Ultrasonic image display method, ultrasonic imaging equipment and medium

Abstract

The embodiment of the invention provides an ultrasonic image display method, ultrasonic imaging equipment and a medium. The ultrasonic image display method comprises the following steps: identifying a target object in a to-be-processed ultrasonic image; identifying a target area where the target object is located from the ultrasonic image based on the attribute information of the target object to obtain a target area image; obtaining rotation offset information of a target object in the target area image; and obtaining a target calibration image corresponding to the target object according to the rotation offset information, and at least displaying the target calibration image. According to the scheme, the complexity of the operation process is greatly reduced, the ultrasonic examination speed is increased, visual angle correction can be achieved according to the rotation offset information, and the observation difficulty of doctors is reduced.

Description

Technical Field

[0001] This application relates to the technical field of medical devices, and particularly to an ultrasonic image display method, an ultrasonic imaging device, and a medium. Background Art

[0002] Currently, since ultrasonic images can intuitively and three-dimensionally display the three-dimensional structure and dynamics of human organs, ultrasonic examinations have become one of the most widely used auxiliary diagnostic means in clinical applications. In ultrasonic examinations, magnifying local images helps to observe the fine structure of tissues / organs, evaluate lesion details, and make more accurate diagnoses.

[0003] However, traditional ultrasonic imaging systems require cumbersome manual operations to magnify local areas of organs. Moreover, due to reasons such as the patient's body position, scanning position, and the probe angle of the ultrasonic imaging device, there are often differences (such as inversion) between the viewing angle of the actual magnified ultrasonic image and the standard reference image, which causes inconvenience to doctors' observations and affects doctors' diagnoses. Summary of the Invention

[0004] The main purpose of the embodiments of this application is to provide an ultrasonic image display method, aiming to automatically calibrate the viewing angle of ultrasonic images, reduce the complexity of the operation process during ultrasonic examinations, speed up the examination speed, and significantly reduce the difficulty of doctors' ultrasonic examinations, so as to assist doctors in observing local areas of organs with high precision and making more accurate diagnoses.

[0005] In a first aspect, the embodiments of this application provide an ultrasonic image display method, including:

[0006] Identifying a target object in the ultrasonic image to be processed;

[0007] Based on the attribute information of the target object, identifying the target area where the target object is located in the ultrasonic image to obtain a target area image;

[0008] Obtaining the rotation offset information of the target object in the target area image;

[0009] Obtaining a target calibration image corresponding to the target object according to the rotation offset information, and at least displaying the target calibration image.

[0010] In a second aspect, the embodiments of this application further provide an ultrasonic imaging device, including:

[0011] An ultrasonic scanning mechanism for performing ultrasonic scanning on a target object to obtain an ultrasonic image;

[0012] A display for image display;

[0013] A controller, electrically connected to the ultrasonic scanning mechanism and the display, and configured to execute any one of the ultrasonic image display methods provided in the specification of the present application.

[0014] In a third aspect, the present application further provides a computer-readable storage medium storing a computer program, which when executed by a processor causes the processor to implement the steps of any one of the ultrasonic image display methods provided in the specification of the present application.

[0015] Based on the traditional ultrasonic imaging system, cumbersome manual operations are required to magnify a local area of an organ. Moreover, due to reasons such as the patient's body position, scanning position, and the probe angle of the ultrasonic imaging device, there are often differences (such as inversion) between the viewing angle of the actual magnified ultrasonic image and the standard reference image, which causes inconvenience to doctors' observation and affects doctors' diagnosis.

[0016] In the ultrasonic image display solution provided by the present application, the target area image is identified based on the attribute information of the target object, and the rotation offset information of the target object is obtained, so as to automatically obtain the target calibration image corresponding to the target object according to the rotation offset information. This not only greatly reduces the complexity of the operation process and speeds up the ultrasonic examination, but also can perform viewing angle correction according to the rotation offset information and reduce the difficulty of doctors' observation.

[0017] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the disclosure of the embodiments of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the following drawings are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1 It is a schematic block diagram of a module structure of an ultrasonic imaging device provided by an embodiment of the present application;

[0020] Figure 2 It is a flowchart of the steps of an ultrasonic image display method provided by an embodiment of the present application;

[0021] Figure 3 It is a schematic flowchart of identifying a target area in an ultrasonic image display method provided by an embodiment of the present application;

[0022] Figure 4 It is a schematic flowchart of converting an initial identification frame into a target identification frame in an ultrasonic image display method provided by an embodiment of the present application;

[0023] Figure 5 Schematic flow chart of obtaining rotation offset information in an ultrasonic image display method provided by an embodiment of the present application;

[0024] Figure 6 Schematic flow chart of obtaining a target calibration image through front-end processing in an ultrasonic image display method provided by an embodiment of the present application;

[0025] Figure 7 Schematic diagram of the effect of displaying a target calibration image in an ultrasonic image display method provided by an embodiment of the present application;

[0026] Reference numerals:

[0027] 100, ultrasonic imaging device; 110, ultrasonic scanning mechanism; 120, display;

[0028] 130, controller; 200, ultrasonic image; 310, initial identification frame;

[0029] 320, target identification frame; 330, calibration identification frame; 400, target area image;

[0030] 510, re-acquired image; 520, target calibration image; 600, standard image;

[0031] 700, standard reference information; 800, display interface. Detailed implementation manners

[0032] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0033] In the description of the present application, unless otherwise clearly defined and limited, the terms "installation", "connection", and "connection" shall be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected, or indirectly connected through an intermediate medium, and it may be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific situations.

