Diaphragm parameter measuring method and ultrasonic image processing system

By automatically determining the M-line sampling points and fusion processing of ultrasonic diaphragm B and M images, the problem of relying on manual operation in the measurement of diaphragm parameters in the prior art is solved, improving the accuracy of measurement and simplification of the process.

CN118986409APending Publication Date: 2024-11-22EDAN INSTR
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202310583259.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-22
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

Existing ultrasonic measuring devices rely on manual operations when measuring diaphragm parameters, resulting in complex measurement processes and inaccurate results.

Method used

By acquiring the ultrasonic diaphragm B image, the M line sampling point position is automatically determined, and the sampling line is placed based on the position to obtain the sampled diaphragm M image, and the parameters in the two images are combined for fusion processing to achieve accurate measurement of the diaphragm thickness parameters.

Benefits of technology

It reduces the dependence on the operator, simplifies the measurement process, improves the accuracy of the measurement results, and realizes efficient and convenient measurement of diaphragm parameters.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118986409A_ABST
    Figure CN118986409A_ABST
Patent Text Reader

Abstract

The invention discloses a diaphragm parameter measuring method and an ultrasonic image processing system. The method comprises the following steps: acquiring a current frame of ultrasonic diaphragm B image for measuring diaphragm thickness; determining the position of an M-line sampling point in the current frame of ultrasonic diaphragm B image; placing a sampling line based on the position of the M line sampling point to obtain a current frame diaphragm B image and a sampling diaphragm M image; determining a first initial diaphragm thickness parameter in the current frame diaphragm B image, and determining a second initial diaphragm thickness parameter in the sampling diaphragm M image; and performing fusion processing on the first initial diaphragm thickness parameter and the second initial diaphragm thickness parameter to obtain a diaphragm thickness parameter. Through the above mode, the dependence on an operator can be reduced, the measurement process can be simplified, and the accuracy of a measurement result can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of ultrasonic technology, and in particular to a method for measuring diaphragm parameters and an ultrasonic image processing system. Background Art

[0002] The diaphragm is an important respiratory muscle of the body, accounting for 60% to 80% of all respiratory muscle functions. Therefore, diaphragm thickness, diaphragm thickening rate and other related diaphragm parameters are important criteria for evaluating human respiratory health. At present, ultrasonic measuring devices are usually used to measure diaphragm parameters such as diaphragm thickness and diaphragm thickening rate. However, in the process of using ultrasonic measuring devices to measure diaphragm parameters, since the measurement process relies on manual operation, the measurement process is usually too complicated and the measurement results are not accurate enough. Summary of the invention

[0003] The embodiments of the present application provide a diaphragm parameter measurement method and an ultrasonic image processing system, which can reduce the dependence on the operator, simplify the measurement process, and improve the accuracy of the measurement results.

[0004] In order to solve the above problems, the present application provides an embodiment, which includes:

[0005] Acquire a current frame ultrasonic diaphragm B image for measuring diaphragm thickness;

[0006] Determine the position of the M-line sampling point in the current frame ultrasound diaphragm B image;

[0007] The sampling line is placed based on the position of the sampling point through the M line to obtain the sampled diaphragm M image;

[0008] Determine a first initial diaphragm thickness parameter in the current diaphragm B image, and determine a second initial diaphragm thickness parameter in the sampled diaphragm M image;

[0009] The first initial diaphragm thickness parameter and the second initial diaphragm thickness parameter are fused to obtain a diaphragm thickness parameter.

[0010] In order to solve the above problems, an embodiment of the present application provides an ultrasound image processing system, which includes an ultrasound probe, a transmitting circuit, a receiving circuit, a processor and a display;

[0011] The transmitting circuit stimulates the ultrasonic probe to transmit ultrasonic waves to the object to be examined through the transmitting / receiving switch;

[0012] The receiving circuit receives an ultrasonic echo signal based on ultrasonic waves returned from the inspection object;

[0013] The processor processes the ultrasonic echo signal to obtain an ultrasonic image corresponding to the inspection object;

[0014] The monitor displays the ultrasound image;

[0015] The processor also executes the above-mentioned method for measuring diaphragm parameters.

[0016] The beneficial effect of the present application is as follows: Different from the prior art, after obtaining the current frame diaphragm B image, the present application automatically determines the position of the M line sampling point in the current frame diaphragm B image, thereby placing the sampling line based on the position of the M line sampling point to obtain the sampled diaphragm M image. This process does not require the operator to determine the position of the M line sampling point, which can reduce the degree of dependence on the operator, and can also simplify the overall measurement process, so that the measurement process is standardized. Then, the current frame diaphragm B image and the corresponding sampled diaphragm M image are further processed to obtain the first initial diaphragm thickness parameter and the second initial diaphragm thickness parameter, and then the parameters of the diaphragm in the two images are combined to obtain more accurate diaphragm parameters, so as to achieve the effect of improving the accuracy of the measurement results. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of a process of an implementation method of the diaphragm parameter measurement method of the present application;

[0018] Figure 2 It is another schematic flow chart of an implementation method of the diaphragm parameter measurement method of the present application;

[0019] Figure 3 It is another flow chart of an implementation method of the diaphragm parameter measurement method of the present application;

[0020] Figure 4 It is a schematic diagram of M-line positioning of the current frame ultrasound diaphragm B image in an embodiment of the diaphragm parameter measurement method of the present application;

[0021] Figure 5 is a schematic diagram of displaying the final diaphragm image in an embodiment of the method for measuring diaphragm parameters of the present application;

[0022] Figure 6 It is a schematic diagram of a movement trend of diaphragm movement parameters in an embodiment of a method for measuring diaphragm parameters of the present application;

[0023] Figure 7 is another schematic diagram of movement trend of diaphragm movement parameters in one embodiment of the method for measuring diaphragm parameters of the present application;

[0024] Figure 8 It is a schematic block diagram of the circuit structure of an embodiment of the ultrasonic image processing system of the present application. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0026] The inventor of the present application has found that currently, ultrasonic measuring devices are usually used to measure diaphragm parameters such as diaphragm thickness and diaphragm thickening rate. However, in the process of using ultrasonic measuring devices to measure diaphragm parameters, since the measurement process relies on manual operation, the measurement process is too complicated and the measurement results are not accurate enough. In order to solve the above problems, the present application proposes the following embodiments.

