A scanning method and device of ultrasonic equipment

Abstract

The present invention relates to the field of ultrasonic scanning technology, and in particular to a scanning method and device of an ultrasonic device, comprising: step S1: scanning an area to be scanned to generate a scanning image; step S2: judging whether it is necessary to scan the area to be scanned in another scanning direction; if so, turning to step S3; if not, ending the scanning process; step S3: identifying the scanning image to obtain a reference point, adjusting the scanning probe of the ultrasonic device according to the reference point and the scanning direction, and then returning to step S1. The beneficial effect of the present invention is that a reference point corresponding to the current scanning state can be generated by identifying an ultrasonic image, so as to accurately adjust the scanning position and direction, thereby avoiding the problem of scanning position offset caused by different scanning positions and directions adopted by the automated scanning device in different scanning stages during the continuous scanning process.

Description

Technical Field

[0001] The present invention relates to the technical field of ultrasonic scanning, and in particular to a scanning method and equipment of ultrasonic equipment. Background Art

[0002] Ultrasound scanning, or medical ultrasound examination, is a medical imaging diagnostic technology based on ultrasound. This technology can visualize the patient's muscle tissue and internal organs, including size, structure and pathological lesions, outside the patient's body based on ultrasound, to assist doctors in making effective diagnosis of the patient's disease. Ultrasound scanning equipment refers to medical instruments that apply the above-mentioned ultrasound scanning technology, which uses ultrasound to image the various tissue parts of the patient to assist medical diagnosis. Usually, ultrasound scanning equipment is a handheld device that transmits ultrasound to the patient through a handheld scanning probe and collects ultrasound echoes. The host then reconstructs the ultrasound echoes in real time for the doctor to make a diagnosis, such as B-ultrasound (B-ultrasound examination, which outputs a grayscale image based on ultrasound echoes). This type of ultrasound scanning equipment mainly relies on the operator's experience during the scanning process, and adjusts the scanning trajectory and position according to the real-time scanning image, which often results in poor scanning results.

[0003] There are already solutions to improve the above technical problems in the prior art, such as replacing manual scanning with automated scanning equipment, or using computer technology to assist operators in scanning, etc. However, the inventors found in the specific implementation process that the scanning method for automated equipment in the prior art did not solve the navigation problem of the scanning equipment when the patient's body surface moves, or the control accuracy during the navigation process was not high, the imaging effect was poor, and manual adjustment was still required, which could not adapt well to the fully automatic scanning scene. Summary of the invention

[0004] In view of the above problems existing in the prior art, a scanning method and device of an ultrasonic device are now provided.

[0005] The specific technical solutions are as follows:

[0006] A scanning method of an ultrasonic device, comprising:

[0007] Step S1: Scanning the area to be scanned to generate a scan image;

[0008] Step S2: determining whether it is necessary to scan the area to be scanned in another scanning direction;

[0009] If yes, go to step S3;

[0010] If not, end the scanning process;

[0011] Step S3: Identify the scanned image to obtain a reference point, adjust the scanning probe of the ultrasound device according to the reference point and the scanning direction, and then return to step S1.

[0012] Preferably, before step S1, a process of identifying the area to be scanned is also included, which specifically includes:

[0013] Step S01: collecting optical images of the patient's body surface;

[0014] The optical image includes an optical image of the area to be scanned;

[0015] Step S02: acquiring the area to be scanned from the optical image;

[0016] Step S03: generating a start point and an end point in the area to be scanned according to a pre-input scanning mode;

[0017] Step S04: Move the scanning probe until the scanning probe is in contact with the patient's body surface at the starting point, and then perform step S1.

[0018] Preferably, the step S02 comprises using an image recognition model to acquire the area to be scanned from the optical image;

[0019] The image recognition model includes:

[0020] An input layer, the input layer receiving the optical image and extracting feature information from the optical image;

[0021] A fusion layer, wherein the fusion layer processes the feature information to generate fusion information;

[0022] An output convolution layer is used to output the area to be scanned in the optical image according to the fusion information.

