Ultrasonic image processing method and device, equipment and storage medium

Abstract

The invention relates to the technical field of image processing, in particular to an ultrasonic image processing method and device, equipment and a storage medium, and the method comprises the steps: obtaining an ultrasonic heart video at a current detection position, and determining the section type of an image frame in the ultrasonic heart video; if a target image frame of which the section type is a right atrium detection section exists in the ultrasonic heart video, performing right atrium recognition on the target image frame to obtain a right atrium image; based on the size of the right atrium area in the right atrium image, determining a target right atrium image in the right atrium image; and performing target parameter measurement on the right atrium based on the target right atrium image, and determining target parameters of the right atrium. Therefore, automatic selection of the target right atrium image is realized, the recognition accuracy and efficiency of the target right atrium image are improved, automatic measurement of the target parameter of the right atrium is realized, the operation is simplified, and the accuracy is high.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and particularly to a method, apparatus, device, and storage medium for processing ultrasonic images. Background Art

[0002] Currently, the measurement steps for the right atrium in ultrasonic images are complex. It is necessary for the operator to manually find the exact picture at the end of cardiac systole, and then select measurement points on the picture at the end of cardiac systole. The selection of the picture and the measurement points depends on the operator's experience, there are subjective factors, and large errors are likely to occur, resulting in low accuracy. Summary of the Invention

[0003] In view of this, the present invention provides a method, apparatus, device, and storage medium for processing ultrasonic images to solve the problems of manual detection of the right atrium, complex operation, and low accuracy.

[0004] In a first aspect, the present invention provides a method for processing ultrasonic images, the method comprising:

[0005] Obtain an ultrasonic cardiac video at a current detection position, and determine the section type of the image frames in the ultrasonic cardiac video;

[0006] If there is a target image frame with a section type of right atrium detection section in the ultrasonic cardiac video, perform right atrium recognition on the target image frame to obtain a right atrium image;

[0007] Based on the size of the right atrium area in the right atrium image, determine a target right atrium image in the right atrium image, where the target right atrium image is the right atrium image at the end of systole;

[0008] Measure target parameters of the right atrium based on the target right atrium image to determine the target parameters of the right atrium.

[0009] The method for processing ultrasonic images provided by the embodiments of the present invention first performs right atrium recognition on the image frames to obtain a right atrium image, and on this basis, determines the image at the end of systole based on the size of the right atrium area, realizing the automatic selection of the target right atrium image, improving the recognition accuracy and efficiency of the target right atrium image; at the same time, measuring the target parameters based on the determined image at the end of systole, thereby realizing the automatic measurement of the target parameters of the right atrium, simplifying the operation, and having high accuracy.

[0010] In an alternative embodiment, based on the size of the right atrium area in the right atrium image, determining a target right atrium image in the right atrium image includes:

[0011] Determine the right atrium image with the largest right atrium area as the target right atrium image.

[0012] In this way, according to the variation law of the right atrial area, the image at the end-systole can be accurately selected from the right atrial images.

[0013] In an alternative embodiment, the method further includes:

[0014] If the section type is the right atrial detection section, display the section type in a first style on the ultrasound interface;

[0015] If the section type is a non-right atrial detection section, display the section type in a second style on the ultrasound interface.

[0016] In this way, it can be visually shown to the user on the ultrasound interface whether an image of the right atrial detection section can be obtained at the current detection position, thereby guiding the user to adjust the detection position.

[0017] In an alternative embodiment, measuring target parameters of the right atrium based on the target right atrial image to determine the target parameters of the right atrium includes:

[0018] Based on the characteristics of the tricuspid valve, determine the tricuspid valve horizontal center point in the target right atrial image;

[0019] Based on the tricuspid valve horizontal center point and the contour of the right atrium, determine the inner diameter of the right atrium, and the target parameters include the inner diameter of the right atrium.

[0020] In an alternative embodiment, based on the characteristics of the tricuspid valve, determining the tricuspid valve horizontal center point in the target right atrial image includes:

[0021] Perform feature extraction on the target right atrial image based on the characteristics of the tricuspid valve to determine the first key point and the second key point of the tricuspid valve;

[0022] Determine the center point of the first key point and the second key point of the tricuspid valve as the tricuspid valve horizontal center point.

[0023] In this way, two key points of the tricuspid valve can be extracted by means of feature extraction, and the position of the tricuspid valve horizontal center point can be determined based on the geometric relationship between the tricuspid valve horizontal center point and the two key points, thereby improving the accuracy of detecting the tricuspid valve horizontal center point.

[0024] In an alternative embodiment, based on the tricuspid valve horizontal center point and the contour of the right atrium, determining the inner diameter of the right atrium includes:

[0025] Determine the intersection point of the straight line where the tricuspid valve horizontal center point is located in the first direction and the contour of the right atrium as the right atrial posterior center point;

[0026] Based on the tricuspid valve horizontal center point and the right atrial posterior center point, determine the major axis of the right atrium; the inner diameter of the right atrium includes the major axis of the right atrium.

[0027] In an alternative embodiment, based on the central point at the level of the tricuspid valve and the contour of the right atrium, determining the inner diameter of the right atrium includes:

[0028] Determining two intersection points of the perpendicular bisector of the major axis and the contour of the right atrium as the first minor axis measurement point and the second minor axis measurement point of the right atrium respectively;

[0029] Based on the first minor axis measurement point and the second minor axis measurement point, determining the minor axis of the right atrium; the inner diameter of the right atrium includes the minor axis of the right atrium.