[0027] The following is an exemplary description of the measurement of diaphragm parameters in the embodiment of the method for measuring diaphragm parameters of the present application.

[0028] Figure 1 FIG. 1 is a flow chart of an embodiment of a method for measuring diaphragm parameters of the present application. Figure 1 As shown, the method comprises the following steps:

[0029] S100: Acquire a current frame ultrasonic diaphragm B image for measuring diaphragm thickness.

[0030] like Figure 2 As shown, there are many methods for obtaining the ultrasonic diaphragm B image of the current frame, and one implementation method can be specifically referred to the following steps included in step S100:

[0031] S110: Acquire an ultrasonic section B image obtained by ultrasonically scanning the area containing the diaphragm.

[0032] Specifically, in response to the user's selection operation, the preset measurement mode corresponding to the diaphragm measurement can be started. The corresponding step of starting the preset measurement mode corresponding to the diaphragm measurement may include determining the corresponding probe device, starting the corresponding preset inspection, etc. After starting the preset measurement mode corresponding to the diaphragm measurement, the area containing the diaphragm is scanned ultrasonically by the probe to obtain an ultrasonic section B image corresponding to the scanned area containing the diaphragm.

[0033] S120: Automatically identify the measurement type of the ultrasound section B image.

[0034] Optionally, when measuring the diaphragm, different diaphragm parameters correspond to different diaphragm features, so different diaphragm parameters correspond to different diaphragm regions and also correspond to different ultrasonic section B images. Therefore, according to different ultrasonic section B images, the diaphragm parameters corresponding to the ultrasonic section images can be determined and matched.

[0035] Specifically, the measurement type can be distinguished according to the diaphragm parameters, for example, the measurement type can be parameters such as measuring diaphragm thickness and measuring diaphragm mobility. Specifically, when automatically identifying the ultrasound section B image, the diaphragm parameters corresponding to the ultrasound section B image can be automatically matched and determined, thereby obtaining the measurement type of the ultrasound section B image.

[0036] In some embodiments, after obtaining the ultrasound section B image corresponding to the scanned area containing the diaphragm, the ultrasound section B image can be automatically identified using an artificial intelligence algorithm and / or a traditional method, thereby obtaining the measurement type of the ultrasound section B image. Among them, the artificial intelligence algorithm can be a target detection method CenterNet based on deep learning, a target classification algorithm RFCN, SSD, YOLO based on deep learning, etc., and the traditional method can be a traditional target tracking method, a traditional target matching method, etc., and the specific identification method is not limited here.

[0037] Optionally, there may be multiple methods for automatically identifying and determining the measurement type, such as comparing the ultrasound section B image with the standard section B image corresponding to different diaphragm parameters, identifying and determining the measurement type based on the similarity obtained by the comparison, or acquiring the shape features of the target diaphragm in the ultrasound section B image, and matching the shape features corresponding to the measurement type. Of course, in other embodiments, there may be other methods for automatically identifying and determining the measurement type, which are not listed here in detail.

[0038] S130: If the measurement type is to measure the diaphragm thickness, the ultrasound section B image is used as the current frame ultrasound diaphragm B image.

[0039] If the measurement type is to measure the diaphragm thickness, the subsequent processing flow will be switched to the processing flow corresponding to the parameters for measuring the diaphragm thickness, and the ultrasonic section B image will be used as the current frame ultrasonic diaphragm B image, and the corresponding processing calculation will be performed on the current frame ultrasonic diaphragm B image.

[0040] S140: If the measurement type is other diaphragm parameters, the processing flow of the ultrasound section B image is switched to the processing flow corresponding to the diaphragm parameter.

[0041] If the measurement type is other diaphragm parameters such as diaphragm motion, the subsequent processing flow can also be switched to the flow corresponding to the measurement of other diaphragm parameters, and the ultrasonic section B image can be used as the current frame ultrasonic diaphragm B image, and the current frame ultrasonic diaphragm B image can be processed and calculated accordingly, so that the corresponding diaphragm parameters can be measured.

[0042] By setting up automatic identification of the measurement type of the ultrasound section B image and performing corresponding process switching, the step of manually selecting and switching the measurement process corresponding to the diaphragm parameters in the traditional process can be omitted, thereby reducing the degree of dependence on the operator. The overall measurement process can also be simplified and automated, making the entire diaphragm parameter measurement process more efficient and convenient.

[0043] Of course, in the actual operation process, the method described in the present application can also respond to the operator's selection operation to turn off the process of automatically identifying the measurement type of the ultrasound section B image, and then the operator can manually choose to switch the diaphragm parameter measurement process required.

[0044] S200: Determine the position of the M-line sampling point in the current frame of ultrasound diaphragm B image.

[0045] Alternatively, if Figure 3 As shown, step S200 may further include the following steps:

[0046] S210: Determine whether the current frame of ultrasonic diaphragm B image is the first frame of ultrasonic diaphragm B image;

[0047] Specifically, it may be determined whether the current frame of the ultrasonic diaphragm B image is the first frame of the ultrasonic diaphragm B image, or it may be determined whether the current frame of the ultrasonic diaphragm B image is a reset ultrasonic diaphragm B image.

[0048] S220: If yes, perform sampling point detection on the ultrasonic diaphragm B image of the current frame to obtain the M line sampling point position.

[0049] Specifically, whether the current frame of ultrasonic diaphragm B image is the first frame of ultrasonic diaphragm B image, or the reset ultrasonic diaphragm B image, the current frame of ultrasonic diaphragm B image is further subjected to sampling point detection. In the process of sampling point detection, the features of the parietal pleura, diaphragm and peritoneum can be automatically identified in the current frame of ultrasonic diaphragm B image based on artificial intelligence algorithms and / or traditional algorithms, and then the M-line sampling point position is obtained based on the features of the pleura, diaphragm and peritoneum. Of course, in other implementations, the standard ultrasonic diaphragm B image and the standard M-line sampling point position of the standard ultrasonic diaphragm B image can be used as a reference to compare the standard ultrasonic diaphragm B image with the current frame of ultrasonic diaphragm B image, so as to obtain the M-line sampling point position of the current frame of ultrasonic diaphragm B image.