[0023] Preferably, the step S04 includes:

[0024] Step S041: moving the scanning probe to above the starting point;

[0025] Step S042: moving the scanning probe downward along a vertical direction, and acquiring distance information of the scanning probe relative to the patient's body surface;

[0026] When the distance information reaches a distance threshold, go to step S043;

[0027] Step S043: Continue to move the scanning probe downward along the vertical direction, and obtain pressure information of the scanning probe;

[0028] When the pressure information reaches a pressure threshold value, it indicates that the scanning probe is in contact with the patient's body surface at the starting point, and then the step S1 is performed.

[0029] Preferably, step S3 comprises:

[0030] Using a central network model to identify the scanned image to obtain the reference point;

[0031] The central network model includes:

[0032] An information extraction layer, wherein the information extraction layer extracts center information and category information from the scanned image;

[0033] A feature extraction layer, wherein the feature extraction layer includes a plurality of convolutional layers connected in series, and the convolutional layer generates a feature map according to the center information, the category information and the scanned image;

[0034] A prediction layer is used to generate a feature label according to the feature map, and to generate the reference point according to the feature label.

[0035] Preferably, the training method of the central network model includes:

[0036] Acquiring a plurality of training ultrasound images corresponding to the area to be scanned to generate a training set;

[0037] Performing region annotation on the training ultrasound image to generate an annotated image, wherein the region annotation is used to annotate multiple organ regions in the training ultrasound image;

[0038] The organ region corresponds to an organ;

[0039] The central network model is trained using the training set, and the trained central network model is verified using the annotated image.

[0040] An ultrasound device comprises a processor and a memory, wherein the memory is provided with computer instructions, and when the processor executes the computer instructions, the above-mentioned scanning method is performed;

[0041] a scanning probe, the scanning probe being connected to the processor to send a scanning image to the processor;

[0042] A mechanical arm, the scanning probe is fixed at the front end of the mechanical arm, and the mechanical arm is connected to the processor to move the scanning probe under the control of the processor;

[0043] An image sensor is connected to the processor and collects an optical image of the patient under the control of the processor.

[0044] Preferably, the front end of the scanning probe is provided with:

[0045] A distance sensor, the distance sensor is directed toward the patient to obtain distance information of the scanning probe relative to the body surface of the patient;

[0046] A pressure sensor, wherein the pressure sensor obtains pressure information of the scanning probe on the body surface of the patient;

[0047] The distance sensor and the pressure sensor are connected to a processor to send the distance information and the pressure information to the processor.

[0048] Preferably, the distance sensor is an infrared sensor, a microwave sensor or a laser sensor.

[0049] The above technical solution has the following advantages or beneficial effects: by identifying the ultrasonic image, a reference point corresponding to the current scanning state can be generated to facilitate accurate adjustment of the scanning position and direction, thereby avoiding the problem of scanning position deviation caused by different scanning positions and directions adopted by the automated scanning equipment in different scanning stages during the continuous scanning process. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The embodiments of the present invention will be described more fully with reference to the attached drawings, which are provided for illustration and description only and are not intended to limit the scope of the present invention.

[0051] Figure 1 It is an overall schematic diagram of the scanning method according to an embodiment of the present invention;

[0052] Figure 2 Schematic diagram of the process of identifying the area to be scanned in an embodiment of the present invention;

[0053] Figure 3 A schematic diagram of an image recognition model in an embodiment of the present invention;

[0054] Figure 4 This is a schematic diagram of sub-steps of step S04 in an embodiment of the present invention;

[0055] Figure 5 This is a schematic diagram of a central network model in an embodiment of the present invention;

[0056] Figure 6 1 is a principle block diagram of an ultrasonic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0059] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, but they are not intended to limit the present invention.

[0060] The present invention comprises:

[0061] A scanning method of an ultrasonic device, such as Figure 1 As shown, including:

[0062] Step S1: Scanning the area to be scanned to generate a scan image;

[0063] Step S2: Determine whether it is necessary to scan the area to be scanned in another scanning direction;

[0064] If yes, go to step S3;

[0065] If not, end the scanning process;

[0066] Step S3: Identify the scanned image to obtain a reference point, adjust the scanning probe of the ultrasound device according to the reference point and the scanning direction, and then return to step S1.

