Melanin aging evaluation method based on skins with different depths

Abstract

The invention relates to a melanin aging evaluation method based on skins with different depths. The melanin aging evaluation method comprises the following steps: acquiring an ultrasonic image of a skin cross section structure and a photoacoustic image containing melanin photoacoustic signals; performing skin boundary positioning and extraction on the ultrasonic image; based on the boundary relation between the ultrasonic image and the photoacoustic image, the skin boundary of the ultrasonic image and the photoacoustic image is set to the same height, the ultrasonic image and the photoacoustic image are fused, and a three-dimensional image is obtained through reconstruction and used for researching melanin space distribution at different depth positions; based on the distribution characteristics of melanin photoacoustic signals along with the depth of the skin, the skin is divided into three anatomical characteristic areas of a keratinization layer (I), a basal layer (II) and a dermal superficial layer (III); respectively calculating the melanin deposition rate of the keratinization layer, the melanin metabolism rate of the substrate layer and the melanin content of the dermal superficial layer; and comprehensively evaluating the skin aging degree by combining a calculation result. The method can improve the accuracy of aging degree evaluation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of dermatological detection, and particularly relates to a melanin aging evaluation method based on different depths of skin. BACKGROUND

[0002] Melanin in the skin is a chromophore that dominates light absorption characteristics, and its total amount and depth distribution has a key influence on skin color presentation, chloasma formation and skin aging process. At present, quantitative analysis of skin melanin mainly relies on the following technologies:

[0003] (1) Individual Typology Angle (ITA) parameter based on the International Commission on Illumination (CIE) Lab* color space, which evaluates skin color through visible and near-infrared reflectance spectroscopy. However, this method can only measure skin surface color information, cannot obtain real melanin content and high-resolution spatial distribution characteristics at different depths, and is easily affected by operator subjective differences.

[0004] (2) Depth-resolved imaging of melanin using photoacoustic imaging technology. Although photoacoustic imaging technology can achieve depth-resolved imaging of melanin, it has wavelength-related limitations and does not clearly quantify the aging characteristics of melanin.

[0005] Therefore, it is urgent to develop an analysis method that can accurately measure the distribution of skin melanin at different depths and quantify the degree of aging. SUMMARY

[0006] The purpose of the present application is to provide a melanin aging evaluation method based on different depths of skin, which can improve the accuracy of aging degree evaluation.

[0007] In order to achieve the above purpose, the technical solution adopted by the present application is: a melanin aging evaluation method based on different depths of skin, comprising the following steps:

[0008] (1) obtaining an ultrasound image of the cross-sectional structure of the skin and a photoacoustic image containing a melanin photoacoustic signal;

[0009] (2) locating and extracting the skin boundary of the ultrasound image through a deep learning convolutional neural network based on the U-Net architecture;

[0010] (3) based on the boundary relationship between the ultrasound image and the photoacoustic image, setting the skin boundaries of the ultrasound image and the photoacoustic image to the same height, fusing the ultrasound image and the photoacoustic image, and reconstructing a three-dimensional image for studying the spatial distribution of melanin at different depths;

[0011] (4) Based on the distribution characteristics of melanin photoacoustic signals with skin depth, the skin is divided into three anatomical characteristic regions: stratum corneum (I), stratum basale (II), and superficial dermis (III);

[0012] (5) Calculate the melanin deposition rate of the stratum corneum, the melanin metabolism rate of the basal layer, and the melanin content of the superficial dermis;

[0013] (6) The degree of skin aging is comprehensively evaluated by combining the melanin deposition rate of the stratum corneum, the melanin metabolism rate of the basal layer, and the melanin content of the superficial dermis.

[0014] Furthermore, in step (1), an ultrasonic image of the cross-sectional structure of the skin in a set area is collected by an ultrasonic imaging unit; at the same time, a photoacoustic excitation unit is used to emit a pulsed laser of a set wavelength to irradiate the skin in the same area to excite the melanin photoacoustic signal, and the corresponding photoacoustic image is collected by the ultrasonic imaging unit.

