Treatment depth control method and device based on ultrasonic image, equipment and medium

Abstract

The invention discloses a treatment depth control method and device based on an ultrasonic image, equipment and a medium, which are applied to the technical field of medical ultrasonic image processing, and comprise the following steps: acquiring a subcutaneous tissue ultrasonic image of a current treatment area; performing feature extraction on the subcutaneous tissue ultrasonic image through a ResNet network to obtain subcutaneous tissue feature images of different semantic hierarchies, and performing fascia layer identification based on the subcutaneous tissue feature images of different semantic hierarchies through a UNet network to obtain position area information of a fascia layer in the subcutaneous tissue ultrasonic image; the center-of-gravity position of the fascia layer is determined based on the position area information of the fascia layer, and the target treatment depth of the current treatment area is determined based on the center-of-gravity position of the fascia layer, so that the position area information of the fascia layer can be quickly and accurately identified through a ResNet and UNet hybrid model. And the center-of-gravity position of the fascia layer can be quickly and accurately calculated as the target treatment depth, so that the ultrasonic treatment effect can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of medical ultrasonic image processing, and in particular to a method, device, equipment and medium for controlling treatment depth based on ultrasonic images. Background Art

[0002] Focused ultrasound beauty equipment is a device that uses ultrasound technology for skin treatment. It focuses ultrasound waves on the fascia layer and generates a large amount of energy to act on the fascia layer to achieve the effect of tightening the skin and stimulating collagen proliferation. Since the depth of the fascia layer in different parts of the human body is different, existing focused ultrasound beauty equipment is usually equipped with a variety of ultrasound treatment heads with different treatment depths for treatment adaptation when it leaves the factory. However, during the treatment process, due to the differences in tissue depths of the same treatment part of different patients, and the different treatment areas of the same patient also have different tissue depths, therefore, although equipped with a variety of ultrasound treatment heads with different treatment depths, the treatment depth interval range of each ultrasound treatment head is large, and it cannot fully cover the more refined treatment depth requirements. Summary of the invention

[0003] The present application provides a method, device, equipment and medium for controlling the depth of treatment based on ultrasound images, which is used to solve the problem that the focused ultrasound beauty equipment in the prior art cannot fully cover the requirements of different treatment depths, resulting in poor treatment effects. Among them, the technical solutions provided by the present application are as follows: On the one hand, the present application provides a method for controlling treatment depth based on ultrasound images, which is applied to a focused ultrasound cosmetic device, comprising: Acquire a subcutaneous tissue ultrasound image of the current treatment area detected according to a target imaging depth; wherein the target imaging depth is greater than a maximum treatment depth; Based on the fascia layer recognition model, the fascia layer of the subcutaneous tissue ultrasound image is recognized to obtain the position area information of the fascia layer in the subcutaneous tissue ultrasound image; wherein the fascia layer recognition model includes a ResNet network and a UNet network connected in sequence; the fascia layer recognition model extracts features of the subcutaneous tissue ultrasound image through the ResNet network to obtain first subcutaneous tissue feature images of different first semantic levels, and after performing feature enhancement on the first subcutaneous tissue feature images of different first semantic levels through the UNet network to obtain second subcutaneous tissue feature images of different second semantic levels, the fascia layer is recognized based on the second subcutaneous tissue feature images of different second semantic levels to obtain the position area information of the fascia layer in the subcutaneous tissue ultrasound image; Based on the position area information of the fascia layer in the subcutaneous tissue ultrasound image, the center of gravity position of the fascia layer in the current treatment area is determined, and based on the center of gravity position of the fascia layer in the current treatment area, the target treatment depth of the current treatment area is determined.

[0004] Optionally, the ResNet network includes a plurality of downsampling layers connected in sequence; the image resolution output by each downsampling layer decreases exponentially, the number of feature channels output by the first downsampling layer is the same as the number of feature channels output by the second downsampling layer, and the number of feature channels output by the second and subsequent downsampling layers increases exponentially; The UNet network includes an adaptation layer, multiple upsampling layers, and a fully connected layer connected in sequence; the multiple upsampling layers are jump-connected to the multiple downsampling layers of the ResNet network in a one-to-one correspondence; the image resolution output by each upsampling layer increases exponentially and the number of feature channels decreases exponentially.

[0005] Optionally, the subcutaneous tissue ultrasound image is subjected to feature extraction through a ResNet network to obtain first subcutaneous tissue feature images at different first semantic levels, including: Through the first downsampling layer in the ResNet network, the subcutaneous tissue ultrasound image is sequentially downsampled and dimensionally reduced to obtain the first subcutaneous tissue feature image at a high-resolution level; Through the second and subsequent downsampling layers in the ResNet network, the first subcutaneous tissue feature image at the high-resolution layer is iteratively downsampled to obtain the first subcutaneous tissue feature images at different low-resolution layers; Based on the first subcutaneous tissue feature image at a high-resolution level and the first subcutaneous tissue feature images at different low-resolution levels, first subcutaneous tissue feature images at different first semantic levels are obtained.

[0006] Optionally, after performing feature enhancement on first subcutaneous tissue feature images of different first semantic levels to obtain second subcutaneous tissue feature images of different second semantic levels through a UNet network, performing fascia layer recognition based on the second subcutaneous tissue feature images of different second semantic levels to obtain location area information of the fascia layer in the subcutaneous tissue ultrasound image, including: The first subcutaneous tissue feature image of the first semantic level output by the last downsampling layer in the ResNet network is adapted through the adaptation layer in the UNet network to obtain the first subcutaneous tissue feature image of the first semantic level with the target feature channel number; After upsampling the first subcutaneous tissue feature image of the first semantic level of the target feature channel number through the first upsampling layer in the UNet network, feature fusion processing is performed with the first subcutaneous tissue feature image of the first semantic level output by the downsampling layer in the corresponding jump-connected ResNet network to obtain a second subcutaneous tissue feature image of the second semantic level; For the second and subsequent upsampling layers in the UNet network, the second subcutaneous tissue feature image of the second semantic level output by the previous upsampling layer is upsampled through the upsampling layer, and then feature fused with the first subcutaneous tissue feature image of the first semantic level output by the downsampling layer in the corresponding jump-connected ResNet network to obtain the second subcutaneous tissue feature image of the second semantic level; Through the fully connected layer in the UNet network, the fascia layer is recognized on the second subcutaneous tissue feature image of the second semantic level output by the last upsampling layer to obtain the position area information of the fascia layer in the subcutaneous tissue ultrasound image.

[0007] Optionally, based on the position area information of the fascia layer in the subcutaneous tissue ultrasound image, determining the center of gravity position of the fascia layer in the current treatment area includes: Calculating the center of gravity coordinates of the fascia layer in the subcutaneous tissue ultrasound image based on the position area information of the fascia layer in the subcutaneous tissue ultrasound image; Based on the target imaging depth, the centroid coordinates of the fascia layer in the subcutaneous tissue ultrasound image are converted into the centroid position of the fascia layer in the current treatment area.

[0008] Optionally, based on the center of gravity position of the fascia layer in the current treatment area, the target treatment depth of the current treatment area is determined, including: If the fascia layer recognition model recognizes that there is a fascia layer in the subcutaneous tissue ultrasound image, the center of gravity position of the fascia layer in the current treatment area is determined as the target treatment depth of the current treatment area; If the fascia layer recognition model identifies that there are two or more fascia layers in the subcutaneous tissue ultrasound image, the center of gravity position of the fascia layer in the current treatment area that meets the skin treatment requirements corresponding to the current treatment area is determined as the target treatment depth of the current treatment area.