[0034] The flow charts shown in the accompanying drawings are only illustrative examples, and do not necessarily include all the contents and operations / steps, nor do they necessarily need to be executed in the described order. For example, some operations / steps can also be decomposed, combined, or partially merged. Therefore, the actual execution order may be changed according to the actual situation.

[0035] The following will describe in detail some embodiments of the present application in conjunction with the accompanying drawings. Without conflict, the features in the following embodiments and implementation manners can be combined with each other.

[0036] Please refer to Figure 1 , Figure 1 which is a schematic diagram of the module structure of an ultrasonic imaging device provided by an embodiment of the present application.

[0037] As Figure 1 shown, the ultrasonic imaging device 100 includes an ultrasonic scanning mechanism 110, a display 120, and a controller 130 connected to the ultrasonic scanning mechanism 110 and the display 120. Among them, the ultrasonic scanning mechanism 110 is used to perform ultrasonic scanning on a target object to obtain an ultrasonic image 200, the display 120 is used for image display, and the controller 130 is used to execute any one of the ultrasonic image 200 display methods provided in the specification of the present application.

[0038] Specifically, the ultrasonic scanning mechanism 110 is used to emit an ultrasonic beam to the target object and collect the echo signal reflected after the ultrasonic beam propagates to the target object, so as to perform ultrasonic scanning on the target object. Exemplarily, the target object is a human body or an animal, etc. The controller 130 is used to obtain the echo signal collected by the ultrasonic scanning mechanism 110, perform corresponding processing on the echo signal to obtain the ultrasonic image 200, and control the display 120 to display the ultrasonic image 200.

[0039] It should be noted that the display 120 is at least used to display the ultrasonic image 200. Further, the display 120 can also be used to display standard reference information 800 matching the ultrasonic image 200, or to magnify / enhance the display of a partial area in the ultrasonic image 200, or to display an identifier on the ultrasonic image 200 to highlight the scanning focus, such as using an identification frame to identify a partial area in the ultrasonic image 200. It should be understood that in the scenario of ultrasonic examination, the display 120 can assist the doctor in observing the results of ultrasonic scanning.

[0040] Please refer to Figure 2 and Figure 3 , Figure 2 which is a flowchart of the steps of an ultrasonic image display method provided by an embodiment of the present application, Figure 3 and is a schematic diagram of the process of identifying a target area in an ultrasonic image display method provided by an embodiment of the present application.

[0041] As Figure 2As shown in the figure, the present application provides a method for displaying an ultrasonic image 200, which is used to process and display the ultrasonic image 200 to be processed, so as to assist in ultrasonic examination of a local area of a target object. It should be noted that the method for displaying the ultrasonic image 200 provided by the present application can be executed by the ultrasonic imaging device 100 provided by the present application or the controller 130 in the ultrasonic imaging device 100, but is not limited to the above-mentioned execution entities. In the specification of the present application, the controller 130 in the ultrasonic imaging device 100 is used as an example to execute the method for displaying the ultrasonic image 200 for specific illustration.

[0042] Specifically, the method for displaying the ultrasonic image 200 specifically includes steps S1 to S4:

[0043] Step S1: Identify the target object in the ultrasonic image 200 to be processed.

[0044] Exemplarily, the ultrasonic image 200 is an image obtained by ultrasonic scanning of a biological object, where the biological object includes a human body or an animal, etc., and the target object is a partial organ tissue of the biological object, which is used to reflect the fine structure of the partial organ tissue. Taking the ultrasonic object as an image obtained by ultrasonic scanning of a fetus as an example, the target object can be an area in the fetus that needs to be scanned and examined key points, such as the fetal heart or the fetal brain, etc.

[0045] In some embodiments, before identifying the target object in the ultrasonic image 200 to be processed, it further includes: obtaining the ultrasonic image 200 to be processed. For example, obtaining the ultrasonic image 200 to be processed can be that the ultrasonic imaging device 100 performs an ultrasonic scanning operation on the target object to obtain the ultrasonic image 200 to be processed, or obtaining an externally input ultrasonic image 200, for example, an ultrasonic image 200 uploaded by a doctor.

[0046] As Figure 3 shown, identifying the target object in the ultrasonic image 200 to be processed can be triggered by an externally input start instruction. For example, the input start instruction includes but is not limited to any one of a key press, voice input, and clicking a virtual key with a mouse.

[0047] Step S2: Based on the attribute information of the target object, identify the target area where the target object is located in the ultrasonic image 200 to obtain a target area image 400.

[0048] As Figure 3 shown, specifically, identifying the target area where the target object is located in the ultrasonic image 200 is, for example: generating a target recognition frame and using the target recognition frame to frame the ultrasonic image 200, where the area framed by the target recognition frame is the target area, and the image in the target area on the ultrasonic image 200 is the target area image 400.

[0049] Taking the partial organ tissue of a biological object as the target object as an example, the attribute information of the target object includes, for example, the organ type of the target object, the shape information of the target object, the area information of the target object, and the position information of the target object relative to the ultrasound image 200, etc.

[0050] In some embodiments, step S2: identifying the target area where the target object is located in the ultrasound image 200 based on the attribute information of the target object specifically includes the following steps:

[0051] Generating a target identification box 320 for identifying the target object based on the attribute information of the target object;

[0052] Using the target identification box 320 to identify the target area where the target object is located in the ultrasound image 200, and intercepting the target area to obtain the target area image 400.

