Skin layering identification method and device and computer readable storage medium

Abstract

The embodiment of the invention discloses a skin layering identification method and device and a computer readable storage medium. Comprising the steps of obtaining a to-be-processed skin cross-sectional image and skin elasticity information; performing layered identification on the to-be-processed skin cross-sectional image to identify a target detection area; the target detection area comprises an epidermal layer area, a corium layer area and a subcutaneous tissue area; wherein the subcutaneous tissue area comprises a fat layer area and a fascia layer area; determining the fat layer content according to the fat layer area and the subcutaneous tissue area; and / or, determining a fascia layer distance according to the fascia layer area and the epidermal layer area; and / or determining the fascia layer tightening degree according to the fascia layer area and the subcutaneous tissue area; and performing elasticity imaging display on the to-be-processed skin cross-sectional image according to the elasticity information. By means of the mode, various parameters of the skin tissue are detected, the skin state can be evaluated conveniently, and a personalized skin management scheme can be made conveniently.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of skin detection, and in particular to a skin layering recognition method, device and computer readable storage medium. BACKGROUND

[0002] As the largest organ of the human body, the epidermis layer, dermis layer, subcutaneous tissue layer, fat layer and fascia layer constitute a complex multi-level structure system, and the physiological state of each layer of tissue (such as epidermal barrier integrity, dermal collagen density, subcutaneous fat distribution, fascia layer tightness, etc.) directly determines the health and appearance of the skin. Therefore, achieving accurate recognition and state quantification of each layer of skin tissue has become an important concern in current medical and aesthetic diagnosis and treatment.

[0003] The skin detection technology in the medical and aesthetic field mainly uses optical imaging as the main detection means. Among them, the multi-spectral imaging technology penetrates different layers of skin through visible light, ultraviolet light and other multi-band light sources, and combines magnifying imaging to present the microscopic structure of the epidermis to the dermis layer, such as pigment distribution and microvascular network. Some systems can also filter out surface reflected light through polarization mode to reveal potential lesions in the dermal papillary layer; optical coherence tomography (OCT) uses near-infrared light interference principle to generate skin cross-sectional images; in addition, high-frequency ultrasound and other technologies can also distinguish the density difference of each layer of skin tissue through echo difference. SUMMARY

[0004] The purpose of the present application is to provide a skin layering recognition method, device and computer readable storage medium, which aims to solve the problem of difficulty in implementing skin layering recognition in the prior art.

[0005] To solve the above technical problems, the first aspect of the present application provides a skin layering recognition method, which comprises: acquiring a skin layering image to be processed; performing layering recognition on the skin layering image to be processed to identify a target detection area; the target detection area includes an epidermis layer area, a dermis layer area and a subcutaneous tissue area; wherein the subcutaneous tissue area includes a fat layer area and a fascia layer area; determining the fat layer content according to the fat layer area and the subcutaneous tissue area; and / or determining the fascia layer distance according to the fascia layer area and the epidermis layer area; and / or determining the fascia layer tightness according to the fascia layer area and the subcutaneous tissue area.

[0006] In an embodiment, determining the fat layer content according to the fat layer area and the subcutaneous tissue area comprises: determining the area ratio of the fat layer area in the subcutaneous tissue area as the fat layer content.

[0007] In an embodiment, the fascia layer distance is determined according to the fascia layer region and the epidermis layer region, including: determining a fascia layer centroid corresponding to the fascia layer region and an epidermis layer centroid corresponding to the epidermis layer region; and determining the fascia layer distance based on a vertical distance between the fascia layer centroid and the epidermis layer centroid.

[0008] In an embodiment, the fascia layer tightness is determined according to the fascia layer region and the subcutaneous tissue region, including: determining a ratio of an area of the fascia layer region in the subcutaneous tissue region as the fascia layer tightness.

[0009] In an embodiment, the method further includes: determining an epidermis layer thickness according to the epidermis layer region; and / or determining a dermis layer density and / or a dermis layer thickness according to the dermis layer region; and / or determining a subcutaneous tissue thickness according to the subcutaneous tissue region.

[0010] In an embodiment, the dermis layer density is determined according to the dermis layer region, including: determining a ratio of pixels with a pixel value greater than a set threshold in the dermis layer region to a total number of pixels in the dermis layer region as the dermis layer density.