[0015] Furthermore, the ultrasonic imaging unit adopts a 60MHz high-frequency ultrasonic probe; the photoacoustic excitation unit adopts a pulsed laser light source with a wavelength of 650nm, and the pulsed laser with a wavelength of 650nm corresponds to the absorption peak of melanin.

[0016] Furthermore, in step (1), the ultrasound image and the photoacoustic image are collected synchronously at the same position.

[0017] Furthermore, in step (3), since the ultrasound image and the photoacoustic image are collected synchronously at the same position, the skin surface boundary extracted from the ultrasound image is the skin boundary in the photoacoustic image.

[0018] Furthermore, in step (4), the interval above the median line of the difference between the maximum and minimum values ​​of the melanin photoacoustic signal distribution curve with skin depth is divided into the basal layer (II), and the two sides of the basal layer (II) are the keratinized layer (I) and the superficial dermis (III).

[0019] Furthermore, in step (5), the relationship between the melanin deposition rate of the stratum corneum and the photoacoustic intensity of the stratum corneum and age is established according to the following formula:

[0020] PA1=C0·ln[γ age ·T]

[0021]

[0022] Among them, γ agerepresents the melanin deposition rate of the stratum corneum; T represents age; PA1 represents the total photoacoustic intensity of the stratum corneum; I1(x1, y1, z1) represents the photoacoustic signal intensity at each position (x1, y1, z1) of the stratum corneum, and its absorption coefficient μ at the position (x1, y1, z1) a1 is linearly proportional to μ a1 It is linearly related to the volume fraction of melanin in the stratum corneum, so PA1 can reflect the content of melanin in the stratum corneum; C0 is the setting parameter, C0 = PA 1,0 , of which PA 1,0 It represents the total photoacoustic intensity of the stratum corneum when the baby is just born; the melanin deposition rate of the stratum corneum can be calculated by the above formula;

[0023] The relationship between the melanin metabolism rate of the basal layer, the photoacoustic intensity of the basal layer, and the skin ITA value is established according to the following formula:

[0024] PA2=C1exp[γ ita °·ITA°]

[0025]

[0026] Among them, γ ita ° represents the melanin metabolism rate of the basal layer; ITA° represents the skin ITA value; PA2 represents the total photoacoustic intensity of the basal layer, I2(x2, y2, z2) represents the photoacoustic signal intensity at each position (x2, y2, z2) in the basal layer, and its absorption coefficient μ at the position (x2, y2, z2) a2 is linearly proportional to μ a2 It is linearly related to the volume fraction of melanin in the basal layer, so PA2 can reflect the content of melanin in the basal layer; C1 is the setting parameter, C1 = PA 2,0 , of which PA 2,0 It represents the total photoacoustic intensity of the basal layer when the baby is just born; the melanin metabolism rate of the basal layer can be calculated by the above formula;

[0027] The calculation formula of the melanin content in the superficial dermis is as follows:

[0028]

[0029] Where PA3 represents the total photoacoustic intensity of the superficial dermis, I3(x3, y3, z3) represents the photoacoustic signal intensity at each position (x3, y3, z3) in the superficial dermis, and its absorption coefficient μ at the position (x3, y3, z3) is a3 is linearly proportional to μ a3 It is linearly related to the volume fraction of melanin in the superficial dermis, so PA3 can reflect the content of melanin in the superficial dermis.

[0030] Furthermore, in step (6), the specific method for comprehensively evaluating the degree of skin aging by combining the melanin deposition rate of the stratum corneum, the melanin metabolism rate of the basal layer, and the melanin content of the superficial dermis is as follows:

[0031] The melanin deposition rate of the stratum corneum, the melanin metabolism rate of the basal layer, and the melanin content of the superficial dermis of the skin to be evaluated are calculated, and the calculated results are compared with the melanin deposition rate of the stratum corneum, the melanin metabolism rate of the basal layer, and the melanin content of the superficial dermis of the skin of the young group. When any one of the following three conditions is met, the skin is assessed as being at level 1 aging; when any two of the following three conditions are met, the skin is assessed as being at level 2 aging; and when all three of the following conditions are met, the skin is assessed as being at level 3 aging:

[0032] 1) The melanin metabolism rate of the basal layer of the skin to be evaluated is lower than that of the basal layer of the skin of the young group;

[0033] 2) The melanin deposition rate of the stratum corneum of the skin to be evaluated is greater than the melanin deposition rate of the stratum corneum of the skin of the youth group;

[0034] 3) The melanin content of the superficial dermis of the skin to be evaluated is greater than the melanin content of the superficial dermis of the skin of the youth group.

