Ultrasonic equipment and parameter adjusting method

Abstract

The invention relates to the technical field of medical treatment, in particular to ultrasonic equipment and a parameter adjusting method. According to the embodiment of the invention, first reference data used for representing the body type of a target object is determined based on a visual image which is transmitted by image acquisition equipment and comprises the target object; determining second reference data used for representing the tissue structure state of the target object based on the ultrasonic image of the detection part containing the target object; based on the first reference data, the second reference data and a mapping relation between pre-stored reference data and adjustment information, target adjustment information corresponding to the ultrasonic equipment is determined, and the target adjustment information comprises at least one adjustment item in the ultrasonic equipment and an adjustment parameter corresponding to each adjustment item in the adjustment items; and performing corresponding adjustment on the ultrasonic equipment based on the target adjustment information.

Description

Technical Field

[0001] This application relates to the field of medical technology, and in particular to an ultrasound device and a method for adjusting its parameters. Background Technology

[0002] The imaging process of medical ultrasound equipment is complex and depends on the parameters of the equipment used. The parameters of the ultrasound equipment are crucial for obtaining high-quality ultrasound images.

[0003] Normally, ultrasound equipment is configured with default parameters. However, due to significant differences between patients, using default parameters cannot guarantee the quality of ultrasound images for all patients. Therefore, when acquiring ultrasound images for each patient, the operator of the ultrasound equipment needs to analyze each patient's individual situation and manually adjust the equipment parameters based on experience.

[0004] However, this adjustment process takes a long time, resulting in low efficiency in adjusting the equipment parameters. Furthermore, this method relies on the operator's subjective judgment, which may lead to inappropriate adjustments of the equipment parameters, resulting in unclear ultrasound images.

[0005] Therefore, the existing methods for adjusting the parameters of ultrasonic equipment have many shortcomings. Summary of the Invention

[0006] To address the problems in the prior art, this application provides an ultrasonic device and a parameter adjustment method for automatically adjusting the parameters in the ultrasonic device.

[0007] In a first aspect, embodiments of this application provide an ultrasonic device, which includes an ultrasonic probe and a processor; the ultrasonic device is connected to an image acquisition device and receives a visual image containing a target object transmitted by the image acquisition device.

[0008] The ultrasonic probe is used to receive ultrasonic echo signals reflected from the detection site of the target object;

[0009] The processor is configured to: determine, based on the visual image, first reference data for characterizing the body shape of the target object; and, based on the ultrasound image corresponding to the ultrasound echo signal, determine second reference data for characterizing the tissue structure state of the target object; determine target adjustment information corresponding to the ultrasound device based on the mapping relationship between the first reference data, the second reference data, and pre-stored reference data and adjustment information, the target adjustment information including at least one adjustment item in the ultrasound device and adjustment parameters corresponding to each adjustment item in the at least one adjustment item; and adjust the parameters of the ultrasound device based on the target adjustment information.

[0010] Because this application embodiment determines first reference data for characterizing the body shape of the target object based on a visual image of the target object acquired by an image acquisition device; and determines second reference data for characterizing the tissue structure state of the target object based on an ultrasound image; that is, this application can automatically analyze the current situation of the target object based on ultrasound images and visual images of the target object acquired by an image acquisition device. Compared with the prior art method of subjective analysis of the target object by personnel operating ultrasound equipment, this application can improve the accuracy of target object analysis. Therefore, when using more accurate analysis results to adjust parameters, the accuracy of parameter adjustment can be improved, so that the ultrasound image obtained based on the adjusted parameters can better guarantee the presentation effect.

[0011] On the other hand, this application determines the target adjustment information corresponding to the ultrasound equipment based on the first reference data, the second reference data, and the mapping relationship between the pre-stored reference data and adjustment information, and adjusts the parameters of the ultrasound equipment based on the target adjustment information. This allows for faster adjustment of the ultrasound equipment parameters, and significantly improves the efficiency of parameter adjustment compared to the prior art where operators manually adjust the parameters.

[0012] In one possible implementation, the processor is specifically used for:

[0013] Based on the length and width of the target object in the visual image, determine the distance ratio;

[0014] The area ratio is determined based on the area of ​​the target object's coverage region in the visual image and the area of ​​the smallest rectangular region containing the coverage region;

[0015] Based on the distance ratio and the area ratio, first reference data for characterizing the body shape of the target object is determined.

[0016] In one possible implementation, the tissue structure of the target object includes muscle tissue and adipose tissue; the processor is specifically used for:

[0017] The ultrasound image corresponding to the ultrasound echo signal is subjected to image segmentation processing to obtain a segmented ultrasound image; the segmented ultrasound image is used to characterize the contour information of muscle tissue and adipose tissue in the tissue structure.

[0018] Based on the contour information of the muscle tissue and the contour information of the adipose tissue, the thickness of the muscle tissue and the thickness of the adipose tissue are determined respectively;

[0019] Based on the thickness of the muscle tissue and the thickness of the adipose tissue, second reference data is determined to characterize the tissue structure state of the target object.

[0020] In one possible implementation, the processor is specifically used for:

[0021] The ultrasonic image corresponding to the ultrasonic echo signal is downsampled multiple times based on the encoder to obtain multiple coded feature sets corresponding to the ultrasonic image; the multiple coded feature sets include a first coded feature set obtained from the last downsampling process, and at least one second coded feature set other than the first coded feature set;

[0022] In reverse order of obtaining the at least one second coding feature set, at least one target coding feature set in the at least one second coding feature set is determined, and the following operations are performed for each target coding feature set: if the target coding feature set is the first determined target coding feature set, then feature fusion is performed based on the reference decoding feature set corresponding to the target coding feature set and the target coding feature set to obtain the fused feature set corresponding to the target coding feature set, wherein the reference decoding feature set is determined based on the next coding feature set obtained after obtaining the target coding feature set from the plurality of coding feature sets; if the target coding feature set is not the first determined target coding feature set, then feature fusion is performed based on the target coding feature set and the fused feature set corresponding to the previous target coding feature set to obtain the fused feature set corresponding to the target coding feature set.

[0023] Based on the fusion feature set corresponding to the last determined target encoding feature set, a segmented ultrasound image corresponding to the target object is generated.

[0024] In one possible implementation, the target coded feature set and the reference decoded feature set have channel dimension and spatial dimension; if the target coded feature set is the first determined target coded feature set, the processor performs feature fusion in the following manner:

[0025] The reference decoded feature set is upsampled to obtain an intermediate decoded feature set of the same size as the target encoded feature set;

[0026] At the channel level, the decoding features corresponding to each channel in the intermediate decoding feature set are processed, and the encoding features corresponding to each channel in the target encoding feature set are processed. The intermediate decoding feature set and the target encoding feature set after processing are concatenated to obtain a first concatenated feature set. Based on the first concatenated feature set after convolution processing, the first channel weight coefficients corresponding to the target encoding feature set and the second channel weight coefficients corresponding to the intermediate decoding feature set are determined.

[0027] In the spatial dimension, the decoding features corresponding to each space in the intermediate decoding feature set are processed, and the encoding features corresponding to each space in the target encoding feature set are processed. The intermediate decoding feature set after processing and the target encoding feature set after processing are concatenated to obtain a second concatenated feature set. Based on the second concatenated feature set after convolution processing, the first spatial weight coefficient corresponding to the target encoding feature set and the second spatial weight coefficient corresponding to the intermediate decoding feature set are determined respectively.

[0028] Based on the first channel weight coefficient and the first spatial weight coefficient corresponding to the target coding feature set, the target coding feature set is processed to obtain the first processing result; based on the second channel weight coefficient and the second spatial weight coefficient corresponding to the intermediate decoding feature set, the intermediate decoding feature set is processed to obtain the second processing result.

[0029] Based on the sum of the first calculation result and the second calculation result, the fusion feature set corresponding to the target encoding feature set is determined.

[0030] In one possible implementation, the processor is specifically used for:

[0031] Based on the first reference data and the mapping relationship between the reference data and the adjustment information, the reference adjustment information corresponding to the first reference data is determined; based on the second reference data and the mapping relationship between the reference data and the adjustment information, the reference adjustment information corresponding to the second reference data is determined; based on the reference adjustment information corresponding to the first reference data and the reference adjustment information corresponding to the second reference data, the target adjustment information corresponding to the ultrasonic device is determined; or

[0032] Based on the first reference data and the second reference data, target reference data corresponding to the target object is determined; based on the target reference data and the mapping relationship between the reference data and the adjustment information, target adjustment information corresponding to the ultrasound device is determined.

[0033] In one possible implementation, the ultrasound device is connected to a body fat harvesting device; the processor is further configured to:

[0034] Receive third reference data sent by the body fat acquisition device to characterize the body fat of the target object;

[0035] Based on the mapping relationship between the first reference data, the second reference data, the third reference data, and the pre-stored reference data and adjustment information, the target adjustment information corresponding to the ultrasound device is determined.

[0036] In one possible implementation, the processor is specifically used for:

[0037] Based on the first reference data and the mapping relationship between pre-stored reference data and adjustment information, the reference adjustment information corresponding to the first reference data is determined; based on the second reference data and the mapping relationship between reference data and adjustment information, the reference adjustment information corresponding to the second reference data is determined; and based on the third reference data and the mapping relationship between pre-stored reference data and adjustment information, the reference adjustment information corresponding to the third reference data is determined; based on the reference adjustment information corresponding to the first reference data, the reference adjustment information corresponding to the second reference data, and the reference adjustment information corresponding to the third reference data, the target adjustment information corresponding to the ultrasound device is determined; or

[0038] Based on the first reference data, the second reference data, and the third reference data, target reference data corresponding to the target object is determined; based on the target reference data and the mapping relationship between the pre-stored reference data and adjustment information, target adjustment information corresponding to the ultrasound device is determined.

[0039] In one possible implementation, the target object in the visual image is selected by the processor in at least one of the following ways:

[0040] Select an object with a preset clothing from the visual image;

[0041] Select objects with preset behaviors from the visual image;

[0042] Select objects in the visual image whose distance from the preset area meets the set distance conditions.