[0053] Exemplarily, the attribute information of the target object includes the organ type of the target object. Generating a target identification box 320 for identifying the target object based on the attribute information of the target object can specifically be: determining the position, shape, and size of the target identification box 320 based on the attribute information of the target object to generate the target identification box 320 for identifying the target object, ensuring that the target identification box 320 can accurately identify the target object in the ultrasound image 200, and enabling the target object to be framed in the target area corresponding to the target identification box 320.

[0054] As Figure 3 shown, after generating the target identification box 320, using the target identification box 320 to identify the target area where the target object is located in the ultrasound image 200, that is, the area framed by the target identification box 320 is the target area, and using the target identification box 320 to intercept the image in the target area to obtain the target area image 400.

[0055] In some embodiments, using the target identification box 320 to identify the target area where the target object is located in the ultrasound image 200, and intercepting the target area to obtain the target area image 400 includes:

[0056] Using the target identification box 320 to identify the target area where the target object is located in the ultrasound image 200;

[0057] Receiving a target confirmation instruction, and in response to the target confirmation instruction, intercepting the target area from the ultrasound image 200 to obtain the target area image 400.

[0058] Specifically, the target confirmation instruction can be input externally. For example, it is the target confirmation instruction input by a doctor when confirming the target area, and the target area can be intercepted from the ultrasound image 200 in response to the target confirmation instruction to obtain the target area image 400.

[0059] Taking the controller 130 of the ultrasonic imaging device 100 in Figure 1 as an example to illustrate, the controller 130 controls the display 120 to display the ultrasonic image 200 and the target identification frame 320 on the ultrasonic image 200 on its interface, so that the doctor can learn about the target area identified by the current target recognition frame. When the doctor confirms the target area and inputs a target confirmation instruction, the controller 130 that executes this method responds to the target confirmation instruction and extracts the target area from the ultrasonic image 200 to obtain the target area image 400.

[0060] Exemplarily, the input target confirmation instruction includes but is not limited to any one of operations such as pressing a key, voice input, and clicking a virtual key with a mouse.

[0061] In some embodiments, at least one of the size, position, and shape of the target identification frame 320 can be adjusted based on external input information.

[0062] It should be noted that the controller 130 controls the display 120 to display the ultrasonic image 200 and the target identification frame 320 on the ultrasonic image 200 on its interface, so that the doctor can learn about the target area identified by the current target recognition frame. The doctor can adjust at least one of the size, position, and shape of the target identification frame 320 according to the target area identified by the current target recognition frame, so as to ensure that the target identification frame 320 can accurately identify the target object in the ultrasonic image 200 and the target object is framed in the target area corresponding to the target identification frame 320.

[0063] In some embodiments, the attribute information includes first attribute information and second attribute information. The first attribute information at least includes the category information of the target object, and the second attribute information at least includes the shape information and area information of the target object; generating a target identification frame 320 for identifying the target object based on the attribute information of the target object includes:

[0064] Generating an initial identification frame 310 based on the first attribute information, and adjusting the size and / or position of the initial identification frame 310 according to the first attribute information and the second attribute information to obtain the target identification frame 320.

[0065] Specifically, the first attribute information at least includes the category information of the target object. Generating an initial identification frame 310 based on the first attribute information specifically includes: calling the automatically recognized model generated by training, and inputting the ultrasonic image 200 containing the target object and the category information of the target object into the automatically recognized model, so that the automatically recognized model generates an initial identification frame 310 on the ultrasonic image 200. Among them, the training process of the automatically recognized model at least includes: constructing a model to be trained based on a deep neural network, and training the model to be trained with ultrasonic image 200 samples containing various tissues / organs to obtain the automatically recognized model.

[0066] Please refer to Figure 4 , Figure 4 which is a schematic flowchart of transforming an initial identification box into a target identification box in an ultrasonic image display method provided by an embodiment of the present application.

[0067] As Figure 4 shown, it should be noted that there may be a problem that the target object is not completely framed in the target area corresponding to the target identification box 320 for the initial identification box 310 generated based on the first attribute information. Therefore, after the initial identification box 310 is generated, the size and / or position of the initial identification box 310 need to be adjusted according to the first attribute information and the second attribute information to obtain the target identification box 320.

[0068] Specifically, after the initial identification box 310 is generated, considering the category information of the target object in the first attribute information, the area information and shape information of the target object in the second attribute information, different amplification coefficients are assigned to the long side and the short side of the initial identification box 310 respectively. Then, according to the amplification coefficient of the long side, the long side of the initial identification box 310 is amplified outward from the initial identification box 310, and according to the amplification coefficient of the long side, the long side of the initial identification box 310 is amplified outward from the initial identification box 310 to adjust the size and position of the initial identification box 310 to obtain the target identification box 320. By amplifying the edges of the initial identification box 310, the target object can be completely framed in the target area corresponding to the target identification box 320.

[0069] Exemplarily, in the process of adjusting the size and / or position of the initial identification box 310, the shape information of the target object in the second attribute information can be represented by the aspect ratio of the initial identification box 310, and the area information of the target object in the second attribute information can be represented by the area size of the initial identification box 310.

