Method for estimating total protein amount of stratum corneum

Abstract

To provide an estimation method for estimating a total protein amount of a horny layer.SOLUTION: An estimation method for estimating a total protein amount of a horny layer specifies a cell region of a horny layer image, a multilayer flaking region and a one-cell region, digitizes one or more selected from a group consisting of a cell region area, a multilayer flaking area, a multilayer flaking ratio, a one-cell luminance average value, a one-cell luminance standard deviation, a one-cell luminance central value and a one-cell luminance minimum value, and estimates a total protein amount of a horny layer with the digitized value as an index.SELECTED DRAWING: None

Description

Technical Field

[0001] The present invention relates to a method for estimating the total protein amount of the stratum corneum.

Background Art

[0002] Methods for evaluating skin conditions and the like based on the amount of specific proteins or the amount of specific gene expression in stratum corneum cells are known. Here, since these protein amounts and gene expression amounts depend on the amount of the sample, for example, the ratio to the total protein amount in the sample is used for evaluation. For example, the present applicant has proposed, in Patent Document 1, a method for evaluating skin viscoelasticity based on the amount of NGAL expression per unit protein amount corrected by the total protein amount in the skin stratum corneum. In addition, since the less the water content of the skin, the more the total protein amount collected, it can also be used as a physiological index. Here, for the measurement of the total protein amount of the collected stratum corneum cells, generally the BCA protein assay is used, but the measurement is time-consuming, and a simple method for estimating the total protein amount is required.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] An object of the present invention is to provide a method for estimating the total protein amount of the stratum corneum.

Means for Solving the Problems

[0005] As a result of intensive studies to solve the above problems, the present invention has been made by finding that the total protein amount of the stratum corneum can be estimated using the stratum corneum structure obtained from an observation image of the stratum corneum as an index.

[0006] Specifically, the means for solving the problems of the present invention are as follows. 1. Identify one or more of the cell region, the stratified exfoliation region, and the single-cell region in the stratum corneum image, Quantify one or more selected from the group consisting of the cell region area, the stratified exfoliation area, the stratified exfoliation rate, the average single-cell luminance value, the standard deviation of single-cell luminance, the median single-cell luminance value, and the minimum single-cell luminance value, A method for estimating the total protein amount in the stratum corneum, which estimates the total protein amount in the stratum corneum using the quantified value as an index. 2. The method for estimating the total protein amount in the stratum corneum according to 1., wherein one or more of the cell region, the stratified exfoliation region, and the single-cell region are identified using a machine learning model obtained by machine learning a plurality of learning stratum corneum images in advance and one or more of the cell region, the stratified exfoliation region, and the single-cell region by visual evaluation in each learning stratum corneum image.

Advantages of the Invention

[0007] The method for estimating the total protein amount of the present invention uses a numerical value obtained from the stratum corneum structure as an index, and can estimate the total protein amount in the stratum corneum very easily and accurately. The value of the total protein amount estimated by the estimation method of the present invention can be used to correct the measured value when evaluating the skin condition based on the specific protein amount in the stratum corneum cells, the expression level of a specific gene, etc. In addition, the value of the total protein amount estimated by the estimation method of the present invention can be used as an index for evaluating the skin condition and the like.

Modes for Carrying Out the Invention

[0008] The present invention relates to a method for estimating the total protein amount in the stratum corneum, which identifies one or more of the cell region, the stratified exfoliation region, and the single-cell region in the stratum corneum image, Quantify one or more selected from the group consisting of the cell region area, the stratified exfoliation area, the stratified exfoliation rate, the average single-cell luminance value, the standard deviation of single-cell luminance, the median single-cell luminance value, and the minimum single-cell luminance value, And estimates the total protein amount in the stratum corneum using the quantified value as an index.

[0009] The method for collecting the stratum corneum to obtain an image may be either biopsy or tape stripping method, but the tape stripping method is preferred because it places less burden on the subject. The tape stripping method is a method of pasting an adhesive tape on the skin and then peeling it off to collect the superficial layer of the skin.

[0010] The stratum corneum cells collected by the tape stripping method are imaged by transmitted light observation (including differential interference method, phase contrast method, dark field observation method, etc.) or reflected light to observe the cell morphology. The stratum corneum cells are preferably observed in an unstained state, but can also be stained if necessary. Cell observation can be performed using a microscope capable of cell observation. For example, the digital microscope VHX-500 manufactured by Keyence Corporation, the digital microscope Dino-Lite manufactured by AnMo Electronics Corporation, etc. can be used. The observation conditions are not limited as long as the details of the cells can be confirmed. For example, conditions such as a resolution of 1.0 μm / pixel or more and about 200,000 pixels or more can be mentioned.