[0043] Secondly, embodiments of this application provide a parameter adjustment method applied to an ultrasonic device, the method comprising:

[0044] Acquire a visual image containing a target object transmitted by an image acquisition device, and determine first reference data for characterizing the body shape of the target object based on the visual image;

[0045] Based on the ultrasound image of the detection site containing the target object, second reference data for characterizing the tissue structure state of the target object is determined;

[0046] Based on the first reference data, the second reference data, and the mapping relationship between the pre-stored reference data and adjustment information, the target adjustment information corresponding to the ultrasound device is determined. The target adjustment information includes at least one adjustment item in the ultrasound device and the adjustment parameter corresponding to each adjustment item in the adjustment item. The ultrasound device is adjusted accordingly based on the target adjustment information.

[0047] Thirdly, embodiments of this application provide a parameter adjustment device, including:

[0048] An acquisition module is used to acquire a visual image containing a target object transmitted by an image acquisition device, and to determine first reference data for characterizing the body shape of the target object based on the visual image;

[0049] The determination module is used to determine second reference data for characterizing the tissue structure state of the target object based on an ultrasound image containing a detection site of the target object;

[0050] An adjustment module is used to determine target adjustment information corresponding to the ultrasound device based on the first reference data, the second reference data, and the mapping relationship between the pre-stored reference data and adjustment information. The target adjustment information includes at least one adjustment item in the ultrasound device and adjustment parameters corresponding to each adjustment item in the adjustment item. The ultrasound device is then adjusted accordingly based on the target adjustment information.

[0051] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method described in the second aspect. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 A hardware configuration block diagram of an ultrasound device provided in an embodiment of this application;

[0054] Figure 2 A schematic diagram of an ultrasonic device provided in an embodiment of this application;

[0055] Figure 3 This is a schematic diagram of the structure of an ultrasonic probe provided in an embodiment of this application;

[0056] Figure 4 An application scenario diagram of an ultrasonic device provided in an embodiment of this application;

[0057] Figure 5 An application scenario diagram of an ultrasonic device provided in an embodiment of this application;

[0058] Figure 6 A flowchart illustrating a parameter adjustment method provided in this application embodiment;

[0059] Figure 7 A schematic diagram of a visual image provided in an embodiment of this application;

[0060] Figure 8 A schematic diagram illustrating the determination of key points and coverage areas provided in this application embodiment;

[0061] Figure 9 A schematic diagram illustrating the definition of key points provided in an embodiment of this application;

[0062] Figure 10 This is a flowchart illustrating a first reference data provided in an embodiment of this application;

[0063] Figure 11 This is a schematic diagram illustrating the determination of a target object according to an embodiment of this application;

[0064] Figure 12 A flowchart for determining second reference data provided in an embodiment of this application;

[0065] Figure 13 A flowchart illustrating the process of obtaining a segmented ultrasound image, as provided in this application embodiment;

[0066] Figure 14 This is a schematic diagram illustrating feature fusion of the first determined target encoded feature set by an anatomical structure segmentation module provided in an embodiment of this application;

[0067] Figure 15 A feature fusion flowchart is provided for an embodiment of this application;

[0068] Figure 16 A schematic diagram illustrating a channel dimension operation provided in an embodiment of this application;

[0069] Figure 17 A schematic diagram illustrating the determination of the weighting coefficient of the first channel, provided as an embodiment of this application;

[0070] Figure 18A schematic diagram illustrating a spatial dimension calculation provided in an embodiment of this application;

[0071] Figure 19 A schematic diagram illustrating the determination of a first spatial weight coefficient, provided as an embodiment of this application;

[0072] Figure 20 A schematic diagram illustrating feature fusion using a feature fusion component provided in an embodiment of this application;

[0073] Figure 21 This is a schematic diagram illustrating feature fusion of a non-first determined target encoded feature set by an anatomical structure segmentation module provided in an embodiment of this application;

[0074] Figure 22 A feature fusion flowchart is provided for an embodiment of this application;

[0075] Figure 23 This is an overall schematic diagram of an anatomical structure segmentation module provided in an embodiment of this application;

[0076] Figure 24 A schematic diagram illustrating the determination of muscle tissue thickness and adipose tissue thickness, provided for an embodiment of this application;

[0077] Figure 25 A flowchart for determining target adjustment information is provided in an embodiment of this application;

[0078] Figure 26 A schematic diagram illustrating the determination of obesity degree represented by a first reference data according to an embodiment of this application;

[0079] Figure 27 A schematic diagram illustrating the determination of obesity degree represented by a second reference data according to an embodiment of this application;

[0080] Figure 28 This is a schematic diagram illustrating the determination of target adjustment information provided in an embodiment of this application;

[0081] Figure 29 A flowchart for determining target adjustment information is provided in an embodiment of this application;

[0082] Figure 30 A schematic diagram of instruction communication provided for an embodiment of this application;

[0083] Figure 31 An overall schematic diagram provided for an embodiment of this application;

[0084] Figure 32 This is a schematic diagram of an application scenario provided by an embodiment of this application;

[0085] Figure 33An overall schematic diagram provided for an embodiment of this application;

[0086] Figure 34 This is a display interface provided in an embodiment of this application. Detailed Implementation

[0087] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. The described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0088] Furthermore, in the description of the embodiments of this application, unless otherwise stated, "and" means "or", for example, A / B can mean A or B; "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone.

[0089] Specifically, in the description of this application, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," and "counterclockwise," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application. Furthermore, the terms "connection" and "linkage" used in this application, unless otherwise specified, include both direct and indirect connections (linkages).

[0090] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified.

[0091] like Figure 1 The diagram shown is a structural schematic of an ultrasonic device according to an embodiment of this application. Figure 1 As shown, the ultrasonic device 10 may include components such as an ultrasonic probe 110, a display 120, a control panel 130, and an ultrasonic host 140.

[0092] The ultrasound probe 110 can convert electrical signals into ultrasound signals, emit ultrasound waves to the patient's human tissue, and receive ultrasound echoes reflected by human tissue, converting the ultrasound signals into electrical signals.

[0093] In this embodiment of the application, the ultrasonic probe 110 is connected to the ultrasonic host 140, and the ultrasonic probe 110 transmits the converted electrical signal to the ultrasonic host 140.

[0094] For example, the ultrasound probe 110 and the ultrasound host 140 can be connected by a cable.

[0095] The ultrasound host 140 can be used to process the received electrical signals, obtain the corresponding ultrasound image data, and transmit the ultrasound image data to the display 120.

[0096] For example, in this embodiment, the received electrical signal can be processed through operations such as amplification, filtering, and timing processing to obtain corresponding ultrasound image data. The display 120 can be used to display information input by the user, information provided to the user, and the interface of the application software in the ultrasound device 10. For example, the display 120 can display user-input information based on signals generated by the human-computer interaction components in the control panel 130 triggered by the user; the information provided to the user may include ultrasound scan operation prompts, and the corresponding ultrasound images displayed by the display 120 based on the ultrasound image data sent by the ultrasound host 140; furthermore, in this embodiment, the interface of the application software may include an ultrasound interface, and the ultrasound interface may include at least one functional area related to ultrasound scanning.

[0097] In this embodiment of the application, by running or executing a software program in the ultrasound host 140, the interface of the corresponding application software can be displayed on the display 120.

[0098] Specifically, the display screen can be configured in the form of a liquid crystal display, a light-emitting diode, etc., and this application does not limit it in this regard.

[0099] The control panel 130 can be equipped with human-computer interaction components, such as one or more of a keyboard, mouse, scroll wheel, trackball, and a touchscreen display. Specifically, when a user triggers an operation on the human-computer interaction component on the control panel, generating signal input related to user settings and function control of the ultrasound device 10, the ultrasound host 140 displays corresponding content on the display 120 based on the generated signals. The keyboard includes multiple keys, and the user sends different character information corresponding to each key to the ultrasound host 140 by triggering different keys.

[0100] Specifically, the display screen on the control panel 130 can be used to receive input numerical or character information and generate signal inputs related to user settings and function control of the ultrasound device 10. Specifically, the display screen can include a touchscreen located on the front of the display, capable of collecting touch operations by the user on or near it, such as clicking buttons, dragging scroll bars, etc.

[0101] For example, the touchscreen can be overlaid on the display screen, or the touchscreen can be integrated with the display screen to realize the input and output functions of the ultrasound device 10.

[0102] Optionally, in this embodiment, the ultrasonic device 10 may further include a caster control device 150. The caster control device 150 can be used to move the position of the ultrasonic device 10.

[0103] It should be understood that, Figure 1 The schematic diagram of the ultrasonic device 10 shown is merely an example, and the ultrasonic device 10 may have more than Figure 1 The more or fewer components shown can be combined into two or more components, or they can have different component configurations. The various components shown in the figure can be implemented in hardware, software, or a combination of hardware and software, including one or more signal processing and / or application-specific integrated circuits.

[0104] In the embodiments of this application, such as Figure 1 The ultrasound host 140 shown may include a processor to process the received ultrasound image data.

[0105] In addition, the ultrasound host 140 may also include components such as a processor, memory, communication interface, and power module. Alternatively, the processor, memory, communication interface, and power module may be located in other positions within the ultrasound device 10, and this application does not impose any restrictions on this.

[0106] Taking an ultrasound host 140, which includes a processor, memory, communication interface, and power module, as an example, the following is a schematic diagram of the hardware structure of an ultrasound host 140 according to an embodiment of this application. Figure 2 As shown, the ultrasound host 140 includes a processor 210, a memory 220, a communication interface 230, and a power module 240.

[0107] In this embodiment of the application, after the ultrasonic host 140 receives the electrical signal transmitted by the ultrasonic probe 110, the received electrical signal can be processed by the processor 210 and the memory 220 in the ultrasonic host 140 respectively.