[0067] Specifically, in order to solve the problem in the prior art that the ultrasonic scanning equipment cannot adjust itself to generate a new scanning trajectory after completing a scanning stage, or the position judgment is inaccurate, the present invention generates reference points by identifying the scanning image, and then realizes automatic navigation of the scanning equipment in the new scanning stage through the reference points and the scanning direction. In the actual implementation process, the ultrasonic scanning equipment should be an ultrasonic scanning equipment with a motion device, which controls the scanning probe to move on the patient's body surface in a specific direction and position through the motion device, thereby realizing the scanning process. The scanning image refers to the ultrasonic image generated by collecting ultrasonic echoes and reconstructing the image during the scanning process. The image reconstruction method can be implemented by the existing technology and is not the focus of the present invention.

[0068] In a preferred embodiment, Figure 2 The process of identifying the area to be scanned is also included before step S1, which specifically includes:

[0069] Step S01: collecting optical images of the patient's body surface;

[0070] The optical image includes an optical image of the area to be scanned;

[0071] Step S02: Acquire the area to be scanned from the optical image;

[0072] Step S03: generating a start point and an end point in the area to be scanned according to the pre-input scanning mode;

[0073] Step S04: Move the scanning probe until the scanning probe is in contact with the patient's body surface at the starting point, and then proceed to step S1.

[0074] Specifically, in view of the technical problem that the ultrasonic scanning equipment in the prior art requires manual intervention at the beginning of the scanning stage, in this embodiment, the area to be scanned is generated by optical image assistance before the start of the scan, so as to help the scanning equipment control the scanning probe to automatically move to the starting point in the current scanning process. For example, taking thyroid scanning as an example, before the start of the scan, a frontal image of the patient's neck can be obtained by at least one image sensor, and the range of the frontal image of the neck should include the patient's chin and clavicle. By identifying the frontal image of the patient's neck, the various parts of the patient's neck can be determined, and then the corresponding starting point, such as the middle of the clavicle line, and the end point, such as a point on the neck close to the chin, are selected according to the scanning mode. In this way, automatic navigation of the scanning equipment can be achieved. As an optional implementation, auxiliary images of the patient, such as horizontal plane images, can also be collected to assist the scanning equipment in positioning in the height direction.

[0075] Furthermore, a scanning path restriction process may be included, including:

[0076] During the execution of steps S1 to S3, it is determined through optical images whether the ultrasound probe is beyond the area to be scanned, so as to timely discover the offset failure of the scanning probe, thereby avoiding the problem of inaccurate imaging caused by the offset of the scanning probe.

[0077] In a preferred embodiment, step S02 includes using an image recognition model to obtain the area to be scanned from the optical image;

[0078] like Figure 3 As shown, the image recognition model includes the following settings:

[0079] An input layer A1 receives an optical image and extracts feature information from the optical image;

[0080] Fusion layer A2, fusion layer A2 processes the feature information to generate fusion information;

[0081] The output convolution layer A3 outputs the area to be scanned in the optical image according to the fusion information.

[0082] Specifically, in this embodiment, in view of the problem that the prior art cannot navigate the automatic scanning device, this embodiment selects an image recognition model to realize the recognition of the optical image, and then extracts the patient's physical features in the optical image, and combines the scanning mode to generate the target area in the optical image, that is, the area to be scanned. In the implementation process, the input layer A1 can be an input layer of the shape of CSPDarknet53, and the input layer A1 is set to achieve a better feature information extraction effect and a faster processing process. The fusion layer A2 can be a fully connected layer, which obtains multiple feature maps of different sizes from the optical image according to the feature information and fuses the feature information in the feature map to obtain fusion information. Subsequently, in the output convolution layer A3, a series of convolution and upsampling operations are performed on the fused information to realize the detection of the area to be scanned in the optical image, and then the area to be scanned is output.

[0083] In a preferred embodiment, Figure 4 As shown, step S04 includes:

[0084] Step S041: Move the scanning probe to above the starting point;

[0085] Step S042: moving the scanning probe downward along the vertical direction, and obtaining distance information of the scanning probe relative to the patient's body surface;

[0086] When the distance information reaches a distance threshold, go to step S043;

[0087] Step S043: Continue to move the scanning probe downward along the vertical direction, and obtain pressure information of the scanning probe;

[0088] When the pressure information reaches a pressure threshold value, it indicates that the scanning probe is in contact with the patient's body surface at the starting point, and then step S1 is performed.