[0050] Among them, the artificial intelligence algorithm can be a target detection method CenterNet based on deep learning, a target classification algorithm RFCN, SSD, YOLO based on deep learning, etc., and the traditional method can be a traditional target tracking method, a traditional target matching method, etc., and the specific identification method is not limited here. Compared with the method in which the operator manually selects and determines the M-line sampling point, the method of automatically obtaining the M-line sampling point position of the current frame ultrasound diaphragm B image using artificial intelligence and / or traditional algorithms can not only obtain the M-line sampling point position more accurately, but also improve the speed and efficiency of obtaining the M-line sampling point position, and at the same time reduce the degree of dependence on the operator.

[0051] Of course, in other embodiments, the process of automatically identifying the M-line sampling point position can be closed in response to the operator's selection, and the operator can manually select the M-line sampling point position in the current frame of the ultrasound diaphragm B image. Or, after the M-line sampling point position is automatically obtained, the automatic identification calculation can be re-performed in response to the user's selection operation to obtain a new M-line sampling point position, or the operator can manually select the M-line sampling point position in the current frame of the ultrasound diaphragm B image.

[0052] S230: If not, then track the M-line sampling point position determined in the first frame of the ultrasonic diaphragm B image to determine the M-line sampling point position in the current frame of the ultrasonic diaphragm B image.

[0053] Optionally, after the M-line sampling point position is obtained in the first frame of the ultrasonic diaphragm B image, the M-line sampling point position determined in the first frame of the ultrasonic diaphragm B image can be used as a basis to track the M-line sampling point position in the second frame and subsequent ultrasonic diaphragm B images, thereby obtaining the M-line sampling point position of each frame. Alternatively, the M-line sampling point position in the ultrasonic diaphragm B image of the previous frame of the current frame of the ultrasonic diaphragm B image can be used as a basis for reference to determine the M-line sampling point position in the current frame of the ultrasonic diaphragm B image that is consistent with the M-line sampling point position in the previous frame of the ultrasonic diaphragm B image.

[0054] With such a setting, it is possible to automatically track and obtain the M-line sampling point positions of all frames of ultrasound diaphragm B images in real time, and it is also possible to make the M-line sampling point positions in all frames of ultrasound diaphragm B images consistent, so that the diaphragm thickness parameter calculated according to the M-line sampling point positions can be more accurate. Of course, in other embodiments, other methods can be used to obtain the M-line sampling point positions of the current frame of ultrasound diaphragm B images, and the process of obtaining the M-line sampling point positions is not specifically limited here.

[0055] Further, step S230 may further include steps S231-S233:

[0056] S231: Selecting a plurality of reference pixel points around the M line sampling point position in the first frame of ultrasonic diaphragm B image.

[0057] Among them, multiple reference pixel points can represent the positions corresponding to certain features such as the pleura, diaphragm and peritoneum displayed in the previous frame ultrasound diaphragm B image, so that the M line sampling point position can be easily identified and selected based on the multiple reference pixel points.

[0058] S232: Determine a plurality of pixel points that match a plurality of reference pixel points in the ultrasonic diaphragm B image of the current frame.

[0059] Among them, multiple reference pixel points in the first frame of ultrasonic diaphragm B image can be tracked to determine multiple pixel points that match the multiple reference pixel points in the current frame of ultrasonic diaphragm B image. In some embodiments, multiple pixel points acquired from the first frame of ultrasonic diaphragm B image can be further detected to obtain the positional relationship between the multiple reference pixel points, and the positional relationship between the multiple pixel points of the current frame of ultrasonic diaphragm B image, and the positional relationship between the multiple pixel points of the first frame of ultrasonic diaphragm B image is matched with the positional relationship between the multiple reference pixel points of the current frame of ultrasonic diaphragm B image, and the pixel points with large positional relationship errors can be discarded and re-acquired, so as to determine more accurate pixel points.

[0060] S233: Determine the current M-line sampling point position in the current frame ultrasound diaphragm B image using the determined multiple pixel points.

[0061] Optionally, the distance relationship between multiple reference pixel points and the M-line sampling point position can be obtained in the first frame of the ultrasonic diaphragm B image, and the distance relationship between multiple pixel points in the current frame of the ultrasonic diaphragm B image and the current M-line sampling point position can be obtained by using this distance relationship as a reference, and then the current M-line sampling point position is determined in the current frame of the ultrasonic diaphragm B image. Of course, in other embodiments, in the process of determining the current M-line sampling point position using multiple pixel points, the current M-line sampling point position can also be obtained by using an artificial intelligence algorithm and / or a traditional algorithm, or the results obtained by the two methods can be superimposed to obtain a final more accurate current M-line sampling point position.

[0062] Of course, in other implementations, the user may independently select and determine the current M-line sampling point position in the current frame ultrasound diaphragm B image in response to the user's selection, or other methods may be used, which are not listed in detail here.

[0063] S300: placing a sampling line based on the position of the sampling point through the M line to obtain a sampled diaphragm M image;

[0064] Specifically, an artificial intelligence algorithm or a traditional algorithm can be used to obtain a sampling line and obtain an ultrasonic diaphragm M image. Figure 4 , Figure 4 In order to mark the current ultrasound diaphragm B image with the sampling line, the current M-line sampling point position in the figure is the characteristic point of the pleura and the peritoneum, and the sampling line connects the characteristic points of the pleura and the peritoneum so that the sampling line can represent the thickness of the diaphragm. Of course, in some embodiments, the sampling line can be manually placed according to the actual situation or needs in response to the user's operation selection.

[0065] S400: Determine a first initial diaphragm thickness parameter in the current frame diaphragm B image, and determine a second initial diaphragm thickness parameter in the sampled diaphragm M image.