[0108] The processor 210 can process electrical signals received from the ultrasound probe 110, or it can process electrical signals stored in the memory 220 to obtain ultrasound image data corresponding to the electrical signals; for example, it can perform signal amplification processing, filtering processing, and other processing methods. Furthermore, the processor 210 is also the control center of the ultrasound device 10, connecting various parts of the ultrasound device 10 through various interfaces and lines. It executes various functions and processes data of the ultrasound device 10 by running or executing software programs stored in the memory 220 and calling data stored in the memory 220. In some embodiments, the processor 210 may include one or more processing units; the processor 210 may also integrate an application processor and a baseband processor, wherein the application processor mainly handles the operating system, ultrasound device interface, and applications, and the baseband processor mainly handles wireless communication. It is understood that the baseband processor may not be integrated into the processor 210. In this application, the processor 210 can run the operating system, applications, ultrasound device interface display and touch response, and the processing methods described in the embodiments of this application.

[0109] The memory 220 can be used to store electrical signals, facilitating processing by the processor 210 or allowing users to access the stored electrical signals. The memory 220 can also be used to store ultrasound image data corresponding to the electrical signals, facilitating processing by the processor 210 or allowing users to access the stored ultrasound image data. Furthermore, the memory 220 can also be used to store software programs and related data. The processor 210 executes various functions of the ultrasound device 10 and related data processing by running the software programs or related data stored in the memory 220. The memory 220 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. The memory 220 stores an operating system that enables the ultrasound device 10 to run. In this application, the memory 220 can store the operating system and various application programs, and may also store code that executes the methods described in the embodiments of this application.

[0110] In this embodiment, the processor 210 is coupled to the display 120, and the display 120 displays corresponding content based on the ultrasound image data transmitted by the processor 210. The communication interface 230 is used for information interaction with other electronic devices. Specifically, the communication interface 230 may include one or more of the following: Ethernet port 231, WiFi module 232, Bluetooth module 233, 4G module 234, and USB 235. Using different communication interfaces 230 allows for the use of corresponding communication methods to interact with other electronic devices.

[0111] The power module 240 supplies power to the various components in the ultrasonic device 10. The power module 240 can be logically connected to the processor 210 through a power management system, thereby enabling the management of charging, discharging, and power consumption. The ultrasonic device 10 may also be equipped with a power button for turning the ultrasonic device on and off, as well as locking the screen.

[0112] In the embodiments of this application, such as Figure 3 The diagram shown is a structural schematic of an ultrasonic probe according to an embodiment of this application. Taking a convex array probe as an example, the ultrasonic probe 110 includes an acoustic lens 1101, a matching layer 1102, a piezoelectric crystal 1103, a backing block 1104, and a housing 1105.

[0113] It should be noted that, for Figure 3 In the ultrasound probe 110, the side of the ultrasound probe that contacts the patient is designated as the front side of the ultrasound probe in this embodiment.

[0114] When using an ultrasound probe to scan a patient, the acoustic lens 1101 is located between the matching layer 1102 of the ultrasound probe and the patient's tissue. It can be used to converge the ultrasound beam and also serves as a protective layer for the ultrasound probe 110. Specifically, when the sound velocity of the lens material corresponding to the acoustic lens 1101 is greater than the sound velocity of the surrounding medium, the ultrasound beam converges.

[0115] Matching layer 1102 is one or more layers of acoustic material located in front of the piezoelectric crystal, used to achieve impedance matching between the high acoustic impedance piezoelectric oscillator and the low acoustic impedance human tissue, thereby improving the maximum transmission efficiency of acoustic energy. Exemplarily, in embodiments of this application, matching layer 1102 can be set to a quarter-wavelength thickness.

[0116] The piezoelectric chip 1103 is used to convert electrical signals into ultrasonic signals and to convert received ultrasonic echoes into electrical signals.

[0117] It should be noted that when mechanical pressure or vibration is applied to the piezoelectric wafer 1103, an electric charge is generated on its surface. This phenomenon of mechanical energy being converted into electrical energy is called the direct piezoelectric effect. When an alternating electric field is applied to the piezoelectric wafer 1103, causing deformation and corresponding mechanical vibration, this phenomenon of electrical energy being converted into mechanical energy is called the inverse piezoelectric effect. In this embodiment, ultrasonic waves are generated through the inverse piezoelectric effect and the echoes are received through the direct piezoelectric effect.

[0118] The backing block 1104 is a sound-absorbing material filled behind the piezoelectric crystal 1103. It is used to absorb backward ultrasound and play a damping role, generating short ultrasonic pulses and improving longitudinal resolution.

[0119] In this embodiment of the application, the ultrasound device is connected to an image acquisition device, and the image acquisition device acquires a visual image containing the target object, which is then transmitted to the ultrasound device. Figure 4 The diagram shown illustrates an application scenario of an ultrasound device according to an embodiment of this application. It includes an ultrasound device 10 and an image acquisition device 41. Figure 4 Taking the image acquisition device 41 as an example of a natural light photography device.

[0120] Among them, the image acquisition equipment can establish a wired transmission with the ultrasound equipment.

[0121] In practice, the embodiments of this application can place the image acquisition device in any position and can arbitrarily adjust the image acquisition area of ​​the image acquisition device.

[0122] Optionally, embodiments of this application can use any spatial region within the space where the ultrasound device is placed as the image acquisition area of ​​the image acquisition device.

[0123] For example, embodiments of this application are able to Figure 4 The space near the central entrance serves as the image acquisition area of ​​this image acquisition device. That is, once the target object enters this image acquisition area, the device can capture a visual image containing the target object.

[0124] In this embodiment of the application, after the user enters the space where the ultrasound equipment is placed, they need to lie on a hospital bed to undergo an ultrasound scan. For example... Figure 5 The diagram shown illustrates an application scenario of an ultrasonic device according to an embodiment of this application.

[0125] In this embodiment of the application, when performing an ultrasound scan using an ultrasound probe, the front side of the probe is placed on the surface of the target body or inserted into the body. The probe emits ultrasound waves into the target body tissue and receives the echoes reflected by the tissue, converting these echoes into electrical signals. As the ultrasound probe moves, the corresponding electrical signals within the ultrasound range are sent to the ultrasound host for processing. Based on the processed electrical signals, corresponding ultrasound images are displayed on a monitor, allowing the user to obtain information about the state of lesions within the target body and the surrounding environment. Figure 4 A schematic diagram is shown using the example of placing an ultrasound probe on the surface of the target human body.

[0126] The foregoing provides many different implementation methods or examples for implementing different structures of this application. To simplify the content of the embodiments of this application, only the components and settings of specific examples are described above. Of course, these are merely examples and are not intended to limit this application.

[0127] Based on the ultrasonic equipment described in the above example, this application provides a flowchart of a parameter adjustment method applied to ultrasonic equipment. For example... Figure 6 As shown, the method may include the following steps:

[0128] Step S601: Based on the visual image of the target object transmitted by the image acquisition device, determine the first reference data for characterizing the body shape of the target object.

[0129] In this embodiment of the application, the visual image containing the target object can be found in the reference. Figure 4 The data was collected in the scene shown.

[0130] During implementation, the ultrasound equipment is connected to the image acquisition equipment to receive visual images containing the target object transmitted by the image acquisition equipment.

[0131] Optionally, the image acquisition device in this application embodiment can be connected to the ultrasound device via a USB data cable.

[0132] For example, the image acquisition device in the embodiments of this application can be a natural light photography device or an infrared imaging device, and this application does not limit it.

[0133] Since the visual images captured by infrared imaging devices do not contain facial details of the target object, infrared imaging devices can be used if there are high requirements for privacy protection.

[0134] Taking a natural light photography device as an example, the visual images acquired in the embodiments of this application can be as follows: Figure 7 As shown.

[0135] Optionally, in embodiments of this application, before determining the first reference data for any object, the key points and coverage areas corresponding to the objects contained in the visual image can be determined first.

[0136] In this embodiment, the human body detection and segmentation module can be used to extract and analyze features from visual images, and output the key points and coverage areas corresponding to each object in the visual image.

[0137] For example, in the human body detection and segmentation module of this application, visual images can be processed using deep learning algorithms.

[0138] The human detection and segmentation module includes several sub-modules: backbone network, feature fusion, prediction output, and post-processing.

[0139] Backbone network: Composed of multiple layers of convolutional neural network, its function is to extract features from the input image and output feature maps at multiple scales. Among them, large-scale feature maps retain more detailed local features, while small-scale feature maps contain more global semantic features.

[0140] Feature fusion: Tensor summation, channel concatenation, and further convolutional neural network layer processing are performed on the multi-scale feature maps output by the backbone network to improve the algorithm's ability to recognize global and local features. This module outputs the fused multi-scale feature maps.

[0141] Predicted output: The fused feature maps are processed by a convolutional neural network to output prediction results such as detection boxes, key points, and segmentation masks at multiple scales.

[0142] Post-processing: Calculations such as confidence thresholding and non-maximum suppression are performed on the predicted output to output the final calculation results of the module.

[0143] In practice, the final calculation result is the key points and coverage area corresponding to each object.

[0144] In other words, in this embodiment of the application, after inputting a visual image into the human body detection and segmentation module, the key points and coverage areas corresponding to all objects contained in the visual image can be obtained.

[0145] For example, such as Figure 8 The diagram illustrates an embodiment of this application for determining key points and coverage areas. The visual image is input into a human detection and segmentation module, and then processed by a backbone network, feature fusion, prediction output, and post-processing submodules to obtain the key points and coverage areas corresponding to all objects contained in the visual image.

[0146] The result is the smallest rectangular region in the visual image that can also include the coverage area of ​​each object.

[0147] Among them, such as Figure 9 The diagram illustrates a key point definition according to an embodiment of this application. For ease of explanation, different letters are used to represent different key points. Specifically, A represents the head, B represents the neck, C represents the right shoulder, D represents the left shoulder, E represents the right elbow, F represents the left elbow, G represents the right hand, H represents the left hand, I represents the right hip, J represents the left hip, K represents the right knee, L represents the left knee, M represents the right foot, and N represents the left foot.

[0148] It should be noted that this application does not limit the number of key points or the location where the key points are set.

[0149] Optionally, in embodiments of this application, the first reference data is determined based on the key points and coverage areas of objects in a visual image.