[0030] In this way, based on the geometric relationship between the central point at the rear of the right atrium and the two measurement points of the minor axis and the central point at the tricuspid valve level, the central point at the rear of the right atrium and the two measurement points of the minor axis can be determined respectively, so as to measure the major axis and minor axis of the right atrium, thereby improving the accuracy of the measurement of the major axis and minor axis of the right atrium.

[0031] In an alternative embodiment, the method further includes:

[0032] Obtaining the major axis and minor axis of the right atrium in the target right atrium image;

[0033] Displaying the image frame corresponding to the target right atrium image on the ultrasound interface;

[0034] Displaying the target parameters of the right atrium on the image frame corresponding to the target right atrium image, where the target parameters include at least one of the right atrium area, the major axis of the right atrium, and the minor axis of the right atrium.

[0035] In this way, the measurement results can be intuitively displayed on the ultrasound interface, facilitating the user to analyze the right atrium image.

[0036] In a second aspect, the present invention provides an ultrasound image processing device, which includes:

[0037] A section type determination module, configured to obtain an ultrasound cardiac video at a current detection position and determine the section type of the image frame in the ultrasound cardiac video;

[0038] A right atrium recognition module, configured to, if there is a target image frame with a section type of a right atrium detection section in the ultrasound cardiac video, perform right atrium recognition on the target image frame to obtain a right atrium image;

[0039] A target right atrium image determination module, configured to obtain the right atrium area based on the right atrium image to determine a target right atrium image in the right atrium image; the target right atrium image is the right atrium image at the end of systole;

[0040] A target parameter determination module, configured to measure the target parameters of the right atrium based on the target right atrium image and determine the target parameters of the right atrium.

[0041] In a third aspect, the present invention provides an ultrasonic device, including: an ultrasonic probe and a display;

[0042] a processor, communicatively connected to the ultrasonic probe and the display, and the processor is configured to execute the ultrasonic image processing method of the first aspect or any corresponding embodiment thereof;

[0043] The display is configured to display an ultrasonic interface.

[0044] In a fourth aspect, the present invention provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to cause a computer to execute the ultrasonic image processing method of the first aspect or any corresponding embodiment thereof. Description of the Drawings

[0045] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0046] Figure 1 is a schematic structural diagram of an ultrasonic device provided by an embodiment of the present invention;

[0047] Figure 2 is a flowchart of the ultrasonic image processing method according to an embodiment of the present invention;

[0048] FIG. 3(a) is a schematic diagram shown in a first style according to an embodiment of the present invention;

[0049] FIG. 3(b) is another schematic diagram shown in a first style according to an embodiment of the present invention;

[0050] FIG. 4(a) is a schematic diagram shown in a second style according to an embodiment of the present invention;

[0051] FIG. 4(b) is another schematic diagram shown in a second style according to an embodiment of the present invention;

[0052] Figure 5 is a flowchart of another ultrasonic image processing method according to an embodiment of the present invention;

[0053] Figure 6 is a schematic diagram of an ultrasonic interface according to an embodiment of the present invention;

[0054] Figure 7 is a block diagram of the structure of an ultrasonic image processing device according to an embodiment of the present invention. Detailed implementation manners

[0055] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0056] Currently, for the measurement of the right atrium, usually an operator judges the four-chamber view of the heart collected by an ultrasound device, manually selects the key frame at the end of systole for freezing, and then selects measurement points on the key frame to measure the inner diameter. Among them, the measurement points for measuring the long diameter of the right atrium need to be the center point at the level of the tricuspid annulus and the center point at the posterior part of the right atrium, and the measurement points for measuring the short diameter of the right atrium need to be the center point of the free wall of the right atrium and the center point of the interatrial septum. This requires the operator to accurately locate the image frame at the end of systole and accurately select the measurement points. In addition, for the measurement of the area of the right atrium, the operator also needs to spend a lot of time depicting the contour of the right atrium, and then perform integral calculus area calculation according to the depicted contour. However, there are certain errors in the manually depicted contour of the right atrium, which leads to errors in the calculated area of the right atrium and low accuracy.

[0057] To solve the above problems, the embodiments of the present invention provide a method for processing ultrasound images. The method obtains an ultrasound cardiac video at the current detection position and determines the section type of the image frames in the ultrasound cardiac video; if there is a target image frame with the section type of the right atrium detection section in the ultrasound cardiac video, the target image frame is identified for the right atrium to obtain a right atrium image; based on the size of the area of the right atrium in the right atrium image, a target right atrium image is determined in the right atrium image, and the target right atrium image is the right atrium image at the end of systole; based on the target right atrium image, target parameters of the right atrium are measured to determine the target parameters of the right atrium. Thus, by first identifying the right atrium in the image frame to obtain a right atrium image, and then determining the image at the end of systole based on the size of the area of the right atrium, the automatic selection of the target right atrium image is realized, improving the recognition accuracy and efficiency of the target right atrium image; at the same time, based on the determined image at the end of systole, the measurement of the target parameters is performed, thereby realizing the automatic measurement of the target parameters of the right atrium, simplifying the operation and having high accuracy.