[0070] As Figure 4 shown, further, after the target area image 400 is obtained by intercepting the target area, the method further includes: performing an image deformation process on the target area image 400 to deform the target area image 400 into a target shape. Even further, in addition to performing an image deformation process on the target area image 400, the method further includes performing an image deformation process on the target identification box 320 to deform the target identification box 320 into a target shape.

[0071] Exemplarily, the target shape includes but is not limited to one of a fan shape and a rectangle, or other preset shapes.

[0072] Step S3: Obtain the rotation offset information of the target object in the target area image 400.

[0073] Specifically, the rotation offset information of the target object represents the offset angle α at which the target object appears in the current ultrasound image 200.

[0074] Please refer to Figure 5 , Figure 5 which is a schematic flow chart for obtaining rotation offset information in an ultrasound image display method provided by an embodiment of the present application.

[0075] As Figure 5 shown, in some embodiments, obtaining the rotation offset information of the target object in the target region image 400 includes:

[0076] Obtaining a standard image 600 that matches the target object according to the attribute information, and comparing the standard image 600 with the target region image 400 to obtain the rotation offset information.

[0077] Preferably, obtaining a standard image 600 that matches the target object according to the attribute information specifically includes: querying the standard image 600 in which the attribute information matches the target object from a preset standard image set, where preset images corresponding to several attribute information are pre-stored in the standard image set.

[0078] Taking the ultrasound image 200 as an example of an image obtained by performing an ultrasound scan on a biological object, the attribute information of the target object includes the organ type, and the standard image 600 in which the organ type matches the target object can be queried from the preset standard image set. For example, the standard image 600 can be a preset image corresponding to an organ type of the atrium or the brain in the attribute information.

[0079] As Figure 5 shown, specifically, the rotation offset information can be represented by the offset angle α of the target region image 400 relative to the standard image 600, where the offset angle is specifically obtained by comparing the target region image 400 with the standard image 600. For the specific comparison method, please refer to the following description.

[0080] In some embodiments, comparing the standard image 600 with the target region image 400 to obtain the rotation offset information includes:

[0081] Determining a target comparison strategy for the standard image 600 and the target region image 400 according to the attribute information;

[0082] Comparing the target region image 400 with the standard image 600 based on the target comparison strategy to obtain the rotation offset information.

[0083] Exemplarily, the correspondence between the attribute information of the target object and the target comparison strategy can be pre-matched. Among them, the attribute information is, for example, the organ type of the target object. The target objects of different organ types are specific organs in different parts, and different methods can be used to extract and compare features based on the target objects of different organ types. Therefore, the corresponding target comparison strategy can be matched according to the organ type of the target object, and then the target region image 400 is compared with the standard image 600 based on the target comparison strategy.

[0084] In some embodiments, the target comparison strategy includes any one of the first comparison strategy and the second comparison strategy; correspondingly, comparing the target region image 400 with the standard image 600 based on the target comparison strategy to obtain the rotation offset information includes:

[0085] When the target comparison strategy is the first comparison strategy, determine the rotation center point from the target region image 400, rotate the target region image 400 with the rotation center point, and calculate the image coincidence degree of the target region image 400 and the standard image 600 during the image rotation. When the image coincidence degree exceeds the preset value, record the rotation angle information of the target region image 400, and use the rotation angle information as the rotation offset information;

[0086] When the target comparison strategy is the second comparison strategy, identify the first target axis corresponding to the target object in the target region image 400, calculate the first included angle between the first target axis and the preset reference normal line. The first target axis includes the long axis and / or the short axis of the target object in the target region image 400; identify the second target axis corresponding to the target object in the standard image 600, calculate the second included angle between the second target axis and the preset reference normal line. The first target axis includes the long axis and / or the short axis of the target object in the target region image 400; calculate the rotation offset information according to the first included angle and the second included angle.

[0087] It should be noted that the above first comparison strategy and second comparison strategy can be used alternatively. Specifically, the controller 130 executing this method can match one of the first comparison strategy and the second comparison strategy according to the attribute information as the target comparison strategy, and compare the target region image 400 with the standard image 600 based on the target comparison strategy to obtain the rotation offset information.

[0088] In some embodiments, when it is determined according to the attribute information that the target object contains a landmark structure with strong structural features, the first comparison strategy can be used as the target comparison strategy. For example, the above landmark structure with strong structural features is, for example: the cross-shaped atrioventricular septum of the four-chamber view, the highlighted line of the spinal bone section, etc.

[0089] Under the first comparison strategy, a rotation center point is determined from the target region image 400, and the target region image 400 is rotated around the rotation center point. During the image rotation process, the image coincidence degree between the target region image 400 and the standard image 600 is calculated. When the image coincidence degree exceeds a preset value, the rotation angle information of the target region image 400 is recorded, and the rotation angle information is used as the rotation offset information.

[0090] Exemplarily, when adopting the first comparison strategy, a method of extracting a high-brightness region can also be used to obtain a first comparison region corresponding to the landmark structure in the target region image 400 and a second comparison region corresponding to the landmark structure in the standard image 600. When calculating the image coincidence degree between the target region image 400 and the standard image 600, the coincidence degree between the first comparison region in the target region image 400 and the second comparison region in the standard image 600 can be calculated as the image coincidence degree.

[0091] Preferably, during the process of rotating the target region image 400, the rotation angle information of the target region image 400 and the corresponding image coincidence degree can be recorded, and the rotation angle information corresponding to the highest image coincidence degree is used as the rotation offset information.

