] Taking the fetal ultrasound video image frame as an example, the examination parts include 23 parts categories, including the brain, cardiovascular system, musculoskeletal limbs, face, spine, digestive system, urinary system, respiratory system, amniotic fluid, placenta and umbilical cord insertion, placenta position, and maternal cervix. It should be noted that among these 23 parts categories, one part only needs a single section to display, such as the placenta insertion section, and another part needs multiple sections to display, such as the brain part actually includes multiple sections such as the thalamus horizontal cross section, the lateral ventricle horizontal cross section, and the cerebellum horizontal cross section. In order to reduce the challenge of the swin transformer model, sections with similar characteristics are grouped into one part.

[0054] Specifically, after obtaining the type of examination part involved in the ultrasound video image frame, the ultrasound video image frame classified according to the examination part is sent to the target detection model of the corresponding examination part to obtain the anatomical structure involved in the ultrasound video image frame and the standard condition of the anatomical structure.

[0055] The anatomical structure involved in the ultrasound video image frame is the type of anatomical structure and the confidence of the anatomical structure obtained after the ultrasound video image frame passes through the target detection model of the corresponding inspection part. The standard condition of the anatomical structure can be measured by the score. The higher the score of the anatomical structure, the more standard the anatomical structure and the inspection part corresponding to the ultrasound video image frame corresponding to the anatomical structure are.

[0056] Specifically, the score of the anatomical structure can also be called the confidence of the anatomical structure, and the confidence is calculated based on the recognition results of the number, type and morphology of the anatomical structure. The standard types of anatomical structures include: standard, basic standard and non-standard.

[0057] S204: If the ultrasound video segment includes at least one most standard slice of the anatomical structure slice type, a video stream segment of the most standard slice is obtained according to ultrasound video image frames related to the anatomical structure slice type in the ultrasound video segment.

[0058] The anatomical section type refers to the type of target detection model corresponding to each inspection part.

[0059] The target detection model corresponding to each examination part processes the ultrasound video clips to obtain the standard conditions of the anatomical structure sections of multiple ultrasound video image frames, and selects the ultrasound video image frame with the highest score among multiple ultrasound video image frames of the same examination part as the most standard section.

[0060] After the most standard section is obtained, the previous and next frames of the most standard section can be combined to obtain a video stream segment of the most standard section.

[0061] It should be understood that the extraction of ultrasound video stream segments is carried out step by step. If the ultrasound video segment does not contain a standard slice of the anatomical structure slice type, the extraction of the ultrasound video segment will continue until the ultrasound video segment includes at least one standard slice of the anatomical structure slice type, thereby further obtaining a video stream segment with the most standard slice.

[0062] In the above-mentioned ultrasound video processing method, an ultrasound video stream segment is obtained, and the detection part type, the anatomical structure section and the standard situation of the anatomical structure section involved in each ultrasound video image frame of the ultrasound video stream segment are determined. If the ultrasound video segment includes at least one most standard section of the anatomical structure section type, then according to the ultrasound video image frame related to the anatomical structure section type in the ultrasound video segment, the video stream segment of the most standard section is obtained. In this way, the most standard section and the related ultrasound video image frames are displayed to the doctor, providing the doctor with ultrasound video dynamic information.

[0063] In one embodiment, the detection part type involved in each ultrasound video image frame of the ultrasound video stream segment, the anatomical structure section to which it belongs, and the standard condition of the anatomical structure section are determined, including: identifying the detection part type involved in each ultrasound video image frame of the ultrasound video stream segment frame by frame; inputting each ultrasound video image frame into an anatomical structure recognition model of the corresponding detection part type to obtain the anatomical structure section to which the ultrasound video image frame belongs and the standard condition of the anatomical structure section.

[0064] In the process of identifying each ultrasound video image frame of the ultrasound video segment frame by frame, a queue of preset length is maintained, for example, the queue length is kept at 10 consecutive frames, and for the queue composed of these 10 ultrasound video image frames, the type of examination part corresponding to the ultrasound video image frame in the queue is obtained.