[0058] An embodiment of the present invention provides an ultrasonic device, including an ultrasonic probe, a display, and a processor. Among them, the processor is communicatively connected to the ultrasonic probe and the display. The processor is configured to execute the ultrasonic image processing method described in any of the following embodiments, and the display is configured to display an ultrasonic interface. Of course, the function of the display is not limited to this, and it is specifically set according to actual needs.

[0059] Please refer to Figure 1 , Figure 1 FIG. is a schematic structural diagram of an ultrasonic device provided by an embodiment of the present invention. The ultrasonic device 100 includes an ultrasonic probe 110, a transmitting circuit 112, a receiving circuit 114, a processor 116, and a display 118. Further, the ultrasonic device may further include a transmit / receive selection switch 120 and a beam synthesis module 122. The transmitting circuit 112 and the receiving circuit 114 may be connected to the ultrasonic probe 110 through the transmit / receive selection switch 120.

[0060] Specifically, the transmitting circuit 112 is configured to excite the ultrasonic probe 110 to transmit ultrasonic waves to a target tissue; the receiving circuit 114 is configured to control the ultrasonic probe 110 to receive ultrasonic echoes returned by the target tissue; the processor 116 is configured to execute the ultrasonic image processing method described in any of the following embodiments.

[0061] The ultrasonic probe 110 includes a transducer (not shown in the figure) composed of a plurality of arrayed elements. The elements are configured to transmit ultrasonic waves according to the excitation electrical signal, or convert the received ultrasonic waves into electrical signals. Therefore, each element can be used to realize the mutual conversion between electrical pulse signals and ultrasonic waves, so as to transmit ultrasonic waves to the biological tissue of the target object and can also be used to receive the echoes of the ultrasonic waves reflected by the tissue.

[0062] The transmitting circuit 112 is configured to control the ultrasonic probe 110 to transmit ultrasonic waves. For example, according to the control of the processor 116, the ultrasonic probe 110 is excited to transmit ultrasonic waves to the target object.

[0063] The receiving circuit 114 is configured to control the ultrasonic probe 110 to receive the echoes of ultrasonic waves. For example, the ultrasonic probe 110 is used to receive the ultrasonic echoes returned from the target object to obtain ultrasonic echo signals, and the ultrasonic echo signals can also be processed. The receiving circuit 114 may include one or more amplifiers, an analog-to-digital converter (ADC), etc.

[0064] The display 118 is configured to perform display or human-computer interaction. For example, it outputs visual information and receives user input. The display 118 includes an input device and at least one display screen. The input device is configured to receive user input, which may adopt a keyboard, operation buttons, a mouse, a trackball, a touchpad, etc., or may also adopt a touch screen integrated with the display screen.

[0065] The memory 124 is used to store various types of data.

[0066] The ultrasonic device may further include a beamforming module 122. The beamforming module 122 is signal-connected to the receiving circuit 114 and is used to perform beamforming processing such as corresponding delay and weighted summation on the echo signals. Since the distances from the ultrasonic receiving points in the tissue under test to the receiving array elements are different, the channel data of the same receiving point output by different receiving array elements have delay differences and need to be delayed to align the phases, and the channel data of different channels of the same receiving point are weighted and summed to obtain the ultrasonic image data after beamforming. The ultrasonic image data output by the beamforming module 122 is also called radio frequency data (RF data). The beamforming module 122 performs processing such as focusing delay, weighting, and channel summation on the ultrasonic echo data, and then sends it to the processor 116. The processor 116 performs signal detection, signal enhancement, data conversion, logarithmic compression, etc. on the ultrasonic echo signal to form an ultrasonic image. The ultrasonic image obtained by the processor 116 can be displayed on the display 118 or stored in the memory 124.

[0067] The processor 116 can be implemented as software, hardware, firmware, or any combination thereof, and can use one or more application specific integrated circuits (ASICs), one or more general integrated circuits, one or more microprocessors, one or more programmable logic devices, or any combination of the foregoing circuits and / or devices, or other suitable circuits or devices. Moreover, the processor 116 can control other components in the ultrasonic device 100 to execute the corresponding steps of the methods in the various embodiments of this specification.

[0068] The display 118 is connected to the processor 116. The display 118 can be a touch display screen, a liquid crystal display screen, etc.; or, the display 118 can be an independent display such as a liquid crystal display or a television outside the ultrasonic device 100; or, the display 118 can be the display screen of an electronic device such as a smart phone or a tablet computer, etc. Among them, the number of displays 118 can be one or more.

[0069] The display 118 can display the ultrasonic image obtained by the processor 116. In addition, while displaying the ultrasonic image, the display 118 can also provide a graphical interface for the user to perform human-computer interaction, set one or more controlled objects on the graphical interface, and provide the user with a human-computer interaction device to input operation instructions to control these controlled objects, so as to perform corresponding control operations. For example, an icon is displayed on the graphical interface, and the icon can be operated by using the human-computer interaction device to perform a specific function, such as drawing a region of interest box on the ultrasonic image.

[0070] Optionally, the ultrasound device 100 may further include other human-machine interaction devices other than the display 118, which are connected to the processor 116. For example, the processor 116 may be connected to the human-machine interaction device through an external input / output port, and the external input / output port may be a wireless communication module, a wired communication module, or a combination of both. The external input / output port may also be implemented based on USB, bus protocols such as CAN, and / or wired network protocols, etc.