[0035] The present invention also provides an aging assessment system for implementing the above method, comprising:

[0036] A data acquisition module, comprising an ultrasonic imaging unit and a photoacoustic excitation unit, for acquiring an ultrasonic image of the skin cross-sectional structure and a photoacoustic image containing a melanin photoacoustic signal;

[0037] An image processing module, comprising an image segmentation and extraction module and a 3D reconstruction module. The image segmentation and extraction module is used to locate and extract the skin boundary of the ultrasound image using a deep learning convolutional neural network based on the U-Net architecture. The 3D reconstruction module is used to set the skin boundary of the ultrasound image and the photoacoustic image to the same height, fuse the ultrasound image and the photoacoustic image, and reconstruct a 3D stereo image.

[0038] The data analysis module is used to divide the skin into three anatomical characteristic regions: the stratum corneum (I), the basal layer (II), and the superficial dermis (III) based on the distribution characteristics of the melanin photoacoustic signal with skin depth. The module then calculates the melanin deposition rate of the stratum corneum, the melanin metabolism rate of the basal layer, and the melanin content of the superficial dermis, and comprehensively evaluates the degree of skin aging.

[0039] The present invention also provides a computer-readable storage medium storing a computer program, wherein the computer program implements the above method when executed by a processor.

[0040] Compared with the prior art, the present application has the following beneficial effects: the present application provides an aging evaluation method based on melanin at different depths of skin, which realizes depth-resolved detection of skin melanin by high-frequency ultrasound-guided photoacoustic imaging technology, divides the skin anatomical feature area by using the depth distribution characteristics of photoacoustic signals, clearly and accurately divides the skin basal layer, keratinization layer and superficial dermis, and solves the problem that the traditional method cannot obtain the distribution of melanin at different depths; on this basis, the melanin deposition rate of the keratinization layer, the melanin metabolic rate of the basal layer and the melanin content of the superficial dermis are calculated, and then the aging degree is quantified based on these parameters, thereby improving the accuracy of the aging degree evaluation. The method can provide accurate quantitative basis for skin disease treatment, anti-aging strategy formulation and whitening and anti-aging cosmetic development, and has strong practicability and broad application prospect. BRIEF DESCRIPTION OF DRAWINGS

[0041] Figure 1 is an ultrasound image and a photoacoustic image obtained in the embodiment of the present application;

[0042] Figure 2 is an image processing result graph in the embodiment of the present application;

[0043] Figure 3 is a melanin spatial distribution graph at different depth positions in the embodiment of the present application;

[0044] Figure 4 is a comparison graph of the melanin deposition rate of the keratinization layer between the young group (20-29 years old) and the old group (50-59 years old) in the embodiment of the present application;

[0045] Figure 5 is a comparison graph of the melanin metabolic rate of the basal layer between the young group (20-29 years old) and the old group (50-59 years old) in the embodiment of the present application;

[0046] Figure 6 is a comparison graph of the melanin content of the superficial dermis between the young group (20-29 years old) and the old group (50-59 years old) in the embodiment of the present application;

[0047] Figure 7 is a method implementation flowchart of the embodiment of the present application. DETAILED DESCRIPTION

[0048] The present application will be further described below in combination with the drawings and embodiments.

[0049] It should be pointed out that the following detailed description is exemplary and is intended to provide further description of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as generally understood by those skilled in the art to which the present application belongs.

[0050] It is to be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, steps, operations, devices, components and / or combinations thereof, but do not preclude the presence or addition of one or more other features, steps, operations, devices, components and / or combinations thereof.