[0150] like Figure 10 As shown in the figure, a flowchart illustrating the determination of first reference data according to an embodiment of this application is presented below, with specific steps as follows:

[0151] Step S1001: Determine the distance ratio based on the length and width of the target object in the visual image.

[0152] Optionally, the target object in this embodiment can be determined by the human target selection module.

[0153] The target object in the visual image is selected using at least one of the following methods:

[0154] Method 1: Select objects with preset clothing in the visual image.

[0155] For example, the preset clothing in this application embodiment can be a patient gown.

[0156] Optionally, in the selection process of this application embodiment, medical clothing may also be excluded.

[0157] Method 2: Select objects with preset behaviors in the visual image.

[0158] For example, the preset behaviors in the embodiments of this application may include at least the behavior of sitting in a wheelchair.

[0159] For example, if a target object is selected using this selection method, then when the processor detects an object exhibiting wheelchair behavior in the visual image, it determines that object as the target object.

[0160] Method 3: Select objects in the visual image whose distance from the preset area meets the set distance conditions.

[0161] For example, in the embodiments of this application, the bed area can be used as a preset area, and the distance condition can be set to: the distance between the bed and the preset area is minimized.

[0162] For example, if the target object is selected using this selection method, the object with the smallest distance from the bed area will be determined as the target object.

[0163] like Figure 11 The diagram shown illustrates an embodiment of this application for determining a target object. A human target selection module is used to identify the target object from among multiple objects. For clarity, the objects with key points and those enclosed within rectangles in the right-hand diagram represent the target objects selected in this application.

[0164] Optionally, in this embodiment of the application, the length and width of the target object are determined based on the defined target object.

[0165] In this embodiment of the application, the length of the target object can be the length of any part of the target object's body.

[0166] For example, the length of the target object in this application embodiment can be the full length of the target object or the half length of the target object. The width of the target object can be the shoulder width or hip width of the target object. This application does not limit the selection of the length and width.

[0167] For example, see Figure 9 If the length of the target object is half its body length, then it can be the distance between keypoints C1 and D1, and the distance between keypoints J1. If the width of the target object is its shoulder width, then it can be the distance between keypoints C1 and D1. If the width of the target object is its hip width, then it can be the distance between keypoints I1 and J1.

[0168] Based on the above example, when using the half-body length of the target object, the average of the distance between keypoints (CI) and the distance between keypoints (DJ) can be used as the half-body length of the target object.

[0169] Similarly, since determining the total length of a target object also includes the lengths of its two legs, the average length of the two legs can be used as the leg length of the target object, and the total length of the target object can be determined based on this leg length.

[0170] It should be noted that the length of the target object used in the embodiments of this application can be determined based on the total length and / or half-length, and the width of the target object can be determined based on the shoulder width and / or hip width. This application does not limit the specific combination method.

[0171] Wherein, if the length of the target object is determined based on the full body length and half body length, then in this embodiment of the application, the calculated result of the full body length and half body length can be used as the length of the target object; if the width of the target object is determined based on the shoulder width and hip width, then in this embodiment of the application, the calculated result of the shoulder width and hip width can be used as the width of the target object.

[0172] It should be noted that the calculation method in the embodiments of this application can be the average calculation, etc.

[0173] Optionally, in embodiments of this application, the distance ratio is obtained based on the length and width of the target object using any of the following methods:

[0174] Method 1: If the length of the target object is the full body length or half body length, and the width of the target object is the shoulder width or hip width, then divide the length and width of the target object to obtain the distance ratio.

[0175] Taking the target object's length as its full length and its width as its shoulder width as an example, the distance ratio is obtained by dividing the target object's full length and its shoulder width.

[0176] Method 2: If the length of the target object is determined based on the full body length and half body length, and the width of the target object is the shoulder width or hip width, then divide the result of the calculation between the full body length and half body length by the width of the target object to obtain the distance ratio.

[0177] For example, the result of the calculation between full body length and half body length can be the average result between full body length and half body length.

[0178] Method 3: If the length of the target object is the full body length or half body length, and the width of the target object is determined based on the shoulder width and hip width, then perform a division operation on the length of the target object and the results of the calculation between the shoulder width and hip width to obtain the distance ratio.

[0179] For example, the result of the calculation between shoulder width and hip width can be the average result between shoulder width and hip width.

[0180] Method 4: If the length of the target object is determined based on the full body length and half body length, and the width of the target object is determined based on the shoulder width and hip width, then perform a division operation on the calculation results between the full body length and half body length, and between the calculation results between the shoulder width and hip width, to obtain the distance ratio.

[0181] In this application embodiment, the calculation results of the whole body length and half body length, and the calculation results between shoulder width and hip width can be determined based on the examples of method two and method three, respectively, which will not be repeated here.

[0182] Step S1002: Determine the area ratio based on the area of ​​the target object's covered region in the visual image and the area of ​​the smallest rectangular region containing the covered region.

[0183] Optionally, in this embodiment of the application, the area of ​​the covered region of the target object in the visual image is divided by the area of ​​the smallest rectangular region containing the covered region to determine the area ratio.

[0184] Step S1003: Based on the distance ratio and area ratio, determine the first reference data used to characterize the body shape of the target object.

[0185] Optionally, this application performs a weighted summation of the distance ratio and the area ratio based on a first preset weight to obtain the first reference data corresponding to the target object.

[0186] It should be noted that the first preset weight in the embodiments of this application is set manually.

[0187] Optionally, after obtaining the first reference data and before acquiring the patient's ultrasound image, this embodiment of the application can further determine the target adjustment information corresponding to the ultrasound device based on the first reference data and the mapping relationship between the reference data and the adjustment information. Then, when acquiring the patient's ultrasound image, this embodiment of the application can adjust the parameters of the ultrasound device based on the determined target adjustment information, so that the ultrasound device acquires the patient's ultrasound image based on the adjusted parameters.

[0188] It should be noted that if no first reference data is obtained before acquiring the patient's ultrasound images, the patient's ultrasound images can be acquired based on the default parameters stored in the ultrasound equipment.

[0189] Step S602: Based on the ultrasound image containing the detection site of the target object, determine the second reference data for characterizing the tissue structure state of the target object.

[0190] Among them, the ultrasound image containing the detection area of ​​the target object can be found in the reference. Figure 5 The data was collected in the scene shown.

[0191] In practice, after receiving the ultrasonic echo signal reflected from the detection area of ​​the target object, the ultrasonic probe in the ultrasonic equipment converts the ultrasonic echo signal into a corresponding electrical signal and transmits the electrical signal to the processor in the ultrasonic equipment for processing. The processor generates an ultrasonic image containing the detection area of ​​the target object based on the received electrical signal.

[0192] In the embodiments of this application, the tissue structure of the target object includes muscle tissue and adipose tissue.

[0193] Optional, such as Figure 12 As shown in the flowchart of an embodiment of this application for determining second reference data, the specific steps are as follows:

[0194] Step S1201: Perform image segmentation processing on the ultrasound image corresponding to the ultrasound echo signal to obtain the segmented ultrasound image.

[0195] Optionally, in embodiments of this application, the segmented ultrasound image can be obtained through an anatomical structure segmentation module.

[0196] The anatomical structure segmentation module in this embodiment is a fully convolutional deep neural network with an "encoder-decoder" architecture. After supervised learning training, it has the ability to segment anatomical structures such as fat and muscle in ultrasound images.

[0197] It should be noted that both the encoder and decoder are composed of multi-layer convolutional components, and there is a feature fusion component between the encoder and decoder, which can improve the network's image recognition ability and enhance segmentation accuracy.

[0198] For example, such as Figure 13 As shown in the flowchart of an embodiment of this application for obtaining a segmented ultrasound image, the specific steps are as follows:

[0199] Step S1301: Based on the encoder, the ultrasound image corresponding to the ultrasound echo signal is downsampled multiple times to obtain multiple coded feature sets corresponding to the ultrasound image.

[0200] The multiple coding feature sets include a first coding feature set obtained from the last downsampling process, and at least one second coding feature set other than the first coding feature set.

[0201] Step S1302: Determine at least one target coding feature set in the at least one second coding feature set in reverse order of obtaining at least one second coding feature set, and execute steps S13021-S13022 for each target coding feature set.

[0202] Step S13021: If the target coding feature set is the first determined target coding feature set, then feature fusion is performed based on the reference decoding feature set corresponding to the target coding feature set and the target coding feature set to obtain the fused feature set corresponding to the target coding feature set.

[0203] The reference decoding feature set is determined based on the next coding feature set obtained after obtaining the target coding feature set from multiple coding feature sets.

[0204] like Figure 14 The diagram illustrates feature fusion of an anatomical structure segmentation module for a first determined target coded feature set, as shown in this embodiment of the application. The anatomical structure segmentation module inputs a patient's ultrasound image, which is then downsampled by a decoder within the module to obtain multiple coded feature sets. For example... Figure 14 As shown, the order of the obtained multiple coded feature sets is: second coded feature set 1, second coded feature set 2, second coded feature set 3, and first coded feature set. In this embodiment, following the reverse order of obtaining at least one second coded feature set, the first determined target coded feature set is second coded feature set 3. Then, feature fusion is performed based on second coded feature set 3 and the reference decoding feature set corresponding to second coded feature set 3 to obtain the fused feature set corresponding to second coded feature set 3.

[0205] Since the first coding feature set is the next coding feature set obtained after obtaining the second coding feature set 3, the reference decoding feature set corresponding to the second coding feature set 3 is determined based on the first coding feature set.

[0206] For example, the first encoded feature set is processed by a convolutional layer component to obtain a reference decoded feature set.

[0207] This application embodiment performs feature fusion based on a feature fusion component.

[0208] It should be noted that the target encoding feature set and the reference decoding feature set in the embodiments of this application have channel dimension and spatial dimension.

[0209] The channel dimension describes the number of different features in the input data. Channel dimensions typically represent color channels, such as red, green, and blue. The channel dimensions of ultrasound images acquired by an ultrasound device in different modes may vary. For example, in mode B, the ultrasound image includes only one channel dimension, while in mode D, it includes three.