[0071] Among them, the human-machine interaction device may include an input device for detecting user input information, and the input information may be, for example, a control instruction for the ultrasonic emission / reception timing, an operation input instruction for drawing points, lines, or frames on the ultrasonic image, or may also include other instruction types. The input device may include one or a combination of multiple ones such as a keyboard, a mouse, a roller, a trackball, a mobile input device (such as a mobile device with a touch display screen, a mobile phone, etc.), a multi-functional knob, and so on. The human-machine interaction device may also include an output device such as a printer.

[0072] The ultrasound device 100 may further include a memory 124 for storing instructions executed by the processor, storing received ultrasonic echoes, storing ultrasonic images, and so on. The memory may be a flash card, a solid-state memory, a hard disk, etc. It may be a volatile memory and / or a non-volatile memory, a removable memory and / or a non-removable memory, etc.

[0073] According to an embodiment of the present invention, an embodiment of a method for processing an ultrasonic image is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings may be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than here.

[0074] In this embodiment, a method for processing an ultrasonic image is provided, which can be used for the above-mentioned ultrasound device, etc. Figure 2 is a flowchart of a method for processing an ultrasonic image according to an embodiment of the present invention, as Figure 2 shown, the process includes the following steps:

[0075] Step S201, obtain an ultrasonic cardiac video at the current detection position, and determine the section type of the image frame in the ultrasonic cardiac video.

[0076] In an embodiment of the present invention, the current detection position is the position where the user holds the ultrasonic device to scan and detect the target object. When performing an ultrasonic scan on the heart of the target object, an ultrasonic heart video detected at the current detection position will be displayed on the ultrasonic interface. At the same time, the ultrasonic device will determine the section type of the image frame in the ultrasonic heart video to determine whether the detection of the right atrium of the heart of the target object can be enabled at the current detection position.

[0077] In an alternative embodiment, the section type of each image frame in the ultrasonic heart video can be determined by extracting and matching features of the image frames. Specifically, an artificial intelligence method can be used, such as the FastRcnn and Centernet object detection methods based on deep learning, or traditional image processing and matching methods, to extract the heart features contained in the image frame, compare the heart features with the features of the standard apical four-chamber ultrasonic image containing the right atrium, and use the similarity or consistency between the two as the image quality of the image frame. The image quality of the image frame is used as the criterion for determining the section type of the image frame, that is, the similarity or consistency between the heart features of the image frame and the standard image features is used as the criterion for determining the section type of the image frame.

[0078] In an alternative embodiment, the section types of the image frames in the ultrasonic heart video can be divided into two categories, namely, the right atrium detection section and the non-right atrium detection section. To facilitate the user to adjust the position of scanning the target object, that is, the current detection position, the section type of the image frame in the ultrasonic heart video can be displayed on the ultrasonic interface in real time to indicate whether the ultrasonic heart video scanned at the current detection position can be used for the next detection of the right atrium, or whether the current detection position needs to be further adjusted. Specifically, if the section type is the right atrium detection section, the section type is displayed in the first style on the ultrasonic interface; if the section type is the non-right atrium detection section, the section type is displayed in the second style on the ultrasonic interface. Among them, the first style and the second style can use different colors and different texts to correspondingly display the section type. For example, referring to FIGS. 3(a), 3(b), 4(a) and 4(b), as shown in FIGS. 3(a) and 3(b), the section type of the image frame is the right atrium detection section, then "measurable section" is displayed in the first color on the ultrasonic interface to indicate that the section of the image frame is the right atrium detection section and the detection of the right atrium can be performed; as shown in FIGS. 4(a) and 4(b), the section type of the image frame is the non-right atrium detection section, then "non-right atrium measurement section" is displayed in the second color on the ultrasonic interface to indicate that the image frame is the non-right atrium detection section and the current detection position needs to be further adjusted. Those skilled in the art should know that the first style and the second style include but are not limited to the above Figures 3(a) to 4(b) shown, and can be specifically set according to the actual needs and usage habits of the user, and no limitation is made thereto herein.

[0079] Step S202: If there is a target image frame with a section type of right atrium detection section in the ultrasonic cardiac video, then perform right atrium recognition on the target image frame to obtain a right atrium image.

[0080] In the embodiment of the present invention, if there is a target image frame with a section type of right atrium detection section in the ultrasonic cardiac video, it indicates that the right atrium section of the heart can be detected at the current detection position, and the right atrium of the heart can be measured at the current detection position. Then, obtain the target image frames in the ultrasonic cardiac video, and perform right atrium recognition on each target image frame respectively. The recognition method of the right atrium includes, but is not limited to, the U-Net segmentation algorithm of deep learning, the Otsu method, the watershed method, etc., which are specifically set according to actual needs and are not limited herein. After performing right atrium recognition on the target image frame, the position of the right atrium in the target image frame is obtained, that is, the contour of the right atrium in the target image frame is obtained, which is also the right atrium image.

[0081] Step S203: Based on the size of the right atrium area in the right atrium image, determine a target right atrium image in the right atrium image, and the target right atrium image is the right atrium image at the end of systole.

[0082] In the embodiment of the present invention, since the right atrium area is the largest at the end of systole, the right atrium image at the end of systole can be located among multiple right atrium images based on the change rule of the right atrium area, that is, the right atrium image with the largest right atrium area is determined as the target right atrium image. Since the subsequent parameters of the right atrium are measured and calculated based on the right atrium image at the end of systole, the right atrium image at the end of systole is used as the target right atrium image, which can also be called a key frame.