[0065] For example, the queue consisting of the first 10 ultrasound video image frames in the ultrasound video stream segment is identified frame by frame, and the inspection site types of the first 5 frames are obtained as the femur and humerus, and the inspection site types of the last 5 frames are the ulna, radius, tibia and fibula.

[0066] Among them, after obtaining the detection part type involved in each ultrasound video image frame in the queue, each ultrasound video image frame in the queue is identified according to the target detection model corresponding to the detection part type to obtain the anatomical structure section to which the ultrasound video image frame belongs and the standard situation of the anatomical structure section.

[0067] For example, the femur-humerus detection model is used to identify the first five ultrasound video image frames of the femur-humerus part, and the anatomical structures and standard conditions of the anatomical structures of the five ultrasound video image frames of the femur-humerus part are obtained. The anatomical structures may include the femur and the humerus, and the standard conditions of the anatomical structures may be the standard and the basic standard.

[0068] Similarly, the steps for frame inspection and recognition of the last five frames of ultrasound video images of the ulna, radius, tibia and fibula are similar and will not be described in detail here.

[0069] It is understandable that the starting point of the queue can be moved so that the ultrasound video image frames contained in the queue change with the progress of frame-by-frame recognition, thereby making the queue contain more comprehensive image features of a certain detection part.

[0070] In this embodiment, by identifying each ultrasound video image frame of the ultrasound video segment frame by frame and maintaining a queue, a more comprehensive image feature of a certain detection part can be saved to provide dynamic information for the doctor.

[0071] In one embodiment, an ultrasound video stream queue corresponding to an ultrasound video stream segment is generated, and the ultrasound video stream queue records the detection part type, the anatomical structure section, and the standard condition of the anatomical structure section involved in each ultrasound video image frame of the ultrasound video stream segment.

[0072] Among them, a timing tag can be set in the ultrasonic video stream segment. Specifically, a certain ultrasound video image frame is selected as the timing tag in the ultrasound video stream segment, and several consecutive ultrasound video image frames before or after the timing tag are saved as an ultrasound video stream queue. Optionally, several consecutive ultrasound video image frames before and after the timing tag can also be saved as an ultrasound video stream queue.

[0073] Specifically, the ultrasound video stream queue is identified to obtain the anatomical structure section and the standard condition of the anatomical structure section in each ultrasound video image frame of a certain detection part, and the score of the ultrasound video image frame is determined according to the anatomical structure section and the standard condition of the anatomical structure section. If the ultrasound video image frame A has the highest score, the ultrasound video image frame A is used as a timing label, and the ultrasound video image frames before and after the ultrasound video image frame A are selected to generate the corresponding ultrasound video stream queue.

[0074] In this embodiment, by setting timing tags and generating an ultrasound video stream queue with the timing tags as reference, the doctor can be provided with ultrasound video image frames several frames before and after the most standard section as a reference, thereby avoiding the situation where key parts flash by during fetal ultrasound detection.

[0075] In one embodiment, the standard condition of the anatomical structure section includes whether the section is a standard section and the score of the section; the method for determining whether the ultrasound video segment includes at least one most standard section of the anatomical structure section type includes: if the ultrasound video segment includes at least one standard section of the anatomical structure section type, the score of the standard section of the anatomical structure section type included in the ultrasound video segment is compared with the score of the current most standard section of the anatomical structure section type; if the score of the standard section of the anatomical structure section type included in the ultrasound video segment is greater than the score of the current most standard section of the anatomical structure section type, the standard section of the anatomical structure section type included in the ultrasound video segment is marked as the current most standard section of the anatomical structure section type.

[0076] Among them, for the same anatomical structure section type, the score of the ultrasound video image frame whose standard type of the anatomical structure is standard is related to the standard type of the anatomical structure. For example, the higher the score of the ultrasound video image frame, the closer the standard type of the anatomical structure is to the standard. Specifically, the standard types of the anatomical structure are divided into standard, basic standard and non-standard.