[0210] Spatial dimension refers to the arrangement of input data in space, representing the width and height of an ultrasound image. For example, for an ultrasound image with a resolution of 256×256, its spatial dimension is (256, 256).

[0211] Regarding the feature fusion process in step S13021, one embodiment of this application is as follows: Figure 15 The feature fusion flowchart shown below details the specific steps:

[0212] Step S1501: Upsample the reference decoded feature set to obtain an intermediate decoded feature set of the same size as the target encoded feature set.

[0213] The intermediate decoding feature set is the processed reference decoding feature set obtained by upsampling the reference decoding feature set.

[0214] Step S1502: In the channel dimension, perform calculations on the decoding features corresponding to each channel in the intermediate decoding feature set and on the encoding features corresponding to each channel in the target encoding feature set; concatenate the intermediate decoding feature set and the target encoding feature set after the calculations to obtain a first concatenated feature set; based on the first concatenated feature set after convolution, determine the first channel weight coefficient corresponding to the target encoding feature set and the second channel weight coefficient corresponding to the intermediate decoding feature set.

[0215] Optionally, embodiments of this application may perform mean calculation on the decoding features corresponding to each channel in the intermediate decoding feature set, and perform mean calculation on the encoding features corresponding to each channel in the target encoding feature set.

[0216] For example, such as Figure 16The diagram illustrates a channel dimension calculation according to an embodiment of this application. If an ultrasound image includes three channels, and taking the pixel values ​​corresponding to different channel features in the intermediate decoding feature set as 3, 4, and 5 respectively, the mean value after averaging is 4, then the pixel value corresponding to one channel feature is 4.

[0217] Similarly, based on the same principle, the coding features corresponding to each channel in the target coding feature set are processed.

[0218] In this embodiment of the application, after obtaining the intermediate decoded feature set and the target encoded feature set after computational processing, the intermediate decoded feature set and the target encoded feature set after computational processing can be spliced ​​together for different channels respectively.

[0219] For example, the dimensions of the intermediate decoded feature set after processing and the dimensions of the target encoded feature set after processing are both 3×3×3 (channels × height × width) (see [reference]). Figure 16 If the size shown is given, then the size of the first spliced ​​feature set after splicing can be 6×3×3.

[0220] Optionally, in this embodiment of the application, the first concatenated feature set after convolution processing determines the first channel weight coefficient corresponding to the target encoded feature set through the Sigmoid function, and the second channel weight coefficient corresponding to the intermediate decoded feature set is determined based on the first channel weight coefficient.

[0221] It should be noted that, in this embodiment of the application, a fully convolutional deep neural network is trained through supervised learning to obtain the trained fully convolutional deep neural network, and the convolution parameters in the feature fusion component of the fully convolutional deep neural network are determined. Therefore, when processing ultrasound images based on the trained fully convolutional deep neural network, convolution processing is performed on the first stitched feature set based on the convolution parameters.

[0222] The convolution parameters can include the parameters of the convolution kernel.

[0223] For example, in this embodiment of the application, the weight coefficient α of the first channel corresponding to the target encoded feature set is determined by the Sigmoid function. c Then based on the first channel weight coefficient α c Determine the second channel weight coefficient 1-α corresponding to the intermediate decoding feature set. c .

[0224] Regarding step S1502, an embodiment of this application provides a schematic diagram of determining the weighting coefficient of the first channel, as shown below. Figure 17As shown in the figure. Where C×H×W represents the dimension of the feature set before the operation, C represents the channel, H represents the height, and W represents the width. The channel dimension of the feature set obtained after averaging on the channel dimension is 1, the channel dimension of the first concatenated feature set is 2, and the channel dimension of the first concatenated feature set after convolution is 1.

[0225] Step S1503: In the spatial dimension, perform calculations on the decoding features corresponding to each space in the intermediate decoding feature set, and perform calculations on the encoding features corresponding to each space in the target encoding feature set; concatenate the intermediate decoding feature set after calculations with the target encoding feature set after calculations to obtain a second concatenated feature set; based on the second concatenated feature set after convolution processing, determine the first spatial weight coefficient corresponding to the target encoding feature set and the second spatial weight coefficient corresponding to the intermediate decoding feature set.

[0226] Optionally, embodiments of this application may perform mean calculation on the decoded features corresponding to each space in the intermediate decoded feature set, and perform mean calculation on the encoded features corresponding to each space in the target encoded feature set.

[0227] For example, such as Figure 18 The diagram illustrates a spatial dimension operation according to an embodiment of this application. Taking the processing of an intermediate decoded feature set as an example, as shown... Figure 18 The middle left figure shows the intermediate decoding feature set, which is obtained by analyzing features such as... Figure 18 The pixel values ​​corresponding to the reference decoded features in the space shown in the middle left figure are averaged to obtain... Figure 18 The pixel value 3 after mean calculation shown in the middle right image is as follows: Figure 18 As shown in the right figure.

[0228] The pixel value 3 is based on Figure 18 The pixel values ​​corresponding to the reference decoding features in the space shown in the middle left figure are determined.

[0229] Similarly, based on the same principle, the coding features corresponding to each space in the target coding feature set are processed.

[0230] In this embodiment of the application, after obtaining the intermediate decoded feature set and the target encoded feature set after computational processing, the intermediate decoded feature set and the target encoded feature set after computational processing can be concatenated.

[0231] For example, the dimensions of the intermediate decoded feature set after processing and the dimension of the target encoded feature set after processing are both 2×2×1 (see...). Figure 18 If the size shown is given, then the size of the second spliced ​​feature set after splicing can be 4×2×1.

[0232] Optionally, in this embodiment, the second concatenated feature set after convolution processing determines the first spatial weight coefficient corresponding to the target encoded feature set through the Sigmoid function, and determines the second spatial weight coefficient corresponding to the intermediate decoded feature set based on the first spatial weight coefficient.

[0233] For example, in this embodiment of the application, the first spatial weight coefficient α corresponding to the target encoded feature set is determined by the Sigmoid function. s Then based on the first spatial weight coefficient α s Determine the second spatial weight coefficient 1-α corresponding to the intermediate decoded feature set. s .

[0234] Regarding step S1503, an embodiment of this application provides a schematic diagram of determining the first spatial weighting coefficient, as shown below. Figure 19 As shown in the figure. Where C×H×W represents the dimension of the feature set before the operation, C represents the channel, H represents the height, and w represents the width. The height and width dimensions of the feature set obtained after averaging across the spatial dimensions are both 1. The height and width dimensions of the concatenated second feature set are both 1, and the channel dimension is 2C. The channel dimension of the concatenated second feature set after convolution is C.

[0235] Step S1504: Based on the first channel weight coefficient and the first spatial weight coefficient corresponding to the target coding feature set, perform calculation processing on the target coding feature set to obtain the first calculation result; based on the second channel weight coefficient and the second spatial weight coefficient corresponding to the intermediate decoding feature set, perform calculation processing on the intermediate decoding feature set to obtain the second calculation result.

[0236] For example, in this embodiment of the application, the first channel weight coefficient and the first spatial weight coefficient are multiplied on the target encoded feature set to obtain a first operation result. Furthermore, the second channel weight coefficient and the second spatial weight coefficient are multiplied on the intermediate decoded feature set to obtain a second operation result.

[0237] Step S1505: Based on the sum of the first operation result and the second operation result, determine the fusion feature set corresponding to the target encoding feature set.

[0238] like Figure 20 The diagram shown illustrates feature fusion using a feature fusion component according to an embodiment of this application. For clarity, the process of processing the target encoded feature set is shown using black lines.

[0239] The feature fusion component receives feature maps F from the encoder. e (the target encoding feature set in this application) and the feature map F of the decoder d(Reference decoding feature set in this application). First, the feature map F... d Upsampling is performed to make the spatial dimensions consistent with F. e The two inputs are then averaged in both the channel and spatial dimensions, concatenated, and processed through a convolutional layer. Finally, the encoder branch in the channel dimension α is obtained using the sigmoid function. c And the weighting coefficient α of the spatial dimension s Correspondingly, the weight coefficients of the decoder branches in the channel dimension and spatial dimension are 1-α. c and 1-α s F e F d After multiplying each feature by its respective weight coefficient and adding them together, the fused feature map (the fused feature set in this application) is obtained, which contains deep semantic features and shallow detail features.

[0240] Step S13022: If the target coding feature set is not the first determined target coding feature set, then feature fusion is performed based on the target coding feature set and the fusion feature set corresponding to the previous target coding feature set to obtain the fusion feature set corresponding to the target coding feature set.

[0241] like Figure 21 As shown, this embodiment of the application illustrates the feature fusion of a non-first determined target coded feature set by an anatomical structure segmentation module. When the second coded feature set 2 is determined to be the target coded feature set, the fused feature set corresponding to the previous target coded feature set ( Figure 14 The second coding feature set 3 obtained in the process is fused with the corresponding fusion feature set to obtain the fusion feature set corresponding to the second coding feature set 2.

[0242] This application embodiment performs feature fusion based on a feature fusion component.

[0243] Regarding the feature fusion process in step S13022, one embodiment of this application is as follows: Figure 22 The feature fusion flowchart shown below details the specific steps:

[0244] Step S2201: Upsample the fusion feature set corresponding to the previous target coding feature set to obtain an intermediate fusion feature set of the same size as the current target coding feature set.

[0245] The intermediate fusion feature set is obtained by upsampling the fusion feature set corresponding to the previous target encoding feature set.

[0246] The intermediate fusion feature set is the fusion feature set obtained by upsampling the fusion feature set corresponding to the previous target encoding feature set.

[0247] Step S2202: In the channel dimension, perform calculations on the decoding features corresponding to each channel in the intermediate fusion feature set, and perform calculations on the encoding features corresponding to each channel in the current target encoding feature set; concatenate the processed intermediate fusion feature set with the processed target encoding feature set to obtain a third concatenated feature set; based on the third concatenated feature set after convolution processing, determine the third channel weight coefficient corresponding to the current target encoding feature set and the fourth channel weight coefficient corresponding to the intermediate fusion feature set.