[0083] In an alternative embodiment, before determining the target right atrium image from the right atrium images, the right atrium images can be preprocessed first to enhance the contrast of the right atrium images, so as to obtain more image details. The preprocessing methods include, but are not limited to, normalization, adaptive histogram equalization, standardization, and gamma correction, etc., which are specifically set according to actual needs and are not limited herein.

[0084] In an alternative embodiment, the method of determining the target right atrium image from the right atrium images can be divided into two categories. The first category is the algorithm based on deep learning, and the second category is the traditional algorithm based on the change rule of the right atrium area. Different algorithms have different post-processing timings for the right atrium images:

[0085] For deep learning-based algorithms, such as the Yolo detection algorithm, optical flow method, etc., the right atrium image can be directly input into the neural network model corresponding to the algorithm. The neural network model will extract key frames according to the change law of the right atrium area in the right atrium image, and then directly output the detected key frames, that is, the target right atrium image can be directly obtained. Therefore, the post-processing of the right atrium image is to perform post-processing only on the target right atrium image after the target right atrium image is determined.

[0086] For traditional algorithms based on the change law of the right atrium area, the right atrium area corresponding to the right atrium image will be calculated respectively, and then the right atrium image with the largest right atrium area will be used as the target right atrium image. Since it is necessary to calculate and compare the right atrium area, in order to ensure the accuracy of the target right atrium image obtained by comparison, the right atrium images are first post-processed respectively, and then the right atrium areas are calculated respectively to obtain the target right atrium image. Optionally, the area of the right atrium can be calculated by binarizing the closed area enclosed by the contour of the right atrium in the right atrium image, or calculating the area based on the chain code method, etc. No limitation is imposed on the method of calculating the area of the right atrium here, and it is specifically set according to actual needs.

[0087] In an optional implementation manner, the post-processing of the right atrium image may include the following operations:

[0088] Perform a region search on the right atrium image, retain the largest segmentation region, and remove the remaining isolated small regions to ensure that the right atrium image only contains the segmentation region corresponding to the right atrium, that is, the contour of the right atrium;

[0089] Perform morphological operations on the right atrium image to avoid the situation where the contour of the right atrium in the right atrium image is not closed, make it form a closed region, facilitate subsequent area calculation and other operations, and at the same time, the convex hull or depression on the contour of the right atrium can be removed, and the contour of the right atrium can be smoothed to achieve detail optimization; The morphological operations may include, but are not limited to, opening operation, seed filling, and flood filling, etc. The specific processing method is not limited to the above description and can be specifically set according to actual needs;

[0090] Filter the right atrium image by means of, for example, Gaussian filtering to achieve edge smoothing and further smooth the contour of the right atrium.

[0091] Step S204, measure the target parameters of the right atrium based on the target right atrium image to determine the target parameters of the right atrium.

[0092] In the embodiments of the present invention, the target parameters include, but are not limited to, the area of the right atrium and the inner diameter of the right atrium, etc., which characterize some physical quantities of the right atrium. The physical quantities of the right atrium are processed depending on the definitions of these physical quantities. For example, the long diameter of the right atrium is the distance from the midpoint of the tricuspid annulus plane perpendicular to the right atrial apex at the end of systole, and the short diameter of the right atrium, that is, the transverse diameter of the right atrium, is the distance from the midpoint of the interatrial septum to the lateral wall at the end of systole.

[0093] In an alternative embodiment, which specific target parameters need to be measured can be set according to actual application requirements, and no limitation is imposed thereon herein.

[0094] The method for processing an ultrasonic image provided by the embodiments of the present invention first identifies the right atrium in an image frame to obtain a right atrial image, and on this basis, determines an image at the end of systole based on the size of the right atrial area, realizing the automatic selection of the target right atrial image, improving the recognition accuracy and efficiency of the target right atrial image; meanwhile, measuring the target parameters based on the determined image at the end of systole, thereby realizing the automatic measurement of the target parameters of the right atrium, simplifying the operation and having high accuracy.

[0095] In this embodiment, a method for processing an ultrasonic image is provided, which can be used for the above-mentioned ultrasonic device, etc. Figure 5 is a flowchart of another method for processing an ultrasonic image according to the embodiments of the present invention, as Figure 5 shown, the process includes the following steps:

[0096] Step S501, obtain an ultrasonic cardiac video at the current detection position and determine the section type of the image frame in the ultrasonic cardiac video. For details, please refer to Figure 2 step S201 of the embodiment shown, which will not be elaborated herein.

[0097] Step S502, if there is a target image frame with a section type of right atrial detection section in the ultrasonic cardiac video, perform right atrial recognition on the target image frame to obtain a right atrial image. For details, please refer to Figure 2 step S202 of the embodiment shown, which will not be elaborated herein.

[0098] Step S503, based on the size of the right atrial area in the right atrial image, determine a target right atrial image in the right atrial image, and the target right atrial image is the right atrial image at the end of systole. For details, please refer to Figure 2 step S203 of the embodiment shown, which will not be elaborated herein.

[0099] Step S504, measure the target parameters of the right atrium based on the target right atrial image to determine the target parameters of the right atrium.