[0011] The captured stratum corneum image is processed using an image processing system to identify one or more of the cell region, multilayer peeling region, and single cell region. Then, based on the identified cell region, multilayer peeling region, and single cell region, one or more selected from the group consisting of cell region area, multilayer peeling area, multilayer peeling rate, single cell luminance average value, single cell luminance standard deviation, single cell luminance median value, and single cell luminance minimum value are quantified. Specifically, the cell region area can be quantified from the cell region, the multilayer peeling area can be quantified from the multilayer peeling region, the multilayer peeling rate can be quantified from the cell region and the multilayer peeling region, and the single cell luminance average value, single cell luminance standard deviation, single cell luminance median value, and single cell luminance minimum value can be quantified from the single cell region. The stratum corneum image may use a color image, an image converted to grayscale by image processing, or both can be used.

[0012] The cell region area is the sum of the areas of the stratum corneum cell regions in the stratum corneum image. The multilayer peeling area refers to the area where two or more horny layers overlap and peel off. The multilayer peeling rate is the ratio of the "multilayer peeling area" to the "cell region area" (multilayer peeling area / cell region area).

[0013] The average value of cell brightness of one cell is the value obtained by averaging the average brightness values within the cell regions of individual horny layer cells in the horny layer image for all cells. The standard deviation of cell brightness of one cell is the value obtained by averaging the standard deviation of brightness values within the cell regions of individual horny layer cells in the horny layer image for all cells. The median value of cell brightness of one cell is the value obtained by averaging the median brightness values within the cell regions of individual horny layer cells in the horny layer image for all cells. The minimum value of cell brightness of one cell is the value obtained by averaging the minimum brightness values within the cell regions of individual horny layer cells in the horny layer image for all cells. The range of brightness values is generally 8 - 16 bit (RGB), but other ranges are also acceptable. Hereinafter, one or more numerical values selected from the group consisting of the cell region area, multilayer peeling area, multilayer peeling rate, average value of cell brightness of one cell, standard deviation of cell brightness of one cell, median value of cell brightness of one cell, and minimum value of cell brightness of one cell are also referred to as horny layer parameter values.

[0014] The digitization by the image processing system can be performed using a known image processing system. For example, the image processing software attached to the above-mentioned digital microscope, commercially available image processing software, etc. can be used. Further, an image processing system having a plurality of learning corner layer images in advance and a machine learning model obtained by performing machine learning on one or more of the cell region (region where cells exist), the multilayer peeling region (region where two or more layers of the stratum corneum overlap and peel off), and the single cell region (region of each single cell) in each learning corner layer image by visual evaluation can also be used. Input the corner layer image to be digitized into this machine learning model, output one or more of the cell region, the multilayer peeling region, and the single cell region of this corner layer image, and calculate the stratum corneum parameter values (cell region area, multilayer peeling area, multilayer peeling rate, single cell brightness average value, single cell brightness standard deviation, single cell brightness median value, single cell brightness minimum value) based on one or more of the cell region, the multilayer peeling region, and the single cell region output by the machine learning model, so that the stratum corneum parameter values equivalent to those based on visual evaluation can be calculated quickly. Further, one or more of the stratum corneum region, the multilayer peeling region, and the single cell region output by the image processing system having the machine learning model can be visually corrected by a person to obtain the stratum corneum parameter values.

[0015] The method for estimating the total protein amount of the stratum corneum using this digitized stratum corneum parameter value as an index is not particularly limited, and a known method can be used. For example, a simple regression analysis or a multiple regression analysis of the stratum corneum parameter values may be performed. The multiple regression analysis may be a linear multiple regression analysis or a non-linear multiple regression analysis. Further, other parameters other than the cell region area, the multilayer peeling area, the multilayer peeling rate, the single cell brightness average value, the single cell brightness standard deviation, the single cell brightness median value, and the single cell brightness minimum value may be included as explanatory variables in the multiple regression analysis.

Example

[0016] <Machine learning sample> For 412 women (aged 18 to 87, average age 46.8 years), stratum corneum cells were collected from the face by the tape stripping method. The collected stratum corneum cells were photographed in a non-stained state using a digital microscope (Keyence Corporation, VHX-5000) at a resolution of 8-bit (RGB color), 0.41 μm / pixel, and a pixel number of 1600x1200 pixels with transmitted light. For each sample, 2 to 3 fields of view were photographed and used for machine learning.

[0017] Using the image annotation software Labelme, the cell region, stratified exfoliation region, and single-cell region were visually identified to obtain stratum corneum images for learning. Each stratum corneum image for learning and the cell region, stratified exfoliation region, and single-cell region by visual evaluation were used for machine learning to obtain a machine learning model capable of outputting the cell region, stratified exfoliation region, and single-cell region.