[0248] In this embodiment, after obtaining the third concatenated feature set after convolution processing, the third channel weight coefficient corresponding to the current target encoded feature set is determined by the Sigmoid function (e.g., using α). c If the weight coefficients of the third channel are used to determine the weight coefficients of the fourth channel corresponding to the intermediate fusion feature set (e.g., using 1-α), then the weight coefficients of the fourth channel are determined based on the weight coefficients of the third channel. c express).

[0249] Step S2203: In the spatial dimension, perform calculations on the decoding features corresponding to each space in the intermediate fusion feature set, and perform calculations on the encoding features corresponding to each space in the current target encoding feature set; concatenate the intermediate fusion feature set after calculations with the target encoding feature set after calculations to obtain the fourth concatenated feature set; based on the fourth concatenated feature set after convolution processing, determine the third spatial weight coefficient corresponding to the current target encoding feature set and the fourth spatial weight coefficient corresponding to the intermediate fusion feature set.

[0250] In this embodiment, after obtaining the fourth concatenated feature set after convolution processing, the third spatial weight coefficients (e.g., α) corresponding to the current target encoded feature set are determined by the Sigmoid function. s If the third spatial weight coefficient is used, then the fourth spatial weight coefficient corresponding to the intermediate fusion feature set is determined (e.g., using 1-α). s express).

[0251] Step S2204: Based on the third channel weight coefficient and the third spatial weight coefficient corresponding to the current target coding feature set, perform calculation processing on the current target coding feature set to obtain the third calculation result; based on the fourth channel weight coefficient and the fourth spatial weight coefficient corresponding to the intermediate fusion feature set, perform calculation processing on the intermediate fusion feature set to obtain the fourth calculation result.

[0252] For example, in this embodiment of the application, the third channel weight coefficient and the third spatial weight coefficient are multiplied on the target encoded feature set to obtain a third operation result. Furthermore, the fourth channel weight coefficient and the fourth spatial weight coefficient are multiplied on the intermediate decoded feature set to obtain a fourth operation result.

[0253] Step S2205: Based on the sum of the third and fourth operation results, determine the fusion feature set corresponding to the current target encoding feature set.

[0254] It should be noted that, Figure 22 For the corresponding method and principle of feature fusion in the feature fusion component, please refer to [link / reference]. Figure 15 and Figure 20 This application will not elaborate further.

[0255] Step S1303: Based on the fusion feature set corresponding to the last determined target encoding feature set, generate the segmented ultrasound image corresponding to the target object.

[0256] The segmented ultrasound images are used to characterize the contour information of muscle and adipose tissue in the tissue structure.

[0257] Optionally, in this embodiment of the application, the fusion feature set corresponding to the last determined target encoding feature set can be upsampled to generate a segmented ultrasound image corresponding to the target object.

[0258] This application embodiment takes feature fusion based on the second coding feature set 2 and the second coding feature set 3 as an example to provide a method such as... Figure 23 The diagram shows the overall structure segmentation module. This yields the segmented ultrasound image corresponding to the target object.

[0259] Among them, such as Figure 23 The segmented ultrasound image shown contains the outlines of muscle and adipose tissue.

[0260] Step S1202: Based on the contour information of muscle tissue and adipose tissue, determine the thickness of muscle tissue and the thickness of adipose tissue respectively.

[0261] Optionally, in this embodiment, based on a preset number of acquisition lines, acquisition points overlapping with the acquisition lines in the contours of muscle and adipose tissue in the segmented ultrasound image can be determined. For each acquisition point on the muscle tissue contour corresponding to an acquisition line, a reference thickness of muscle corresponding to each acquisition line can be determined, and the average value of the muscle reference thickness measured at all acquisition points can be used as the thickness of the muscle tissue. Similarly, for each acquisition point on the adipose tissue contour corresponding to an acquisition line, a reference thickness of fat corresponding to each acquisition line can be determined, and the average value of the fat reference thickness measured at all acquisition points can be used as the thickness of the adipose tissue.

[0262] It should be noted that the direction of the acquisition line in this embodiment is parallel to the side of the ultrasound image and intersects with the ultrasound image.

[0263] like Figure 24The diagram shown illustrates an embodiment of this application for determining the thickness of muscle tissue and adipose tissue. Two acquisition lines (e.g., ...) are used. Figure 24 Taking the two dashed lines shown as an example, the obtained acquisition points are acquisition point 11, acquisition point 12, acquisition point 13, acquisition point 14, acquisition point 21, acquisition point 22, acquisition point 23, and acquisition point 24. Specifically, based on the contour information of adipose tissue, the distance between acquisition point 11 and acquisition point 12 is used as the fat reference thickness corresponding to acquisition line 1, and the distance between acquisition point 21 and acquisition point 22 is used as the fat reference thickness corresponding to acquisition line 2. Based on the determined fat reference thicknesses corresponding to the two acquisition lines, the thickness of the adipose tissue is determined. Similarly, the process of determining the thickness of muscle tissue based on these two acquisition points can be referred to the previous text, and will not be repeated here.

[0264] It should be noted that if the acquired ultrasound image of the patient does not contain muscle and adipose tissue, the segmented ultrasound image generated in this embodiment may not contain the contour information of the segmented muscle and adipose tissue. In this case, the thickness of the obtained muscle and adipose tissue will be 0.

[0265] Step S1203: Based on the thickness of muscle tissue and the thickness of adipose tissue, determine second reference data for characterizing the tissue structure state of the target object.

[0266] Optionally, this application performs a weighted summation of the thickness of muscle tissue and the thickness of adipose tissue based on a second preset weight to obtain the second reference data corresponding to the target object.

[0267] It should be noted that the second preset weight in this embodiment is set manually.

[0268] Step S603: Based on the mapping relationship between the first reference data, the second reference data, and the pre-stored reference data and adjustment information, determine the target adjustment information corresponding to the ultrasound device.

[0269] The target adjustment information includes at least one adjustment item in the ultrasound equipment and the adjustment parameters corresponding to each adjustment item.

[0270] Optionally, the target adjustment information can be determined through any of the following processes in the embodiments of this application:

[0271] In one optional implementation process, the embodiments of this application determine the reference adjustment information corresponding to the first reference data and the second reference data respectively, and determine the target adjustment information corresponding to the ultrasonic device based on the reference adjustment information corresponding to the first reference data and the reference adjustment information corresponding to the second reference data.

[0272] like Figure 25As shown in the flowchart of an embodiment of this application for determining target adjustment information, the specific steps are as follows:

[0273] Step S2501: Based on the first reference data and the mapping relationship between the reference data and the adjustment information, determine the reference adjustment information corresponding to the first reference data.

[0274] In this application, step S2501 can be executed based on the body feature analysis module.

[0275] Optionally, embodiments of this application pre-establish a mapping relationship between reference data and adjustment information. Different adjustment information corresponds to different reference data.

[0276] In this embodiment of the application, a reference data range is set to correspond to an adjustment information. If the first reference data is reference data in any reference data range, then the adjustment information corresponding to the reference data range is used as the reference adjustment information corresponding to the first reference data.

[0277] Optionally, different reference data intervals in the embodiments of this application can characterize different body shape states.

[0278] For example, body shape status in this application embodiment can be the degree of obesity. For instance, different reference data intervals can represent the degree of obesity as follows: thin, underweight, average, overweight, and obese.

[0279] It should be noted that the reference data ranges for different body types can be set manually.

[0280] Optionally, the body feature analysis module in this embodiment can also determine the degree of obesity of the target object based on the first reference data.

[0281] For example, such as Figure 26 As shown, this application embodiment illustrates a method for determining the degree of obesity represented by a first reference data. Wherein, based on... Figure 9 The first reference data obtained from the key points and coverage area corresponding to the target object can be compared with the preset reference data interval to determine the degree of obesity represented by the reference data interval to which the first reference data of the target object belongs, which is skewed fat.

[0282] Optionally, in the embodiments of this application, the reference adjustment information corresponding to the first reference data includes at least one first reference adjustment item in the ultrasonic device, and a first reference adjustment parameter corresponding to each first reference adjustment item in the at least one first reference adjustment item.

[0283] For example, the first reference adjustment item in the embodiments of this application may include at least one of the adjustment items such as penetration, depth, focus, emission frequency, window size and gain.

[0284] In this embodiment, the reference adjustment information corresponding to the first reference data is determined based on the first reference data and the mapping relationship between the reference data and the adjustment parameters.

[0285] Step S2502: Based on the second reference data and the mapping relationship between the reference data and the adjustment information, determine the reference adjustment information corresponding to the second reference data.

[0286] In this application, step S2502 can be performed based on the human body composition analysis module.

[0287] Optionally, the body composition analysis module in this embodiment can also determine the degree of obesity of the target object based on the second reference data.

[0288] The method principle is the same as that in step S2501, such as... Figure 27 As shown, this application embodiment illustrates a method for determining the degree of obesity represented by a second reference data. Wherein, based on... Figure 23 The segmented ultrasound image obtained can be compared with the second reference data corresponding to the segmented ultrasound image and a preset reference data interval to determine the degree of obesity represented by the reference data interval to which the second reference data of the target object belongs, which is skewed fat.

[0289] Optionally, in the embodiments of this application, the reference adjustment information corresponding to the second reference data includes at least one second reference adjustment item in the ultrasonic device, and a second reference adjustment parameter corresponding to each second reference adjustment item in the at least one second reference adjustment item.

[0290] For example, the second reference adjustment item in the embodiments of this application may include at least one of the adjustment items such as penetration, depth, focus, emission frequency, window size and gain.

[0291] For example, this application can adjust the numerical value of depth, the number of focal points, and the position of the focal points, etc.

[0292] It should be noted that the second reference adjustment item in the embodiments of this application may be the same as or different from the first reference adjustment item, and this application does not impose any restrictions on this.

[0293] In this embodiment, the reference adjustment information corresponding to the second reference data is determined based on the second reference data and the mapping relationship between the reference data and the adjustment parameters.

[0294] It should be noted that this application does not restrict the order of performing steps S2501 and S2502.