[0092] In some embodiments, when the shape feature of the target object is determined to be strong according to the attribute information, the second comparison strategy can be adopted as the target comparison strategy. For example, the above-mentioned target object with strong shape features is, for example, the skull.

[0093] Under the second comparison strategy, a first target axis corresponding to the target object is identified in the target region image 400, and a first included angle between the first target axis and a preset reference normal line is calculated. The first target axis includes the major axis and / or minor axis of the target object in the target region image 400; a second target axis corresponding to the target object is identified in the standard image 600, and a second included angle between the second target axis and the preset reference normal line is calculated. The first target axis includes the major axis and / or minor axis of the target object in the target region image 400; the rotation offset information is calculated according to the first included angle and the second included angle.

[0094] It should be noted that the first target axis is specifically at least one of the long axis and the short axis of the target object in the target region image 400, and the second target axis is specifically at least one of the long axis and the short axis of the target object in the standard image 600. For example, the long axis of the target object in the target region image 400 can be used as the first target axis for calculating the first included angle, and the long axis of the target object in the standard image 600 can be used as the second target axis for calculating the second included angle; similarly, the short axis of the target object in the target region image 400 can also be used as the first target axis for calculating the first included angle, and the short axis of the target object in the standard image 600 can be used as the second target axis for calculating the second included angle; or, the long and short axes of the target object in the target region image 400 and the reference image can be comprehensively considered to calculate the second included angle.

[0095] Exemplarily, calculating the rotation offset information according to the first included angle and the second included angle specifically includes: subtracting the angles of the first included angle and the second included angle, and using the obtained subtracted angle as the rotation offset information.

[0096] It should be understood that the above first comparison strategy and second comparison strategy essentially extract different features of the target object, and determine the rotation offset information based on the extracted features. By determining the matching target comparison strategy according to the attribute information in the embodiments of the present application, it is beneficial to adopt corresponding comparison methods for organs with different parts, and accurately compare the rotation offset information of the target region image 400 relative to the reference image.

[0097] In some embodiments, comparing the standard image 600 with the target region image 400 to obtain the rotation offset information further includes another strategy, specifically including:

[0098] Obtaining a plurality of first feature points from the target region image 400, and obtaining second feature points that are in one-to-one correspondence with the plurality of first feature points from the standard image 600;

[0099] Determining the rotation offset information according to the first position information corresponding to the first feature points and the second position information corresponding to the second feature points.

[0100] In some embodiments, obtaining a plurality of first feature points from the target region image 400 and obtaining second feature points that are in one-to-one correspondence with the plurality of first feature points from the standard image 600 specifically includes: detecting first candidate points and second candidate points with invariance on the target region image 400 and the standard image 600. The first candidate points are located on the target region image 400, and the second candidate points are located on the standard image 600. The first candidate points and the second candidate points remain stable when the target region image 400 and the standard image 600 undergo size changes and rotations. Then, the BRISK descriptor (Binary Robust Invariant Scalable Keypoints) is used to respectively construct descriptions of the first candidate points and the second candidate points, specifically including: randomly selecting several neighboring points near the first candidate points and generating a first string based on the gray values of the selected neighboring points to describe the first candidate points; randomly selecting several neighboring points near the second candidate points and generating a second string based on the gray values of the selected neighboring points to describe the second candidate points. Then, the first string corresponding to the first candidate points is compared with the second string corresponding to the second candidate points, and when the first string and the second string match, it is determined that the first candidate points and the second candidate points are respectively a pair of mutually matching first feature points and second feature points.

[0101] After that, rotation offset information is determined according to the first position information corresponding to the first feature points and the second position information corresponding to the second feature points.

[0102] Specifically, based on the one-to-one correspondence formed by the first feature points in the target region image 400 and the second feature points of the standard image 600, according to the first position information corresponding to the first feature points and the second position information corresponding to the second feature points, first, a feature point pairing between the first feature points and the second feature points is established, and then a homography transformation matrix between the target region image 400 and the image is generated according to a preset number of feature point pairings. After that, the homography transformation matrix is degraded into a rotation transformation matrix, and then the offset angle α of the target region image 400 relative to the standard image 600 is solved according to the rotation transformation matrix as the rotation offset information.

[0103] Exemplarily, based on the properties of the homography transformation matrix, the preset number of feature point pairings is at least four.

[0104] Preferably, establishing the feature point pairing between the first feature point and the second feature point includes: establishing a first coordinate system corresponding to the target region image 400, and using the coordinates of the first feature point in the first coordinate system as the first position information to represent the relative position of the first feature point in the target region image 400. Similarly, a second coordinate system corresponding to the standard image 600 can be established, and the coordinates of the second feature point in the second coordinate system are used as the second position information to represent the relative position of the second feature point in the target region image 400. After that, the coordinates of the first feature point in the first coordinate system are associated with the coordinates of the second feature point in the second coordinate system as a pair of feature point pairings.

[0105] Step S4: Obtain a target calibration image 520 corresponding to the target object according to the rotation offset information, and at least display the target calibration image 520.

[0106] Specifically, obtaining the target calibration image 520 corresponding to the target object may be to perform back-end processing on the ultrasound image 200, including: performing angle calibration on the target region according to the rotation offset information, and extracting the corrected target calibration image 520 based on the angle-calibrated target region and the ultrasound image 200. It may also be to perform front-end processing on the ultrasound image 200, including: adjusting the scanning parameters of the ultrasound scanning mechanism 110 according to the rotation offset information, so that the ultrasound scanning mechanism 110 performs ultrasound scanning on the target object based on the adjusted scanning parameters to obtain the target calibration image 520.