[0009] Optionally, the ultrasound image-based treatment depth control method provided by the present application also includes: If the fascia layer in the subcutaneous tissue ultrasound image is not identified based on the fascia layer identification model, prompt information for indicating that the fascia layer in the current treatment area is not identified is generated and displayed.

[0010] On the other hand, the present application provides a treatment depth control device based on ultrasound images, which is applied to a focused ultrasound cosmetic device, comprising: An ultrasonic image acquisition unit, used to acquire an ultrasonic image of subcutaneous tissue of a current treatment area detected according to a target imaging depth; wherein the target imaging depth is greater than a maximum treatment depth; A fascia layer recognition unit is used to perform fascia layer recognition on a subcutaneous tissue ultrasound image based on a fascia layer recognition model to obtain position area information of the fascia layer in the subcutaneous tissue ultrasound image; wherein the fascia layer recognition model includes a ResNet network and a UNet network connected in sequence; the fascia layer recognition model performs feature extraction on the subcutaneous tissue ultrasound image through the ResNet network to obtain first subcutaneous tissue feature images of different first semantic levels, performs feature enhancement on the first subcutaneous tissue feature images of different first semantic levels through the UNet network to obtain second subcutaneous tissue feature images of different second semantic levels, and then performs fascia layer recognition based on the second subcutaneous tissue feature images of different second semantic levels to obtain position area information of the fascia layer in the subcutaneous tissue ultrasound image; A treatment depth control unit is used to determine the center of gravity position of the fascia layer in the current treatment area based on the position area information of the fascia layer in the subcutaneous tissue ultrasound image, and to determine the target treatment depth of the current treatment area based on the center of gravity position of the fascia layer in the current treatment area.

[0011] On the other hand, the present application provides a focused ultrasound beauty device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned ultrasound image-based treatment depth control method when executing the computer program.

[0012] On the other hand, the present application provides a computer-readable storage medium, which stores computer instructions. When the computer instructions are executed by a processor, the above-mentioned ultrasound image-based treatment depth control method is implemented.

[0013] The beneficial effects of this application are as follows: This application uses a hybrid model of ResNet and UNet to quickly and accurately identify the location area information of the fascia layer, so that the center of gravity of the fascia layer can be quickly and accurately calculated as the target treatment depth, and then the infinite regulation of the treatment depth based on the ultrasound image of the subcutaneous tissue can be achieved, thereby achieving adaptive treatment of different fascia layer depths in different parts of different patients, thereby improving the effect of ultrasound treatment.

[0014] Other features and advantages of the present application will be described in the subsequent description, and in part, will become apparent from the description, or will be understood by practicing the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 Schematic diagram of the overview of the treatment depth control method based on ultrasound images in an embodiment of the present application; Figure 2 It is a schematic diagram of the general structure of the fascia layer identification model in the embodiment of the present application; Figure 3 This is a schematic diagram of the specific structure of the fascia layer identification model in the embodiment of the present application; Figure 4 This is a schematic diagram of the overview of the fascia layer recognition model training method in the embodiment of the present application; Figure 5 Schematic diagram of the functional structure of the ultrasound image-based treatment depth control device in an embodiment of the present application; Figure 6 Schematic diagram of the hardware structure of the focused ultrasound beauty device in the embodiment of the present application. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and beneficial effects of this application clearer, the technical solution in the embodiment of this application will be clearly and completely described below in conjunction with the drawings in the embodiment of this application. Obviously, the described embodiment is only a part of the embodiment of this application, not all the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0017] In order to facilitate those skilled in the art to better understand the present application, the technical terms involved in the present application are briefly introduced below.

[0018] The fascia layer recognition model is a neural network model for identifying the position area information of the fascia layer in the subcutaneous tissue ultrasound image. The neural network architecture adopted by the model is improved based on the UNet network, and is a hybrid network architecture based on the ResNet network (such as the ResNet34 network) and the UNet network. Among them, the ResNet network, as the front-end network of the fascia layer recognition model, that is, as the encoder of the fascia layer recognition model, can extract the low-resolution feature information of the subcutaneous tissue in the subcutaneous tissue ultrasound image at a deeper level, and will not cause the problems of gradient disappearance and grid degradation, and can also accelerate network convergence; the UNet network, as the back-end network of the fascia layer recognition model, that is, as the decoder of the fascia layer recognition model, can fully extract the high-resolution feature information of the subcutaneous tissue in the subcutaneous tissue ultrasound image (that is, the segmentation detail feature information) through feature splicing and multi-scale fusion, so as to fully integrate the different low-resolution feature information (that is, deep feature information) and different high-resolution feature information (that is, shallow feature information) of the subcutaneous tissue ultrasound image, and thus can more accurately complete the recognition of the position area information of the fascia layer in the subcutaneous tissue ultrasound image.

[0019] The target imaging depth is the ultrasonic detection depth used by the ultrasonic beauty device to collect ultrasonic images of subcutaneous tissue; in the present application, the target imaging depth is a fixed value and is greater than the maximum treatment depth of the ultrasonic beauty device, for example, the target imaging depth is 8 mm.

[0020] The initial treatment depth is one of the treatment depths selected from the different treatment depths equipped with the ultrasonic beauty device according to the patient's treatment needs; in the present application, the different treatment depths equipped with the ultrasonic beauty device include 1.5mm, 3mm, 4.5mm, etc., and the initial treatment depth is one of 1.5mm, 3mm, 4.5mm, etc.

[0021] The target treatment depth is the treatment depth determined based on the center of gravity position of the fascia layer identified by the fascia layer identification model within the current treatment area.

[0022] After introducing the technical terms involved in this application, the application scenarios and design concepts of this application are briefly introduced.

[0023] The treatment principle of focused ultrasound beauty equipment is to focus ultrasound on the target treatment area (such as the face) and generate a large amount of energy to act on the fascia layer, thereby tightening the skin and stimulating the proliferation of telomerase. Since the depth of the fascia layer in different treatment areas of the target treatment area is different, the focused ultrasound beauty equipment will be equipped with ultrasound probes of different treatment depths for treatment adaptation when it leaves the factory. For example, the focused ultrasound beauty equipment is equipped with ultrasound probes of various treatment depths such as 1.5mm, 3mm, and 4.5mm for treatment adaptation when it leaves the factory. However, since the tissue depth of the same treatment area of ​​different patients is inconsistent, and different treatment areas of the same treatment area of ​​the same patient also have different tissue depths, although the focused ultrasound beauty equipment is equipped with multiple ultrasound probes of treatment depths, the depth interval range between the treatment depths of each ultrasound probe is large, and it cannot fully cover the more refined treatment depth requirements.

[0024] To this end, in the present application, the ultrasonic beauty device is equipped with an ultrasonic probe with a target imaging depth, and the target imaging depth is greater than all treatment depths of the ultrasonic beauty device. For example, the target imaging depth is 8 mm subcutaneously, so that the ultrasonic probe can detect ultrasonic images of subcutaneous tissue that meet all treatment depths. Based on this, when the ultrasonic beauty device is ready to treat the current treatment area of ​​the target patient, the ultrasonic probe can be used to detect the current treatment area according to the target imaging depth to obtain an ultrasonic image of the subcutaneous tissue of the current treatment area. Afterwards, the subcutaneous tissue ultrasonic image is feature extracted through the ResNet network in the fascia layer recognition model to obtain first subcutaneous tissue feature images of different first semantic levels, and the UNet network in the fascia layer recognition model is used to extract the subcutaneous tissue feature images. After feature enhancement processing is performed on the first subcutaneous tissue feature images of different first semantic levels to obtain second subcutaneous tissue feature images of different second semantic levels, fascia layer identification is performed based on the second subcutaneous tissue feature images of different second semantic levels to obtain the position area information of the fascia layer in the subcutaneous tissue ultrasound image, so that the center of gravity position of the fascia layer in the current treatment area can be quickly and accurately determined based on the position area information of the fascia layer in the subcutaneous tissue ultrasound image, and then the target treatment depth of the current treatment area can be quickly and accurately determined based on the center of gravity position of the fascia layer in the current treatment area, thereby realizing stepless control of the treatment depth based on the subcutaneous tissue ultrasound image, thereby realizing adaptive treatment of different fascia layer depths in different parts of different patients, and thereby improving the ultrasound treatment effect.