[0100] Specifically, the above step S504 includes:

[0101] Step S5041: Based on the characteristics of the tricuspid valve, determine the center point of the tricuspid valve level in the target right atrium image.

[0102] In the embodiment of the present invention, by using the characteristics of the tricuspid valve, the position of the tricuspid valve is determined in the target right atrium image. Thus, according to the geometric position relationship between the tricuspid valve and the center point of the tricuspid valve level, the position of the center point of the tricuspid valve level can be determined.

[0103] Specifically, the above step S5041 may include the following steps:

[0104] Step a1: Perform feature extraction on the target right atrium image based on the characteristics of the tricuspid valve to determine the first key point and the second key point of the tricuspid valve.

[0105] In step a1, based on artificial intelligence methods, such as FastRcnn and Centernet object detection methods based on deep learning, or traditional image processing methods, features of the target right atrium image can be obtained to get the features of the tricuspid valve in the target right atrium image, specifically the first key point and the second key point of the tricuspid valve. Among them, the first key point and the second key point of the tricuspid valve are respectively the leftmost point and the rightmost point of the tricuspid valve annulus plane, which can represent the specific position of the tricuspid valve annulus plane.

[0106] Step a2: Determine the center point of the first key point and the second key point of the tricuspid valve as the center point of the tricuspid valve level.

[0107] In step a2, since the center point of the tricuspid valve level is the midpoint of the tricuspid valve annulus plane, and the first key point and the second key point are respectively the leftmost point and the rightmost point of the tricuspid valve annulus plane, then the center point of the tricuspid valve level is also the center point of the first key point and the second key point. Based on this, by the positions of the first key point and the second key point of the tricuspid valve, calculate the position of their center point to obtain the position of the center point of the tricuspid valve level. Thus, by means of feature extraction, two key points of the tricuspid valve are obtained, and based on the geometric relationship between the center point of the tricuspid valve level and the two key points, the position of the center point of the tricuspid valve level is determined, thereby improving the accuracy of detecting the center point of the tricuspid valve level.

[0108] Step S5042: Based on the center point of the tricuspid valve level and the contour of the right atrium, determine the inner diameter of the right atrium. The target parameter includes the inner diameter of the right atrium.

[0109] In an embodiment of the present invention, the target parameters of the right atrium include the inner diameter of the right atrium, and the inner diameter of the right atrium further includes the long diameter and the short diameter of the right atrium. Then step S5052 can be divided into two steps of determining the long diameter of the right atrium and determining the short diameter of the right atrium. Since the short diameter of the right atrium is perpendicular to the long diameter of the right atrium and is determined by the position of the long diameter of the right atrium, in step S5052, first, based on the center point at the tricuspid valve level and the contour of the right atrium, the long diameter of the right atrium is determined, and then based on the long diameter of the right atrium and the contour of the right atrium, the short diameter of the right atrium is determined.

[0110] Specifically, in step S5042, based on the center point at the tricuspid valve level and the contour of the right atrium, determining the long diameter of the right atrium may include the following steps:

[0111] Step b1: Determine the center point of the posterior part of the right atrium as the intersection point of the straight line where the center point at the tricuspid valve level is located in the first direction and the contour of the right atrium.

[0112] In step b1, the first direction is the direction perpendicular to the tricuspid valve plane, that is, the direction perpendicular to the connection line between the first key point and the second key point. At the same time, the center point at the tricuspid valve level is the center point of the first key point and the second key point. Then the straight line where the center point at the tricuspid valve level is located in the first direction is the perpendicular bisector of the tricuspid valve plane. Based on this, the intersection point of the straight line where the center point at the tricuspid valve level is located in the first direction and the contour of the right atrium is the center point of the posterior part of the right atrium, that is, another measurement point of the long diameter of the right atrium.

[0113] Step b2: Determine the long diameter of the right atrium based on the center point at the tricuspid valve level and the center point of the posterior part of the right atrium.

[0114] In step b2, the line segment with the center point at the tricuspid valve level and the center point of the posterior part of the right atrium as endpoints is the connection line corresponding to the long diameter of the right atrium. Calculating the distance between the center point at the tricuspid valve level and the center point of the posterior part of the right atrium can obtain the specific value of the long diameter of the right atrium.

[0115] In step S5042, based on the long diameter of the right atrium and the contour of the right atrium, determining the short diameter of the right atrium may include the following steps:

[0116] Step c1: Determine the two intersection points of the perpendicular bisector of the long diameter and the contour of the right atrium as the first short diameter measurement point and the second short diameter measurement point of the right atrium respectively.

[0117] In step c1, since the short diameter of the right atrium is perpendicular to the long diameter of the right atrium and is located on the perpendicular bisector of the long diameter of the right atrium, then the two intersection points of the perpendicular bisector of the long diameter and the contour of the right atrium are the two measurement points of the short diameter, and they are respectively determined as the first short diameter measurement point and the second short diameter measurement point, corresponding to the midpoint of the atrial septum of the right atrium and the measurement point on the lateral wall of the right atrium respectively.

[0118] Step c2: Determine the minor diameter of the right atrium based on the first minor diameter measurement point and the second minor diameter measurement point; the inner diameter of the right atrium includes the minor diameter of the right atrium.

