Blood vessel estimation device, blood vessel estimation method, and program

Abstract

A blood vessel state is easy to evaluate. A blood vessel estimation device according to one embodiment of the present invention is provided with an acquisition unit that acquires a skin index on the face of a subject and / or an in-vivo index pertaining to the skin, and a blood vessel estimation unit that estimates blood vessels from the skin index on the face of the subject and / or the in-vivo index pertaining to the skin. The state of blood capillaries and / or the state of blood vessels other than blood capillaries on the face of the subject is estimated.

Description

Technical Field

[0001] The present invention relates to a blood vessel estimation device, a blood vessel estimation method and a program. Background Art

[0002] Conventionally, there are known methods for visualizing blood vessels and evaluating the state of blood vessels. For example, Patent Document 1 describes obtaining an enlarged image of at least the upper dermis where microvessels are distributed, generating a blood vessel image by performing designated image processing to make the microvessels in the obtained enlarged image clear, and evaluating at least one of the distribution and state of the microvessels from the generated blood vessel image.

[0003] [Prior art literature]

[0004] [Patent Literature]

[0005] [Patent Document 1] Patent No. 5977408 Summary of the invention

[0006] [Problems to be solved by the invention]

[0007] However, conventional blood vessel visualization techniques require expensive dedicated equipment for measurement and expensive instruments for analysis. Therefore, there is a need for a method that can evaluate blood vessel status in a simple and low-cost manner.

[0008] Therefore, the present invention aims to facilitate evaluation of the state of blood vessels.

[0009]

Methods to solve the problem

[0010] As one embodiment of the present invention, a blood vessel estimation device includes an acquisition unit that acquires skin indicators on the face of a subject and / or in vivo indicators related to the skin, and a blood vessel estimation unit that estimates the state of capillaries on the face of the subject and / or the state of blood vessels other than capillaries based on the skin indicators on the face of the subject and / or in vivo indicators related to the skin.

[0011] [Effects of the invention]

[0012] According to the present invention, the state of blood vessels can be easily evaluated. BRIEF DESCRIPTION OF THE DRAWINGS

[0013]

Figure 1

[0014]

Figure 2

[0015]

Figure 3

[0016]

Figure 4

[0017]

Figure 5

[0018]

Figure 6

[0019]

Figure 7

[0020]

Figure 8

[0021] Hereinafter, embodiments of the present invention will be described based on the drawings.

[0022] <Overall structure example>

[0023] Figure 1 This is an overall configuration example according to one embodiment of the present invention.

[0024] [Structural Example 1]

[0025] The blood vessel estimation system 1 includes a blood vessel estimation device 10 and a skin index measurement device 20. Each of these will be described below.

[0026] <<Blood Vessel Prediction Device>>

[0027] The blood vessel estimation device 10 is a device for estimating the state of capillaries and the state of blood vessels other than capillaries (hereinafter, "capillaries" and "blood vessels other than capillaries" are collectively referred to as skin blood vessels) of the subject 30. The blood vessel estimation device 10 can obtain the results measured by the skin index measurement device 20 from the skin index measurement device 20. For example, the blood vessel estimation device 10 may be a personal computer, a tablet terminal, a smartphone, etc.

[0028] Specifically, the blood vessel estimation device 10 acquires skin indices on the face of the subject 30. In addition, the blood vessel estimation device 10 estimates the state of capillaries and / or the state of blood vessels other than capillaries (i.e., at least one of "the state of capillaries" and "the state of blood vessels other than capillaries") on the face of the subject 30 from the skin indices on the face of the subject 30. In addition, the blood vessel estimation device 10 estimates which of a plurality of types the future skin condition of the subject 30 will be based on the estimated state of capillaries and / or the state of blood vessels other than capillaries (i.e., at least one of "the state of capillaries" and "the state of blood vessels other than capillaries"). In addition, the blood vessel estimation device 10 recommends at least one product or service related to beauty care based on at least one of the state of capillaries and / or the state of blood vessels other than capillaries (i.e., at least one of "the state of capillaries" and "the state of blood vessels other than capillaries") and the future skin condition (e.g., displayed on the screen of the blood vessel estimation device 10, the skin index measurement device 20 (e.g., a smart mirror)).