[0295] Step S2503: Based on the reference adjustment information corresponding to the first reference data and the reference adjustment information corresponding to the second reference data, determine the target adjustment information corresponding to the ultrasound equipment.

[0296] In this embodiment of the application, step S2503 is executed through the parameter adjustment strategy module.

[0297] Optionally, in this embodiment of the application, a weighted average calculation is performed on the reference adjustment information corresponding to the first reference data and the reference adjustment information corresponding to the second reference data based on a third preset parameter to obtain the target adjustment information corresponding to the ultrasonic device.

[0298] It should be noted that the third preset parameters include at least the weight parameters corresponding to the first reference data and the second reference data.

[0299] This may include at least one of the following adjustment items: penetration, depth, focus, emission frequency, window size, and gain.

[0300] Optionally, step S2503 can be executed by the parameter adjustment strategy module.

[0301] like Figure 28 As shown, based on Figure 22 and 23 The representation is too bloated. This application provides a schematic diagram illustrating the determination of target adjustment information in an embodiment. For ease of explanation, Figure 28 In this context, x, y, z, and m represent the adjustment parameters corresponding to different adjustment items in the target adjustment information.

[0302] In another optional implementation process, this application determines the target reference data corresponding to the target object based on the first reference data and the second reference data, and determines the target adjustment information based on the target reference data.

[0303] like Figure 29 As shown in the flowchart of an embodiment of this application for determining target adjustment information, the specific steps are as follows:

[0304] Step S2901: Based on the first reference data and the second reference data, determine the target reference data corresponding to the target object.

[0305] For example, a weighted average operation is performed on the first reference data and the second reference data based on the third preset parameter to obtain the target reference data corresponding to the target object.

[0306] It should be noted that the third preset parameters include at least the weight parameters corresponding to the first reference data and the second reference data.

[0307] Step S2902: Based on the target reference data and the mapping relationship between the reference data and the adjustment information, determine the target adjustment information corresponding to the ultrasound equipment.

[0308] In this embodiment, the parameter adjustment strategy is executed through the parameter adjustment strategy module. Figure 29 The process is shown below.

[0309] Optionally, during the ultrasound image acquisition process, the third preset parameter used in steps S2503 and S2901 can be fixed or changed according to the detection site scanned by the ultrasound probe.

[0310] For example, regarding the process of changing the third preset parameter according to the detection site scanned by the ultrasonic probe, the embodiments of this application determine the third preset parameter based on the currently needed parameter in the following way:

[0311] Method 1: Based on the ultrasound probe being used and the mapping relationship between the pre-stored ultrasound probe and the third preset parameter, determine the third preset parameter that needs to be used at the moment.

[0312] It should be noted that since the ultrasound probe used is determined by the detection site to be scanned, the acquisition principle is similar when using the same ultrasound probe to acquire ultrasound images of at least one detection site, and the same third preset parameters can be used.

[0313] Method 2: Perform image recognition on the acquired ultrasound images to determine the detection sites in the ultrasound images, and determine the third preset parameters to be used based on the pre-stored mapping relationship between the detection sites and the third preset parameters.

[0314] Optionally, in embodiments of this application, an automatic parameter adjustment system can be added to the ultrasonic equipment, and the above process can be performed through the automatic parameter adjustment system to obtain target adjustment information.

[0315] The automatic parameter adjustment system can run on the same hardware platform as the ultrasound system software.

[0316] It should be noted that, during the above process of the automatic parameter adjustment system of this application, the ultrasound image used in step S1201 can be obtained through shared memory.

[0317] After obtaining the target adjustment information, this embodiment of the application sends the determined target adjustment information to the ultrasonic equipment software system through the instruction communication module in the parameter automatic adjustment system, and the ultrasonic equipment software system executes step S504.

[0318] Optionally, in this embodiment, the instruction encoding function in the instruction communication module converts the strategy into a binary byte stream message. This message is then sent according to the communication method agreed upon with the ultrasound device (such as TCP connection, HTTP request, etc.).

[0319] Step S604: Adjust the ultrasound equipment accordingly based on the target adjustment information.

[0320] like Figure 30 As shown, this embodiment of the application illustrates a command communication diagram. The command communication module encodes the determined target adjustment information into a strategy and sends the encoded data to the ultrasound equipment software system. Upon receiving the encoded data, the ultrasound equipment software system decodes the strategy and adjusts the parameters based on the decoded data.

[0321] In this embodiment of the application, the ultrasound device acquires ultrasound images of the patient based on the adjusted device parameters, thereby changing the ultrasound imaging effect.

[0322] like Figure 31 As shown, this is an overall schematic diagram of an embodiment of the present application.

[0323] Optionally, during the automatic parameter adjustment process of this application, the ultrasound device in the embodiments of this application may also be connected to a body fat collection device.

[0324] like Figure 32 The diagram illustrates an application scenario according to an embodiment of this application. It also suggests that the body fat analyzer 42 may be connected to an ultrasound device.

[0325] Optionally, in this embodiment of the application, after receiving the third reference data sent by the body fat acquisition device, the ultrasound device can determine the target adjustment information corresponding to the ultrasound device based on the third reference data.

[0326] If the first reference data and the third reference data are determined, the target adjustment information corresponding to the ultrasound equipment is determined based on the mapping relationship between the first reference data, the third reference data, and the pre-stored reference data and adjustment information.

[0327] The embodiments of this application can be based on Figure 25 and Figure 29 The method shown determines the target adjustment information corresponding to the ultrasonic equipment.

[0328] Optionally, in this embodiment of the application, a weighted average operation is performed on the reference adjustment information corresponding to the first reference data and the reference adjustment information corresponding to the third reference data based on the third preset parameter to obtain the target adjustment information corresponding to the ultrasound device; or, a weighted average operation is performed on the first reference data and the third reference data based on the third preset parameter to obtain the target reference data corresponding to the target object, and then the target adjustment information corresponding to the ultrasound device is determined based on the target reference data and the mapping relationship between the reference data and the adjustment information.

[0329] It should be noted that the third preset parameters include at least the weight parameters corresponding to the first reference data and the third reference data.

[0330] If the first reference data, the second reference data, and the third reference data are determined, the target adjustment information corresponding to the ultrasound equipment is determined based on the mapping relationship between the first reference data, the second reference data, the third reference data, and the pre-stored reference data and adjustment information.

[0331] Optionally, embodiments of this application determine the target adjustment information corresponding to the ultrasound device based on the first reference data, the second reference data, and the third reference data using any of the following methods:

[0332] Method 1: Based on the first reference data and the mapping relationship between pre-stored reference data and adjustment information, determine the reference adjustment information corresponding to the first reference data; based on the second reference data and the mapping relationship between reference data and adjustment information, determine the reference adjustment information corresponding to the second reference data; and based on the third reference data and the mapping relationship between pre-stored reference data and adjustment information, determine the reference adjustment information corresponding to the third reference data; based on the reference adjustment information corresponding to the first reference data, the reference adjustment information corresponding to the second reference data, and the reference adjustment information corresponding to the third reference data, determine the target adjustment information corresponding to the ultrasound equipment.

[0333] Optionally, in this embodiment of the application, a weighted average calculation is performed on the reference adjustment information corresponding to the first reference data, the reference adjustment information corresponding to the second reference data, and the reference adjustment information corresponding to the third reference data based on a third preset parameter to obtain the target adjustment information corresponding to the ultrasonic device.

[0334] Method 2: Based on the first reference data, the second reference data, and the third reference data, determine the target reference data corresponding to the target object; based on the target reference data and the mapping relationship between the pre-stored reference data and the adjustment information, determine the target adjustment information corresponding to the ultrasound equipment.

[0335] Optionally, in this embodiment of the application, the first reference data, the second reference data, and the third reference data are weighted and averaged based on a third preset parameter to obtain the target reference data corresponding to the target object.

[0336] It should be noted that the third preset parameter includes the weights corresponding to the first reference data, the second reference data, and the third reference data.

[0337] The method for determining the third preset parameter has been described above and will not be repeated here.

[0338] It should be noted that when a body fat measurement device is deployed at the bedside, the patient keeps their hand in contact with the device while receiving an ultrasound examination. The body fat measurement module receives the input data from the device, and the body shape feature analysis module corrects the vision-based analysis results to obtain more accurate target adjustment information.

[0339] like Figure 33 As shown, this is an overall schematic diagram of an embodiment of the present application.

[0340] Based on the preceding information regarding adjusting the parameters of the ultrasonic equipment, the on / off status of the automatic parameter adjustment system can be displayed on the ultrasonic equipment's screen, such as... Figure 34 As shown.

[0341] When "Automatic parameter adjustment: On (Off)" is displayed as "Automatic parameter adjustment: On", it means that the current automatic parameter adjustment system is on. When "Automatic parameter adjustment: On (Off)" is displayed as "Automatic parameter adjustment: Off", it means that the current automatic parameter adjustment system is off.

[0342] It should be noted that the main functions of this application require no human intervention and are relatively simple in terms of user interaction. After integrating this function into the system software of the ultrasound equipment, a button is added to the touch screen interface to indicate whether the function is currently enabled. Users can click the button to change the activation status of the function as needed. For example, in rare cases, experienced operators can disable automatic parameter adjustment and complete the examination manually.

[0343] Optionally, embodiments of this application may also display target adjustment information on the display screen of the ultrasound device.

[0344] It should be noted that after the parameters of the ultrasound equipment are automatically adjusted in this application, the operator can also make adaptive adjustments based on the adjusted parameters of the ultrasound equipment, and then acquire ultrasound images based on the adaptively adjusted parameters.

[0345] The advantages of this application include:

[0346] 1. High efficiency.

[0347] To achieve better imaging results, operators using ultrasound equipment need to adjust multiple equipment parameters, such as penetration, depth, and focal length, based on the patient's body shape (e.g., degree of obesity). For patients with different body shapes, repeated adjustments are necessary, each lasting from tens of seconds to several minutes. These adjustments may include setting the transmission frequency, window size, depth, probe focal length, and gain.