[0051] As shown in Figure 7 , the present embodiment provides an aging evaluation method based on melanin at different depths of skin, comprising the following steps:

[0052] (1) acquiring an ultrasound image of the cross-sectional structure of the skin and a photoacoustic image containing a melanin photoacoustic signal;

[0053] (2) locating and extracting the skin boundary of the ultrasound image by a deep learning convolutional neural network based on the U-Net architecture;

[0054] (3) based on the boundary relationship between the ultrasound image and the photoacoustic image, setting the skin boundaries of the ultrasound image and the photoacoustic image to the same height, fusing the ultrasound image and the photoacoustic image, and reconstructing a three-dimensional image for studying the spatial distribution of melanin at different depths;

[0055] (4) based on the distribution characteristics of the melanin photoacoustic signal with the depth of the skin, dividing the skin into three anatomical feature regions of the keratinization layer (I), the basal layer (II) and the superficial dermis layer (III);

[0056] (5) calculating the melanin deposition rate of the keratinization layer, the melanin metabolic rate of the basal layer and the melanin content of the superficial dermis layer, respectively;

[0057] (6) combining the melanin deposition rate of the keratinization layer, the melanin metabolic rate of the basal layer and the melanin content of the superficial dermis layer to comprehensively evaluate the degree of skin aging.

[0058] I. Sample preparation and image acquisition

[0059] 1) Sample preparation: clean the designated area of the skin to be tested, and measure the skin ITA value using a skin colorimeter.

[0060] 2) Dual-mode imaging:

[0061] Acquire the ultrasound image of the cross-sectional structure of the skin in the region by the ultrasound imaging unit, as shown in Figure 1 (a). In the present embodiment, the ultrasound imaging unit adopts a 60MHz high-frequency ultrasound probe.

[0062] At the same time, the photoacoustic excitation unit emits a pulsed laser of a set wavelength to irradiate the skin of the same area to stimulate the melanin photoacoustic signal, and the corresponding photoacoustic image is collected by the ultrasound imaging unit, such as Figure 1 In this embodiment, the photoacoustic excitation unit uses a pulsed laser light source with a wavelength of 650 nm, and the pulsed laser with a wavelength of 650 nm corresponds to the absorption peak of melanin.

[0063] In this method, the ultrasound image and the photoacoustic image are collected synchronously at the same position to facilitate the fusion of the ultrasound image and the photoacoustic image.

[0064] Figure 1 The following are cross-sectional images of the cheek skin in this embodiment, where (a) is an ultrasound image and (b) is a photoacoustic image with a wavelength of 650 nm. The image size is 3.84 mm × 6 mm.

[0065] 2. Image Processing

[0066] First, the skin boundary of the ultrasound image is located and segmented using a deep learning convolutional neural network based on the U-Net architecture. The segmentation results are shown in the figure below. Figure 2 As shown in (a).

[0067] On this basis, the skin boundary in the ultrasound image is extracted. The skin boundary extraction results are as follows: Figure 2 As shown in (b).

[0068] Since the ultrasound image and the photoacoustic image are collected synchronously at the same position, the skin surface boundary extracted from the ultrasound image is the skin boundary in the photoacoustic image. Figure 2 As shown in (c).

[0069] The skin boundary of the ultrasound image and the photoacoustic image is set to the same height, and the ultrasound image and the photoacoustic image are fused to reconstruct a three-dimensional stereo image. The three-dimensional stereo image is used to more conveniently observe the pigment distribution at different depths from the skin XY direction (top view angle) and to study the spatial distribution of melanin at different depths, such as Figure 3 shown.

[0070] 3. Data Analysis

[0071] Depth distribution analysis:

[0072] 1) Based on the distribution characteristics of melanin photoacoustic signals with skin depth, the skin is divided into three anatomical characteristic regions: keratinized layer (I), basal layer (II) and superficial dermis (III), and the PA intensity of each layer is calculated ( Figure 3 ).