[0029] <<Skin Index Measurement Device>>

[0030] The skin index measuring device 20 is a device for measuring skin indexes on the face of the subject 30 and in vivo indexes related to the skin. For example, the skin index measuring device 20 is a device that can measure at least one of the following: the amount of spots, TEWL (transepidermal water evaporation), the degree of redness, the degree of yellowness, the area ratio of the furrows, the unevenness of the texture, the area ratio of the pores, the collagen density, the amount of wrinkles, the elasticity index, the degree of relaxation, the inflammatory cytokines, and the blood pressure. For example, the skin index measuring device 20 is a device that can measure and analyze skin indexes, such as a camera device (for example, a smart mirror (specifically, a mirror-type display screen built into the camera)), a stratum corneum analysis device, etc. (In this case, the measuring device obtains at least one of the amount of spots, TEWL (transepidermal water evaporation), the degree of redness, the degree of yellowness, the area ratio of the furrows, the unevenness of the texture, the area ratio of the pores, the collagen density, the amount of wrinkles, the elasticity index, the degree of relaxation, and the inflammatory cytokines from the information on the face of the subject 30 being measured (for example, an image on the face). Furthermore, for example, the skin index measurement device 20 is a sphygmomanometer for measuring blood pressure.

[0031] [Structural Example 2]

[0032] The blood vessel estimation system 1 includes a blood vessel estimation device 10, a terminal 11, and a skin index measurement device 20. The blood vessel estimation device 10 and the terminal 11 are communicably connected via an arbitrary network.

[0033] <<Blood Vessel Prediction Device>>

[0034] The blood vessel estimation device 10 is a device for estimating the state of capillaries and blood vessels other than capillaries of the subject 30. The blood vessel estimation device 10 can obtain the results measured by the skin index measurement device 20 from the terminal 11. For example, the blood vessel estimation device 10 is a server composed of one or more computers.

[0035] Specifically, the blood vessel estimation device 10 obtains skin indicators on the face of the subject 30. In addition, the blood vessel estimation device 10 estimates the skin blood vessels on the face of the subject 30, that is, the state of the capillaries and / or the state of the blood vessels other than the capillaries, from the skin indicators on the face of the subject 30. In addition, the blood vessel estimation device 10 estimates which type of the future skin condition of the subject 30 will be from the estimated state of the capillaries and / or the state of the blood vessels other than the capillaries. In addition, the blood vessel estimation device 10 recommends at least one of the beauty-related products and services based on at least one of the state of the capillaries and / or the state of the blood vessels other than the capillaries and the future skin condition (for example, displayed on the screen of the terminal 11, the skin indicator measurement device 20 (for example, a smart mirror)).

[0036] <<Terminal>>

[0037] The terminal 11 acquires the skin index on the face of the subject 30 from the skin index measurement device 20, and provides the acquired skin index on the face of the subject 30 to the blood vessel estimation device 10. In addition, the terminal 11 acquires and displays at least one piece of information on beauty products and services based on at least one of the state of capillaries and / or the state of blood vessels other than capillaries and the future skin state from the blood vessel estimation device 10. In addition, the terminal 11 can execute a part of the processing of the blood vessel estimation device 10 described in this specification. For example, the terminal 11 is a personal computer, a tablet terminal, a smart phone, etc.

[0038] <<Skin Index Measurement Device>>

[0039] The skin index measurement device 20 is the same as that in Configuration Example 1, and its description is omitted.

[0040] Furthermore, in the configuration example 2, the blood vessel estimation system 1 does not include the terminal 11 , and the skin index measurement device 20 can directly transmit and receive data with the blood vessel estimation device 10 .

[0041] <Function Block>

[0042] Figure 21 is a functional block diagram of a blood vessel estimation device 10 according to an embodiment of the present invention. The blood vessel estimation device 10 includes an acquisition unit 101, a blood vessel estimation unit 102, a skin estimation unit 103, a suggestion unit 104, a model storage unit 105, and a product information storage unit 106. The blood vessel estimation device 10 functions as the acquisition unit 101, the blood vessel estimation unit 102, the skin estimation unit 103, and the suggestion unit 104 by executing a program. Each of these will be described below.

[0043] The acquisition unit 101 acquires a skin index on the face of the subject 30 and / or an in-vivo index related to the skin (ie, at least one of “a skin index on the face” and “an in-vivo index related to the skin”).

[0044] [Indicators measured using the skin index measurement device 20]

[0045] For example, the acquisition unit 101 may acquire the skin index on the face of the subject 30 measured by the skin index measurement device 20 and / or an in-vivo index related to the skin.

[0046] [Case of using index acquired from image captured by skin index measurement device 20]

[0047] For example, the acquisition unit 101 may acquire the skin index on the face of the subject person 30 acquired from an image of the face of the subject person 30 captured by the skin index measurement device 20 (eg, an imaging device).

[0048] [When using the index input by the subject person 30 etc.]

[0049] For example, the acquisition unit 101 may acquire the skin index on the face of the subject 30 , which is input by the subject 30 or the like into the blood vessel estimation device 10 or the terminal 11 .