[0011] In an embodiment, before the ratio of pixels with a pixel value greater than a set threshold in the dermis layer region to a total number of pixels in the dermis layer region is determined as the dermis layer density, the method further includes: determining pixels with a pixel value greater than a set threshold in the dermis layer region as selected pixels; calculating a pixel distance between each selected pixel and a surrounding selected pixel; determining selected pixels with a pixel distance greater than a set distance threshold as noise points; and determining a ratio of the selected pixels after removing the noise points to a total number of pixels in the dermis layer region as the dermis layer density.

[0012] To solve the above technical problems, a second aspect of the present application provides a skin layer identification device, which includes a processor and a memory coupled with each other; the memory stores a computer program, and the processor is configured to execute the computer program to implement the steps of the method provided in the first aspect.

[0013] To solve the above technical problems, a third aspect of the present application provides a computer readable storage medium, which stores program data, and the program data is executed by a processor to implement the steps of the method provided in the first aspect.

[0014] The embodiment of the present application has the following beneficial effects: Different from the prior art, the present application obtains a skin layer image to be processed and skin elasticity information, performs layer identification on the skin layer image to be processed to identify a target detection area, the target detection area includes an epidermis layer area, a dermis layer area and a subcutaneous tissue area, the subcutaneous tissue area includes a fat layer area and a fascia layer area, the fat layer content is determined according to the fat layer area and the subcutaneous tissue area, the fascia layer distance is determined according to the fascia layer area and the epidermis layer area, and the fascia layer tightness is determined according to the fascia layer area and the subcutaneous tissue area, and the skin layer image to be processed is displayed by elasticity imaging according to the elasticity information. The embodiment of the present application realizes parameter detection of skin tissue in layers, facilitates evaluation of skin state, and facilitates development of a personalized skin management scheme according to various skin parameter information. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort.

[0016] In the formula, the parameters are as follows:

[0017] Figure 1 is a flowchart of an embodiment of the skin layer identification method of the present application;

[0018] Figure 2 is a schematic diagram of an embodiment of the skin layer image to be processed of the present application;

[0019] Figure 3 is a flowchart of an embodiment of the step S13 of determining the fascia layer distance of the present application;

[0020] Figure 4 is a schematic diagram of an embodiment of left cheek elasticity imaging;

[0021] Figure 5 is a schematic diagram of an embodiment of right cheek elasticity imaging;

[0022] Figure 6 is a schematic diagram of another embodiment of left cheek elasticity imaging;

[0023] Figure 7 is a schematic diagram of still another embodiment of left cheek elasticity imaging;

[0024] Figure 8 is a schematic diagram of yet another embodiment of left cheek elasticity imaging;

[0025] Figure 9 is a flowchart diagram of an embodiment of the present application for determining epidermis layer thickness;

[0026] Figure 10 is a flowchart diagram of an embodiment of the present application for determining subcutaneous tissue thickness;

[0027] Figure 11 is a flowchart diagram of an embodiment of the present application for determining dermis layer density;

[0028] Figure 12 is a flowchart diagram of an embodiment of the present application for determining dermis layer thickness;

[0029] Figure 13 is a result image of an embodiment of the present application for pre-auricular skin layering identification;

[0030] Figure 14 is a result image of an embodiment of the present application for right lower mandibular margin inferior skin layering identification;

[0031] Figure 15 is a result image of an embodiment of the present application for right lower mandibular margin inferior skin layering identification; Figure 14 is a flowchart diagram of an embodiment of the present application for processing a skin layering image;

[0032] Figure 16 is a flowchart diagram of an embodiment of the present application for processing a skin layering image; Figure 14 is a flowchart diagram of an embodiment of the present application for processing a skin layering image;

[0033] Figure 17 is a result image of an embodiment of the present application for left lower mandibular margin superior skin layering identification;

[0034] Figure 18 is a flowchart diagram of an embodiment of the present application for processing a skin layering image; Figure 17

[0035] is a flowchart diagram of an embodiment of the present application for processing a skin layering image; Figure 19 Figure 17 is a flowchart diagram of an embodiment of the present application for processing a skin layering image;

[0036] Figure 20 is a block diagram of an embodiment of the skin layering identification apparatus of the present application;

[0037] Figure 21 is a block diagram of an embodiment of the skin layering identification apparatus of the present application;

[0038] Figure 22 is a block diagram of an embodiment of the computer readable storage medium of the present application. DETAILED DESCRIPTION

[0039] ​With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments of the present application, all the other embodiments obtained by a person of ordinary skill in the art without creative effort belong to the scope of the present application.