[0066] Optionally, the current frame diaphragm B image and the sampled diaphragm M image are processed respectively to obtain a first initial diaphragm thickness parameter and a second initial diaphragm thickness parameter. The specific processing flow may be shown in steps S410-S430:

[0067] S410: Separate the current frame diaphragm B image from the sampled diaphragm M image.

[0068] S420: Determine a first initial diaphragm thickness parameter in the current frame diaphragm B image.

[0069] Optionally, features at the sampling line may be automatically identified in the current frame diaphragm B image to obtain a first initial diaphragm thickness parameter.

[0070] Among them, an artificial intelligence algorithm or a traditional algorithm can be used to automatically identify the features at the sampling line, and calculate the first initial diaphragm thickness parameter. In this embodiment, a target recognition model based on deep learning is used to identify the features of the current frame diaphragm B image at the sampling line to obtain the first initial diaphragm thickness parameter, so that the calculation result of the first initial diaphragm thickness parameter can be more accurate, and the accuracy of the result can be improved. In other embodiments, other artificial intelligence algorithms or traditional algorithms such as RFCN, SSD, YOLO target classification algorithms based on deep learning or traditional target matching methods can also be used, which are not listed one by one here.

[0071] In some embodiments, the first initial diaphragm thickness parameter may include multiple first thickness parameters and a first comprehensive thickness parameter. Optionally, the first thickness parameter may be determined in the current frame diaphragm B image, and at least two of the multiple first thickness parameters may be used for comprehensive calculation to obtain at least one first comprehensive thickness parameter.

[0072] In some embodiments, the plurality of first thickness parameters may include at least one of a first diaphragm thickness maximum value and a first diaphragm thickness minimum value. The at least one first comprehensive thickness parameter may include at least one of a first thickness average value, a first diaphragm thickening rate, and a first strain rate.

[0073] For example, in some embodiments, a plurality of first thickness parameters include a first diaphragm thickness maximum value and a first diaphragm thickness minimum value, and the first comprehensive thickness parameter includes a first thickness average value, a first diaphragm thickening rate, and a first strain rate. Specifically, the first diaphragm thickness maximum value and the first diaphragm thickness minimum value are added and averaged to obtain the first thickness average value. The first diaphragm thickening rate can be obtained by subtracting the first diaphragm thickness minimum value from the first diaphragm thickness maximum value and dividing it by the first diaphragm thickness minimum value. The first strain rate can be calculated from the first diaphragm thickness maximum value, the first diaphragm thickness minimum value, and time. Thus, in this embodiment, the first initial diaphragm thickness parameter determined in the current frame diaphragm B image may include: a diaphragm thickness maximum value, a first diaphragm thickness minimum value, a first thickness average value, a first diaphragm thickening rate, and a first strain rate. Moreover, all first initial diaphragm thickness parameters can be displayed on the display interface or in the current frame diaphragm B image.

[0074] S430: Determine a second initial diaphragm thickness parameter in the sampled diaphragm M image.

[0075] Optionally, in the process of determining the second initial diaphragm thickness parameter in the sampled diaphragm M image, the diaphragm area may be determined based on the sampled diaphragm M image, and the second initial diaphragm thickness parameter may be acquired based on the diaphragm area.

[0076] In some embodiments, the process of determining the diaphragm region based on the sampled diaphragm M image may include steps S431-S437:

[0077] S431: performing preset processing on the sampled diaphragm muscle M image to obtain an image to be segmented.

[0078] Among them, the preset processing may include at least one of normalization processing, adaptive histogram equalization processing, standardization processing and gamma correction processing. In the preset processing process, different preset processing methods can be used according to actual conditions. Using the preset processing to normalize, standardize or correct the sampled diaphragm M image can make the sampled diaphragm M image more standardized, so that the obtained image to be segmented can facilitate other subsequent processing and calculation. Of course, in other embodiments, the preset processing can also be other processing methods, and the specific limitation of the preset processing is not made here.

[0079] S432: Perform image segmentation processing on the image to be segmented to obtain a segmented diaphragm image.

[0080] Specifically, an artificial intelligence algorithm and / or a traditional method can be used to perform image segmentation processing on the image to be segmented, and targets such as the pleura, diaphragm and peritoneum can be separated from the background to obtain a segmented diaphragm image with a clear target image. Among them, the artificial intelligence algorithm can be a deep learning U-Net, the maximum between-class variance method (OTSU), etc., and the traditional method can be a watershed method, etc.

[0081] S433: Binarization processing is performed on the segmented diaphragm image to obtain a binary image.

[0082] Specifically, the segmented diaphragm image is binarized, and the grayscale value of the points on the image is 0 or 255, so that the segmented diaphragm image presents an obvious black and white effect, and a binary image that can still reflect the overall and local features of the image is obtained. Binarization of the segmented diaphragm image can better highlight the image contours of targets such as the pleura, diaphragm and peritoneum in the image, so as to facilitate subsequent image processing and calculation, thereby obtaining more accurate diaphragm thickness parameters.

[0083] S434: determining a plurality of contour regions in the binary image according to differences in pixel area, determining a maximum contour region among the plurality of contours, and removing other contour regions.

[0084] Specifically, the outermost contour is determined in the binary image, multiple contours corresponding to the number of pixels are determined within the outermost contour, and the contour area corresponding to each pixel is determined, thereby retaining the largest contour area and removing other contour areas. This can more clearly highlight the contour of the target diaphragm and reduce interference from other small areas.

[0085] S435: performing a morphological operation on the binary image from which other contour areas are removed, so as to fill the holes left by removing other contour areas, and obtain an image to be smoothed.

[0086] Specifically, after removing other contour areas, holes may be left behind, which may affect the subsequent calculation of diaphragm motion parameters, so that a hole filling algorithm needs to be used to fill the holes to reduce the number of holes.