[0050] <Skin Indicators>

[0051] Here, skin indexes are described. Skin indexes are skin indexes that can affect the state of blood vessels.

[0052] For example, the skin index is an index related to skin aging, such as the amount of spots, collagen density, amount of wrinkles, elasticity index, and sagging degree.

[0053] For example, the skin index is an index associated with skin roughness. For example, the index associated with skin roughness is TEWL (transepidermal water evaporation), redness, texture heterogeneity, and inflammatory cytokines.

[0054] For example, the skin index is at least one of the amount of spots, TEWL (transepidermal water evaporation), skin color (redness, yellowness), furrow area ratio, texture heterogeneity, pore area ratio, collagen density, wrinkle amount, elasticity index, degree of relaxation, and inflammatory cytokines. The information about the skin of the subject 30 acquired by the acquisition unit 101 may be only the skin index, or the skin index and an in vivo index about the skin (e.g., blood pressure). Each of these is described below.

[0055] "Spot quantity" refers to the amount, color, area, and distribution of spots on the face.

[0056] "TEWL (transepidermal water evaporation)" is the amount of water evaporated through the stratum corneum.

[0057] "Redness" is the degree of redness of the skin.

[0058] The "yellowness level" is the degree of yellowness of the skin.

[0059] "Skin groove area ratio" refers to the ratio of the skin groove area per unit area on the face.

[0060] "Texture heterogeneity" refers to the degree of unevenness of skin texture (skin surface irregularities).

[0061] The "pore area ratio" is the ratio of the area of ​​the pores per unit area on the face.

[0062] "Collagen density" is the ratio of collagen per specific unit in the acquisition area on the face, which is the thickness of the collagen network.

[0063] “Wrinkle quantity” refers to the number, root number, depth, area, and distribution of folds.

[0064] The "elasticity index" refers to the responsiveness of the skin when force is applied.

[0065] The “degree of sagging” refers to the degree of swelling and looseness of the skin on the face.

[0066] The “inflammatory cytokines” include cytokines sampled from the stratum corneum, and are the amount of IL-1α, the amount of IL-1ra, the ratio of IL-1α to IL-1ra, the amount of SCCA1, the amount of S100A8A9, and the like.

[0067] As described above, skin indices (e.g., at least one of the amount of spots, TEWL (transepidermal water evaporation), redness, yellowness, furrow area ratio, texture heterogeneity, pore area ratio, collagen density, wrinkle amount, elasticity index, sagging degree, and inflammatory cytokines) can be obtained from the image of the face of the subject 30 photographed by the skin index measurement device 20. The blood vessel estimation device 10 (or the skin index measurement device 20) can analyze the image of the face of the subject 30 photographed by the skin index measurement device 20 to calculate the skin index. In addition, the blood vessel estimation device 10 (or the skin index measurement device 20) can analyze the sampled stratum corneum to calculate, for example, inflammatory cytokines. Furthermore, the blood vessel estimation device 10 (or the skin index measurement device 20) can measure the blood pressure of the subject 30 by a sphygmomanometer to calculate the in vivo index.

[0068] The blood vessel estimation unit 102 estimates the state of the capillaries on the face of the subject 30 and / or the state of the blood vessels other than the capillaries from the skin indicators on the face of the subject 30 acquired by the acquisition unit 101 and / or the internal indicators related to the skin. Specifically, the blood vessel estimation unit 102 estimates the state of the capillaries on the face of the subject 30 and / or the state of the blood vessels other than the capillaries from the skin indicators on the face of the subject 30 and / or the internal indicators related to the skin using a regression model. In addition, the regression model can be a statistical model (i.e., a mathematical model that derives the state of the capillaries on the face and / or the state of the blood vessels other than the capillaries from the skin indicators on the face and / or the internal indicators related to the skin), or a machine learning model (i.e., a model that has been machine-learned in a manner that outputs the state of the capillaries on the face and / or the state of the blood vessels other than the capillaries when the skin indicators on the face and / or the internal indicators related to the skin are input).

[0069] <Conditions of capillaries and blood vessels other than capillaries>

[0070] Here, the state of capillaries and the state of blood vessels other than capillaries are described. The state of capillaries and / or the state of blood vessels other than capillaries may be principal components (also called blood vessel scores) obtained by reducing variables representing the state of capillaries and / or the state of blood vessels other than capillaries through principal component analysis, or may be the variables themselves representing the state of capillaries and / or the state of blood vessels other than capillaries.