[0040] The terms "first", "second", etc. in the present application are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the technical features indicated. Therefore, the features defined with "first", "second", etc. can explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "a plurality of" is at least two, for example, two, three, etc., unless otherwise explicitly and specifically limited. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed or can optionally include other steps or units inherent to the process, method, product or device.

[0041] In this document, the term "embodiment" means that the specific features, structures or characteristics described in connection with the embodiment can be included in at least one embodiment of the present application. The phrase appears at various places in the specification does not necessarily all refer to the same embodiment, nor is it necessarily independent or alternative embodiments to each other. A person of ordinary skill in the art explicitly and implicitly understands that the embodiments described herein can be combined with other embodiments.

[0042] Please refer to Figure 1 , Figure 1 is a flowchart of an embodiment of the skin layer identification method of the present application. It should be noted that the present embodiment is not limited to the order of the flowchart shown in Figure 1 . The skin layer identification method of the present embodiment includes the following steps S11-S14:

[0043] S11: Obtain the skin layer image to be processed and the skin elasticity information.

[0044] The skin layer image to be processed, for example, is an ultrasonic image generated by scanning the skin to be detected of a subject by ultrasonic waves. The skin layer image generated by the above means is a longitudinal section image that can display the layered structure of the skin from the epidermis layer (keratin layer) to the deep layer (subcutaneous tissue).

[0045] In the skin layer image obtained by the standard operation, the skin tissue layers are arranged from top to bottom as follows: epidermis layer, dermis layer and subcutaneous tissue layer. Among them, the subcutaneous tissue layer is located below the dermis layer and above the superficial fascia, and is partially intermingled with the superficial fascia; the subcutaneous tissue layer is composed of fat layer, loose connective tissue, micro blood vessels and nerves, and mainly functions to connect the skin and deep tissues and support the fat layer; the fat layer is the main part of the subcutaneous tissue layer, mainly composed of adipocytes and a small amount of fibers; the fascia layer is located in the deep layer of the subcutaneous tissue and is intermingled with the subcutaneous tissue.

[0046] For example, refer to Figure 2 , Figure 2 is a schematic diagram of an embodiment of the skin layer image to be processed in the present application. Different skin tissue layers exhibit different image textures, Figure 2 As can be seen from the three layers of skin tissue structure arranged from top to bottom, the skin tissue layers from top to bottom are epidermis layer 100, dermis layer 200 and subcutaneous tissue layer 300.

[0047] Among them, the skin elasticity information can be obtained by transmitting a shear wave to the skin through an ultrasonic transmitting probe. The shear wave propagates at different speeds in skin tissues with different elasticity. The skin tissue with good elasticity propagates faster. Therefore, the skin elasticity information can be inversely deduced according to the propagation speed of the shear wave. The skin elasticity information is, for example, an elasticity value obtained according to the propagation speed of the shear wave.

[0048] Through subsequent step identification and processing of the skin layer image, the skin condition can be detected.

[0049] S12: Layered identification is performed on the skin layer image to be processed to identify a target detection area; the target detection area includes epidermis layer area, dermis layer area and subcutaneous tissue area, wherein the subcutaneous tissue area contains fat layer area and fascia layer area.

[0050] Specifically, the embodiment can use a trained region identification model to perform layered identification on the skin layer image to be processed, and mark the target detection area. For example, an improved U-Net semantic segmentation model can be used to perform layered identification on the preprocessed image. Specifically, the improved U-Net semantic segmentation model can add a multi-scale residual module in the encoder part to capture the subtle features of different skin tissue layers, and add an attention mechanism in the decoder part to strengthen the identification of the boundary between the epidermis layer area and the dermis layer area, and the boundary between the dermis layer area and the subcutaneous tissue area. Further, a weighted sum of cross-entropy loss function and Dice loss function is used as the loss function of the model, and the U-Net semantic segmentation model is trained. The trained model can be used as a region identification model in step S12 to perform layered identification on the skin layer image to be processed.

[0051] In one embodiment, during the training phase of the region recognition model, corresponding spatial ranges are defined for the epidermis, dermis, subcutaneous tissue, fat layer, and fascia layer. The deviation between the boundary of the target detection region predicted by the region recognition model and the defined spatial range is incorporated into the loss function and used to train the region recognition model. In this way, the location of the target detection region detected by the region recognition model through layered identification of the skin tomographic image under processing is more accurate.