[0073] Specifically, the interval above the median line of the difference between the maximum and minimum of the melanin photoacoustic signal distribution curve with skin depth is divided into the basal layer (II), and the keratinization layer (I) and the superficial dermis layer (III) are respectively arranged on both sides of the basal layer (II).

[0074] Figure 3 is the graph based on 650 nm wavelength photoacoustic imaging in this embodiment. Among them: (a) z=0 μm; (b) z=60 μm; (c) z=120 μm; (d) z=240 μm; (e) melanin spatial distribution reconstruction graph; the image size is 6 mm x 6 mm; (f) depth-resolved photoacoustic intensity curve: straight line A represents the median line of the difference between the maximum and minimum, and straight line B is the "baseline" absorption photoacoustic intensity of the epidermis without melanin.

[0075] 2) Establish the absorption coefficient model of different layers of skin at a wavelength of 650 nm:

[0076] μ a,i =M f ·μ a,i,mel +(1-M f )·μ a,i,0

[0077] Where M f is the average volume fraction of melanin in the epidermis, μ a,i,mel is the absorption coefficient of melanin in different skin layers, and μ a,0 is the "baseline" absorption coefficient of the epidermis tissue without melanin. i takes the values of 1, 2 and 3, which represent the keratinization layer, the basal layer and the superficial dermis layer, respectively.

[0078] 3) Inverse melanin volume fraction M f .

[0079] Parameter calculation:

[0080] 1) The photoacoustic signal is related to the absorption coefficient μ a , the photoacoustic signal intensity I i (x i , y i , z i ) is proportional to the absorption coefficient μ a,i , which can be expressed as I i (x, y, z) = μ a,i ·Γ·Φ. Where Γ is the Green function parameter, Φ is the local light flux, i takes the values of 1, 2 and 3, which represent the keratinization layer, the basal layer and the superficial dermis layer, respectively. The true melanin and the brown melanin show similar absorption spectrum and are usually regarded as a single chromophore in VIS-NIR research. The spatially resolved absorption coefficient of the epidermis tissue can be calculated as follows:

[0081] μ a,i= M f · μ a,i,mel + (1 - M f ) · μ a,i,0

[0082] 2) The relationship between the melanin deposition rate of the stratum corneum and the photoacoustic intensity of the stratum corneum and the age is established according to the following formula:

[0083] PA1 = C0 · ln[γ age · T]

[0084]

[0085] Wherein, γ age represents the melanin deposition rate of the stratum corneum; T represents the age; PA1 represents the total photoacoustic intensity of the stratum corneum; I1(x1, y1, z1) represents the photoacoustic signal intensity of each position (x1, y1, z1) of the stratum corneum, which is linearly proportional to the absorption coefficient μ a1 of the (x1, y1, z1) position, while μ a1 is linearly related to the volume fraction of melanin in the stratum corneum, so PA1 can reflect the content of melanin in the stratum corneum; C0 is a set parameter, C0 = PA 1,0 , wherein PA 1,0 represents the total photoacoustic intensity of the stratum corneum when the baby is just born; the melanin deposition rate of the stratum corneum is calculated through the above formula.

[0086] The relationship between the melanin metabolic rate of the basal layer and the photoacoustic intensity of the basal layer and the skin ITA value is established according to the following formula:

[0087] PA2 = C1exp[γ ita ° · ITA°]

[0088]

[0089] Wherein, γ ita° represents the melanin metabolic rate of the basal layer; ITA° represents the skin ITA value; PA2 represents the total photoacoustic intensity of the basal layer, I2(x2, y2, z2) represents the photoacoustic signal intensity of each position (x2, y2, z2) of the basal layer, which is linearly proportional to the absorption coefficient μ a2 of the (x2, y2, z2) position, while μ a2 is linearly related to the volume fraction of melanin in the basal layer, so PA2 can reflect the content of melanin in the basal layer; C1 is a set parameter, C1 = PA 2,0 , wherein PA 2,0 represents the total photoacoustic intensity of the basal layer when the baby is just born; the melanin metabolic rate of the basal layer is calculated through the above formula.