[0071] [Vascular score]

[0072] For example, the state of capillaries and the state of blood vessels other than capillaries are the blood vessel scores (principal components obtained by reducing the variables representing the state of capillaries and the state of blood vessels other than capillaries through principal component analysis) as the target variables of the regression model described in the later section. In addition, the principal component is related to at least one of (1) blood vessel density, (2) the number of blood vessels (the number of capillaries, the number of thick blood vessels), (3) the number of blood vessel branches, (4) the distance from the base of the epidermis to the blood vessel, and (5) the thickness of the epidermis.

[0073] [The state of capillaries and the state of blood vessels other than capillaries]

[0074] For example, the state of capillaries and the state of blood vessels other than capillaries are the state of capillaries themselves and the state of blood vessels other than capillaries themselves (i.e., the state of capillaries and the state of blood vessels other than capillaries themselves) as the target variable of the regression model described in the later section. Specifically, the state of capillaries and the state of blood vessels other than capillaries are at least one of (1) the density of blood vessels, (2) the number of blood vessels (the number of capillaries, the number of thick blood vessels), (3) the number of branches of blood vessels, (4) the distance from the base of the epidermis to the blood vessels, and (5) the thickness of the epidermis itself (i.e., itself).

[0075] The following will explain each one separately.

[0076] The “number of blood vessels” refers to the number of capillaries and / or blood vessels other than capillaries on the face. The number of capillaries refers to the number of blood vessels with a diameter of 40 μm or less, and includes thin blood vessels in addition to the so-called capillaries. The number of thick blood vessels refers to the number of blood vessels with a diameter of 160 μm or more among blood vessels other than capillaries.

[0077] The “blood vessel density” is the ratio of capillaries and / or blood vessels other than capillaries per specific unit in the acquisition site on the face.

[0078] The “number of blood vessel branches” refers to the number of capillaries and / or blood vessel branches other than capillaries.

[0079] The “distance from the base of the epidermis to the blood vessel” is a representative value such as an average value, a maximum value, a minimum value, a median, etc. of the distance between the base of the epidermis and the capillaries and / or the blood vessels other than the capillaries.

[0080] The “thickness of the epidermis” is a representative value such as an average value, a maximum value, a minimum value, and a median of the thickness of the epidermis.

[0081] The skin estimation unit 103 estimates which of the multiple types the future skin condition of the subject 30 will be based on the state of the capillaries on the face of the subject 30 estimated by the blood vessel estimation unit 102 and / or the state of the blood vessels other than the capillaries. Specifically, the skin estimation unit 103 estimates which of the multiple types the future skin condition of the subject 30 will be based on the state of the capillaries on the face of the subject 30 and / or the state of the blood vessels other than the capillaries. In addition, the model may be a statistical model (i.e., a mathematical model that deduces which of the multiple types the future skin condition will be based on the state of the capillaries on the face and / or the state of the blood vessels other than the capillaries), or a machine learning model (i.e., a model that has been learned by machine learning in a manner that outputs which of the multiple types the future skin condition will be based on the state of the capillaries on the face and / or the state of the blood vessels other than the capillaries).

[0082] The suggestion unit 104 suggests at least one of the beauty-related products and services based on at least one of the state of the capillaries and / or the state of the blood vessels other than the capillaries estimated by the blood vessel estimation unit 102 and the future skin state estimated by the skin estimation unit 103. Specifically, the suggestion unit 104 suggests at least one of the beauty-related products and services based on at least one of the state of the capillaries and / or the state of the blood vessels other than the capillaries and the type of the future skin state and at least one of the beauty-related products and services (the correspondence is predetermined).

[0083] For example, beauty products include basic cosmetics such as lotions, emulsions, serums, and creams. For example, beauty products include beauty equipment, supplements, and food and beverages such as beverages.

[0084] For example, beauty services include cosmetic surgery, cosmetic consultation, etc.

[0085] The model storage unit 105 stores a model referred to by the blood vessel estimation unit 102 and a model referred to by the skin estimation unit 103 .

[0086] The product information storage unit 106 stores the correspondence referred to by the recommendation unit 104 (specifically, the correspondence between at least one of the state of capillaries and / or the state of blood vessels other than capillaries (i.e., the state of skin blood vessels) and the type of future skin condition, and at least one of the beauty-related products and services applicable to at least one of the state of capillaries and / or the state of blood vessels other than capillaries (i.e., the state of skin blood vessels) and the type of future skin condition).

[0087] <Method>

[0088] Figure 3 This is a flowchart of a blood vessel estimation process according to one embodiment of the present invention.

[0089] In step 1 ( S1 ), the blood vessel estimation device 10 (acquisition unit 101 ) acquires skin indices on the face of the subject 30 and / or in-vivo indices related to the skin.