[0052] In one embodiment, before step S12, the skin tomographic image to be processed can be preprocessed to denoise and enhance the image, making the recognition result of the target detection area more accurate. For example, for ultrasound images, a speckle noise suppression algorithm can be used to denoise the skin tomographic image.

[0053] S13: Determine the fat layer content based on the fat layer region and the subcutaneous tissue region; and / or, determine the fascial layer distance based on the fascial layer region and the epidermal layer region; and / or, determine the fascial layer tightness based on the fascial layer region and the subcutaneous tissue region.

[0054] In one embodiment, the fat layer content can be determined by the ratio of the fat layer area to the subcutaneous tissue area. Specifically, the area of ​​the fat layer area and the area of ​​the subcutaneous tissue area can be calculated separately, and the fat layer content can be calculated according to the following formula: Fat layer content = (Area of ​​fat layer area / Area of ​​subcutaneous tissue area) × 100%.

[0055] In one embodiment, please refer to [reference needed]. Figure 3 , Figure 3 This is a schematic flowchart illustrating an embodiment of step S13 of this application, which determines the distance to the fascia layer. It should be noted that if substantially the same result is obtained, this embodiment does not necessarily reflect that outcome. Figure 3 The sequence of processes shown is limited. This embodiment determines the fascial layer distance using the following steps S31–S32:

[0056] S31: Determine the centroid of the fascia layer corresponding to the fascia layer region and the centroid of the epidermis layer corresponding to the epidermis layer region. Specifically, pixel coordinates can be extracted from the identified epidermis layer region and fascia layer region respectively to obtain the epidermis layer pixel set {(x 11 ,y 11 ),(x 12 ,y 12 ),…,(x 1n ,y 1n )} and fascia layer pixel set

[0057] {(x 21 ,y 21 ),(x 22 ,y 22 ),…,(x2m ,y 2m )}.

[0058] The centroid of the epidermis is calculated using the following formula:

[0059]

[0060] Among them, C x1 C y1 These are the x and y coordinates of the centroid of the epidermis, respectively. 1i ,y 1i ) represents the coordinates of the pixels in the epidermal region, and n represents the total number of pixels in the epidermal region.

[0061] The centroid of the fascia layer is calculated using the following formula:

[0062]

[0063] Among them, C x2 C y2 Let x and y be the x and y coordinates of the centroid of the fascia layer, respectively. 2j ,y 2j ) represents the coordinates of the pixels in the fascia layer region, and m represents the total number of pixels in the fascia layer region.

[0064] S32: Determine the fascial layer distance based on the vertical distance between the centroid of the fascial layer and the centroid of the epidermal layer.

[0065] The vertical distance between the centroids of the fascia layer and the epidermal layer can be calculated by the difference in their ordinates, and then the fascial distance D1 can be calculated using the following formula:

[0066] D1=d1×r

[0067] In the above formula, d1 is the difference in the vertical coordinate between the centroid of the fascia layer and the centroid of the epidermis layer, and r is the vertical resolution of the tomographic image of the skin to be processed.

[0068] In one embodiment, step S13, determining the fascial layer tightness based on the fascial layer region and the subcutaneous tissue region, includes: determining the area ratio of the fascial layer region to the subcutaneous tissue region as the fascial layer tightness. Specifically, the area of ​​the fascial layer region and the area of ​​the subcutaneous tissue region can be calculated separately, and the fascial layer tightness can be calculated according to the following formula: Fascial layer tightness = (Fascial layer region area / Subcutaneous tissue region area) × 100%.

[0069] S14: Display the tomographic image of the skin to be processed using elasticity imaging based on the elasticity information.

[0070] This process involves using color to differentiate regions of the skin tomographic image based on their elasticity values. A continuous color gradient map is then generated, displaying regions with lower elasticity using warmer colors and those with higher elasticity using cooler colors, or vice versa. This can be customized to meet specific needs. By converting the skin's elasticity information into a visible light image, the mechanical properties of the tissue can be determined, leading to the assessment of the corresponding elasticity coefficient.

[0071] Please see Figures 4-8 , Figure 4 This is a schematic diagram of an embodiment of left cheek elastography. Figure 4 The two images are displayed side by side. The image on the left is a cross-sectional image of the skin on the left cheek, and the image on the right is an elastography image of the left cheek. The elastomer coefficient assessment result is 71.1%.