[0087] For example, in some embodiments, when filling holes, it is necessary to process the eight connected areas around each pixel. Specifically, the original binary image can be copied to generate a copied binary image, and then the pixel to be filled is taken as the center, and the entire copied binary image is scanned in a 3*3 block, and the number N of points with a grayscale value of 255 among the 9 points covered by this block is recorded by identification. Further, the number N is judged, if N>=5, that is, at least 5 of the 9 points belong to the foreground, then the grayscale value of the pixel is assigned to 255, that is, the pixel is considered to belong to the foreground, otherwise it is considered to belong to the background. Finally, the original binary image is copied to the copied binary image, and mathematical morphology processing is performed to obtain the image to be smoothed.

[0088] S436: Perform edge smoothing on the image to be smoothed to obtain a final diaphragm image.

[0089] Specifically, a Gaussian convolution kernel is first constructed in the horizontal direction, and then the image matrix to be smoothed in the horizontal direction is obtained by matrix transposition. Then, the image matrix to be smoothed is convolved with the horizontal Gaussian kernel, and then Gaussian convolution is performed with the convolution kernel in the vertical direction, so that Gaussian noise can be removed to obtain the final diaphragm image. Edge smoothing can reduce image noise in other images to be smoothed, thereby removing the influence of image noise on the results, reducing calculation errors, and improving the accuracy of the results.

[0090] S437: Determine the diaphragm region in the final diaphragm image using the pixel value difference between the diaphragm region and the non-diaphragm region.

[0091] For example, if the pixel value of the target diaphragm area in the final diaphragm image is 255 and the pixel value of the non-diaphragm area is 0, the diaphragm area and the non-diaphragm area can be distinguished based on the difference in pixel values ​​between the two, thereby determining the diaphragm area in the final diaphragm image.

[0092] Furthermore, if Figure 5 As shown, the edge information of the diaphragm region can be obtained, and then the envelope line can be obtained. Among them, the edge information of the diaphragm region can be automatically identified by using an artificial intelligence algorithm such as RFCN, SSD, YOLO, etc., a target classification algorithm based on deep learning, or a traditional algorithm such as traditional target tracking, so as to automatically envelop the edge of the diaphragm region in the final diaphragm image, thereby obtaining an envelope line to characterize the movement trajectory of the diaphragm when the human body is breathing.

[0093] Further, the second initial diaphragm thickness parameter can be calculated based on the envelope. Figure 5As shown, the envelope features of the parietal pleura and peritoneum are identified in the final diaphragm image, the skeleton can be extracted from the envelope to obtain the diaphragm motion trajectory, and the extreme points within the cycle can be determined on the diaphragm motion trajectory to calculate the second initial diaphragm thickness parameter. Optionally, the diaphragm motion trajectory can be processed using an artificial intelligence algorithm or a traditional algorithm to obtain the second initial diaphragm thickness parameter. For example, multiple peak points and trough points within a cycle can be determined on the diaphragm motion trajectory to determine multiple extreme points within a cycle, and further calculate the second initial diaphragm thickness parameter based on multiple cycle value points.

[0094] Among them, the function of automatically acquiring the envelope line can support the user to choose to turn it on or off. In other embodiments, other processing methods can be used to process the sampled diaphragm M image to obtain the final diaphragm image, such as the OTSU threshold method, etc. Different processing can be performed according to specific circumstances in different embodiments, and the specific processing method is not limited here.

[0095] Optionally, the second initial diaphragm thickness parameter may include a plurality of second thickness parameters and a second comprehensive thickness parameter. Optionally, the plurality of second thickness parameters include at least one of a second diaphragm thickness maximum value and a second diaphragm thickness minimum value. At least one second comprehensive thickness parameter includes at least one of a second thickness average value, a second diaphragm thickening rate, and a second strain rate.

[0096] Specifically, the second thickness parameter may be determined in the sampled diaphragm muscle M image, and at least two of the plurality of second thickness parameters may be used for comprehensive calculation to obtain at least one second comprehensive thickness parameter.

[0097] For example, in some embodiments, the second diaphragm thickness maximum value and the second diaphragm thickness minimum value in the plurality of second thickness parameters can be calculated from a plurality of maximum points in the envelope cycle and a minimum point in the cycle. The second thickness average value, the second diaphragm thickening rate, the second strain rate and other parameters included in at least one second comprehensive thickness parameter can all be calculated using the second diaphragm thickness maximum value and the second diaphragm thickness minimum value.

[0098] Therefore, the first initial diaphragm thickness parameters determined in the current frame diaphragm B image may include: the first diaphragm thickness maximum value, the first diaphragm thickness minimum value, the first thickness average value, the first diaphragm thickening rate, and the first strain rate. All the first initial diaphragm thickness parameters may be displayed on the display interface, and may be displayed in the current frame diaphragm B image.

[0099] S500: Fusing the first initial diaphragm thickness parameter and the second initial diaphragm thickness parameter to obtain a diaphragm thickness parameter.

[0100] Specifically, multiple first thickness parameters and multiple second thickness parameters are fused and calculated one by one, and at least one first comprehensive thickness parameter and at least one second comprehensive thickness parameter are fused and calculated one by one to obtain the diaphragm thickness parameter.

[0101] In some embodiments, the diaphragm thickness parameter includes at least one of a maximum diaphragm thickness and a minimum diaphragm thickness, and at least one of an average thickness, a diaphragm thickening rate, and a strain rate.

[0102] Among them, the maximum value of diaphragm thickness and / or the minimum value of diaphragm thickness are calculated by the one-to-one fusion of multiple first thickness parameters and multiple second thickness parameters, and the average thickness, diaphragm thickening rate and strain rate can be calculated by the one-to-one fusion of the first comprehensive thickness parameter and the second comprehensive thickness parameter.

[0103] In some embodiments, the corresponding fusion method can be a weighted calculation. Specifically, the first initial diaphragm thickness parameter and the second initial diaphragm thickness parameter are weightedly calculated to obtain the diaphragm thickness parameter. By assigning different weight ratios to the first initial diaphragm thickness parameter and the second initial diaphragm thickness parameter, the two sets of data can assist each other in fusion, reduce the impact of errors, and thus obtain the final diaphragm thickness parameter with higher accuracy, which can improve the accuracy of the measurement result. Moreover, the process of processing the current frame diaphragm B image and the sampled diaphragm M image to obtain the first initial diaphragm thickness parameter and the second initial diaphragm thickness parameter can be performed synchronously to reduce the time of diaphragm parameter measurement and improve the efficiency of measuring diaphragm parameters. Of course, in other embodiments, the diaphragm thickness parameter can also be obtained by other methods such as deep learning model calculation, and no specific processing method is limited here.