[0090] In step 2 (S2), the blood vessel estimation device 10 (blood vessel estimation unit 102) estimates the state of the capillaries on the face of the subject 30 and / or the state of the blood vessels other than the capillaries (i.e., the state of the skin blood vessels) based on the skin indicators on the face of the subject 30 obtained in S1 and / or the body indicators related to the skin.

[0091] In step 3 (S3), the blood vessel estimation device 10 (skin estimation unit 103) estimates which of multiple types the future skin condition of the subject 30 will be based on the state of capillaries on the face of the subject 30 estimated in S2 and / or the state of blood vessels other than capillaries.

[0092] In step 4 (S4), the blood vessel estimation device 10 (suggestion unit 104) suggests at least one product or service related to beauty care based on at least one of the state of capillaries and / or the state of blood vessels other than capillaries estimated in S2 and the future skin state estimated in S3.

[0093] <Generation of regression model>

[0094] The following describes the generation of a regression model used in the present invention for estimating the state of capillaries from skin indices on the face.

[0095] [Target variable (state of capillaries)]

[0096] In the present invention, principal component analysis is performed on data acquired using OCT (optical coherence tomography), and the principal components calculated by principal component analysis are used as target variables of the regression model. Specifically, by performing image analysis on images photographed using OCT, the three-dimensional structure of the vascular network of the dermis can be evaluated. Then, a quantitative analysis of the vascular network of the dermis is performed (in addition, the quantitative items are (1) the density of blood vessels, (2) the number of blood vessels (the number of capillaries, the number of thick blood vessels), (3) the number of branches of blood vessels, (4) the distance from the base of the epidermis to the blood vessels, and (5) the thickness of the epidermis), and the quantitative values ​​of these blood vessels are reduced by principal component analysis, and the correlation analysis between blood vessels and skin is performed.

[0097] Figure 4 Indicates the results of principal component analysis. The principal component loadings of the two variables (principal component 1 (PC1) and principal component 2 (PC2)) generated in the principal component analysis are given.

[0098] PC1 showed positive correlation with "the number of capillaries", "the density of blood vessels", "the number of blood vessel branches", and "the thickness of the epidermis". In addition, PC1 showed negative correlation with "the distance from the base of the epidermis to the blood vessels". In the present invention, this PC1 (which indicates how firmly the capillaries are distributed. It is also called the blood vessel score) is used as the target variable of the regression model.

[0099] PC2 showed a positive correlation with the “number of thick blood vessels”.

[0100] [Model Generation]

[0101] The regression model for estimating the above PC1 (vascular score) was studied by multiple regression analysis. Specifically, the combination of explanatory variables was fully verified, and meaningful explanatory variables (skin indexes on the face and in vivo indexes related to the skin) were explored.

[0102] [Measurement of skin indicators on the face]

[0103] First, the following testers measured the following measurement items. In addition, all the measurement values ​​were standardized (mean: 0, variance: 1).

[0104] · Gender of experimenters: Female, Number of participants: 123, Age: 20-79 years old

[0105] Measurement items: Age, moisture content, TEWL (transepidermal water evaporation), collagen density, wrinkle volume, elasticity index, sagging degree, texture heterogeneity, furrow area ratio, pore area ratio, skin color (redness, yellowness), spot volume, inflammatory cytokines, glycation degree

[0106] Furthermore, the above-mentioned PC1 (vascular score) of the experimenter was calculated.

[0107] Next, the analytical process of multiple regression analysis is explained.

[0108] Implement in the following order.

[0109] 1. To avoid multicollinearity, reduce the number of explanatory variables

[0110] 2. Construct a multiple regression model using all combinations of explanatory variables

[0111] 3. Select model candidates based on AIC

[0112] 4. Determine the most appropriate model based on the significance of the regression coefficients of the explanatory variables

[0113] Hereinafter, 1 to 4 will be described in detail.

[0114] [1. Reduction of explanatory variables]

[0115] Variable reduction is performed so that the VIF (Value inflation factor) value does not exceed a certain value and the influence of multicollinearity is eliminated.

[0116] [2. List creation of multiple regression model]

[0117] A multivariate regression model was constructed using all combinations of explanatory variables (again, using the method of least squares), and the AIC was calculated for model evaluation.

[0118] Here, we will explain AIC (Akaike Information Criterion). AIC is an indicator of the goodness of fit of a model, and the smaller the AIC, the better.

[0119] [3. Selection of model candidate groups]

[0120] The most suitable model candidate is selected based on the AIC value, explanatory power, and dominance of the variables.

[0121] [4. Selection of models with significant variables]

[0122] p-value: Using 0.1 as the benchmark, explore the model that is significant for all variables. Figure 5 Three models are given in which all variables are recognized to be significant.