[0072] Figure 5 This is a schematic diagram of an embodiment of right cheek elastography. Figure 5 The two images are displayed side by side. The image on the left is a cross-sectional image of the skin on the right cheek, and the image on the right is an elastography image of the right cheek. The elastomer coefficient assessment result is 71.5%.

[0073] Figure 6 This is a schematic diagram of another embodiment of elastography on the left cheek. Figure 6 The two images are displayed side by side. The image on the left is a cross-sectional image of the skin on the left cheek, and the image on the right is an elastography image of the left cheek. The elastomer coefficient assessment result is 87.9%.

[0074] Figure 7 This is a schematic diagram of yet another embodiment of elastography on the left cheek. Figure 7 The two images are displayed side by side. The image on the left is a cross-sectional image of the skin on the left cheek, and the image on the right is an elastography image of the left cheek. The elastomer coefficient assessment result is 67.5%.

[0075] Figure 8 This is a schematic diagram of another embodiment of left cheek elastography. Figure 8 The two images are displayed side by side. The image on the left is a cross-sectional image of the skin on the left cheek, and the image on the right is an elastography image of the left cheek. The elastomer coefficient assessment result is 76.1%.

[0076] Through the above methods, this application can realize the parameter detection of each layer of skin tissue of the subject, obtain various skin information, and is convenient to operate, highly accurate, easy to assess skin condition, and easy to formulate personalized skin management plan based on various skin parameter information.

[0077] In one embodiment, step S13 may further determine the epidermal layer thickness based on the epidermal layer region. See also... Figure 9 , Figure 9 This is a schematic flowchart illustrating an embodiment of determining epidermal thickness according to this application. In this embodiment, determining the epidermal thickness based on the epidermal region may include the following steps S41 to S42:

[0078] S41: Identify the upper and lower boundaries of the epidermal region.

[0079] It should be understood that "up" and "down" here are based on Figure 1 The image shown is a cross-sectional view of the skin. The upper boundary is the boundary of the epidermal region near the outer side of the skin (the side in contact with air), and the lower boundary is the boundary of the epidermal region near the inner side of the skin (the side away from air).

[0080] S42: Determine the epidermal thickness based on the distance between the upper boundary and the lower boundary of the epidermal region.

[0081] In one embodiment, the distance between the upper and lower boundaries of the epidermal region can be determined by the difference between the average ordinate of all pixels at the upper boundary of the epidermal region and the average ordinate of all pixels at the lower boundary of the epidermal region. In another embodiment, the distance can be determined by the difference between the maximum ordinate of all pixels at the upper boundary of the epidermal region and the maximum ordinate of all pixels at the lower boundary of the epidermal region. Alternatively, the distance can be determined by the difference between the minimum ordinate of all pixels at the upper boundary of the epidermal region and the minimum ordinate of all pixels at the lower boundary of the epidermal region. After determining the distance between the upper and lower boundaries of the epidermal region using the above methods, the epidermal thickness D2 is further determined by the following formula:

[0082] D2=d2×r

[0083] In the above formula, d2 is the distance between the upper boundary and the lower boundary of the epidermal region, and r is the longitudinal resolution of the tomographic image of the skin to be processed.

[0084] In one embodiment, step S13 may further determine the subcutaneous tissue thickness based on the subcutaneous tissue region. See also... Figure 10 , Figure 10 This is a schematic flowchart illustrating an embodiment of determining subcutaneous tissue thickness according to this application. In this embodiment, determining the subcutaneous tissue thickness based on the subcutaneous tissue region may include the following steps S51-S52:

[0085] S51: Identify the upper and lower boundaries of the subcutaneous tissue region.

[0086] It should be understood that "up" and "down" here are based on Figure 1 The image shown is a cross-sectional image of the skin. The upper boundary is the boundary of the subcutaneous tissue area closer to the dermis, and the lower boundary is the boundary of the subcutaneous tissue area away from the dermis.

[0087] S52: Determine the subcutaneous tissue thickness based on the distance between the upper boundary and the lower boundary of the subcutaneous tissue region.