[0077] Among them, if the score of the standard section of the anatomical structure section type included in the ultrasound video segment is greater than the score of the current most standard section of the anatomical structure section type, the section with the highest score of the standard section of the anatomical structure section type included in the ultrasound segment is marked as the current most standard section of the anatomical structure section type.

[0078] If the scores of the standard slices of the anatomical structure slice type included in the ultrasound video segment are all smaller than the score of the current most standard slice of the anatomical structure slice type, the current most standard slice of the anatomical structure slice type is retained.

[0079] Specifically, for standard sections of the same anatomical section type, the score of the standard section of the anatomical section type is determined based on prenatal ultrasound diagnosis of the fetus and the number and morphology of the anatomical structures in the standard section of the anatomical section type.

[0080] In this embodiment, the anatomical sections are scored according to their standard conditions, and the sections with the highest scores are retained for the same type of sections, so that the most standard sections with rich information and good anatomical structure are provided for doctors to refer to.

[0081] In one embodiment, after the step of obtaining the video stream segment of the most standard section, the method further includes: outputting the video stream segment of the most standard section of at least one anatomical structure section type currently detected.

[0082] The number of video stream segments of the most standard section is greater than or equal to the number of detection part types.

[0083] Taking the fetal nasolabial coronal section as an example, the anatomical section types include: nose, bilateral nostrils, nasal column, philtrum, upper lip, lower lip, corner of mouth, mandible, etc. For each anatomical section type, a video stream segment of the most standard section can be output, and at least one anatomical structure type can be output as a video stream segment of the most standard section.

[0084] It can be understood that when the ultrasound video stream segment completes the detection, each anatomical structure type outputs at least one video stream segment with the most standard section.

[0085] In this embodiment, by outputting the video stream segment of the most standard section of at least one anatomical structure section type currently being detected, it can provide real-time reference for doctors and provide a basis for doctors to adjust detection techniques, thereby ensuring the overall detection quality of the ultrasound video stream segment.

[0086] In one embodiment, the most standard section of each anatomical section type detected by all current ultrasound video stream segments is stored; after the ultrasound examination is completed, the most standard section of each anatomical section type and the video stream segment of the most standard section are obtained.

[0087] Among them, the processor can store the most standard section of each anatomical section type detected by all current ultrasound video stream fragments. After the ultrasound examination is completed, the processor will output the most standard section of each anatomical section type and the video stream fragment of the most standard section to the display device of the ultrasound instrument.

[0088] Specifically, after detecting and obtaining the most standard section of each anatomical structure section type, the processor combines the ultrasound video image frames of the same examination part as the most standard section according to the examination part to which the most standard section belongs, and stores them, and outputs them when the ultrasound examination is completed or in real time during the ultrasound examination for the doctor's reference.

[0089] In this embodiment, by storing the most standard section and the video stream segment of the most standard section, comprehensive and dynamic information reference can be provided to doctors.

[0090] In one embodiment, a video stream segment of the most standard section is obtained based on ultrasound video image frames related to the anatomical section type in an ultrasound video segment, including: taking the ultrasound video image frame of the most standard section as the tail of a first ultrasound video stream queue and the head of a second ultrasound video stream queue; selecting ultrasound video image frames of the same anatomical section type as the ultrasound video image frame of the most standard section in the first ultrasound video stream queue and the second ultrasound video stream queue, and combining them into a video stream segment of the most standard section.

[0091] Specifically, Figure 3 As shown, the process of determining the most standard ultrasound video image frame is explained.

[0092] S300, setting the length of the preset queue.

[0093] S302, determining a queue according to a preset queue length, and storing each ultrasound video image frame of a continuous ultrasound video stream segment into the queue respectively.

[0094] S304, calculating the scores of the ultrasound video image frames in the queue.

[0095] S306, if the score of the standard section of the anatomical structure section type included in the queue is greater than the score of the current most standard section of the anatomical structure section type, execute S308, if the score of the standard section of the anatomical structure section type included in the queue is less than the score of the current most standard section of the anatomical structure section type, execute S310.

[0096] S308: Replace the current most standard section of the anatomical structure section type.