[0089] Specifically, in order to address the problem in the prior art that the automated scanning equipment cannot accurately locate the patient's body surface, and thus the scanning probe cannot effectively fit the patient's body surface, resulting in poor imaging effects, this embodiment uses a distance sensor and a pressure sensor to collect real-time distance information and pressure information of the scanning probe relative to the patient's body surface, and then determine the current height of the scanning probe relative to the patient's body surface in the vertical direction, so as to control the movement of the scanning probe in the height direction, so that the scanning probe can better fit the patient's body surface and achieve better imaging effects.

[0090] As an optional implementation, during the execution of steps S1 to S3, the height of the pressure probe is also closed-loop controlled according to the pressure information to ensure that the scanning probe effectively fits the patient's body surface during the scanning process.

[0091] In a preferred embodiment, step S3 includes:

[0092] A central network model is used to identify the scanned image to obtain reference points;

[0093] like Figure 5 As shown, the central network model includes the following:

[0094] Information extraction layer B1, the information extraction layer B1 extracts the center information and category information from the scanned image;

[0095] Feature extraction layer B2, which includes a plurality of convolutional layers connected in series, and the convolutional layers generate feature maps according to center information, category information and scanned images;

[0096] Prediction layer B3, prediction layer B3 generates feature labels based on feature maps, and generates reference points based on feature labels.

[0097] Specifically, in view of the problem that the ultrasonic scanning equipment in the prior art cannot effectively adjust the scanning position according to the ultrasonic image, the central network model is selected in this embodiment to identify the scanning image and obtain the reference point to realize the control of the scanning equipment. Among them, the information extraction layer B1 is a MobileNetV2-like structure in the implementation process, and its downsampling multiple is 8 times. Compared with the traditional MobileNetV2, its structure is simplified to achieve a faster extraction speed. Through the information extraction layer B1, a series of upsampling, downsampling, convolution and normalization operations on the ultrasonic image can effectively extract the central information and category information used to characterize the target structure, which is the characterization of the organ structure corresponding to the reference point in the ultrasonic image. The feature extraction layer B2 generates a feature map through the standard convolution layer and the depth separable convolution layer connected in series as shown in Table 1 below, and further represents the target structure. After the feature extraction layer B2 obtains the feature map, the prediction layer B3 extracts the target category corresponding to the target structure to be detected in the feature map column by column, and then generates feature labels corresponding to each part of the feature map, and then obtains the reference point according to the calculation results of the feature label. Compared with the common central network model in the prior art, the above central network model only detects the center point of the target structure but does not predict the range of the target structure, thereby improving the detection speed.

[0098]

[0099]

[0100] Table 1

[0101] As an optional implementation, the information extraction layer includes:

[0102] An input convolution group includes a first convolution layer, a second convolution layer, a third convolution layer and a fourth convolution layer which are connected in series in sequence, and scales the input image to a specific specification to generate a scaled image.

[0103] Convolutional network, the convolutional network obtains feature information from the scaled image through multiple sets of continuous convolutional layers;

[0104] An upsampling group, wherein the upsampling group includes a transposed convolution layer and a normalization layer arranged in sequence to generate transposed data according to feature information, and the upsampling group also includes an upsampling layer to generate upsampled information. The upsampling group performs a connection operation on the transposed data and the upsampled information to generate upsampled features;

[0105] Output convolution group, the output convolution group crops the upsampled features to output center information and category information.

[0106] In a preferred embodiment, the training method of the central network model includes:

[0107] Acquire a plurality of training ultrasound images corresponding to the area to be scanned to generate a training set;

[0108] Performing region annotation on the training ultrasound image to generate an annotated image, where the region annotation is used to annotate multiple organ regions in the training ultrasound image;

[0109] An organ region corresponds to an organ;

[0110] The training set is used to train the central network model, and the labeled images are used to verify the trained central network model.