[0088] In one embodiment, the distance between the upper and lower boundaries of the subcutaneous tissue region can be determined by the difference between the average ordinate of all pixels at the upper boundary and the average ordinate of all pixels at the lower boundary. In another embodiment, the distance can be determined by the difference between the maximum ordinate of all pixels at the upper boundary and the maximum ordinate of all pixels at the lower boundary. Alternatively, the distance can be determined by the difference between the minimum ordinate of all pixels at the upper boundary and the minimum ordinate of all pixels at the lower boundary. After determining the distance between the upper and lower boundaries of the subcutaneous tissue region using the above methods, the subcutaneous tissue thickness D3 is further determined by the following formula:

[0089] D3=d3×r

[0090] In the above formula, d3 is the distance between the upper boundary and the lower boundary of the subcutaneous tissue region, and r is the longitudinal resolution of the tomographic image of the skin to be processed.

[0091] In one embodiment, step S13 may further determine the dermal density based on the dermal region.

[0092] In one embodiment, the dermal density can be determined as the proportion of pixels with a value greater than a set threshold in the dermal region of the total number of pixels in the dermal region. Specifically, pixels with a value greater than the set threshold in the dermal region are identified as selected pixels, and the proportion of the number of selected pixels to the total number of pixels in the dermal region is determined as the dermal density.

[0093] The threshold can be set according to differences in imaging methods or other factors, and is not limited here.

[0094] Please see Figure 11 , Figure 11 This is a schematic flowchart illustrating an embodiment of determining dermal density according to this application. This embodiment, determining dermal density based on a dermal region, may include the following steps S61 to S64:

[0095] S61: Select pixels in the dermal region whose pixel values ​​are greater than a set threshold.

[0096] The threshold can be set according to your needs; there are no strict limitations here.

[0097] S62: Calculate the pixel distance between each selected pixel and its surrounding selected pixels.

[0098] This step calculates the distance between each selected pixel and its surrounding selected pixels, treating each selected pixel as the target pixel. The distance can be calculated using methods such as Euclidean distance, Manhattan distance, or Chebyshev distance.

[0099] S63: Identify selected pixels whose pixel distance is greater than a set distance threshold as noise.

[0100] The distance threshold can be set according to actual needs, such as a distance of 3 pixels, a distance of 5 pixels, etc.

[0101] S64: The proportion of the selected pixels after noise removal in the total number of pixels in the dermal region is determined as the dermal density.

[0102] In this embodiment, selected pixels that are greater than a set distance threshold from surrounding selected pixels are identified as noise. The remaining selected pixels after removing noise are then identified as valid pixels for calculating dermal density. This minimizes false detections of noise generated by detecting epidermal impurities, blood vessels, etc., thereby improving the accuracy of dermal density detection.

[0103] In one embodiment, step S13 may further determine the dermal layer thickness based on the dermal layer region. See also... Figure 12 , Figure 12 This is a schematic flowchart illustrating an embodiment of determining dermal thickness according to this application. In this embodiment, determining the dermal thickness based on the subcutaneous tissue region may include the following steps S71-S72:

[0104] S71: Identify the upper and lower boundaries of the dermal region.

[0105] It should be understood that "up" and "down" here are based on Figure 1 The image shown is a cross-sectional image of the skin. The upper boundary is the boundary of the dermal region on the side closer to the dermis, and the lower boundary is the boundary of the dermal region on the side farther from the dermis.

[0106] S72: Determine the dermal thickness based on the distance between the upper boundary and the lower boundary of the dermal region.

[0107] In one embodiment, the distance between the upper and lower boundaries of the dermal region can be determined by the difference between the average ordinate of all pixels at the upper boundary of the dermal region and the average ordinate of all pixels at the lower boundary of the dermal region. In another embodiment, the distance can be determined by the difference between the maximum ordinate of all pixels at the upper boundary of the dermal region and the maximum ordinate of all pixels at the lower boundary of the dermal region. Alternatively, the distance can be determined by the difference between the minimum ordinate of all pixels at the upper boundary of the dermal region and the minimum ordinate of all pixels at the lower boundary of the dermal region. After determining the distance between the upper and lower boundaries of the dermal region using the above methods, the dermal thickness D4 is further determined by the following formula:

[0108] D4 = d4 × r

[0109] In the above formula, d4 is the distance between the upper boundary and the lower boundary of the dermal region, and r is the longitudinal resolution of the tomographic image of the skin to be processed.