[0025] After introducing the application scenarios and design ideas of the present application, the technical solutions provided by the present application are described in detail below.

[0026] The present application embodiment provides a method for controlling the depth of treatment based on ultrasound images, which can be applied to focused ultrasound cosmetic equipment. Figure 1 As shown, the general process of the treatment depth control method based on ultrasound images provided in the embodiment of the present application is as follows: Step 101: Acquire a subcutaneous tissue ultrasound image of a current treatment area detected at a target imaging depth; wherein the target imaging depth is greater than a maximum treatment depth.

[0027] In an embodiment of the present application, the ultrasonic beauty device detects the current treatment area through an ultrasonic probe of a target imaging depth to obtain an ultrasonic image of the subcutaneous tissue of the current treatment area. In one embodiment, the ultrasonic probe of the target imaging depth may be a new ultrasonic probe equipped for the ultrasonic beauty device, and the new ultrasonic probe has a fixed ultrasonic detection depth (i.e., the target imaging depth). In another embodiment, the ultrasonic probe of the target imaging depth may also be one of the original ultrasonic probes of the ultrasonic beauty device, for example, an ultrasonic probe with the largest treatment depth. When collecting the ultrasonic image of the subcutaneous tissue, the ultrasonic detection depth of the ultrasonic probe with the largest treatment depth is increased to the target imaging depth by driving the servo motor corresponding to the ultrasonic probe with the largest treatment depth, so that the current treatment area can be detected according to the target imaging depth to obtain an ultrasonic image of the subcutaneous tissue of the current treatment area. In a specific implementation, when obtaining the ultrasonic image of the subcutaneous tissue of the current treatment area detected according to the target imaging depth, the waveform data obtained by the ultrasonic probe detecting the current treatment area according to the target imaging depth may be first obtained, and then the waveform data may be cleaned, Fourier transformed, and low-pass filtered to obtain the ultrasonic image of the subcutaneous tissue of the current treatment area.

[0028] Step 102: Perform fascia layer recognition on the subcutaneous tissue ultrasound image based on the fascia layer recognition model to obtain the position area information of the fascia layer in the subcutaneous tissue ultrasound image; wherein the fascia layer recognition model includes a ResNet network and a UNet network connected in sequence; the fascia layer recognition model performs feature extraction processing on the subcutaneous tissue ultrasound image through the ResNet network to obtain first subcutaneous tissue feature images of different first semantic levels, performs feature enhancement processing on the first subcutaneous tissue feature images of different first semantic levels through the UNet network to obtain second subcutaneous tissue feature images of different second semantic levels, and then performs fascia layer recognition based on the second subcutaneous tissue feature images of different second semantic levels to obtain the position area information of the fascia layer in the subcutaneous tissue ultrasound image.

[0029] In the present application, see Figure 2As shown, the fascia layer recognition model includes a ResNet network and a UNet network connected in sequence; the ResNet network includes multiple downsampling layers connected in sequence; the image resolution output by each downsampling layer decreases exponentially, the number of feature channels output by the first downsampling layer is the same as the number of feature channels output by the second downsampling layer, and the number of feature channels output by the second and subsequent downsampling layers increases exponentially; the UNet network includes an adaptation layer, multiple upsampling layers, and a fully connected layer connected in sequence; the multiple upsampling layers are jump-connected to the multiple downsampling layers of the ResNet network in a one-to-one correspondence; the image resolution output by each upsampling layer increases exponentially and the number of feature channels decreases exponentially, so that each upsampling layer in the UNet network can gradually restore the resolution level, ensuring that the input and output resolution levels of the fascia layer recognition model are the same. Among them, Figure 2 This is only an exemplary fascia layer recognition model. The number of downsampling layers included in the ResNet network and the number of upsampling layers included in the UNet network in the fascia layer recognition model can be flexibly set according to actual needs. It is only necessary to ensure that the number of downsampling layers in the ResNet network is the same as the number of upsampling layers in the UNet network and have one-to-one corresponding jump connections.

[0030] Based on Figure 2 In the process of performing fascia layer recognition on the subcutaneous tissue ultrasound image based on the fascia layer recognition model, when performing feature extraction processing on the subcutaneous tissue ultrasound image through the ResNet network to obtain the first subcutaneous tissue feature images of different first semantic levels, the following methods may be used but are not limited to: First, the subcutaneous tissue ultrasound image is downsampled and dimensionally reduced in sequence through the first downsampling layer in the ResNet network to obtain the first subcutaneous tissue feature image at a high-resolution level.

[0031] Then, the first subcutaneous tissue feature image at the high-resolution level is iteratively downsampled through the second and subsequent downsampling layers in the ResNet network to obtain the first subcutaneous tissue feature images at different low-resolution levels.

[0032] Finally, based on the first subcutaneous tissue feature image at the high-resolution level and the first subcutaneous tissue feature images at different low-resolution levels, first subcutaneous tissue feature images at different first semantic levels are obtained.

[0033] Based on Figure 2The fascia layer recognition model shown in the figure, in the process of performing fascia layer recognition on the subcutaneous tissue ultrasound image based on the fascia layer recognition model, after performing feature enhancement processing on the first subcutaneous tissue feature images of different first semantic levels through the UNet network to obtain the second subcutaneous tissue feature images of different second semantic levels, when performing fascia layer recognition based on the second subcutaneous tissue feature images of different second semantic levels to obtain the position area information of the fascia layer in the subcutaneous tissue ultrasound image, the following methods can be used but are not limited to: First, the first subcutaneous tissue feature image of the first semantic level output by the last downsampling layer in the ResNet network is adapted through the adaptation layer in the UNet network to obtain the first subcutaneous tissue feature image of the first semantic level with the target number of feature channels.

[0034] Next, the first subcutaneous tissue feature image of the first semantic level with the target feature channel number is upsampled by the first upsampling layer in the UNet network, and then feature fused with the first subcutaneous tissue feature image of the first semantic level output by the downsampling layer in the corresponding jump-connected ResNet network to obtain the second subcutaneous tissue feature image of the second semantic level.

[0035] Then, for the second and subsequent upsampling layers in the UNet network, the second subcutaneous tissue feature image of the second semantic level output by the previous upsampling layer is upsampled through the upsampling layer, and then feature fused with the first subcutaneous tissue feature image of the first semantic level output by the downsampling layer in the corresponding jump-connected ResNet network to obtain the second subcutaneous tissue feature image of the second semantic level.

[0036] Finally, the fully connected layer in the UNet network is used to perform fascia layer recognition on the second subcutaneous tissue feature image of the second semantic level output by the last upsampling layer to obtain the position area information of the fascia layer in the subcutaneous tissue ultrasound image; wherein, the position area information of the fascia layer can be represented by a mask image, that is, the fascia layer recognition model outputs a mask image, and the position area information of the fascia layer and the position area information of other subcutaneous tissues in the mask image are represented by different identifiers. For example, in the mask image, each pixel point in the position area where the fascia layer is located is represented by the identifier "1", and each pixel point in the position area where all other subcutaneous tissues except the fascia layer are located is represented by the identifier "0".