[0090] The formula for calculating the melanin content of the superficial dermis is as follows:

[0091]

[0092] Wherein, PA3 represents the total photoacoustic intensity of the superficial dermis, I3(x3, y3, z3) represents the photoacoustic signal intensity of the superficial dermis at each position (x3, y3, z3), which is linearly proportional to the absorption coefficient μ a3 of the position (x3, y3, z3), and μ a3 is linearly related to the volume fraction of melanin in the superficial dermis, so PA3 can reflect the melanin content of the superficial dermis.

[0093] On this basis, the degree of skin aging is comprehensively evaluated by combining the melanin deposition rate of the stratum corneum, the melanin metabolic rate of the basal layer, and the melanin content of the superficial dermis, and the specific implementation method is as follows:

[0094] The melanin deposition rate of the stratum corneum, the melanin metabolic rate of the basal layer, and the melanin content of the superficial dermis of the skin to be evaluated are calculated, and the calculation results are compared with the melanin deposition rate of the stratum corneum, the melanin metabolic rate of the basal layer, and the melanin content of the superficial dermis of the young group skin. When any one of the following three conditions is met, it is rated as skin aging 1 degree; when any two of the following three conditions are met, it is rated as skin aging 2 degree; and when all the following three conditions are met, it is rated as skin aging 3 degree:

[0095] 1) The melanin metabolic rate of the basal layer of the skin to be evaluated is less than the melanin metabolic rate of the basal layer of the young group skin;

[0096] 2) The melanin deposition rate of the stratum corneum of the skin to be evaluated is greater than the melanin deposition rate of the stratum corneum of the young group skin;

[0097] 3) The melanin content of the superficial dermis of the skin to be evaluated is greater than the melanin content of the superficial dermis of the young group skin.

[0098] Figure 4 is a comparison chart of the melanin deposition rate of the stratum corneum between the young group (20-29 years old) and the old group (50-59 years old) in this embodiment. Figure 4 It shows that the melanin deposition rate caused by the stratum corneum increases by one year of age, and the old population (50-59 years old) is about 3 times that of the young people (20-29 years old).

[0099] Figure 5 is a comparison chart of the melanin metabolic rate of the basal layer between the young group (20-29 years old) and the old group (50-59 years old) in this embodiment. Figure 5It shows that in the basal layer, for every ITA° change in skin color, the amount of melanin metabolized by the elderly aged 50-59 is about 1.5 times that of the young people aged 20-29.

[0100] Figure 6 3 is a comparison chart of the melanin content in the superficial dermis between the young group (20-29 years old) and the elderly group (50-59 years old) in this embodiment. Figure 6 The results showed that in the superficial dermis, the melanin content in the elderly group was greater than that in the young group. This was because the aging of the basal layer structure caused the melanin to pass through the basal layer and reach the superficial dermis.

[0101] This embodiment also provides an aging assessment system for implementing the above method, including: a data acquisition module, an image processing module and a data analysis module.

[0102] The data acquisition module includes an ultrasonic imaging unit and a photoacoustic excitation unit, which are used to acquire an ultrasonic image of the skin cross-sectional structure and a photoacoustic image containing a melanin photoacoustic signal.

[0103] The image processing module includes an image segmentation and extraction module and a three-dimensional reconstruction module. The image segmentation and extraction module is used to locate and extract the skin boundary of the ultrasound image through a deep learning convolutional neural network based on the U-Net architecture. The three-dimensional reconstruction module is used to set the skin boundary of the ultrasound image and the photoacoustic image to the same height, fuse the ultrasound image and the photoacoustic image, and reconstruct a three-dimensional stereo image.

[0104] The data analysis module is used to divide the skin into three anatomically characteristic regions: the stratum corneum (I), the basal layer (II), and the superficial dermis (III) based on the distribution characteristics of the melanin photoacoustic signal with skin depth. The module then calculates the melanin deposition rate of the stratum corneum, the melanin metabolism rate of the basal layer, and the melanin content of the superficial dermis, and comprehensively evaluates the degree of skin aging.