[0097] If the score of the ultrasound video image frame outside the queue is greater than the score of the original video image frame, the new ultrasound video image frame replaces the original video image frame, shifts right by one frame of the initial queue timing point, and executes S302.

[0098] S310, retaining the current most standard section of the anatomical structure section type.

[0099] Specifically, taking the initial queue timing point as the 10th frame and the preset queue length as 10 frames as an example, if the 10th frame happens to be the ultrasound video image frame with the highest score, the ultrasound video image frame with the highest score is used as the tail of the first ultrasound video stream queue and the head of the second ultrasound video stream queue, that is, ultrasound video image frames from frames 1 to 19 are selected, and ultrasound video image frames of the same anatomical structure section type as the ultrasound video image frame with the highest score are screened out, and combined into the video stream segment with the most standard section according to the timing.

[0100] In this embodiment, by setting a queue and taking into account the computing power and acquisition frequency of the processor, the most standard ultrasound video image frame can be accurately obtained, and further, the video stream segment of the most standard section can be generated.

[0101] In one embodiment, Figure 4 As shown, a method for real-time recognition and capture of standard video stream segments is provided, and the steps are as follows:

[0102] S400: Acquire an ultrasound video stream segment.

[0103] S402 : Identify the detection part type involved in each ultrasound video image frame of the ultrasound video stream segment frame by frame.

[0104] S404, input each ultrasound video image frame into the anatomical structure recognition model of the corresponding detection part type, and obtain the anatomical structure section to which the ultrasound video image frame belongs and the standard condition of the anatomical structure section.

[0105] Among them, an ultrasound video stream queue corresponding to the ultrasound video stream segment is generated, and the ultrasound video stream queue records the detection part type, the anatomical structure section and the standard situation of the anatomical structure section involved in each ultrasound video image frame of the ultrasound video stream segment.

[0106] Specifically, the ultrasound video image frame of the most standard section is used as the tail of the first ultrasound video stream queue and the head of the second ultrasound video stream queue; ultrasound video image frames of the same anatomical section type as the ultrasound video image frame of the most standard section are selected from the first ultrasound video stream queue and the second ultrasound video stream queue and combined into a video stream segment of the most standard section.

[0107] S406, determining whether the ultrasound video segment includes at least one standard section of the anatomical structure section type. If yes, executing S408, otherwise returning to S400.

[0108] S408, determining whether the score of the standard section of the anatomical structure section type included in the ultrasound video segment is greater than the score of the current most standard section of the anatomical structure section type. If yes, execute S410, if no, execute S412.

[0109] S410: If the scores of the standard slices of the anatomical structure slice type included in the ultrasound video segment are all smaller than the score of the current most standard slice of the anatomical structure slice type, the current most standard slice of the anatomical structure slice type is retained.

[0110] S412, if the score of the standard section of the anatomical structure section type included in the ultrasound video segment is greater than the score of the current most standard section of the anatomical structure section type, the section with the highest score among the standard sections of the anatomical structure section type included in the ultrasound segment is marked as the current most standard section of the anatomical structure section type.

[0111] S414, storing the most standard section of each anatomical section type detected by all current ultrasound video stream segments, and after the ultrasound examination is completed, obtaining the most standard section of each anatomical section type and the video stream segment of the most standard section.

[0112] In this embodiment, an ultrasound video stream segment is obtained, a plurality of continuous frames of images are obtained, and the front and back changes of the section are retained. The detection part type, the anatomical section to which each ultrasound video image frame of the ultrasound video stream segment belongs, and the standard situation of the anatomical section are determined. If the ultrasound video segment includes at least one most standard section of the anatomical section type, the video stream segment of the most standard section is obtained according to the ultrasound video image frame related to the anatomical section type in the ultrasound video segment. In this way, the ultrasound video image frames of the most standard section and those related to the most standard section are displayed to the doctor, and the doctor is provided with ultrasound video dynamic information, which reduces the consumption of manpower and material resources caused by intercepting ultrasound video images, and also solves the influence of the doctor's cognitive level on the examination results. Furthermore, the dynamic change segment of the standard section of the fetus in the ultrasound video stream is obtained in real time, which is convenient for the doctor to analyze the transformation relationship between his own operation method and the standard section.