[0037] Step 103: Based on the position area information of the fascia layer in the subcutaneous tissue ultrasound image, determine the center of gravity position of the fascia layer in the current treatment area, and based on the center of gravity position of the fascia layer in the current treatment area, determine the target treatment depth of the current treatment area.

[0038] In the embodiment of the present application, based on the position area information of the fascia layer in the ultrasound image of the subcutaneous tissue, when determining the center of gravity position of the fascia layer in the current treatment area, the following methods may be used but are not limited to: First, based on the position area information of the fascia layer in the subcutaneous tissue ultrasound image, the centroid coordinates of the fascia layer in the subcutaneous tissue ultrasound image (ie, the centroid coordinates in the pixel coordinate system) are calculated.

[0039] Then, based on the target imaging depth, the centroid coordinates of the fascia layer in the subcutaneous tissue ultrasound image are converted into the centroid position of the fascia layer in the current treatment area (ie, the centroid position in the spatial coordinate system).

[0040] In the embodiment of the present application, based on the center of gravity position of the fascia layer in the current treatment area, the target treatment depth of the current treatment area can be determined by, but not limited to, the following methods: If the fascia layer recognition model recognizes that there is a fascia layer in the subcutaneous tissue ultrasound image, the center of gravity position of the fascia layer in the current treatment area is determined as the target treatment depth of the current treatment area; If the fascia layer recognition model identifies that there are two or more fascia layers in the subcutaneous tissue ultrasound image, the center of gravity position of the fascia layer closest to the initial treatment depth corresponding to the current treatment area among each fascia layer is determined as the target treatment depth of the current treatment area; wherein the initial treatment depth is one of the multiple treatment depths equipped by the focused ultrasound beauty device.

[0041] It is worth mentioning that in an embodiment of the present application, if the fascia layer in the subcutaneous tissue ultrasound image is not identified based on the fascia layer recognition model, prompt information representing that the fascia layer in the current treatment area is not identified can be generated and displayed so that the operator can choose to continue treatment according to the initial treatment depth or adjust the initial treatment depth before treatment.

[0042] In this way, by utilizing the hybrid model of ResNet and UNet, the position area information of the fascia layer can be quickly and accurately identified, so that the center of gravity of the fascia layer can be quickly and accurately calculated as the target treatment depth, and then the infinite regulation of the treatment depth based on the ultrasound image of the subcutaneous tissue can be achieved, thereby achieving adaptive treatment of different fascia layer depths in different parts of different patients, thereby improving the effect of ultrasound treatment.

[0043] The following is a detailed description of the fascia layer recognition model and the treatment depth control method based on ultrasound images. Figure 3 As shown, the fascia layer recognition model includes a ResNet network (such as a ResNet34 network) and a UNet network connected in sequence; wherein: The ResNet network is a process of continuously fitting residuals. By learning the residuals between input and output, the network converges faster and has higher recognition accuracy. As the encoder part of the encoder-decoder structure, the ResNet network consists of multiple downsampling layers connected in sequence. Figure 3 In the example, the ResNet network consists of 5 downsampling layers. The first downsampling layer consists of a convolution layer and a pooling layer. The number of convolution kernels in the convolution layer is 64, the size is 7x7, and the step size is 2. The number of pooling windows in the pooling layer is 64, the size is 2 x 2, and the step size is 2; each of the remaining downsampling layers consists of a convolution layer and the number of residual blocks in the convolution layer contained in each of the remaining downsampling layers is the same or different. Specifically, the convolution layer contained in the second downsampling layer consists of 3 residual blocks, and the number of convolution kernels in each residual block is 64, the size is 3x3, and the step size is 1; the convolution layer contained in the third downsampling layer consists of 4 residual blocks, the number of convolution kernels in the first residual block is 128, the size is 3x3, the step size is 2, and the number of convolution kernels in the second residual block to the fourth residual block is 12. 8, size is 3x3, and step size is 1; the convolution layer contained in the 4th downsampling layer consists of 6 residual blocks, the number of convolution kernels in the 1st residual block is 256, the size is 3x3, the step size is 2, and the number of convolution kernels in the 2nd to 6th residual blocks is 256, the size is 3x3, and the step size is 1; the convolution layer contained in the 5th downsampling layer consists of 3 residual blocks, the number of convolution kernels in the 1st residual block is 512, the size is 3x3, the step size is 2, and the number of convolution kernels in the 2nd to 3rd residual blocks is 512, the size is 3x3, and the step size is 1.

[0044] Based on Figure 3 In the fascia layer recognition model shown in the figure, after the subcutaneous tissue ultrasound image is input into the fascia layer recognition model, the specific process of the ResNet network in the fascia layer recognition model to extract features of the subcutaneous tissue ultrasound image is as follows: First, in the first downsampling layer, the subcutaneous tissue ultrasound image (taking only the grayscale subcutaneous tissue ultrasound image of 800x800x1 as an example) is subjected to a convolution operation of 7x7 and a step length of 2 through a convolution layer, and 64 first subcutaneous tissue feature images with an image dimension of 400x400x1 are obtained. After that, the 64 first subcutaneous tissue feature images with an image dimension of 400x400x1 are subjected to a dimensionality reduction operation through a pooling layer, and 64 first subcutaneous tissue feature images with an image dimension of 200x200x1 are output. In this way, by connecting a layer of pooling layers, the data dimension can be reduced, the computational complexity can be reduced, and the risk of overfitting can also be reduced.

[0045] Next, in the second downsampling layer, the 64 first subcutaneous tissue feature images with an image dimension of 200x200x1 are sequentially convolved through the three residual blocks in the convolution layer with a size of 3x3 and a step size of 1. At the same time, a short connection operation is performed between each residual block to perform residual learning between residual blocks, and 64 first subcutaneous tissue feature images with an image dimension of 200x200x1 are output.

[0046] Then, in the third downsampling layer, the 64 first subcutaneous tissue feature images with an image dimension of 200x200x1 are subjected to a convolution operation with a size of 3x3 and a step size of 2 through the first residual block in the convolution layer, and then sequentially subjected to a convolution operation with a size of 3x3 and a step size of 1 through the second to fourth residual blocks in the convolution layer. At the same time, a short connection operation is performed between each residual block to perform residual learning between the residual blocks, and 128 first subcutaneous tissue feature images with an image dimension of 100x100x1 are output.

[0047] Secondly, in the fourth downsampling layer, the 128 first subcutaneous tissue feature images with an image dimension of 100x100x1 are convolved with the first residual block in the convolution layer with a size of 3x3 and a step size of 2, and then successively pass through the second to sixth residual blocks in the convolution layer to perform convolution operations with a size of 3x3 and a step size of 1. At the same time, a short connection operation is performed between each residual block to perform residual learning between residual blocks, and 128 first subcutaneous tissue feature images with an image dimension of 50x50x1 are output.

[0048] Finally, in the fifth downsampling layer, the 128 first subcutaneous tissue feature images with a dimension of 50x50x1 are convolved with the first residual block in the convolution layer with a size of 3x3 and a step size of 2, and then convolved with the second to third residual blocks in the convolution layer with a size of 3x3 and a step size of 1. At the same time, a short connection operation is performed between each residual block to perform residual learning between residual blocks, and 512 first subcutaneous tissue feature images with an image dimension of 25x25x1 are output.

[0049] In this way, after the deep convolution operation of the ResNet network, sufficiently macroscopic and abstract subcutaneous tissue features can be extracted, that is, the first subcutaneous tissue feature images of different first semantic levels are obtained through the deep convolution operation of the ResNet network.