[0119] In step c2, the line segment with the first minor diameter measurement point and the second minor diameter measurement point as endpoints is the connection corresponding to the minor diameter of the right atrium. By calculating the distance between the first minor diameter measurement point and the second minor diameter measurement point, the specific value of the minor diameter of the right atrium can be obtained.

[0120] Thus, through the above method, based on the geometric relationship between the central point of the posterior part of the right atrium, the two measurement points of the minor diameter, and the central point at the tricuspid valve level, the central point of the posterior part of the right atrium and the two measurement points of the minor diameter are respectively determined to measure the major diameter and minor diameter of the right atrium, thereby improving the accuracy of measuring the major diameter and minor diameter of the right atrium.

[0121] In the above embodiment, as Figure 6 shown, the target parameters of the right atrium and the corresponding image frames of the target right atrium image can also be displayed on the ultrasound interface to facilitate the user's analysis of the right atrium image. Specifically, obtain the major diameter and minor diameter of the right atrium in the target right atrium image; display the image frame corresponding to the target right atrium image on the ultrasound interface; display the target parameters of the right atrium on the image frame corresponding to the target right atrium image, and the target parameters include at least one of the right atrium area, the major diameter of the right atrium, and the minor diameter.

[0122] In an alternative embodiment, when analyzing and processing the ultrasound image, multiple parameters of the right atrium can be obtained, but the user can select some target parameters for display through interactive operations. Correspondingly, only the measured values of the selected target parameters are displayed on the ultrasound interface.

[0123] In an alternative embodiment, when the inner diameter of the right atrium is displayed on the ultrasound interface, the specific position of the displayed inner diameter on the image frame is also displayed on the image frame to facilitate the user to more intuitively understand the state of the right atrium.

[0124] In this embodiment, a processing device for ultrasound images is also provided. This device is used to implement the above embodiments and preferred embodiments, and those that have been described will not be repeated. As used below, the terms "module" and "unit" can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0125] This embodiment provides a processing device for ultrasound images, as Figure 7 shown, this device includes:

[0126] The sectional plane type determination module 701 is configured to obtain an ultrasonic cardiac video at the current detection position and determine the sectional plane type of the image frames in the ultrasonic cardiac video;

[0127] The right atrium recognition module 702 is configured to, if there is a target image frame with a sectional plane type of right atrium detection sectional plane in the ultrasonic cardiac video, perform right atrium recognition on the target image frame to obtain a right atrium image;

[0128] The target right atrium image determination module 703 is configured to obtain the right atrium area based on the right atrium image to determine a target right atrium image in the right atrium image; the target right atrium image is the right atrium image at the end of systole;

[0129] The target parameter determination module 704 is configured to measure target parameters of the right atrium based on the target right atrium image and determine the target parameters of the right atrium.

[0130] In an alternative embodiment, the target right atrium image determination module 703 is configured to:

[0131] Determine the right atrium image with the largest right atrium area as the target right atrium image.

[0132] In an alternative embodiment, the device further includes a sectional plane type display module: the sectional plane type display module includes:

[0133] The first display unit is configured to, if the sectional plane type is the right atrium detection sectional plane, display the sectional plane type in a first style on the ultrasonic interface;

[0134] The second display unit is configured to, if the sectional plane type is a non-right atrium detection sectional plane, display the sectional plane type in a second style on the ultrasonic interface.

[0135] In an alternative embodiment, the target parameter determination module 704 includes:

[0136] The tricuspid valve level center point determination unit is configured to determine the tricuspid valve level center point in the target right atrium image based on the characteristics of the tricuspid valve;

[0137] The inner diameter determination unit is configured to determine the inner diameter of the right atrium based on the tricuspid valve level center point and the contour of the right atrium, and the target parameters include the inner diameter of the right atrium.

[0138] In an alternative embodiment, the tricuspid valve level center point determination unit includes:

[0139] The key point extraction subunit is configured to perform feature extraction on the target right atrium image based on the characteristics of the tricuspid valve to determine the first key point and the second key point of the tricuspid valve;

[0140] A central point determination subunit, configured to determine the central point of the first key point and the second key point of the tricuspid valve as the horizontal central point of the tricuspid valve.

[0141] In an alternative embodiment, the inner diameter determination unit includes:

[0142] A right atrium posterior central point determination subunit, configured to determine the intersection point of the straight line where the horizontal central point of the tricuspid valve is located in the first direction and the contour of the right atrium as the right atrium posterior central point;

[0143] A major axis determination subunit, configured to determine the major axis of the right atrium based on the horizontal central point of the tricuspid valve and the right atrium posterior central point; the inner diameter of the right atrium includes the major axis of the right atrium.

[0144] In an alternative embodiment, the inner diameter determination unit includes:

[0145] A minor axis measurement point determination subunit, configured to determine the two intersection points of the perpendicular bisector of the major axis and the contour of the right atrium as the first minor axis measurement point and the second minor axis measurement point of the right atrium respectively;

[0146] A minor axis determination subunit, configured to determine the minor axis of the right atrium based on the first minor axis measurement point and the second minor axis measurement point; the inner diameter of the right atrium includes the minor axis of the right atrium.

[0147] In an alternative embodiment, the device further includes a display module: The display module includes:

[0148] An inner diameter acquisition unit, configured to acquire the major axis and the minor axis of the right atrium in the target right atrium image;

[0149] An image frame display unit, configured to display the image frame corresponding to the target right atrium image on the ultrasound interface;

[0150] A target parameter display unit, configured to display the target parameters of the right atrium on the image frame corresponding to the target right atrium image, and the target parameters include at least one of the right atrium area, the major axis of the right atrium, and the minor axis.