[0104] Optionally, the weights of the first initial diaphragm thickness parameter and the second initial diaphragm thickness parameter can be obtained according to the quality characteristics of the image. Specifically, a first weight that matches the image quality of the diaphragm B image of the current frame can be obtained, and a second weight that matches the image quality of the sampled diaphragm M image can be obtained. Then, the first initial diaphragm thickness parameter and the second initial diaphragm thickness parameter are weighted and summed one by one with the first weight and the second weight to obtain the diaphragm thickness parameter. The acquisition process of the first weight and the second weight can be obtained by matching an artificial intelligence algorithm and / or a traditional algorithm.

[0105] Optionally, the first weight may be greater than or equal to 0 and less than or equal to 1. The second weight may be greater than or equal to 0 and less than or equal to 1. The sum of the first weight and the second weight may be greater than 0 and less than or equal to 1. In other embodiments, other weights may be added to perform a correction check on the result obtained by weighting the first initial diaphragm thickness parameter and the second initial diaphragm thickness parameter, so as to obtain a more accurate diaphragm thickness parameter. Of course, other processing processes may be performed later, which are not listed here one by one.

[0106] Assigning weights to the parameters corresponding to the current frame diaphragm B image and the sampled diaphragm M image based on image quality features such as whether the image is clear can reduce the error caused by image quality problems, thereby improving the accuracy of the diaphragm thickness parameter and making the diaphragm thickness parameter closer to the actual value.

[0107] Of course, in other embodiments, in response to the user's selection, the first initial diaphragm thickness parameter of the current frame diaphragm B image can be directly used as the final diaphragm thickness parameter, or the second initial diaphragm thickness parameter of the sampled diaphragm M image can be used as the final diaphragm thickness parameter, and the processing process of the sampled diaphragm M image and the subsequent fusion process of the two image parameters can be directly omitted.

[0108] After the diaphragm thickness parameter is obtained, the diaphragm thickness parameter can be displayed on the display interface. At the same time, the diaphragm thickness parameter can also be processed to display a trend image corresponding to the diaphragm thickness parameter, so as to intuitively reflect the trend change relationship of the diaphragm thickness parameter. Of course, in some embodiments, in response to the user's selection, the first initial diaphragm thickness parameter of the current frame diaphragm B image and the second initial diaphragm thickness parameter of the sampled diaphragm M image can be displayed on the display interface, and multiple analysis curves corresponding to the first initial diaphragm thickness parameter and the second initial diaphragm thickness parameter can also be calculated. Alternatively, the first initial diaphragm thickness parameter, the second initial diaphragm thickness parameter and the change trend line corresponding to the diaphragm thickness parameter can be displayed in the same trend image.

[0109] Specifically, if there are multiple diaphragm motion parameters, multiple analysis curve graphs corresponding to multiple diaphragm thickness parameters can be obtained, or a line graph that can reflect multiple diaphragm thickness parameters can be obtained. Figure 6 As shown, a reference line can be set in the change trend image corresponding to the diaphragm thickness parameter, and the reference line can be represented as the diaphragm thickness parameter value of a normal human body. At the same time, the diaphragm movement parameter can be set to be highlighted in the change trend image, for example, red, yellow, and green can be set to highlight the display, and when the obtained diaphragm thickness parameter is consistent with the reference line value, green can be displayed, yellow can be displayed when the value difference is too small, and red can be displayed when the value difference is too large.

[0110] When the obtained trend image is reflected in multiple diaphragm thickness parameters, it can be Figure 7 As shown, the changing trend lines of multiple diaphragm thickness parameters are plotted in a changing trend image, and the changing trend lines of each diaphragm thickness parameter in the image can respond to the user's selection. When the user selects a changing trend line of a certain diaphragm movement parameter, the changing trend line can display specific information, wherein the specific information may include numerical values, scatter point colors, etc.

[0111] Of course, in other embodiments, the variation trend of the diaphragm thickness parameter may be presented in different forms, such as a scatter plot with a smooth straight line, etc., which will not be listed here one by one.

[0112] In summary, the present application can automatically measure the section type after obtaining the ultrasonic section B image, and automatically switch the processing flow of the section type without the operator manually selecting the switch, thereby reducing the degree of dependence on the operator and simplifying the measurement process of the diaphragm parameters. After obtaining the current frame diaphragm B image, the M-line sampling point position of the previous frame diaphragm B image is automatically tracked, and the M-line sampling point position is automatically determined in the current frame diaphragm B image and then the sampling line is placed to obtain the sampled diaphragm M image, thereby ensuring the consistency and accuracy based on the M-line sampling point position, and then the accuracy of the measurement result can be ensured, and the process of determining the M-line sampling point position in the current frame diaphragm B image and then placing the sampling line to obtain the sampled diaphragm M image also does not require the operator to determine the M-line sampling point position, which can reduce the degree of dependence on the operator, and can also simplify the overall measurement process, so that the measurement process is standardized. Then, the first initial diaphragm thickness parameter and the second initial diaphragm thickness parameter are obtained by processing the current frame diaphragm B image and the corresponding sampled diaphragm M image respectively, and then the diaphragm parameters in the two images are combined to obtain more accurate diaphragm parameters, thereby achieving the effect of improving the accuracy of the measurement results.

[0113] like Figure 8 As shown, Figure 8 6 is a schematic block diagram of the circuit structure of an embodiment of the ultrasound image processing system 600 of the present application. The ultrasound image processing system 600 includes an ultrasound probe 610, a transmitting circuit 620, a receiving circuit 630, a processor 640 and a display 650. Further, the ultrasound image processing system 600 may also include a memory 660, a transmitting / receiving selection switch 670 and a beamforming module 680, and the transmitting circuit 620 and the receiving circuit 630 may be connected to the ultrasound probe 610 through the transmitting / receiving selection switch 670.