[0123] Model 8 can explain PC1 (vascular score) with fewer variables, and it can be considered that the model has good explanatory power. In addition, for variables related to PC1 (vascular score) (correlations with |r|>0.2 or more), the coefficients of single correlation and partial regression in Model 8 are consistent in sign, so the model is considered to be highly appropriate. The correlation coefficient (Spearman's rank correlation coefficient) and VIF value between the explanatory variables of Model 8 are suppressed to low values, and it can be judged that the risk of multicollinearity is low.

[0124] Furthermore, in one embodiment of the present invention, model 10 and model 0 may be used.

[0125] Figure 6 Explanatory variables and their explanations for PC1 (vascular score) that contribute to model 8 are given. When the elements required for the inference of PC1 (vascular score) are summarized, the association between the two factors of "aging" and "rough skin" is inferred. Specifically, it is found that when there is a tendency for skin aging (many spots, low collagen content), PC1 (vascular score) is low. It is also found that when there is a tendency for skin roughness (high TEWL / redness, and a tendency for messy texture), PC1 (vascular score) is high. Figure 6 The results showed that PC1 (vascular score) can be estimated from the following formula.

[0126] PC1 (vascular score) = -0.30 × spot amount + 0.30 × TEWL + 0.21 × redness + 0.15 × yellowness

[0127] +0.24×skin groove area ratio+0.22×texture heterogeneity+-0.19×pore area ratio+0.29×collagen density

[0128] Figure 7 This is a list of minimum models for estimating the state of capillaries. This is a list of explanatory variables and coefficients for each model (model A to model E). In model A, PC1 (vascular score) = 0.32 × TEWL + 0.33 × collagen density, with a determination coefficient of 0.26. In model B, PC1 (vascular score) = 0.37 × TEWL + -0.31 × spot amount, with a determination coefficient of 0.26. In model C, PC1 (vascular score) = -0.29 × spot amount + 0.36 × collagen density, with a determination coefficient of 0.25. In model D, PC1 (vascular score) = 0.38 × TEWL + -0.23 × glycation degree, with a determination coefficient of 0.21. In model E, PC1 (vascular score) = 0.19 × redness + 0.42 × collagen density, with a determination coefficient of 0.20.

[0129] In one embodiment of the present invention, the above-mentioned model 8 (in addition, model 10 and model 0 may also be used) with high estimation accuracy may be used, or the above-mentioned models A to E with a small number of explanatory variables may be used.

[0130] <Other Embodiments of Generating a Regression Model>

[0131] Another embodiment of generating a regression model for estimating the state of capillaries and / or the state of blood vessels other than capillaries from skin indices on the face used in the present invention will be described below.

[0132] [Target variable (state of capillaries and / or state of blood vessels other than capillaries)]

[0133] The target variable of the regression model is (1) the principal component (vascular score) obtained by reducing the variables representing the state of capillaries and / or the state of blood vessels other than capillaries through principal component analysis, or (2) the variable representing the state of capillaries and / or the state of blood vessels other than capillaries itself (i.e., the state of capillaries and / or the state of blood vessels other than capillaries themselves).

[0134] (1) When variables representing the state of capillaries and / or the state of blood vessels other than capillaries are reduced to principal components (vascular scores) by principal component analysis

[0135] As described above, data acquired using OCT (optical coherence tomography) are subjected to principal component analysis, and the principal components calculated by principal component analysis are used as target variables of the regression model. Specifically, by performing image analysis on images photographed using OCT, the three-dimensional structure of the vascular network of the dermis can be evaluated. Then, a quantitative analysis of the vascular network of the dermis is performed (in addition, the quantitative items are (1) the density of blood vessels, (2) the number of blood vessels (the number of capillaries, the number of thick blood vessels), (3) the number of branches of blood vessels, (4) the distance from the base of the epidermis to the blood vessels, and (5) the thickness of the epidermis), and the quantitative values ​​of these blood vessels are reduced by principal component analysis, and the correlation analysis between blood vessels and skin is performed.

[0136] As described above, principal component 1 (PC1) generated in principal component analysis shows positive correlation with "the number of capillaries", "the density of blood vessels", "the number of blood vessel branches", and "the thickness of the epidermis". In addition, PC1 shows negative correlation with "the distance from the base of the epidermis to the blood vessels". In the present invention, this PC1 (indicating how firmly the fine blood vessels are distributed. It is also called a blood vessel score) is used as the target variable of the regression model. In addition, principal component 2 (PC2) shows positive correlation with "the number of thick blood vessels".