[0110] Unlike existing technologies, this application can detect the epidermal layer, subcutaneous tissue layer, fat layer, fascia layer, and dermal layer using the methods described in the above embodiments. Then, based on the identified skin tissue areas, indicators such as fat layer content, fascia layer distance, fascia layer tightness, epidermal layer thickness, dermal layer density, dermal layer thickness, and subcutaneous tissue thickness are determined. These indicators can be used to assist in assessing skin condition and cosmetic effects, and can also provide reliable reference data for the development of personalized skin management plans.

[0111] In one embodiment, the fat layer content, fascia layer distance, fascia layer tightness, epidermal layer thickness, dermal layer density, dermal layer thickness, and subcutaneous tissue thickness obtained from skin tissue layer identification are displayed on an electronic display screen along with the skin tomographic image. This visualizes the skin layer identification parameters, making the skin tissue layer identification results more intuitive and facilitating the combined judgment of the subject's skin condition by combining the image and various parameters.

[0112] Please see Figure 13 , Figure 13 This is a result image of an embodiment of facial anterior tragus skin layer recognition. It shows that the epidermis layer thickness on the subject's right anterior tragus is 0.3 mm, with an area of ​​15.3 square millimeters; the dermis layer thickness is 1.9 mm, with an area of ​​69.7 square millimeters; the subcutaneous tissue thickness is 3.4 mm, with an area of ​​118.7 square millimeters; and the fascia layer distance is 3.9 mm. The dermis layer thickness accounts for 74%, the dermis layer density is 86.7%, the fat layer content is 51.2%, and the fascia layer tightness is 48.8%.

[0113] Please refer to the following: Figures 14-16 , Figure 14 This is a result image of an embodiment of skin layer recognition on the lower side of the right mandibular border. Figure 15 yes Figure 14 A schematic diagram of an embodiment of the skin tomography image recognition process to be processed. Figure 16 yes Figure 14 This is a schematic diagram of another embodiment of the skin tomographic image recognition process. The recognition results show that the epidermis on the lower right side of the subject's mandible is 0.3 mm thick with an area of ​​14 square millimeters, the dermis is 1.3 mm thick with an area of ​​48.1 square millimeters, the subcutaneous tissue is 3.5 mm thick with an area of ​​145.4 square millimeters, and the fascia layer is 3.3 mm in distance. The dermis accounts for 54.5% of the thickness, has a density of 85.6%, a fat layer content of 60%, and a fascia layer tightness of 40%.

[0114] Please refer to the following: Figures 17-19 , Figure 17 This is a result image of an embodiment of skin layer recognition on the upper side of the left mandibular border. Figure 18 yes Figure 17 A schematic diagram of an embodiment of the skin tomography image recognition process to be processed. Figure 19 yes Figure 17 This is a schematic diagram of another embodiment of the skin tomographic image recognition process. The recognition results show that the epidermis on the upper side of the left mandibular border of the subject has a thickness of 0.3 mm and an area of ​​14.9 square millimeters; the dermis has a thickness of 1.5 mm and an area of ​​58.8 square millimeters; the subcutaneous tissue has a thickness of 4 mm and an area of ​​155.4 square millimeters; and the fascia layer distance is 3.8 mm. The dermis layer thickness accounts for 64.1%, the dermis layer density is 86.4%, the fat layer content is 66.2%, and the fascia layer tightness is 33.8%.

[0115] Please see Figure 20 , Figure 20 This is a schematic block diagram of an embodiment of the skin layer recognition device of this application. The skin layer recognition device 900 includes a processor 910 and a memory 920 coupled to each other. The memory 920 stores a computer program, and the processor 910 is used to execute the computer program to implement the skin layer recognition method described in the above embodiments.

[0116] For a description of each step of the processing, please refer to the description of each step in the above embodiment of the skin layer recognition method of this application, and it will not be repeated here.

[0117] The memory 920 can be used to store program data and modules. The processor 910 executes various functional applications and data processing by running the program data and modules stored in the memory 920. The memory 920 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as image processing functions, data processing functions, etc.), etc.; the data storage area may store data created based on the use of the skin layer recognition device 900 (such as pixel coordinate data, parameters of each skin tissue layer, etc.). In addition, the memory 920 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 920 may also include a memory controller to provide the processor 910 with access to the memory 920.