[0107] In some embodiments, obtaining the target calibration image 520 corresponding to the target object according to the rotation offset information includes:

[0108] Performing angle calibration on the target region according to the rotation offset information to obtain the target calibration image 520.

[0109] It should be noted that in this embodiment, the target calibration image 520 is obtained through back-end processing, that is, there is no need to re-perform ultrasound scanning on the target object. Specifically, the target region is angle-calibrated on the ultrasound image 200 according to the rotation offset information to obtain a calibration region on the ultrasound image 200, and then the image in the calibration region is extracted to obtain the target calibration image 520.

[0110] Exemplarily, the rotation offset information includes the offset angle α of the target region image 400 relative to the standard image 600. Performing angle calibration on the target region on the ultrasound image 200 according to the rotation offset information includes: rotating the target identification frame 320 on the ultrasound image 200 by the opposite angle -α of the offset angle α, and the region framed by the rotated target identification frame 320 is the calibration region.

[0111] Please refer to Figure 6 ,Figure 6 This is a schematic flow diagram of obtaining a target calibration image through front-end processing in an ultrasonic image display method provided by an embodiment of the present application.

[0112] As Figure 6 shown, in some embodiments, obtaining a target calibration image 520 corresponding to a target object according to rotation offset information includes:

[0113] Correcting a target area corresponding to a target area image 400 according to rotation offset information to obtain a calibrated area;

[0114] Adjusting scanning parameters of a preset ultrasonic scanning mechanism 110 according to calibration position information of the calibrated area relative to an ultrasonic image 200 and attribute information of the target object, so that the ultrasonic scanning mechanism 110 performs ultrasonic scanning on the target object based on the adjusted scanning parameters to obtain a target calibration image 520;

[0115] Among them, the resolution of the target calibration image 520 is greater than that of the image within the calibrated area in the ultrasonic image 200.

[0116] It should be noted that in this embodiment, the target calibration image 520 is obtained through front-end processing, that is, the scanning parameters of the ultrasonic scanning mechanism 110 need to be adjusted, and the ultrasonic scanning mechanism 110 is controlled to perform ultrasonic scanning on the target object based on the adjusted scanning parameters. For example, the scanning parameters of the ultrasonic scanning mechanism 110 include but are not limited to parameters such as transmission frequency, focusing depth, dynamic aperture, and time compensation gain.

[0117] Specifically, a controller 130 executing this method first corrects a target area corresponding to a target area image 400 according to rotation offset information to obtain a calibrated area, and then adjusts scanning parameters of a preset ultrasonic scanning mechanism 110 according to both calibration position information of the calibrated area relative to an ultrasonic image 200 and attribute information of the target object, so that the ultrasonic scanning mechanism 110 performs ultrasonic scanning on the target object based on the adjusted scanning parameters to obtain a target calibration image 520.

[0118] Exemplarily, in the embodiments of the present application, the ultrasound image 200 may be obtained by scanning a biological object with the ultrasound scanning mechanism 110. Based on this, adjusting the scanning parameters of the preset ultrasound scanning mechanism 110 according to the calibration position information of the calibration area relative to the ultrasound image 200 at least includes: adjusting the scanning parameters of the ultrasound scanning mechanism 110 so that the ultrasound scanning mechanism 110 scans a local position corresponding to the calibration area in the biological object. Therefore, the resolution of the scanned target calibration image 520 is greater than that of the image within the calibration area in the ultrasound image 200, and the number of pixels of the target calibration image 520 is also greater than that of the image within the calibration area in the ultrasound image 200, thereby magnifying the local area of the biological object and reducing the difficulty for doctors to observe.

[0119] Exemplarily, taking the attribute information of the target object including the organ type of the target object and the scanning parameter of the ultrasound scanning mechanism 110 including the emission frequency as an example: adjusting the scanning parameters of the preset ultrasound scanning mechanism 110 according to the attribute information of the target object includes adjusting the emission frequency according to the organ type of the target object. For example, if the target object is a fetal heart, the emission frequency is increased to obtain a higher frame rate for observing the heart movement; if the target object is a fetal brain, the emission frequency is maintained to obtain a higher resolution for observing the tissue characteristics of the fetal brain.

[0120] It should be understood that through the above two implementation manners, the target calibration image 520 corresponding to the target object can be obtained according to the rotation offset information, the automatic angle calibration of the ultrasound image 200 can be completed, the inspection speed can be accelerated, and the difficulty of doctors' ultrasound inspection can be significantly reduced, so as to assist doctors in observing the local area of the organ with high precision and making a more accurate diagnosis.

[0121] In Figure 6 As shown, in some embodiments, correcting the target area corresponding to the target area image 400 according to the rotation offset information to obtain a calibration area includes:

[0122] Rotating the target identification frame 320 on the ultrasound image 200 by an angle -α opposite to the offset angle α to obtain a calibration identification frame 330, and using the calibration identification frame 330 to determine the calibration area.

[0123] Specifically as Figure 6 (a)(b) shown, taking the target identification frame 320 as a sector as an example for illustration, rotating the target identification frame 320 on the ultrasound image 200 by an angle -α opposite to the offset angle α to obtain a calibration identification frame 330, and then taking the area corresponding to the calibration identification frame 330 as the calibration area.