[0050] The UNet network is a process of continuously splicing features. It gradually restores the image resolution through a series of deconvolutions (also called transposed convolutions or upsampling), while performing feature fusion through a series of jump connections to make the output subcutaneous tissue distribution more accurate. The UNet network, as the decoder part of the encoder-decoder structure, consists of an adaptation layer, multiple upsampling layers, and a fully connected layer connected in sequence. Figure 3 In this paper, we only take the UNet network consisting of 1 adaptation layer, 5 upsampling layers and 1 fully connected layer as an example. The adaptation layer consists of two convolutional layers, and the number of convolution kernels in the first convolutional layer is one of 512, 768 and 1024 ( Figure 3 Only 1024 are taken as an example), the size is 3x3, the stride is 1, the number of convolution kernels in the second convolution layer is 1024, the size is 3x3, and the stride is 1; the first upsampling layer consists of 1 deconvolution layer, 1 splicing layer and 2 convolution layers, and the splicing layer is skipped with the 5th downsampling layer in the ResNet network. The number of convolution kernels in the deconvolution layer is 1024, the size is 2 x 2, the stride is 2, and the number of convolution kernels in the 2 convolution layers is 512, the size is 3x3, and the stride is 1; the second upsampling layer consists of 1 deconvolution layer, 1 splicing layer and 2 convolution layers, and the splicing layer is skipped with the 4th downsampling layer in the ResNet network. The number of convolution kernels in the deconvolution layer is 512, the size is 2 x 2, stride 2, the number of convolution kernels in the 2 convolution layers is 256, the size is 3x3, and the stride is 1; the third upsampling layer consists of 1 deconvolution layer, 1 splicing layer and 2 convolution layers, and the splicing layer is skip-connected to the 3rd downsampling layer in the ResNet network. The number of convolution kernels in the deconvolution layer is 256, the size is 2 x 2, the stride is 2, the number of convolution kernels in the 2 convolution layers is 128, the size is 3x3, and the stride is 1; the fourth upsampling layer consists of 1 deconvolution layer, 1 splicing layer and 2 convolution layers, and the splicing layer is skip-connected to the 2nd downsampling layer in the ResNet network. The number of convolution kernels in the deconvolution layer is 128, the size is 2 x 2, with a stride of 2. The number of convolution kernels in the two convolution layers is 64, with a size of 3x3 and a stride of 1. The fifth upsampling layer consists of 1 deconvolution layer, 1 concatenation layer and 2 convolution layers, and the concatenation layer is jump-connected to the first downsampling layer in the ResNet network. The number of convolution kernels in the deconvolution layer is 64, with a size of 2 x 2 and a stride of 2. The number of convolution kernels in the two convolution layers is 32, with a size of 3x3 and a stride of 1. The fully connected layer consists of 1 point convolution layer and 1 binary label mapping layer. The size of the convolution kernel in the point convolution layer is 1x1, with a stride of 1.

[0051] Based on Figure 3In the fascia layer recognition model shown in the figure, after the ResNet network in the fascia layer recognition model extracts features from the subcutaneous tissue ultrasound image and outputs the first subcutaneous tissue feature images of different first semantic levels, the UNet network in the fascia layer recognition model performs feature enhancement on the first subcutaneous tissue feature images of different first semantic levels and then performs fascia layer recognition. The specific process is as follows: First, in the adaptation layer, the 512 first subcutaneous tissue feature images with a dimension of 25x25x1 output by the last downsampling layer in the ResNet network are sequentially convolved through two convolutional layers with a size of 3x3 and a step size of 1, and 1024 first subcutaneous tissue feature images with a dimension of 25x25x1 are output.

[0052] Next, in the first upsampling layer, the 1024 first subcutaneous tissue feature images with an image dimension of 25x25x1 are upsampled by a deconvolution layer with a size of 2 x 2 and a step size of 2 to obtain 1024 subcutaneous tissue feature images with an image dimension of 50x50x1. They are then fused with the 128 first subcutaneous tissue feature images with an image dimension of 50x50x1 output by the fifth downsampling layer in the ResNet network through a splicing layer, and then convolution operations with a size of 3x3 and a step size of 1 are performed in two convolutional layers in sequence to output 512 second subcutaneous tissue feature images with an image dimension of 50x50x1.

[0053] Then, in the second upsampling layer, 512 second subcutaneous tissue feature images with an image dimension of 50x50x1 are upsampled by a deconvolution layer with a size of 2 x 2 and a step size of 2 to obtain 512 subcutaneous tissue feature images with an image dimension of 100x100x1. They are then fused with the 256 first subcutaneous tissue feature images with an image dimension of 100x100x1 output by the fourth downsampling layer in the ResNet network through a splicing layer, and then convolution operations with a size of 3x3 and a step size of 1 are performed in two convolutional layers in sequence to output 256 second subcutaneous tissue feature images with an image dimension of 100x100x1.

[0054] Secondly, in the third upsampling layer, the 256 second subcutaneous tissue feature images with an image dimension of 100x100x1 are upsampled by a deconvolution layer with a size of 2 x 2 and a step size of 2 to obtain 256 subcutaneous tissue feature images with an image dimension of 200x200x1. Then, they are fused with the 128 first subcutaneous tissue feature images with an image dimension of 200x200x1 output by the third downsampling layer in the ResNet network through a splicing layer, and then convolution operations with a size of 3x3 and a step size of 1 are performed in two convolutional layers in sequence to output 128 second subcutaneous tissue feature images with an image dimension of 200x200x1.

[0055] Afterwards, in the fourth upsampling layer, the 128 second subcutaneous tissue feature images with an image dimension of 200x200x1 are upsampled by a deconvolution layer with a size of 2 x 2 and a step size of 2 to obtain 128 subcutaneous tissue feature images with an image dimension of 400x400x1. They are then fused with the 64 first subcutaneous tissue feature images with an image dimension of 400x400x1 output by the second downsampling layer in the ResNet network through a splicing layer, and then convolution operations with a size of 3x3 and a step size of 1 are performed in two convolutional layers in sequence to output 64 second subcutaneous tissue feature images with an image dimension of 400x400x1.

[0056] Subsequently, in the fifth upsampling layer, the 64 second subcutaneous tissue feature images with an image dimension of 400x400x1 are upsampled by a deconvolution layer with a size of 2 x 2 and a step size of 2 to obtain 64 subcutaneous tissue feature images with an image dimension of 800x800x1. They are then fused with the 32 first subcutaneous tissue feature images with an image dimension of 800x800x1 output by the first downsampling layer in the ResNet network through a splicing layer, and then convolution operations with a size of 3x3 and a step size of 1 are performed in two convolutional layers in sequence to output 32 second subcutaneous tissue feature images with an image dimension of 800x800x1.

[0057] Finally, in the fully connected layer, the 32 second subcutaneous tissue feature images with an image dimension of 800x800x1 are subjected to a point convolution operation with a size of 1x1 and a step size of 1 through a point convolution layer, and then masked through a binary classification label mapping layer to output a mask image for representing the positional area information of the fascia layer in the subcutaneous tissue ultrasound image; wherein the positional area information of the fascia layer and other subcutaneous tissues in the mask image is represented by two different identifiers.

[0058] In an embodiment of the present application, after the position area information of the fascia layer in the subcutaneous tissue ultrasound image is identified by the fascia layer recognition model, the center of gravity position of the fascia layer in the current treatment area is determined based on the position area information of the fascia layer in the subcutaneous tissue ultrasound image, and the target treatment depth of the current treatment area is determined based on the center of gravity position of the fascia layer in the current treatment area, thereby realizing stepless regulation of the treatment depth based on the subcutaneous tissue ultrasound image, and then realizing adaptive treatment of different fascia layer depths in different parts of different patients, thereby improving the effect of ultrasound treatment.