[0137] (2) The case where the variable itself represents the state of the capillaries and / or the state of the blood vessels other than the capillaries (i.e., the state of the capillaries and / or the state of the blood vessels other than the capillaries themselves)

[0138] The variable itself representing the state of capillaries and / or the state of blood vessels other than capillaries (specifically, at least one of the number of capillaries, the number of thick blood vessels, the density of blood vessels, the number of blood vessel branches, the distance from the base of the epidermis to the blood vessels, and the thickness of the epidermis) is used as the target variable of the regression model.

[0139] [Model Generation]

[0140] Using multiple regression analysis, we studied regression models for estimating "(1) the principal component (vascular score) obtained by reducing the variables representing the state of capillaries and / or the state of blood vessels other than capillaries through principal component analysis" or "(2) the variables representing the state of capillaries and / or the state of blood vessels other than capillaries themselves (i.e., the state of capillaries and / or the state of blood vessels other than capillaries themselves)". Specifically, we verified all combinations of explanatory variables and explored meaningful explanatory variables (skin indicators on the face and in vivo indicators related to the skin).

[0141] [Measurement of skin indicators on the face and body indicators]

[0142] First, the values ​​of the following measurement items were measured by the following experimenters. In addition, all the measurement values ​​were standardized (mean: 0, variance: 1).

[0143] · Gender of experimenters: female, male, number of participants: 274, age: 20-79 years old

[0144] Measurement items: age, water content, TEWL (transepidermal water evaporation), collagen density, wrinkle amount, elasticity index, degree of sagging, texture heterogeneity, furrow area ratio, pore area ratio, skin color (redness, yellowness), spot amount, inflammatory cytokines (including cytokines sampled from the stratum corneum, IL-1α amount, IL-1ra amount, IL-1αIL-1ra ratio, SCCA1 amount, S100A8A9 amount, etc.), glycation degree, blood pressure.

[0145] In addition, the experimenter's "(1) principal components (vascular scores) obtained by reducing the variables representing the state of capillaries and / or the state of blood vessels other than capillaries through principal component analysis" and "(2) variables representing the state of capillaries themselves and / or the state of blood vessels other than capillaries (i.e., the state of capillaries and / or the state of blood vessels other than capillaries themselves)" were calculated.

[0146] When a multivariate regression analysis is performed on the relationship between the skin indicators on the face and the state of the capillaries and / or the state of the blood vessels other than the capillaries, it is possible to infer "(1) the principal component (vascular score) obtained by reducing the variables representing the state of the capillaries and / or the state of the blood vessels other than the capillaries through principal component analysis" from the skin indicators on the face.

[0147] When a multivariate regression analysis is performed on the relationship between the skin indicators on the face and the state of the capillaries and / or the state of the blood vessels other than the capillaries, "(2) the variable itself indicating the state of the capillaries and / or the state of the blood vessels other than the capillaries" can be inferred from the skin indicators on the face. In addition, it is understood that the state of the capillaries and / or the state of the blood vessels other than the capillaries themselves can be inferred by using blood pressure as an in vivo indicator associated with the skin on the face.

[0148] <Effect>

[0149] In this way, by focusing on blood vessels, it is possible to provide consultation focusing on the potential of the skin and to recommend beauty products and services. For example, in consultation at a cosmetics store or event, skin indicators can be extracted from the image of the face taken by the smart mirror, the state of the capillaries can be diagnosed, and the characteristics of the skin under the state of each capillary can be introduced. Furthermore, cosmetics focusing on the characteristics of the skin under the state of each capillary can be recommended.

[0150] <Hardware Structure>

[0151] Figure 81 is a hardware configuration diagram of a blood vessel estimation device 10 and a terminal 11 according to an embodiment of the present invention. The blood vessel estimation device 10 and the terminal 11 may include a control unit 1001, a main storage unit 1002, an auxiliary storage unit 1003, an input unit 1004, an output unit 1005, and an interface unit 1006. Each of these will be described below.

[0152] The control unit 1001 is a processor (for example, a CPU (central processing unit), a GPU (graphics processing unit), etc.) that executes various programs installed in the auxiliary storage unit 1003 .

[0153] The main storage unit 1002 includes a nonvolatile memory (ROM (read only memory)) and a volatile memory (RAM (random access memory)). The ROM stores various programs and data required for the control unit 1001 to execute various programs installed in the auxiliary storage unit 1003. The RAM provides a work area in which various programs installed in the auxiliary storage unit 1003 are launched when they are executed by the control unit 1001.

[0154] The auxiliary storage unit 1003 is an auxiliary storage device that stores various programs and information used when the various programs are executed.

[0155] The input unit 1004 is an input device for the operator of the blood vessel estimation apparatus 10 or the terminal 11 to input various instructions to the blood vessel estimation apparatus 10 or the terminal 11 .