[0111] An ultrasonic device, such as Figure 6 As shown, it includes a processor 1 and a memory 2, the memory 2 is provided with computer instructions, and when the processor 1 executes the computer instructions, the above-mentioned scanning method is executed;

[0112] A scanning probe 3, the scanning probe 3 is connected to the processor 1 to send a scanning image to the processor 1;

[0113] A mechanical arm 4, a scanning probe 3 is fixed at the front end of the mechanical arm 4, and the mechanical arm 4 is connected to the processor 1 to move the scanning probe 3 under the control of the processor 1;

[0114] The image sensor 5 is connected to the processor 1 and collects optical images of the patient under the control of the processor 1 .

[0115] Specifically, in view of the technical problem that the ultrasonic scanning equipment in the prior art requires manual intervention at the beginning of the scanning stage, in this embodiment, at the beginning of the scan, an optical image of the patient is collected by setting an image sensor 5 to help the scanning equipment control the scanning probe to automatically move to the starting point in the current scanning process. For example, taking thyroid scanning as an example, before starting the scan, a frontal image of the patient's neck can be obtained by at least one image sensor, and the range of the frontal image of the neck should include the patient's chin and clavicle. By identifying the frontal image of the patient's neck, the various parts of the patient's neck can be determined, and then the corresponding starting point, such as the middle of the clavicle line, and the end point, such as a point on the neck close to the chin, are selected according to the scanning mode. In this way, automatic navigation of the scanning equipment can be achieved. As an optional implementation, auxiliary images of the patient, such as horizontal plane images, can also be collected to assist the scanning equipment in positioning in the height direction.

[0116] It should be noted that the above-mentioned processor 1 can be understood as one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers (MCUs), microprocessors (Microprocessors), or other electronic components implemented to execute the above-mentioned computer instructions.

[0117] The memory 2 may be a computer-readable signal medium or a computer-readable storage medium. Computer-readable storage media include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or apparatuses, or any suitable combination of the foregoing, such as random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable read-only memory (CD-ROM).

[0118] In a preferred embodiment, the front end of the scanning probe 3 is provided with:

[0119] A distance sensor 31, the distance sensor 31 points to the patient to obtain distance information of the scanning probe relative to the patient's body surface;

[0120] A pressure sensor 32, the pressure sensor 32 obtains pressure information of the scanning probe 3 on the patient's body surface;

[0121] The distance sensor 31 and the pressure sensor 32 are connected to the processor 1 to send distance information and pressure information to the processor 1 .

[0122] Specifically, in view of the problem in the prior art that the automated scanning equipment cannot accurately locate the patient's body surface, and thus the scanning probe 3 cannot effectively fit the patient's body surface, resulting in poor imaging effect, this embodiment adopts the use of setting a distance sensor 31 and a pressure sensor 32 to collect the distance information and pressure information of the scanning probe relative to the patient's body surface in real time, and then judge the current height of the scanning probe 3 relative to the patient's body surface in the vertical direction to control the movement of the scanning probe 3 in the height direction, so that the scanning probe 3 can better fit the patient's body surface and achieve better imaging effect. In the actual implementation process, the distance sensor 31 can be set on the surface lower than the acoustic window of the scanning probe 3, so that the distance sensor 31 can still effectively collect distance information when the scanning probe 3 fits the patient's body surface.

[0123] In a preferred embodiment, the distance sensor 31 is an infrared sensor, a microwave sensor, or a laser sensor.

[0124] The beneficial effect of the present invention is that by identifying the ultrasonic image, a reference point corresponding to the current scanning state can be generated to facilitate accurate adjustment of the scanning position and direction, thereby avoiding the problem of scanning position deviation caused by different scanning positions and directions adopted by the automated scanning equipment in different scanning stages during the continuous scanning process.

[0125] The above are only preferred embodiments of the present invention, and are not intended to limit the implementation methods and protection scope of the present invention. Those skilled in the art should be aware that all solutions obtained by equivalent substitutions and obvious changes made using the description and illustrations of the present invention should be included in the protection scope of the present invention.