[0105] This embodiment further provides an electronic device, including a memory, a processor, and a computer program stored in the memory, wherein the processor implements the above method when executing the computer program.

[0106] This embodiment further provides a computer-readable storage medium storing a computer program, which implements the above method when executed by a processor.

[0107] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0108] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0109] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0110] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0111] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any other manner. Any person skilled in the art may utilize the above-disclosed technical content to modify or modify the present invention into equivalent embodiments. However, any simple modifications, equivalent variations, and modifications to the above embodiments that do not depart from the technical content of the present invention and are based on the technical essence of the present invention remain within the scope of protection of the present invention.

Claims

1. A method for evaluating aging based on melanin at different depths of skin, characterized in that: The following steps are involved: (1) Acquiring an ultrasound image of the skin cross-sectional structure and a photoacoustic image containing melanin photoacoustic signals; (2) Using a deep learning convolutional neural network based on the U-Net architecture to locate and extract skin boundaries from ultrasound images; (3) Based on the boundary relationship between the ultrasound image and the photoacoustic image, the skin boundary of the ultrasound image and the photoacoustic image is set to the same height, the ultrasound image and the photoacoustic image are fused, and a three-dimensional stereo image is reconstructed to study the spatial distribution of melanin at different depths; (4) Based on the distribution characteristics of melanin photoacoustic signals with skin depth, the skin is divided into three anatomical characteristic regions: stratum corneum (I), stratum basale (II), and superficial dermis (III); (5) Calculate the melanin deposition rate of the stratum corneum, the melanin metabolism rate of the basal layer, and the melanin content of the superficial dermis; (6) The degree of skin aging is comprehensively evaluated by combining the melanin deposition rate of the stratum corneum, the melanin metabolism rate of the basal layer, and the melanin content of the superficial dermis.

2. The aging evaluation method based on melanin of different skin depths according to claim 1, characterized in that: In step (1), an ultrasonic image of the cross-sectional structure of the skin in a set area is collected by an ultrasonic imaging unit; at the same time, a photoacoustic excitation unit is used to emit a pulsed laser of a set wavelength to irradiate the skin in the same area to excite the melanin photoacoustic signal, and the corresponding photoacoustic image is collected by the ultrasonic imaging unit.

3. The aging evaluation method based on melanin of different skin depths according to claim 2, characterized in that: The ultrasonic imaging unit adopts a 60MHz high-frequency ultrasonic probe; the photoacoustic excitation unit adopts a pulsed laser light source with a wavelength of 650nm, and the pulsed laser with a wavelength of 650nm corresponds to the absorption peak of melanin.

4. The aging evaluation method based on melanin of different skin depths according to claim 1, characterized in that: In step (1), the ultrasound image and the photoacoustic image are collected synchronously at the same position.

5. The aging evaluation method based on melanin of different skin depths according to claim 1, characterized in that: In step (3), since the ultrasound image and the photoacoustic image are collected synchronously at the same position, the skin surface boundary extracted from the ultrasound image is the skin boundary in the photoacoustic image.

6. The aging evaluation method based on melanin of different skin depths according to claim 1, characterized in that: In step (4), the interval above the median line of the difference between the maximum and minimum values ​​of the melanin photoacoustic signal distribution curve with skin depth is divided into the basal layer (II), and the two sides of the basal layer (II) are the keratinized layer (I) and the superficial dermis (III).