[0118] Please see Figure 21 , Figure 21 This is a schematic block diagram of another embodiment of the skin layer recognition device of this application. The skin layer recognition device 800 includes a display 830, a processor 810, and a memory 820 coupled to each other. The memory 820 stores a computer program. The processor 810 is used to execute the computer program to implement the skin layer recognition method described in the above embodiments. The display 830 is used to display skin tomographic images and the detection results of skin parameters such as fat layer content, fascia layer distance, fascia layer tightness, epidermal layer thickness, dermal layer density, dermal layer thickness, and subcutaneous tissue thickness.

[0119] In the various embodiments of this application, the disclosed methods, apparatus, and devices can be implemented in other ways. For example, the embodiments of the skin layer recognition device described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms.

[0120] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0121] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0122] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium.

[0123] See Figure 22 , Figure 22 This is a schematic block diagram of a computer-readable storage medium according to an embodiment of the present application. The computer-readable storage medium 700 stores program data 710, which, when executed, implements the steps of the skin layer recognition method embodiments described above.

[0124] For a description of each step of the processing, please refer to the description of each step in the above embodiment of the skin layer recognition method of this application, and it will not be repeated here.

[0125] The computer-readable storage medium 700 can be any medium capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0126] The above description discloses only preferred embodiments of the present invention and should not be construed as limiting the scope of the present invention. Therefore, equivalent variations made in accordance with the claims of the present invention are still within the scope of the present invention.

Claims

1. A method for skin layer recognition, characterized in that, The method includes: Acquire tomographic images of the skin to be processed and skin elasticity information; The to-doped image of the skin to be processed is subjected to layer recognition to identify the target detection area; the target detection area includes the epidermal layer, the dermal layer, and the subcutaneous tissue area; wherein, the subcutaneous tissue area includes the fat layer and the fascia layer. The fat layer content is determined based on the fat layer region and the subcutaneous tissue region; and / or, Determine the fascial distance based on the fascial layer region and the epidermal layer region; and / or, The tightness of the fascia layer is determined based on the fascia layer region and the subcutaneous tissue region; Based on the elasticity information, the tomographic image of the skin to be processed is displayed using elastic imaging.

2. The skin layer recognition method according to claim 1, characterized in that, Determining the fat layer content based on the fat layer region and the subcutaneous tissue region includes: The fat layer content is defined as the area ratio of the fat layer region to the subcutaneous tissue region.

3. The skin layer recognition method according to claim 1, characterized in that, Determining the fascial distance based on the fascial layer region and the epidermal layer region includes: Determine the centroid of the fascia layer corresponding to the fascia layer region and the centroid of the epidermis layer corresponding to the epidermis layer region; The distance of the fascia layer is determined based on the vertical distance between the centroid of the fascia layer and the centroid of the epidermis layer.

4. The skin layer recognition method according to claim 1, characterized in that, Determining the tightness of the fascia layer based on the fascia layer region and the subcutaneous tissue region includes: The area ratio of the fascia layer region to the subcutaneous tissue region is determined as the fascia layer tightness.

5. The skin layer recognition method according to claim 1, characterized in that, The method further includes: The epidermal thickness is determined based on the epidermal region; and / or, Determine the dermal density and / or dermal thickness based on the dermal region; and / or, The thickness of the subcutaneous tissue is determined based on the subcutaneous tissue region.

6. The skin layer recognition method according to claim 5, characterized in that, Determining the dermal density based on the dermal region includes: The dermal density is defined as the proportion of pixels in the dermal region whose pixel value is greater than a set threshold among the total pixels in the dermal region.

7. The skin layer recognition method according to claim 6, characterized in that, Before determining the proportion of pixels with pixel values ​​greater than a set threshold in the dermal region as the dermal density, the method further includes: In the dermal region, pixels with pixel values ​​greater than a set threshold are identified as selected pixels; Calculate the pixel distance between each selected pixel and its surrounding selected pixels; Selected pixels whose pixel distance is greater than a set distance threshold are identified as noise. The step of determining the proportion of pixels with pixel values ​​greater than a set threshold in the dermal region as the dermal density includes: determining the proportion of the selected pixels after removing the noise in the total pixels in the dermal region as the dermal density.

8. A skin layer recognition device, characterized in that, The skin layer recognition device includes a processor and a memory coupled to each other; the memory stores a computer program, and the processor executes the computer program to implement the steps of the method as described in any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores program data that, when executed by a processor, implements the steps of the method as described in any one of claims 1-7.

Images