[0059] For example, first, after the ultrasonic probe corresponding to the initial treatment depth of the current treatment area is inserted into the focused ultrasonic beauty device, the focused ultrasonic beauty device identifies the initial treatment depth of the current treatment area. Assuming that the initial treatment depth of the current treatment area is 4.5 mm, the focused ultrasonic beauty device obtains the subcutaneous tissue ultrasonic image of the current treatment area detected by the ultrasonic probe at the target imaging depth, and performs fascia layer detection on the subcutaneous tissue ultrasonic image through the fascia layer recognition model.

[0060] When it is detected that there is no fascia layer at the initial treatment depth of 4.5mm, if it is detected that there is a fascia layer within the fine-tuning range of the initial treatment depth of 4.5mm±0.5mm, the center of gravity position of the fascia layer is calculated based on the position area information of the fascia layer within the fine-tuning range, and the initial treatment depth of 4.5mm is adjusted to the center of gravity position of the fascia layer. After that, a prompt message indicating that the initial treatment depth has been adjusted to the target treatment depth is issued through a pop-up window and / or voice, so that the operator can perform immediate treatment after confirmation or the operator can fine-tune the target treatment depth before performing treatment, so that the operator can manually adjust the treatment depth through the interface interaction function; if it is detected that there is no fascia layer within the fine-tuning range of the initial treatment depth of 4.5mm±0.5mm, the initial treatment depth is not adjusted, that is, the initial treatment depth is determined as the target treatment depth, and a prompt message indicating that there is no fascia layer in the current treatment area is issued through a pop-up window and / or voice, so that the operator can determine whether to continue treatment according to the initial treatment depth or adjust the initial treatment depth before performing treatment.

[0061] When two or more fascia layers are detected at the initial treatment depth of 4.5 mm, the initial treatment depth of 4.5 mm is adjusted to the center of gravity position corresponding to the fascia layer closest to the initial treatment depth of 4.5 mm among the fascia layers.

[0062] It is worth mentioning that in the embodiments of the present application, the ultrasonic beauty device usually predetermines an initial treatment line for the target treatment site (such as the face) of the target patient. The initial treatment line includes different treatment areas of the target treatment site and the initial treatment depth corresponding to each treatment area. The current treatment area mentioned above can be the treatment area currently undergoing skin treatment in the initial treatment line, or it can be the next treatment area in the initial treatment line that is about to undergo skin treatment. That is, while treating one of the treatment areas in the initial treatment line, the initial treatment depth of the next treatment area is adjusted based on the center of gravity position of the fascia layer, thereby improving the treatment effect while also improving the treatment efficiency.

[0063] The following is a detailed description of the fascia layer recognition model training method in the embodiment of the present application. Figure 4As shown, the specific process of the fascia layer recognition model training method provided in the embodiment of the present application is as follows: Step 401: Obtain a sample set of a target human body part (e.g., face); wherein the sample set includes multiple sample groups, each sample group includes an original subcutaneous tissue ultrasound image and a standard mask image of the target human body part (e.g., face), and the standard mask image is a binary mask image; each pixel value in the binary mask image is 0 or 1, 1 represents the fascia layer, and 0 represents other subcutaneous tissues except the fascia layer.

[0064] In specific implementation, when obtaining a sample set of a target human body part (such as a face), the following methods may be used but are not limited to: First, multiple original subcutaneous tissue ultrasound images are collected; each original subcutaneous tissue ultrasound image contains relatively rich subcutaneous tissue information such as the fascia layer, bones, blood vessels, etc. under the skin of the target human body part (such as the face).

[0065] Then, Labelme software is used to mark the position area information of the fascia layer of each original subcutaneous tissue ultrasound image to generate a standard mask image; for example, each pixel point in the position area where the fascia layer is located in the original subcutaneous tissue ultrasound image is marked as 1, and each pixel point in the position area where the remaining subcutaneous tissues are located is marked as 0, thereby generating a standard mask image with the same image size as the original subcutaneous tissue ultrasound image.

[0066] Finally, a plurality of sample groups are formed based on the plurality of original subcutaneous tissue ultrasound images and the plurality of standard mask images of the original subcutaneous tissue ultrasound images to obtain a sample set of the target human body part (eg, face).

[0067] Step 402: After performing image enhancement processing on a sample set of a target human body part (eg, face), the sample set after image enhancement processing is randomly divided into a training sample set and a test sample set.

[0068] Step 403: training the fascia layer recognition model based on the training sample set.

[0069] In specific implementation, when training the fascia layer recognition model based on the training sample set, the following methods may be used but are not limited to: The training operation is iteratively performed on the initial fascia layer recognition model based on the training sample set until it is determined that the iteration termination condition is met (for example, the number of iterations is greater than the first threshold and / or the current loss value is less than the second threshold, etc.), and the fascia layer recognition model is obtained based on the weights of the ResNet network and the UNet network in the initial fascia layer recognition model updated when the training operation was last performed; wherein each training operation performed includes: Select a target sample group from the training sample set; Inputting the original subcutaneous tissue ultrasound image in the target sample group into the initial fascia layer recognition model to obtain a predicted mask image for representing the position area information of the fascia layer in the original subcutaneous tissue ultrasound image; Calculate the current loss value based on the predicted mask image and the standard mask image in the target sample group; Update the weights of the ResNet network and the UNet network in the initial fascia layer recognition model based on the current loss value.

[0070] Step 404: Evaluate the trained fascia layer recognition model based on the test sample set.

[0071] Step 405: Determine the fascia layer recognition model that has passed the evaluation as the final fascia layer recognition model and save it to a computer storage medium.

[0072] Based on the above embodiments, the present application provides a treatment depth control device based on ultrasound images, which is applied to a focused ultrasound beauty device. Figure 5 As shown, the ultrasound image-based treatment depth control device 500 provided in the embodiment of the present application at least includes: The ultrasonic image acquisition unit 501 is used to acquire an ultrasonic image of subcutaneous tissue of the current treatment area detected according to the target imaging depth; wherein the target imaging depth is greater than the maximum treatment depth; The fascia layer recognition unit 502 is used to perform fascia layer recognition on the subcutaneous tissue ultrasound image based on the fascia layer recognition model to obtain the position area information of the fascia layer in the subcutaneous tissue ultrasound image; wherein the fascia layer recognition model includes a ResNet network and a UNet network connected in sequence; the fascia layer recognition model performs feature extraction on the subcutaneous tissue ultrasound image through the ResNet network to obtain first subcutaneous tissue feature images of different first semantic levels, performs feature enhancement on the first subcutaneous tissue feature images of different first semantic levels through the UNet network to obtain second subcutaneous tissue feature images of different second semantic levels, and then performs fascia layer recognition based on the second subcutaneous tissue feature images of different second semantic levels to obtain the position area information of the fascia layer in the subcutaneous tissue ultrasound image; The treatment depth control unit 503 is used to determine the center of gravity position of the fascia layer in the current treatment area based on the position area information of the fascia layer in the subcutaneous tissue ultrasound image, and determine the target treatment depth of the current treatment area based on the center of gravity position of the fascia layer in the current treatment area.

[0073] In a possible implementation, the ResNet network includes a plurality of downsampling layers connected in sequence; the image resolution output by each downsampling layer decreases exponentially, the number of feature channels output by the first downsampling layer is the same as the number of feature channels output by the second downsampling layer, and the number of feature channels output by the second and subsequent downsampling layers increases exponentially; The UNet network includes an adaptation layer, multiple upsampling layers, and a fully connected layer connected in sequence; the multiple upsampling layers are jump-connected to the multiple downsampling layers of the ResNet network in a one-to-one correspondence; the image resolution output by each upsampling layer increases exponentially and the number of feature channels decreases exponentially.