[0114] The transmitting circuit 620 stimulates the ultrasonic probe 610 to transmit ultrasonic waves to the object of inspection through the transmitting / receiving switch. The receiving circuit 630 receives the ultrasonic echo signal based on the ultrasonic wave returned from the object of inspection. The processor 640 processes the ultrasonic echo signal to obtain an ultrasonic image corresponding to the object of inspection, and also executes the above-mentioned method for measuring the diaphragm parameters. The display 650 displays the ultrasonic image.

[0115] Specifically, the ultrasonic probe 610 is used to generate an ultrasonic wave that propagates in a target tissue of a target object. The transmitting circuit 620 is used to excite the ultrasonic probe 610 to transmit a first ultrasonic wave that tracks a shear wave to the target tissue. The receiving circuit 630 is used to control the ultrasonic probe 610 to receive an ultrasonic echo returned by the target tissue to obtain a first echo signal of the first ultrasonic wave.

[0116] The ultrasonic probe 610 includes a transducer (not shown) composed of a plurality of array elements arranged in an array. The array element is used to transmit ultrasonic waves according to an excitation electrical signal, or to convert received ultrasonic waves into electrical signals. Therefore, each array element can be used to realize the mutual conversion between electrical pulse signals and ultrasonic waves, thereby transmitting ultrasonic waves to the biological tissue of the target object, and can also be used to receive the echo of ultrasonic waves reflected back by the tissue.

[0117] The transmitting circuit 620 is used to control the ultrasonic probe 610 to transmit ultrasonic waves, for example, according to the control of the processor 640, stimulate the ultrasonic probe 610 to transmit ultrasonic waves toward the target object.

[0118] The receiving circuit 630 is used to control the ultrasonic probe 610 to receive ultrasonic echoes, for example, to receive ultrasonic echoes returned from the target object through the ultrasonic probe 610 to obtain ultrasonic echo signals, and can also process the ultrasonic echo signals. The receiving circuit 630 may include one or more amplifiers, analog-to-digital converters (ADCs), etc.

[0119] The beamforming module 680 is connected to the receiving circuit 630 signal, and is used to perform beamforming processing such as corresponding delay and weighted summation on the echo signal. Since the distances from the ultrasonic receiving point in the measured tissue to the receiving array element are different, the channel data of the same receiving point output by different receiving array elements have delay differences, and delay processing is required to align the phases and perform weighted summation on the different channel data of the same receiving point to obtain the ultrasonic image data after beamforming. The ultrasonic image data output by the beamforming module 680 is also called radio frequency data (RF data). The beamforming module 680 performs focusing delay, weighting and channel summation on the ultrasonic echo data, and then sends it to the processor 640.

[0120] The processor 640 performs signal detection, signal enhancement, data conversion, logarithmic compression and other processing on the ultrasonic echo signal to form an ultrasonic image. The ultrasonic image obtained by the processor 640 can be displayed on the display 650 or stored in the memory 660.

[0121] The processor 640 may be implemented as software, hardware, firmware or any combination thereof, and may use a single or multiple application specific integrated circuits (ASICs), a single or multiple general purpose integrated circuits, a single or multiple microprocessors, a single or multiple programmable logic devices, or any combination of the aforementioned circuits and / or devices, or other suitable circuits or devices. Furthermore, the processor 640 may control other components in the ultrasound image processing system 600 to perform the corresponding steps of the methods in various embodiments of the present specification.

[0122] The memory 660 is connected to the processor 640, and is used to store instructions executed by the processor 640, store received ultrasound echoes, store ultrasound images, etc. The memory 660 can be a flash memory card, a solid-state memory, a hard disk, etc. It can be a volatile memory and / or a non-volatile memory, a removable memory and / or a non-removable memory, etc.

[0123] The display 650 is connected to the processor 640, and the display 650 may be a touch screen, a liquid crystal display, etc. Alternatively, the display 650 may be an independent display such as a liquid crystal display, a television, etc., which is independent of the ultrasound image processing system 600. Alternatively, the display 650 may be a display screen of an electronic device such as a smart phone, a tablet computer, etc. The number of the display 650 may be one or more.

[0124] The display 650 can display the ultrasound image obtained by the processor 640. In addition, while displaying the ultrasound image, the display 650 can also provide the user with a graphical interface for human-computer interaction. One or more controlled objects are set on the graphical interface, and the user is provided with a human-computer interaction device to input operation instructions to control these controlled objects, thereby performing corresponding control operations. For example, an icon is displayed on the graphical interface, and the icon can be operated by the human-computer interaction device to perform a specific function, such as drawing a region of interest box on the ultrasound image.

[0125] Optionally, the ultrasound image processing system 600 may further include other human-computer interaction devices in addition to the display 650, which are connected to the processor 640. For example, the processor 640 may be connected to the human-computer interaction device via an external input / output port, and the external input / output port may be a wireless communication module, or a wired communication module, or a combination of the two. The external input / output port may also be implemented based on USB, bus protocols such as CAN, and / or wired network protocols.

[0126] The human-computer interaction device may include an input device for detecting user input information, which may be, for example, a control instruction for ultrasonic transmission / reception timing, an operation input instruction for drawing points, lines or frames on an ultrasonic image, or other instruction types. The input device may include a keyboard, a mouse, a scroll wheel, a trackball, a mobile input device (such as a mobile device with a touch screen, a mobile phone, etc.), a multi-function knob, etc., or a combination of multiple thereof. The human-computer interaction device may also include an output device such as a printer.

[0127] The above descriptions are merely embodiments of the present application and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for measuring diaphragm parameters, It is characterized in that include: Acquire a current frame ultrasonic diaphragm B image for measuring diaphragm thickness; Determining the position of the M-line sampling point in the current frame ultrasonic diaphragm B image; A sampling diaphragm M image is obtained based on placing a sampling line through the M line sampling point position; Determine a first initial diaphragm thickness parameter in the current frame diaphragm B image, and determine a second initial diaphragm thickness parameter in the sampled diaphragm M image; The first initial diaphragm thickness parameter and the second initial diaphragm thickness parameter are fused to obtain a diaphragm thickness parameter.