[0113] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0114] Based on the same inventive concept, the embodiment of the present application also provides an ultrasonic video processing device for implementing the ultrasonic video processing method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more ultrasonic video processing devices provided below can refer to the limitations of the ultrasonic video processing method above, and will not be repeated here.

[0115] In one embodiment, Figure 5 As shown, a device for processing ultrasound video is provided, comprising: an image acquisition module 500, an image frame determination module 502, and an output module 504, wherein:

[0116] An image acquisition module 500 is used to acquire ultrasound video stream segments;

[0117] An image frame determination module 502 is used to determine the detection part type, the anatomical structure section and the standard condition of the anatomical structure section involved in each ultrasound video image frame of the ultrasound video stream segment;

[0118] The output module 504 is configured to obtain a video stream segment of the most standard section according to ultrasound video image frames related to the anatomical section type in the ultrasound video segment if the ultrasound video segment includes at least one most standard section of the anatomical section type.

[0119] In one embodiment, the image frame determination module 502 is also used to identify the detection part type involved in each ultrasound video image frame of the ultrasound video stream segment frame by frame; each ultrasound video image frame is input into the anatomical structure recognition model of the corresponding detection part type to obtain the anatomical structure section to which the ultrasound video image frame belongs and the standard condition of the anatomical structure section.

[0120] In one embodiment, the output module 504 is also used to generate an ultrasound video stream queue corresponding to the ultrasound video stream segment, and the ultrasound video stream queue records the detection part type, the anatomical structure section and the standard condition of the anatomical structure section involved in each ultrasound video image frame of the ultrasound video stream segment.

[0121] In one embodiment, the ultrasound video processing device also includes: a replacement module, which is used to compare the score of the standard section of the anatomical structure section type included in the ultrasound video segment with the score of the current most standard section of the anatomical structure section type if the ultrasound video segment includes at least one standard section of the anatomical structure section type; if the score of the standard section of the anatomical structure section type included in the ultrasound video segment is greater than the score of the current most standard section of the anatomical structure section type, then mark the standard section of the anatomical structure section type included in the ultrasound video segment as the current most standard section of the anatomical structure section type.

[0122] In one embodiment, the output module 504 is further configured to output a video stream segment of the most standard slice of at least one anatomical structure slice type currently detected.

[0123] In one embodiment, the ultrasound video processing device also includes: a storage module for storing the most standard section of each anatomical section type detected by all current ultrasound video stream segments; after the ultrasound examination is completed, the most standard section of each anatomical section type and the video stream segment of the most standard section are obtained.

[0124] In one embodiment, the output module 504 is also used to use the ultrasound video image frame of the most standard section as the tail of the first ultrasound video stream queue and the head of the second ultrasound video stream queue; select ultrasound video image frames of the same anatomical structure section type as the ultrasound video image frame of the most standard section in the first ultrasound video stream queue and the second ultrasound video stream queue, and combine them into a video stream segment of the most standard section.

[0125] Each module in the above-mentioned ultrasound video processing device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0126] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 6 As shown. 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, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store ultrasound video image frame data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for processing ultrasound video is implemented.

[0127] 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.

[0128] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0129] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0130] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0131] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0132] Those skilled 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. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. 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). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0133] The technical features of the above embodiments may be combined arbitrarily. 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.

[0134] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for processing ultrasound video, characterized in that: The method comprises: Obtaining ultrasound video stream segments; Determining the detection part type involved in each ultrasound video image frame of the ultrasound video stream segment, the anatomical structure section to which it belongs, and the standard condition of the anatomical structure section; If the ultrasound video stream segment includes at least one most standard slice of an anatomical structure slice type, the ultrasound video image frame of the most standard slice is used as the tail of the first ultrasound video stream queue and the head of the second ultrasound video stream queue; Selecting ultrasound video image frames of the first ultrasound video stream queue and the second ultrasound video stream queue, which have the same anatomical structure section type as the ultrasound video image frame of the most standard section, and combining them into a video stream segment of the most standard section; An ultrasound video stream queue corresponding to the ultrasound video stream segment is generated, wherein the ultrasound video stream queue records the detection part type, the anatomical structure section and the standard condition of the anatomical structure section involved in each ultrasound video image frame of the ultrasound video stream segment.