[0074] In a possible implementation, the fascia layer identification unit 502 is used to sequentially downsample and dimensionally reduce the subcutaneous tissue ultrasound image through the first downsampling layer in the ResNet network to obtain a first subcutaneous tissue feature image at a high-resolution level; iteratively downsample the first subcutaneous tissue feature image at a high-resolution level through the second and subsequent downsampling layers in the ResNet network to obtain first subcutaneous tissue feature images at different low-resolution levels; based on the first subcutaneous tissue feature image at the high-resolution level and the first subcutaneous tissue feature images at different low-resolution levels, obtain first subcutaneous tissue feature images at different first semantic levels.

[0075] In a possible implementation, the fascia layer recognition unit 502 is used to adapt the first subcutaneous tissue feature image of the first semantic level output by the last downsampling layer in the ResNet network through the adaptation layer in the UNet network to obtain the first subcutaneous tissue feature image of the first semantic level with the target feature channel number; after upsampling the first subcutaneous tissue feature image of the first semantic level with the target feature channel number through the first upsampling layer in the UNet network, perform feature fusion processing with the first subcutaneous tissue feature image of the first semantic level output by the downsampling layer in the corresponding jump-connected ResNet network to obtain the second semantic level. The second subcutaneous tissue feature image of the second semantic level is obtained by upsampling the second subcutaneous tissue feature image of the previous upsampling layer through the upsampling layer, and then the feature fusion process is performed with the first subcutaneous tissue feature image of the first semantic level output by the downsampling layer in the corresponding jump-connected ResNet network to obtain the second subcutaneous tissue feature image of the second semantic level; the fascia layer is identified on the second subcutaneous tissue feature image of the second semantic level output by the last upsampling layer through the fully connected layer in the UNet network to obtain the position area information of the fascia layer in the subcutaneous tissue ultrasound image.

[0076] In a possible embodiment, the treatment depth control unit 503 is used to calculate the centroid coordinates of the fascia layer in the subcutaneous tissue ultrasound image based on the position area information of the fascia layer in the subcutaneous tissue ultrasound image; based on the target imaging depth, the centroid coordinates of the fascia layer in the subcutaneous tissue ultrasound image are converted into the centroid position of the fascia layer in the current treatment area.

[0077] In one possible embodiment, the treatment depth control unit 503 is used to determine the center of gravity position of the fascia layer in the current treatment area as the target treatment depth of the current treatment area if the fascia layer recognition model recognizes that there is a fascia layer in the subcutaneous tissue ultrasound image; if the fascia layer recognition model recognizes that there are two or more fascia layers in the subcutaneous tissue ultrasound image, then the center of gravity position of the fascia layer in the current treatment area that meets the skin treatment requirements corresponding to the current treatment area is determined as the target treatment depth of the current treatment area.

[0078] In a possible implementation, the ultrasound image-based treatment depth control device 500 provided in the embodiment of the present application further includes: The treatment prompt unit 504 is used to generate and display prompt information for indicating that the fascia layer in the current treatment area has not been identified if the fascia layer in the subcutaneous tissue ultrasound image has not been identified based on the fascia layer identification model.

[0079] It should be noted that the principle of solving the technical problem by the above-mentioned ultrasound image-based treatment depth control device provided in the embodiment of the present application is similar to the above-mentioned ultrasound image-based treatment depth control method provided in the embodiment of the present application. Therefore, the implementation of the above-mentioned ultrasound image-based treatment depth control device provided in the embodiment of the present application can refer to the implementation of the above-mentioned ultrasound image-based treatment depth control method provided in the embodiment of the present application, and the repeated parts will not be repeated.

[0080] After introducing the method and device for controlling the treatment depth based on ultrasound images provided in the embodiments of the present application, the focused ultrasound beauty device provided in the embodiments of the present application is briefly introduced.

[0081] See also Figure 6 As shown, the focused ultrasound beauty device 600 provided in the embodiment of the present application includes at least a processor 601, a memory 602, and a computer program stored in the memory 602 and executable on the processor 601. When the processor 601 executes the computer program, the above-mentioned ultrasound image-based treatment depth control method provided in the embodiment of the present application is implemented.

[0082] The focused ultrasound beauty device 600 provided in the embodiment of the present application may also include a bus 603 connecting different components (including the processor 601 and the memory 602). The bus 603 represents one or more of several types of bus structures, including a memory bus, a peripheral bus, a local bus, and the like.

[0083] The memory 602 may include a readable medium in the form of a volatile memory, such as a random access memory (RAM) 6021 and / or a cache memory 6022, and may further include a read-only memory (ROM) 6023. The memory 602 may also include a program tool 6025 having a group (at least one) of program modules 6024, and the program modules 6024 include but are not limited to an operating subsystem, one or more application programs, other program modules, and program data, each of which or some combination may include the implementation of a network environment.

[0084] The processor 601 may be a processing element or a collective term for multiple processing elements. For example, the processor 601 may be a microcontroller unit (MCU), a central processing unit (CPU), or one or more integrated circuits configured to implement the above-mentioned ultrasound image-based treatment depth control method provided in the embodiment of the present application. Specifically, the processor 601 may be a general-purpose processor, including but not limited to a CPU, an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc.

[0085] The focused ultrasound beauty device 600 can also communicate with one or more devices (such as mobile phones, computers, etc.) that allow users to interact with the focused ultrasound beauty device 600, and / or with various external devices 604 such as devices (such as routers, modems, etc.) that allow the focused ultrasound beauty device 600 to communicate with one or more other focused ultrasound beauty devices. Such communication can be performed through an input / output (I / O) interface 605. In addition, the focused ultrasound beauty device 600 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN) and / or a public network, such as the Internet) through a network adapter 606. Figure 6As shown, the network adapter 606 communicates with other modules of the focused ultrasound cosmetic device 600 via the bus 603. It should be understood that although Figure 6 Not shown, other hardware and / or software modules may be used in conjunction with the focused ultrasound cosmetic device 600, including but not limited to microcode, device drivers, redundant processors, external disk drive arrays, disk arrays (Redundant Arrays of Independent Disks, RAID) subsystems, tape drives, and data backup storage subsystems.

[0086] It should be noted that Figure 6 The focused ultrasound cosmetic device 600 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0087] In addition, the embodiment of the present application further provides a computer-readable storage medium, which stores computer instructions, and when the computer instructions are executed by the processor, the treatment depth control method based on ultrasound images provided in the embodiment of the present application is implemented. Specifically, the computer instructions can be built-in or installed in the processor, so that the processor can implement the above-mentioned treatment depth control method based on ultrasound images provided in the embodiment of the present application by executing the built-in or installed computer instructions.

[0088] Moreover, the ultrasound image-based treatment depth control method provided in the embodiment of the present application can also be implemented as a program product, which includes a program code. When the program code is executed by a processor, it implements the above-mentioned ultrasound image-based treatment depth control method provided in the embodiment of the present application.

[0089] The program product provided in the embodiments of the present application may adopt any combination of one or more readable media, wherein the readable medium may be a readable signal medium or a readable storage medium, and the readable storage medium may be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any combination of the above. Specifically, more specific examples of readable storage media (a non-exhaustive list) include an electrical connection with one or more wires, a portable disk, a hard disk, RAM, ROM, Erasable Programmable Read Only Memory (EPROM), optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0090] The program product provided in the embodiment of the present application may adopt a CD-ROM and include program code, and may also be run on a focused ultrasound beauty device. However, the program product provided in the embodiment of the present application is not limited thereto. In the embodiment of the present application, the readable storage medium may be any tangible medium containing or storing a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.

[0091] It should be noted that, although several units or subunits of the device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided into multiple units to be embodied.