[0124] As Figure 6As shown, in some embodiments, the image obtained by the ultrasonic scanning mechanism 110 performing ultrasonic scanning on the target object based on the adjusted scanning parameters is the re-acquired image 510. After the ultrasonic scanning mechanism 110 performs ultrasonic scanning on the target object based on the adjusted scanning parameters to obtain the re-acquired image 510, it further includes:

[0125] Rotating the re-acquired image 510 according to the rotation offset information to obtain the target calibration image 520.

[0126] Specifically, when the rotation offset information includes the offset angle α of the target region image 400 relative to the standard image 600, based on the fact that in the foregoing steps, the target region corresponding to the target region image 400 is corrected according to the rotation offset information to obtain the calibration region. Therefore, rotating the target calibration image 520 according to the rotation offset information includes: rotating the target calibration image 520 by the offset angle α.

[0127] Specifically, as Figure 6 (c) shows, taking the target identification frame 320 being a sector as an example for illustration. In the process as Figure 6 shown, on the ultrasonic image 200, the target identification frame 320 is rotated by the opposite angle -α of the offset angle α to obtain the calibration identification frame 330. The calibration region is determined by using the calibration identification frame 330, and the target calibration image 520 is generated according to the calibration region. Based on this, there is an offset angle α between the target calibration image 520 obtained by performing ultrasonic scanning on the target object based on the adjusted scanning parameters and the ultrasonic image 200.

[0128] Specifically, as Figure 6 (c)(d) shows, rotating the target calibration image 520 by the offset angle α corresponding to the rotation offset information can ensure that the rotated target calibration image 520 is at the same angle as the target identification frame 320, thus facilitating the doctor to observe the target object from the correct perspective.

[0129] After obtaining the target calibration image 520 corresponding to the target object according to the rotation offset information, at least display the target calibration image 520. For example, at least displaying the target calibration image 520 includes: the controller 130 controls the display 120 to perform image display, and the image displayed by the display 120 at least includes the target calibration image 520.

[0130] In some embodiments, at least displaying the target calibration image 520 includes:

[0131] Preprocessing the target calibration image 520 and displaying the preprocessed target calibration image 520;

[0132] Among them, the preprocessing includes at least one of image magnification and pixel interpolation processing of the target calibration image 520.

[0133] It should be noted that the above preprocessing is a post - processing of the target calibration image 520 after the generation of the target calibration image 520. Among them, image magnification or pixel interpolation processing of the target calibration image 520 aims to increase the pixels in the target calibration image 520, so that the displayed target calibration image 520 is clearer.

[0134] Please refer to Figure 7 , Figure 7 which is a schematic diagram of the effect of displaying a target calibration image in an ultrasonic image display method provided by an embodiment of the present application.

[0135] As Figure 7 shown, in some embodiments, at least displaying the target calibration image 520 includes:

[0136] Displaying the target calibration image 520 and the standard reference information 800 matched with the target calibration image 520 in the display interface 800, where the standard reference information 800 includes a standard reference image and / or a standard reference video.

[0137] It should be noted that the standard reference information 800 can be at least one of a standard reference image and a standard reference video. Further, at least one of the standard reference image and the standard reference video can also be selected for display according to external input information. For example, the standard reference image can be a standard image 600 matched with the target object.

[0138] Exemplarily, the display interface 800 can be an interface in the display 120, and the controller 130 executing this method can control the display 120 to display the target calibration image 520 and the standard reference information 800 on the display interface 800.

[0139] By displaying the target calibration image 520 and the standard reference information 800 in the display interface 800 in the embodiment of the present application, the comparison function between the target calibration image 520 and the standard reference information 800 is increased, which is convenient for doctors to compare and evaluate and complete more accurate diagnosis.

[0140] The embodiment of the present application also provides a computer - readable storage medium. The computer - readable storage medium stores a computer program, and the computer program can be executed by one or more processors. When the computer program is executed by the processor, the processor realizes the steps of any ultrasonic image 200 display method provided in the specification of the present application.

[0141] Among them, the storage medium may be the internal storage unit of the controller 130 described in the foregoing embodiments, such as the hard disk or memory of the controller 130. The storage medium may also be an external storage device of the controller 130, such as a plug-in hard disk equipped on the controller 130, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc.

[0142] In summary, the embodiments of the present application provide an ultrasonic image 200 display method, an ultrasonic imaging device 100, and a medium. The ultrasonic image 200 display method includes: identifying a target object in the ultrasonic image 200 to be processed; identifying a target area where the target object is located from the ultrasonic image 200 based on the attribute information of the target object to obtain a target area image 400; obtaining the rotation offset information of the target object in the target area image 400; obtaining a target calibration image 520 corresponding to the target object according to the rotation offset information, and at least displaying the target calibration image 520. This solution not only greatly reduces the complexity of the operation process and speeds up the ultrasonic examination, but also can perform perspective correction according to the rotation offset information, reducing the difficulty for doctors to observe.

[0143] It should be noted that those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the liquid suction control method described above can refer to the corresponding working process of the foregoing ultrasonic image display method, and will not be elaborated here.

[0144] It should be understood that the terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification of the present application and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms.

[0145] It should also be understood that the term "and / or" used in the specification of the present application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations. It should be noted that in this article, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or system. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or system including the element.