[0151] The ultrasound image processing device in this embodiment is presented in the form of functional units. Here, the unit refers to an ASIC circuit, a processor and a memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0152] The further function descriptions of the above-mentioned respective modules are the same as those in the corresponding above-mentioned embodiments, and will not be elaborated here.

[0153] Embodiments of the present invention also provide a computer-readable storage medium. The methods according to the embodiments of the present invention can be implemented in hardware, firmware, or be implemented as computer code that can be recorded on a storage medium, or be implemented as computer code that is originally stored in a remote storage medium or a non-transitory computer-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the methods described herein can be stored as such software processes on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid-state drive, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code, and when the software or computer code is accessed and executed by the computer, the processor, or the hardware, the methods shown in the above embodiments are implemented.

[0154] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for processing ultrasonic images, characterized in that, The method includes: Obtaining an ultrasonic cardiac video at the current detection position and determining the section type of the image frames in the ultrasonic cardiac video; If there is a target image frame with a section type of the right atrium detection section in the ultrasonic cardiac video, then performing right atrium recognition on the target image frame to obtain a right atrium image; Based on the size of the right atrium area in the right atrium image, determining a target right atrium image in the right atrium image, where the target right atrium image is the right atrium image at the end of systole; Measuring target parameters of the right atrium based on the target right atrium image and determining the target parameters of the right atrium.

2. The method according to claim 1, characterized in that, The determining a target right atrium image in the right atrium image based on the size of the right atrium area in the right atrium image includes: Determining the right atrium image with the largest right atrium area as the target right atrium image.

3. The method according to claim 1, wherein The method further includes: If the section type is the right atrium detection section, then displaying the section type in a first style in the ultrasonic interface; If the section type is a non-right atrium detection section, then displaying the section type in a second style in the ultrasonic interface.

4. The method according to claim 1, wherein The measuring target parameters of the right atrium based on the target right atrium image and determining the target parameters of the right atrium includes: Based on the characteristics of the tricuspid valve, determining the tricuspid valve horizontal center point in the target right atrium image; Based on the tricuspid valve horizontal center point and the contour of the right atrium, determining the inner diameter of the right atrium, where the target parameters include the inner diameter of the right atrium.

5. The method according to claim 4, wherein The determining the tricuspid valve horizontal center point in the target right atrium image based on the characteristics of the tricuspid valve includes: Performing feature extraction on the target right atrium image based on the characteristics of the tricuspid valve to determine the first key point and the second key point of the tricuspid valve; Determining the center point of the first key point and the second key point of the tricuspid valve as the tricuspid valve horizontal center point.

6. The method according to claim 4, characterized in that The determining the inner diameter of the right atrium based on the tricuspid valve horizontal center point and the contour of the right atrium includes: Determining the intersection point of the straight line where the tricuspid valve horizontal center point is located in the first direction and the contour of the right atrium as the right atrium posterior center point; Based on the tricuspid valve horizontal center point and the right atrium posterior center point, determining the long diameter of the right atrium; the inner diameter of the right atrium includes the long diameter of the right atrium.

7. The method according to claim 6, wherein The determining the inner diameter of the right atrium based on the tricuspid valve horizontal center point and the contour of the right atrium includes: Determining the two intersection points of the perpendicular bisector of the long diameter and the contour of the right atrium as the first short diameter measurement point and the second short diameter measurement point of the right atrium respectively; Based on the first short diameter measurement point and the second short diameter measurement point, determining the short diameter of the right atrium; the inner diameter of the right atrium includes the short diameter of the right atrium.

8. The method according to any one of claims 1-7, characterized in that, The method further includes: Obtaining the long diameter and the short diameter of the right atrium in the target right atrium image; Displaying the image frame corresponding to the target right atrium image on the ultrasonic interface; Display the target parameters of the right atrium on the image frame corresponding to the target right atrium image, where the target parameters include at least one of the right atrium area, the long diameter, and the short diameter of the right atrium.

9. An apparatus for processing an ultrasonic image, characterized in that, The device includes: A cross-section type determination module, configured to obtain an ultrasonic cardiac video at a current detection position and determine the cross-section type of the image frames in the ultrasonic cardiac video; A right atrium recognition module, configured to, if there is a target image frame with a cross-section type of a right atrium detection cross-section in the ultrasonic cardiac video, perform right atrium recognition on the target image frame to obtain a right atrium image; A target right atrium image determination module, configured to obtain a right atrium area based on the right atrium image to determine a target right atrium image in the right atrium image; the target right atrium image is a right atrium image at the end of systole; A target parameter determination module, configured to measure target parameters of the right atrium based on the target right atrium image and determine the target parameters of the right atrium.

10. An ultrasonic device, characterized in that, It includes: An ultrasonic probe and a display; A processor, communicatively connected to the ultrasonic probe and the display, where the processor is configured to execute the ultrasonic image processing method according to any one of claims 1-8; The display is configured to display an ultrasonic interface.

11. A computer-readable storage medium, characterized in that, Computer instructions are stored on the computer-readable storage medium, and the computer instructions are configured to cause a computer to execute the ultrasonic image processing method according to any one of claims 1 to 8.

Images