7. The aging evaluation method based on melanin of different skin depths according to claim 1, characterized in that: In step (5), the relationship between the melanin deposition rate of the stratum corneum and the photoacoustic intensity of the stratum corneum and age is established according to the following formula: PA1=C0·ln[γ age ·T] Among them, γ age represents the melanin deposition rate of the stratum corneum; T represents age; PA1 represents the total photoacoustic intensity of the stratum corneum; I1(x1, y1, z1) represents the photoacoustic signal intensity at each position (x1, y1, z1) of the stratum corneum, and its absorption coefficient μ at the position (x1, y1, z1) a1 is linearly proportional to μ a1 It is linearly related to the volume fraction of melanin in the stratum corneum, so PA1 can reflect the content of melanin in the stratum corneum; C0 is the setting parameter, C0 = PA 1,0 , of which PA 1,0 It represents the total photoacoustic intensity of the stratum corneum when the baby is just born; the melanin deposition rate of the stratum corneum can be calculated by the above formula; The relationship between the melanin metabolism rate of the basal layer, the photoacoustic intensity of the basal layer, and the skin ITA value is established according to the following formula: in, Indicates the melanin metabolism rate in the basal layer; Represents the skin ITA value; PA2 represents the total photoacoustic intensity of the basal layer, I2(x2, y2, z2) represents the photoacoustic signal intensity at each position (x2, y2, z2) of the basal layer, and its absorption coefficient μ at the position (x2, y2, z2) a2 is linearly proportional to μ a2 It is linearly related to the volume fraction of melanin in the basal layer, so PA2 can reflect the content of melanin in the basal layer; C1 is the setting parameter, C1 = PA 2,0 , of which PA 2,0 It represents the total photoacoustic intensity of the basal layer when the baby is just born; the melanin metabolism rate of the basal layer can be calculated by the above formula; The calculation formula of the melanin content in the superficial dermis is as follows: Where PA3 represents the total photoacoustic intensity of the superficial dermis, I3(x3, y3, z3) represents the photoacoustic signal intensity at each position (x3, y3, z3) in the superficial dermis, and its absorption coefficient μ at the position (x3, y3, z3) is a3 is linearly proportional to μ a3 It is linearly related to the volume fraction of melanin in the superficial dermis, so PA3 can reflect the content of melanin in the superficial dermis.

8. The aging evaluation method based on melanin of different skin depths according to claim 1, characterized in that: In step (6), the specific method for comprehensively evaluating the degree of skin aging by combining the melanin deposition rate of the stratum corneum, the melanin metabolism rate of the basal layer, and the melanin content of the superficial dermis is: The melanin deposition rate of the stratum corneum, the melanin metabolism rate of the basal layer, and the melanin content of the superficial dermis of the skin to be evaluated are calculated, and the calculated results are compared with the melanin deposition rate of the stratum corneum, the melanin metabolism rate of the basal layer, and the melanin content of the superficial dermis of the skin of the young group. When any one of the following three conditions is met, the skin is assessed as being at level 1 aging; when any two of the following three conditions are met, the skin is assessed as being at level 2 aging; and when all three of the following conditions are met, the skin is assessed as being at level 3 aging: 1) The melanin metabolism rate of the basal layer of the skin to be evaluated is lower than that of the basal layer of the skin of the young group; 2) The melanin deposition rate of the stratum corneum of the skin to be evaluated is greater than the melanin deposition rate of the stratum corneum of the skin of the youth group; 3) The melanin content of the superficial dermis of the skin to be evaluated is greater than the melanin content of the superficial dermis of the skin of the youth group.

9. An aging assessment system for implementing the method according to any one of claims 1 to 8, characterized in that: include: A data acquisition module, comprising an ultrasonic imaging unit and a photoacoustic excitation unit, for acquiring an ultrasonic image of the skin cross-sectional structure and a photoacoustic image containing a melanin photoacoustic signal; An image processing module, comprising an image segmentation and extraction module and a 3D reconstruction module. The image segmentation and extraction module is used to locate and extract the skin boundary of the ultrasound image using a deep learning convolutional neural network based on the U-Net architecture. The 3D reconstruction module is used to set the skin boundary of the ultrasound image and the photoacoustic image to the same height, fuse the ultrasound image and the photoacoustic image, and reconstruct a 3D stereo image. The data analysis module is used to divide the skin into three anatomical characteristic regions: the stratum corneum (I), the basal layer (II), and the superficial dermis (III) based on the distribution characteristics of the melanin photoacoustic signal with skin depth. The module then calculates the melanin deposition rate of the stratum corneum, the melanin metabolism rate of the basal layer, and the melanin content of the superficial dermis, and comprehensively evaluates the degree of skin aging.

10. A computer-readable storage medium, characterized in that A computer program is stored, and when the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images