2. The method according to claim 1, It is characterized in that Determining a first initial diaphragm thickness parameter in the current frame diaphragm B image includes: Automatically identify features at the sampling line in the current frame diaphragm B image to obtain the first initial diaphragm thickness parameter.

3. The method according to claim 2, It is characterized in that The automatically identifying the features at the sampling line in the current frame diaphragm B image to obtain the first initial diaphragm thickness parameter includes: A deep learning-based target recognition model is used to identify features of the current frame diaphragm B image at the sampling line to obtain the first initial diaphragm thickness parameter.

4. The method according to claim 1, It is characterized in that Determining the second initial diaphragm thickness parameter in the sampled diaphragm M image comprises: A diaphragm area is determined based on the sampled diaphragm M image, and the second initial diaphragm thickness parameter is acquired based on the diaphragm area.

5. The method according to claim 4, It is characterized in that The acquiring the second initial diaphragm thickness parameter based on the diaphragm area comprises: Acquiring edge information of the diaphragm region, and then obtaining an envelope line; The second initial diaphragm thickness parameter is calculated based on the envelope.

6. The method according to claim 5, It is characterized in that The calculating the second initial diaphragm thickness parameter based on the envelope line comprises: A skeleton is extracted from the envelope to obtain a diaphragm motion trajectory, and the second initial diaphragm thickness parameter is determined on the diaphragm motion trajectory.

7. The method according to claim 1, It is characterized in that The fusing the first initial diaphragm thickness parameter and the second initial diaphragm thickness parameter to obtain the diaphragm thickness parameter includes: The first initial diaphragm thickness parameter and the second initial diaphragm thickness parameter are weightedly calculated to obtain the diaphragm thickness parameter.

8. The method according to claim 1, It is characterized in that The first initial diaphragm thickness parameter includes a plurality of first thickness parameters and a first comprehensive thickness parameter, and the second initial diaphragm thickness parameter includes a plurality of second thickness parameters and a second comprehensive thickness parameter; Determining a first initial diaphragm thickness parameter in the current frame diaphragm B image, and determining a second initial diaphragm thickness parameter in the sampled diaphragm M image, comprises: Determine the first thickness parameter in the current frame diaphragm B image, and use at least two of the multiple first thickness parameters to perform comprehensive calculation to obtain at least one first comprehensive thickness parameter; Determining the second thickness parameter in the sampled diaphragm muscle M image, and performing comprehensive calculation using at least two of the plurality of second thickness parameters to obtain at least one second comprehensive thickness parameter; The multiple first thickness parameters and the multiple second thickness parameters are fused and calculated one by one, and the at least one first comprehensive thickness parameter and the at least one second comprehensive thickness parameter are fused and calculated one by one to obtain the diaphragm thickness parameter.

9. The method according to claim 8, It is characterized in that The plurality of first thickness parameters include at least one of a first diaphragm thickness maximum value and a first diaphragm thickness minimum value; the at least one first comprehensive thickness parameter includes at least one of a first thickness average value, a first diaphragm thickening rate, and a first strain rate; The plurality of second thickness parameters include at least one of a second diaphragm thickness maximum value and a second diaphragm thickness minimum value; the at least one second comprehensive thickness parameter includes at least one of a second thickness average value, a second diaphragm thickening rate, and a second strain rate; The diaphragm thickness parameters include at least one of a maximum diaphragm thickness and a minimum diaphragm thickness, and at least one of an average thickness value, a diaphragm thickening rate, and a strain rate.

10. The method according to claim 1, It is characterized in that Determining the position of the M-line sampling point in the current frame ultrasound diaphragm B image includes: Determine whether the current frame of ultrasonic diaphragm B image is the first frame of ultrasonic diaphragm B image; If not, the position of the M-line sampling point determined in the first frame of ultrasonic diaphragm B image is tracked to determine the position of the M-line sampling point in the current frame of ultrasonic diaphragm B image.

11. The method according to claim 10, It is characterized in that Tracking the position of the M-line sampling point determined in the first frame of the ultrasonic diaphragm B image to determine the current position of the M-line sampling point in the current frame of the ultrasonic diaphragm B image includes: Selecting a plurality of reference pixel points around the M-line sampling point position in the first frame of ultrasonic diaphragm B image; Determining a plurality of pixel points matching the plurality of reference pixel points in the current frame ultrasonic diaphragm B image; The current M-line sampling point position is determined in the current frame ultrasound diaphragm B image using the determined multiple pixel points.

12. The method according to claim 10, It is characterized in that After determining whether the current frame of the ultrasonic diaphragm B image is the first frame of the ultrasonic diaphragm B image, the method includes: If so, sampling point detection is performed on the current frame ultrasound diaphragm B image to obtain the M line sampling point position.

13. The method according to claim 1, It is characterized in that The step of obtaining a current frame ultrasonic diaphragm B image for measuring diaphragm thickness includes: Obtaining an ultrasound section B image obtained by ultrasound scanning of the area containing the diaphragm; Automatically identifying the measurement type of the ultrasound section B image; If the measurement type is measuring the diaphragm thickness, the ultrasound section B image is used as the current frame ultrasound diaphragm B image.

14. An ultrasonic image processing system, It is characterized in that include: Ultrasound probe; A transmitting circuit, wherein the transmitting circuit stimulates the ultrasonic probe to transmit ultrasonic waves to the inspection object through a transmitting / receiving switch; a receiving circuit that receives an ultrasonic echo signal based on the ultrasonic wave returned from the inspection object; a processor, wherein the processor processes the ultrasonic echo signal to obtain an ultrasonic image corresponding to the inspection object; a display, wherein the display displays the ultrasound image; The processor further executes the method according to any one of claims 1-13.

Citation Information

Cited By

  • Diaphragm thickening rate measurement method and system based on deep learning ultrasonic image segmentation

    CN122199382A