Claims

1. A scanning method of an ultrasonic device, characterized in that: include: Step S1: Scanning the area to be scanned to generate a scan image; Step S2: determining whether it is necessary to scan the area to be scanned in another scanning direction; If yes, go to step S3; If not, end the scanning process; Step S3: Identify the scanned image to obtain a reference point, adjust the scanning probe of the ultrasound device according to the reference point and the scanning direction, and then return to step S1; Before step S1, a process of identifying the area to be scanned is also included, which specifically includes: Step S01: collecting optical images of the patient's body surface; The optical image includes an optical image of the area to be scanned; Step S02: acquiring the area to be scanned from the optical image; Step S03: generating a start point and an end point in the area to be scanned according to a pre-input scanning mode; Step S04: moving the scanning probe until the scanning probe is attached to the patient's body surface at the starting point, and then performing step S1; The step S02 includes using an image recognition model to acquire the area to be scanned from the optical image; The image recognition model includes: An input layer, the input layer receiving the optical image and extracting feature information from the optical image; A fusion layer, wherein the fusion layer processes the feature information to generate fusion information; An output convolution layer, wherein the output convolution layer outputs the area to be scanned in the optical image according to the fusion information; The input layer is an input layer implemented based on CSPDarknet53; The fusion layer is a fully connected layer, and the fusion layer obtains a plurality of feature maps of different sizes from the optical image according to the feature information and fuses the feature information in the feature map to obtain fusion information; The output convolution layer performs multiple convolution and up-sampling operations on the fused information to detect the area to be scanned in the optical image, and then outputs the area to be scanned; The area to be scanned is the thyroid gland, the range of the optical image includes the patient's chin and clavicle, the starting point is the middle of the clavicle line, and the ending point is a point on the neck close to the chin.

2. The scanning method according to claim 1, characterized in that: The step S04 comprises: Step S041: moving the scanning probe to above the starting point; Step S042: moving the scanning probe downward along a vertical direction, and acquiring distance information of the scanning probe relative to the patient's body surface; When the distance information reaches a distance threshold, go to step S043; Step S043: Continue to move the scanning probe downward along the vertical direction, and obtain pressure information of the scanning probe; When the pressure information reaches a pressure threshold value, it indicates that the scanning probe is in contact with the patient's body surface at the starting point, and then the step S1 is performed.

3. The scanning method according to claim 1, characterized in that: The step S3 comprises: Using a central network model to identify the scanned image to obtain the reference point; The central network model includes: An information extraction layer, wherein the information extraction layer extracts center information and category information from the scanned image; A feature extraction layer, wherein the feature extraction layer includes a plurality of convolutional layers connected in series, and the convolutional layer generates a feature map according to the center information, the category information and the scanned image; A prediction layer is used to generate a feature label according to the feature map, and to generate the reference point according to the feature label.

4. The scanning method according to claim 3, characterized in that: The training method of the central network model includes: Acquiring a plurality of training ultrasound images corresponding to the area to be scanned to generate a training set; Performing region annotation on the training ultrasound image to generate an annotated image, wherein the region annotation is used to annotate multiple organ regions in the training ultrasound image; The organ region corresponds to an organ; The central network model is trained using the training set, and the trained central network model is verified using the annotated image.

5. An ultrasonic device, characterized in that: It comprises a processor and a memory, wherein the memory is provided with computer instructions, and when the processor executes the computer instructions, the scanning method according to any one of claims 1 to 4 is executed; a scanning probe, the scanning probe being connected to the processor to send a scanning image to the processor; A mechanical arm, the scanning probe is fixed at the front end of the mechanical arm, and the mechanical arm is connected to the processor to move the scanning probe under the control of the processor; An image sensor is connected to the processor and collects an optical image of the patient under the control of the processor.

6. The ultrasonic device according to claim 5, characterized in that The front end of the scanning probe is provided with: A distance sensor, the distance sensor is directed toward the patient to obtain distance information of the scanning probe relative to the body surface of the patient; A pressure sensor, wherein the pressure sensor obtains pressure information of the scanning probe on the body surface of the patient; The distance sensor and the pressure sensor are connected to a processor to send the distance information and the pressure information to the processor.

7. The ultrasonic device according to claim 6, characterized in that The distance sensor is an infrared sensor, a microwave sensor or a laser sensor.

Images