[0348] This application can automatically generate parameter adjustment strategies based on the analysis results of patient image features, eliminating the need for manual adjustments by operators, thus saving significant working time and improving examination efficiency. If operators are not satisfied with the adjustment results of some parameters, they can make fine adjustments themselves, and the time consumed is still shorter than the fully manual process in existing technologies.

[0349] 2. Simple

[0350] Manually adjusting ultrasound equipment parameters is not only time-consuming but also requires extensive professional knowledge and clinical experience. Many staff members in primary healthcare institutions, lacking specialized training, often choose not to make any adjustments and leave the settings at default, which affects the quality of ultrasound examinations.

[0351] Based on the opinions of numerous experts, this application automatically assists operators in adjusting and optimizing parameters without requiring operators to possess a high level of technical expertise, thus reducing the operational difficulty for operators.

[0352] 3. Safety

[0353] This application obtains patient vital signs information through a non-contact visual method. Adjusting the parameters of the ultrasound equipment only affects the imaging effect and can be manually turned off at any time (i.e., restored to default settings), without causing any physical or psychological harm to the patient.

[0354] The entire calculation process is completed within the ultrasound equipment, without internet connection. The acquired digital image information is used only for real-time vital sign analysis and is persistently stored, thus eliminating the risk of information leakage. To avoid patient concerns about privacy, the optical imaging equipment can be deployed directly opposite the entrance to the examination room, avoiding the capture of patients undressed in bed.

[0355] For better privacy protection, infrared imaging devices can be used, which do not capture detailed facial features of the patient.

[0356] Based on the same inventive concept, the parameter adjustment method described above in this application can also be implemented by a parameter adjustment device. The effect of this parameter adjustment device is similar to that of the aforementioned method, and will not be described in detail here.

[0357] Based on the same inventive concept as the above method embodiments, this application also provides an electronic device. The principle of the electronic device in solving the problem is similar to that of the method in the above embodiments. Therefore, the implementation of the electronic device can refer to the implementation of the above method, and the repeated parts will not be described again.

[0358] This application also provides a computer storage medium storing computer-executable instructions for implementing the parameter adjustment method described in any embodiment of this application.

[0359] In the description of this application, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection. They can refer to a mechanical connection or an electrical connection. They can refer to a direct connection or an indirect connection through an intermediate medium, and they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in this invention can be understood according to the specific circumstances.

[0360] Furthermore, in the description of this application, the reference to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., indicates that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of the present invention. In this application, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0361] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0362] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0363] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0364] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0365] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. An ultrasonic device, characterized in that, The ultrasound device includes an ultrasound probe and a processor; the ultrasound device is connected to an image acquisition device and receives a visual image containing the target object transmitted by the image acquisition device. The ultrasonic probe is used to receive ultrasonic echo signals reflected from the detection site of the target object; The processor is configured to: determine first reference data for characterizing the body shape of the target object based on the visual image; and determine second reference data for characterizing the tissue structure state of the target object based on the ultrasound image corresponding to the ultrasound echo signal. Based on the first reference data, the second reference data, and the mapping relationship between the pre-stored reference data and adjustment information, the target adjustment information corresponding to the ultrasound device is determined. The target adjustment information includes at least one adjustment item in the ultrasound device and the adjustment parameter corresponding to each adjustment item in the at least one adjustment item. The ultrasound device is then adjusted based on the target adjustment information.

2. The ultrasonic device as described in claim 1, characterized in that, The processor is specifically used for: Based on the length and width of the target object in the visual image, determine the distance ratio; The area ratio is determined based on the area of ​​the target object's coverage region in the visual image and the area of ​​the smallest rectangular region containing the coverage region; Based on the distance ratio and the area ratio, first reference data for characterizing the body shape of the target object is determined.

3. The ultrasonic device as described in claim 1, characterized in that, The target object's tissue structure includes muscle tissue and adipose tissue; the processor is specifically used for: The ultrasound image corresponding to the ultrasound echo signal is subjected to image segmentation processing to obtain a segmented ultrasound image; the segmented ultrasound image is used to characterize the contour information of muscle tissue and adipose tissue in the tissue structure. Based on the contour information of the muscle tissue and the contour information of the adipose tissue, the thickness of the muscle tissue and the thickness of the adipose tissue are determined respectively; Based on the thickness of the muscle tissue and the thickness of the adipose tissue, second reference data is determined to characterize the tissue structure state of the target object.

4. The ultrasonic device as described in claim 3, characterized in that, The processor is specifically used for: The ultrasonic image corresponding to the ultrasonic echo signal is downsampled multiple times based on the encoder to obtain multiple coded feature sets corresponding to the ultrasonic image; the multiple coded feature sets include a first coded feature set obtained from the last downsampling process, and at least one second coded feature set other than the first coded feature set; In reverse order of obtaining the at least one second coding feature set, at least one target coding feature set in the at least one second coding feature set is determined, and the following operations are performed for each target coding feature set: if the target coding feature set is the first determined target coding feature set, then feature fusion is performed based on the reference decoding feature set corresponding to the target coding feature set and the target coding feature set to obtain the fused feature set corresponding to the target coding feature set, wherein the reference decoding feature set is determined based on the next coding feature set obtained after obtaining the target coding feature set from the plurality of coding feature sets; if the target coding feature set is not the first determined target coding feature set, then feature fusion is performed based on the target coding feature set and the fused feature set corresponding to the previous target coding feature set to obtain the fused feature set corresponding to the target coding feature set. Based on the fusion feature set corresponding to the last determined target encoding feature set, a segmented ultrasound image corresponding to the target object is generated.

5. The ultrasonic device as described in claim 4, characterized in that, The target coding feature set and the reference decoding feature set have channel dimension and spatial dimension; if the target coding feature set is the first determined target coding feature set, the processor performs feature fusion in the following manner: The reference decoded feature set is upsampled to obtain an intermediate decoded feature set of the same size as the target encoded feature set; In the channel dimension, the decoding features corresponding to each channel in the intermediate decoding feature set are processed, and the encoding features corresponding to each channel in the target encoding feature set are processed. The intermediate decoding feature set after processing and the target encoding feature set after processing are concatenated to obtain a first concatenated feature set. Based on the first concatenated feature set after convolution processing, the first channel weight coefficient corresponding to the target encoding feature set and the second channel weight coefficient corresponding to the intermediate decoding feature set are determined respectively. as well as In the spatial dimension, the decoding features corresponding to each space in the intermediate decoding feature set are processed, and the encoding features corresponding to each space in the target encoding feature set are processed. The intermediate decoding feature set after processing and the target encoding feature set after processing are concatenated to obtain a second concatenated feature set. Based on the second concatenated feature set after convolution processing, the first spatial weight coefficient corresponding to the target encoding feature set and the second spatial weight coefficient corresponding to the intermediate decoding feature set are determined respectively. Based on the first channel weight coefficient and the first spatial weight coefficient corresponding to the target coding feature set, the target coding feature set is processed to obtain the first calculation result; Based on the second channel weight coefficient and the second spatial weight coefficient corresponding to the intermediate decoding feature set, the intermediate decoding feature set is processed to obtain the second calculation result; Based on the sum of the first calculation result and the second calculation result, the fusion feature set corresponding to the target encoding feature set is determined.

6. The ultrasonic device according to any one of claims 1 to 5, characterized in that, The processor is specifically used for: Based on the first reference data and the mapping relationship between the reference data and the adjustment information, the reference adjustment information corresponding to the first reference data is determined; Based on the second reference data and the mapping relationship between the reference data and the adjustment information, the reference adjustment information corresponding to the second reference data is determined; Based on the reference adjustment information corresponding to the first reference data and the reference adjustment information corresponding to the second reference data, the target adjustment information corresponding to the ultrasound device is determined. or Based on the first reference data and the second reference data, the target reference data corresponding to the target object is determined; Based on the target reference data and the mapping relationship between the reference data and the adjustment information, the target adjustment information corresponding to the ultrasound device is determined.

7. The ultrasonic device as described in claim 1, characterized in that, The ultrasound device is connected to the body fat collection device; the processor is also used for: Receive third reference data sent by the body fat acquisition device to characterize the body fat of the target object; Based on the mapping relationship between the first reference data, the second reference data, the third reference data, and the pre-stored reference data and adjustment information, the target adjustment information corresponding to the ultrasound device is determined.

8. The ultrasonic device as described in claim 7, characterized in that, The processor is specifically used for: Based on the first reference data and the mapping relationship between the pre-stored reference data and adjustment information, the reference adjustment information corresponding to the first reference data is determined. Based on the second reference data and the mapping relationship between the reference data and the adjustment information, the reference adjustment information corresponding to the second reference data is determined; And based on the mapping relationship between the third reference data and the pre-stored reference data and adjustment information, the reference adjustment information corresponding to the third reference data is determined; Based on the reference adjustment information corresponding to the first reference data, the reference adjustment information corresponding to the second reference data, and the reference adjustment information corresponding to the third reference data, the target adjustment information corresponding to the ultrasound device is determined. or Based on the first reference data, the second reference data, and the third reference data, the target reference data corresponding to the target object is determined; Based on the target reference data and the mapping relationship between the pre-stored reference data and adjustment information, the target adjustment information corresponding to the ultrasound device is determined.

9. The ultrasonic device according to any one of claims 1 to 5, characterized in that, The target object in the visual image is selected by the processor in at least one of the following ways: Select an object with a preset clothing from the visual image; Select objects with preset behaviors from the visual image; Select objects in the visual image whose distance from the preset area meets the set distance conditions.

10. A parameter adjustment method applied to ultrasonic equipment, characterized in that, The method includes: Based on a visual image containing a target object transmitted by an image acquisition device, first reference data for characterizing the body shape of the target object is determined. Based on the ultrasound image of the detection site containing the target object, second reference data for characterizing the tissue structure state of the target object is determined; Based on the first reference data, the second reference data, and the mapping relationship between the pre-stored reference data and adjustment information, the target adjustment information corresponding to the ultrasound device is determined. The target adjustment information includes at least one adjustment item in the ultrasound device and the adjustment parameter corresponding to each adjustment item in the adjustment item. The ultrasound device is adjusted accordingly based on the target adjustment information.

Images