[0146] The serial numbers of the embodiments of the present application above are only for description and do not represent the superiority or inferiority of the embodiments. As mentioned above, the above is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. An ultrasonic image display method, characterized in that, The method includes: Identifying a target object in an ultrasonic image to be processed; Identifying a target area where the target object is located in the ultrasonic image based on the attribute information of the target object to obtain a target area image; Obtaining rotation offset information of the target object in the target area image; Obtaining a target calibration image corresponding to the target object according to the rotation offset information and at least displaying the target calibration image.

2. The ultrasonic image display method according to claim 1, characterized in that, The identifying the target area where the target object is located in the ultrasonic image based on the attribute information of the target object includes: Generating a target identification frame for identifying the target object based on the attribute information of the target object; Using the target identification frame to identify the target area where the target object is located in the ultrasonic image and cropping the target area to obtain a target area image.

3. The ultrasonic image display method according to claim 2, wherein The attribute information includes first attribute information and second attribute information. The first attribute information at least includes category information of the target object, and the second attribute information at least includes shape information and area information of the target object; The generating a target identification frame for identifying the target object based on the attribute information of the target object includes: Generating an initial identification frame based on the first attribute information, and adjusting the size and / or position of the initial identification frame according to the first attribute information and the second attribute information to obtain a target identification frame.

4. The ultrasonic image display method according to claim 2, wherein, The using the target identification frame to identify the target area where the target object is located in the ultrasonic image and cropping the target area to obtain a target area image includes: Using the target identification frame to identify the target area where the target object is located in the ultrasonic image; Receiving a target confirmation instruction and, in response to the target confirmation instruction, cropping the target area from the ultrasonic image to obtain a target area image.

5. The ultrasonic image display method according to claim 2, characterized in that At least one of the size, position, and shape of the target identification frame can be adjusted based on external input information.

6. The ultrasonic image display method according to claim 1, wherein, The obtaining rotation offset information of the target object in the target area image includes: Obtaining a standard image matching the target object according to the attribute information and comparing the standard image with the target area image to obtain the rotation offset information.

7. The ultrasonic image display method according to claim 6, wherein The comparing the standard image with the target area image to obtain the rotation offset information includes: Determining a target comparison strategy between the standard image and the target area image according to the attribute information; Comparing the target area image with the standard image based on the target comparison strategy to obtain the rotation offset information.

8. The ultrasonic image display method according to claim 7, wherein The target comparison strategy includes any one of a first comparison strategy and a second comparison strategy; The comparing the target area image with the standard image based on the target comparison strategy to obtain the rotation offset information includes: When the target comparison strategy is the first comparison strategy, determine the rotation center point from the target area image, rotate the target area image with the rotation center point, and calculate the image coincidence degree between the target area image and the standard image during the image rotation. When the image coincidence degree exceeds a preset value, record the rotation angle information of the target area image, and use the rotation angle information as the rotation offset information; When the target comparison strategy is the second comparison strategy, identify a first target axis corresponding to the target object in the target area image, calculate a first included angle between the first target axis and a preset reference normal line, where the first target axis includes the major axis and / or minor axis of the target object in the target area image; identify a second target axis corresponding to the target object in the standard image, calculate a second included angle between the second target axis and the preset reference normal line, where the first target axis includes the major axis and / or minor axis of the target object in the target area image; calculate the rotation offset information based on the first included angle and the second included angle.

9. The ultrasonic image display method according to claim 6, wherein, The obtaining the rotation offset information by comparing the standard image with the target area image includes: Obtain a plurality of first feature points from the target area image, and obtain second feature points that match the plurality of first feature points one by one from the standard image; Determine the rotation offset information based on the first position information corresponding to the first feature points and the second position information corresponding to the second feature points.

10. The ultrasonic image display method according to any one of claims 1-9, characterized in that, The obtaining the target calibration image corresponding to the target object based on the rotation offset information includes: Perform angle calibration on the target area according to the rotation offset information to obtain a target calibration image.

11. The ultrasonic image display method according to any one of claims 1-9, characterized in that, The at least displaying the target calibration image includes: Perform preprocessing on the target calibration image, and display the preprocessed target calibration image; Wherein, the preprocessing includes at least one of image magnification and pixel interpolation processing on the target calibration image.

12. The ultrasonic image display method according to any one of claims 1-9, characterized in that The obtaining the target calibration image corresponding to the target object based on the rotation offset information includes: Correct the target area corresponding to the target area image according to the rotation offset information to obtain a calibration area; Adjust the scanning parameters of a preset ultrasonic scanning mechanism according to the calibration position information of the calibration area relative to the ultrasonic image and the attribute information of the target object, so that the ultrasonic scanning mechanism performs ultrasonic scanning on the target object based on the adjusted scanning parameters to obtain the target calibration image; Wherein, the resolution of the target calibration image is greater than the image within the calibration area in the ultrasonic image.

13. The ultrasonic image display method according to any one of claims 1-9, wherein the at least displaying the target calibration image includes: Display the target calibration image and standard reference information matching the target calibration image in a display interface, where the standard reference information includes a standard reference image and / or a standard reference video.

14. An ultrasonic imaging device, characterized in that, The ultrasonic imaging device at least includes: An ultrasonic scanning mechanism for performing ultrasonic scanning on a target object to obtain an ultrasonic image; A display for image display; A controller electrically connected to the ultrasonic scanning mechanism and the display, and configured to execute the ultrasonic image display method according to any one of claims 1 to 13.

15. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor is caused to implement the steps of the ultrasonic image display method according to any one of claims 1 to 14.

Images