2. The method according to claim 1, characterized in that The step of determining the detection part type involved in each ultrasound video image frame of the ultrasound video stream segment, the anatomical structure section to which it belongs, and the standard condition of the anatomical structure section includes: Identifying the detection part type involved in each ultrasound video image frame of the ultrasound video stream segment frame by frame; Each of the ultrasound video image frames is input into an anatomical structure recognition model of a corresponding detection part type to obtain the anatomical structure section to which the ultrasound video image frame belongs and a standard condition of the anatomical structure section.

3. The method according to claim 1, characterized in that The standard condition of the anatomical structure section includes whether the section is a standard section and a score of the section; the method of determining whether the ultrasound video stream segment includes at least one most standard section of the anatomical structure section type includes: If the ultrasound video stream segment includes at least one standard slice of an anatomical structure slice type, comparing the score of the standard slice of the anatomical structure slice type included in the ultrasound video stream segment with the score of the most current standard slice of the anatomical structure slice type; If the score of the standard section of the anatomical structure section type included in the ultrasound video stream segment is greater than the score of the current most standard section of the anatomical structure section type, the standard section of the anatomical structure section type included in the ultrasound video stream segment is marked as the current most standard section of the anatomical structure section type.

4. The method according to claim 1, characterized in that: After the step of obtaining the video stream segment of the most standard section, the method further includes: Output a video stream segment of the most standard slice of at least one anatomical structure slice type currently detected.

5. The method according to claim 1, characterized in that The method further comprises: storing the most standard section of each anatomical structure section type detected through all current ultrasound video stream segments; After the ultrasonic examination is completed, the most standard section of each anatomical structure section type and the video stream segment of the most standard section are obtained.

6. An ultrasonic video processing device, used for processing the ultrasonic video processing method according to claim 1, characterized in that: The device comprises: An image acquisition module, used for acquiring ultrasound video stream segments; An image frame determination module, used to determine the detection part type involved in each ultrasound video image frame of the ultrasound video stream segment, the anatomical structure section to which it belongs, and the standard condition of the anatomical structure section; The output module is used for, if the ultrasound video stream segment includes at least one most standard section of an anatomical structure section type, using the ultrasound video image frame of the most standard section as the tail of the first ultrasound video stream queue and the head of the second ultrasound video stream queue; selecting ultrasound video image frames of the same type of anatomical structure section as the ultrasound video image frame of the most standard section in the first ultrasound video stream queue and the second ultrasound video stream queue, and combining them into a video stream segment of the most standard section; generating an ultrasound video stream queue corresponding to the ultrasound video stream segment, the ultrasound video stream queue recording the detection part type involved in each of the ultrasound video image frames of the ultrasound video stream segment, the anatomical structure section to which it belongs, and the standard condition of the anatomical structure section.

7. The device according to claim 6, characterized in that The image frame determination module is also used to: identify the detection part type involved in each ultrasound video image frame of the ultrasound video stream segment frame by frame; input each of the ultrasound video image frames into the anatomical structure recognition model of the corresponding detection part type to obtain the anatomical structure section to which the ultrasound video image frame belongs and the standard condition of the anatomical structure section.

8. The device according to claim 6, characterized in that The ultrasonic video processing device also includes: A replacement module is used to compare the score of the standard section of the anatomical structure section type included in the ultrasound video stream segment with the score of the current most standard section of the anatomical structure section type if the ultrasound video stream segment includes at least one standard section of the anatomical structure section type; if the score of the standard section of the anatomical structure section type included in the ultrasound video stream segment is greater than the score of the current most standard section of the anatomical structure section type, mark the standard section of the anatomical structure section type included in the ultrasound video stream segment as the current most standard section of the anatomical structure section type.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images