[0156] The output unit 1005 is an output device that outputs the internal states of the blood vessel estimation apparatus 10 and the terminal 11 and the like.

[0157] The interface unit 1006 is a communication device connected to a network for communicating with other devices.

[0158] As mentioned above, although the embodiment of the present invention is described in detail, the present invention is not limited to the above-mentioned specific embodiment, and various deformation|transformation and changes are possible within the scope of the summary of the present invention described in the patent claims.

[0159] The present international application claims the benefit of priority based on Japanese Patent Application No. 2022-166887 filed on October 18, 2022, the entire contents of which are hereby incorporated by reference into the present international application.

[0160] [Description of Reference Numerals]

[0161] 1 Vascular inference system

[0162] 10. Blood vessel estimation device

[0163] 11 Terminal

[0164] 20 Skin index measurement device

[0165] 30 Targeted persons

[0166] 101 Acquisition Department

[0167] 102 Vascular Speculation Department

[0168] 103 Skin Prediction Department

[0169] 104 Suggestion Department

[0170] 105 Model storage unit

[0171] 106 Product Information Storage Department

[0172] 1001 Control Department

[0173] 1002 Main storage unit

[0174] 1003 Subsidy Storage Department

[0175] 1004 Input

[0176] 1005 Output

[0177] 1006 Interface Department.

Claims

1. A blood vessel estimation device, comprising: an acquisition unit that acquires skin indices on the face of the subject and / or in-vivo indices related to the skin, and A blood vessel estimation unit estimates the state of capillaries on the face of the subject and / or the state of blood vessels other than capillaries based on skin indicators on the face of the subject and / or in-vivo indicators related to the skin.

2. According to the blood vessel estimation device according to claim 1, the state of the capillaries and / or the state of blood vessels other than capillaries is a principal component obtained by reducing the variables representing the state of the capillaries and / or the state of blood vessels other than capillaries through principal component analysis.

3. The blood vessel estimation device according to claim 2, wherein the principal component is related to at least one of the number of capillaries, the density of blood vessels, the number of blood vessel branches, the distance from the base of the epidermis to the blood vessels, and the thickness of the epidermis.

4. According to the blood vessel estimation device according to claim 1, the state of the capillaries and / or the state of blood vessels other than capillaries is at least one of (1) the density of blood vessels, (2) the number of blood vessels, i.e., the number of capillaries, the number of thick blood vessels, (3) the number of blood vessel branches, (4) the distance from the base of the epidermis to the blood vessels, and (5) the thickness of the epidermis. 5 . The blood vessel estimation device according to claim 1 , wherein the skin index is an index associated with skin aging. 6 . The blood vessel estimation device according to claim 1 , wherein the skin index is an index associated with skin roughness.

7. According to the blood vessel inference device according to claim 1, the skin indicator is at least one of the spot amount, transepidermal water evaporation (TEWL), redness degree, yellowness degree, furrow area ratio, texture heterogeneity, pore area ratio, collagen density, wrinkle amount, elasticity index, relaxation degree and inflammatory cytokines.

8. The blood vessel estimation device according to claim 1, wherein the in vivo index is blood pressure. 9 . The blood vessel estimation device according to claim 1 , wherein the skin index is acquired from an image of a face of the subject.

10. The blood vessel estimation device according to any one of claims 1 to 4, further comprising a skin estimation unit which estimates which of a plurality of types the future skin condition of the subject will be based on the estimated capillary conditions and / or blood vessel conditions other than capillaries.

11. The blood vessel estimation device according to claim 10 further comprises a suggestion unit which suggests at least one beauty-related product or service based on at least one of the state of the capillaries and / or the state of blood vessels other than capillaries and the future skin state.

12. According to any one of claims 1 to 4, the blood vessel estimation unit uses a regression model to estimate the state of capillaries on the face of the subject and / or the state of blood vessels other than capillaries from skin indicators on the face of the subject and / or in vivo indicators related to the skin. 13 . The blood vessel estimation device according to claim 12 , wherein the regression model is a statistical model or a machine learning model.

14. A blood vessel estimation method, comprising: The step of obtaining skin indexes on the face of the subject and / or in vivo indexes related to the skin, The step of estimating the state of capillaries on the face of the subject and / or the state of blood vessels other than capillaries based on skin indicators on the face of the subject and / or in vivo indicators related to the skin.

15. A program for causing a blood vessel estimation device to: an acquisition unit that acquires skin indicators on the face of the subject and / or in-vivo indicators related to the skin, A blood vessel estimation unit estimates the state of capillaries on the face of the subject and / or the state of blood vessels other than capillaries based on skin indicators on the face of the subject and / or in-vivo indicators related to the skin.

Images