[0092] In addition, although the operations of the method of the present application are described in a specific order in the drawings, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0093] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they are aware of the basic creative concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0094] Obviously, those skilled in the art can make various changes and modifications to the embodiments of the present application without departing from the spirit and scope of the embodiments of the present application. Thus, if these modifications and variations of the embodiments of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for controlling treatment depth based on ultrasound images, characterized in that: Applied to focused ultrasound beauty equipment, including: Acquire a subcutaneous tissue ultrasound image of the current treatment area detected according to a target imaging depth; wherein the target imaging depth is greater than a maximum treatment depth; Based on the fascia layer recognition model, the fascia layer of the subcutaneous tissue ultrasound image is recognized to obtain the position area information of the fascia layer in the subcutaneous tissue ultrasound image; wherein the fascia layer recognition model includes a ResNet network and a UNet network connected in sequence; the fascia layer recognition model performs feature extraction on the subcutaneous tissue ultrasound image through the ResNet network to obtain first subcutaneous tissue feature images of different first semantic levels, and after performing feature enhancement on the first subcutaneous tissue feature images of different first semantic levels through the UNet network to obtain second subcutaneous tissue feature images of different second semantic levels, the fascia layer is recognized based on the second subcutaneous tissue feature images of different second semantic levels to obtain the position area information of the fascia layer in the subcutaneous tissue ultrasound image; Based on the position area information of the fascia layer in the subcutaneous tissue ultrasound image, the center of gravity position of the fascia layer in the current treatment area is determined, and based on the center of gravity position of the fascia layer in the current treatment area, the target treatment depth of the current treatment area is determined.

2. The method for controlling the treatment depth based on ultrasound images according to claim 1, characterized in that: The ResNet network includes a plurality of downsampling layers connected in sequence; the image resolution output by each downsampling layer decreases exponentially, the number of feature channels output by the first downsampling layer is the same as the number of feature channels output by the second downsampling layer, and the number of feature channels output by the second and subsequent downsampling layers increases exponentially; The UNet network includes an adaptation layer, multiple upsampling layers, and a fully connected layer connected in sequence; the multiple upsampling layers are jump-connected to the multiple downsampling layers of the ResNet network in a one-to-one correspondence; the image resolution output by each upsampling layer increases exponentially and the number of feature channels decreases exponentially.

3. The method for controlling the treatment depth based on ultrasound images according to claim 2, characterized in that: By using the ResNet network, the subcutaneous tissue ultrasound image is subjected to feature extraction to obtain first subcutaneous tissue feature images of different first semantic levels, including: The subcutaneous tissue ultrasound image is sequentially downsampled and dimensionally reduced through the first downsampling layer in the ResNet network to obtain a first subcutaneous tissue feature image at a high resolution level; Iteratively downsampling the first subcutaneous tissue feature image at the high-resolution level through the second and subsequent downsampling layers in the ResNet network to obtain first subcutaneous tissue feature images at different low-resolution levels; Based on the first subcutaneous tissue feature image at the high-resolution level and the first subcutaneous tissue feature images at the different low-resolution levels, the first subcutaneous tissue feature images at the different first semantic levels are obtained.

4. The method for controlling the treatment depth based on ultrasound images according to claim 2, characterized in that: After the first subcutaneous tissue feature images of different first semantic levels are feature enhanced by the UNet network to obtain second subcutaneous tissue feature images of different second semantic levels, fascia layer recognition is performed based on the second subcutaneous tissue feature images of different second semantic levels to obtain position area information of the fascia layer in the subcutaneous tissue ultrasound image, including: The first subcutaneous tissue feature image of the first semantic level output by the last downsampling layer in the ResNet network is adapted through the adaptation layer in the UNet network to obtain the first subcutaneous tissue feature image of the first semantic level with the target feature channel number; After upsampling the first subcutaneous tissue feature image of the first semantic level of the target feature channel number through the first upsampling layer in the UNet network, feature fusion processing is performed with the first subcutaneous tissue feature image of the first semantic level output by the downsampling layer in the ResNet network corresponding to the jump connection to obtain a second subcutaneous tissue feature image of the second semantic level; For each upsampling layer in the UNet network, the second subcutaneous tissue feature image of the second semantic level output by the previous upsampling layer is upsampled by the upsampling layer, and then the feature fusion process is performed with the first subcutaneous tissue feature image of the first semantic level output by the downsampling layer in the ResNet network connected to the corresponding jump layer, so as to obtain the second subcutaneous tissue feature image of the second semantic level; Through the fully connected layer in the UNet network, the fascia layer is identified on the second subcutaneous tissue feature image of the second semantic level output by the last upsampling layer to obtain the position area information of the fascia layer in the subcutaneous tissue ultrasound image.

5. The method for controlling treatment depth based on ultrasound images according to claim 1, characterized in that: Determining the center of gravity of the fascia layer in the current treatment area based on the position area information of the fascia layer in the subcutaneous tissue ultrasound image includes: Calculating the centroid coordinates of the fascia layer in the subcutaneous tissue ultrasound image based on the position area information of the fascia layer in the subcutaneous tissue ultrasound image; Based on the target imaging depth, the center-of-gravity coordinates of the fascia layer in the subcutaneous tissue ultrasound image are converted into the center-of-gravity position of the fascia layer in the current treatment area.

6. The method for controlling treatment depth based on ultrasound images according to claim 1, characterized in that: Determining a target treatment depth of the current treatment area based on the center of gravity position of the fascia layer in the current treatment area includes: If the fascia layer recognition model recognizes that there is a fascia layer in the subcutaneous tissue ultrasound image, the center of gravity position of the fascia layer in the current treatment area is determined as the target treatment depth of the current treatment area; If the fascia layer identification model identifies that there are two or more fascia layers in the subcutaneous tissue ultrasound image, the center of gravity position of the fascia layer in the current treatment area that meets the skin treatment requirements corresponding to the current treatment area is determined as the target treatment depth of the current treatment area.

7. The method for controlling treatment depth based on ultrasound images according to any one of claims 1 to 6, characterized in that: Also includes: If the fascia layer in the subcutaneous tissue ultrasound image is not identified based on the fascia layer identification model, prompt information indicating that the fascia layer in the current treatment area is not identified is generated and displayed.

8. A treatment depth control device based on ultrasound images, characterized in that: Applied to focused ultrasound beauty equipment, including: An ultrasonic image acquisition unit, used to acquire an ultrasonic image of subcutaneous tissue of a current treatment area detected according to a target imaging depth; wherein the target imaging depth is greater than a maximum treatment depth; A fascia layer recognition unit is used to perform fascia layer recognition on the subcutaneous tissue ultrasound image based on a fascia layer recognition model to obtain position area information of the fascia layer in the subcutaneous tissue ultrasound image; wherein the fascia layer recognition model includes a ResNet network and a UNet network connected in sequence; the fascia layer recognition model performs feature extraction on the subcutaneous tissue ultrasound image through the ResNet network to obtain first subcutaneous tissue feature images of different first semantic levels, performs feature enhancement on the first subcutaneous tissue feature images of different first semantic levels through the UNet network to obtain second subcutaneous tissue feature images of different second semantic levels, and then performs fascia layer recognition based on the second subcutaneous tissue feature images of different second semantic levels to obtain the position area information of the fascia layer in the subcutaneous tissue ultrasound image; A treatment depth control unit is used to determine the center of gravity position of the fascia layer in the current treatment area based on the position area information of the fascia layer in the subcutaneous tissue ultrasound image, and to determine the target treatment depth of the current treatment area based on the center of gravity position of the fascia layer in the current treatment area.

9. A focused ultrasound beauty device, characterized in that: It comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for controlling the treatment depth based on ultrasound images as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method for controlling the treatment depth based on ultrasound images as described in any one of claims 1 to 7 is implemented.

Images