[0018] <Sample> For 227 women (aged 28 to 87, average 47.2 years old), stratum corneum cells were collected from the face by the tape stripping method. 3 to 5 samples were collected per person, and a total of 966 sample images were obtained. The sample preparation method is the same as that for the machine learning samples. The sample images were analyzed by an image processing device equipped with a machine learning model, and the cell region area, stratified exfoliation area, stratified exfoliation rate, average value of single-cell brightness, standard deviation of single-cell brightness, median value of single-cell brightness, and minimum value of single-cell brightness of each sample image were quantified to obtain stratum corneum parameter values.

[0019] Furthermore, the single-cell area, single-cell perimeter length, circularity, area of the rectangle circumscribing a single cell, aspect ratio of the long and short sides of the rectangle circumscribing a single cell, approximated 4-6 polygon, and maximum value of single-cell brightness were also quantified to obtain stratum corneum parameter values. The single-cell area is the value obtained by averaging the areas of individual stratum corneum cells in the stratum corneum image over all cells. The single-cell perimeter length is the value obtained by averaging the perimeter lengths of individual stratum corneum cells in the stratum corneum image over all cells. The circularity is the value obtained by averaging the degree of circularity (calculated by 4π×(area) / (perimeter squared)) of the regions of individual stratum corneum cells in the stratum corneum image over all cells. The rectangular area circumscribing a single cell is the value obtained by averaging, over all cells, the area of the rectangle with the minimum area that covers all the individual stratum corneum cells in the stratum corneum image. The aspect ratio of the rectangle circumscribing a single cell is the value obtained by averaging, over all cells, the ratio of the long side to the short side (long side / short side) of the rectangle with the minimum area that covers all the individual stratum corneum cells in the stratum corneum image. The approximated 4 - 6 - gon is defined as follows: With the centroid of the shape of each individual stratum corneum cell as the center, a regular 4 - 6 - gon is placed within the stratum corneum cell region. The angle and size are adjusted so that the area of the region protruding from the regular 4 - 6 - gon is minimized. When the area of the protruding region is minimized, the area of the protruding region is divided by the area of the stratum corneum cell, and the n for which this value is the minimum among the regular n - gons (n is 4 - 6) is defined as the approximated n - gon. The value obtained by averaging, over all cells, the n of each individual stratum corneum cell in the stratum corneum image is the approximated 4 - 6 - gon. The maximum brightness value of a single cell is the value obtained by averaging, over all cells, the maximum brightness value within the cell region of each individual stratum corneum cell in the stratum corneum image.

[0020] Regarding 966 samples, as a result of comparing the cell region and the delamination region by visual evaluation with the cell region and the delamination region analyzed by an image processing apparatus equipped with a machine learning model, respectively, the ratio of the cell region area by visual evaluation to the cell region area analyzed by the image processing apparatus equipped with a machine learning model was 95%, and the ratio of the delamination region area by visual evaluation to the delamination region area analyzed by the image processing apparatus equipped with a machine learning model was 86%. The cell region and the delamination region by visual evaluation were equivalent to the cell region and the delamination region analyzed by the image processing apparatus equipped with a machine learning model.

[0021] <Measurement of total protein amount> For the samples after image imaging, the total protein amount was measured using a BCA protein assay (BCA Protein Assay kit, Thermo fisher scientific).

[0022] "Simple regression analysis" The single regression analysis was performed on each stratum corneum parameter value (cell area, multilayer exfoliation area, multilayer exfoliation rate, average brightness value of a single cell, standard deviation of brightness of a single cell, median brightness of a single cell, minimum brightness value of a single cell) and the total protein amount. The correlation coefficient r, p-value, and the equation of the single regression line (Y = aX + b, where X is each stratum corneum parameter value and Y is the total protein amount) are shown in Table 1.

Table 1

[0023] The cell area, multilayer exfoliation area, multilayer exfoliation rate, average brightness value of a single cell, standard deviation of brightness of a single cell, median brightness of a single cell, and minimum brightness value of a single cell, which are the stratum corneum parameter values of the present invention, had a correlation (|r|≥0.2) with the total protein amount. Also, when the single regression analysis was performed in the same manner, no correlation was found between the total protein amount and the area of a single cell, perimeter of a single cell, circularity, area of the rectangle circumscribing a single cell, aspect ratio of the long and short sides of the rectangle circumscribing a single cell, approximated 4-6 polygon, and maximum brightness value of a single cell, which are not the stratum corneum parameter values of the present invention (|r| was less than 0.15 in all cases).

[0024] "Multiple regression analysis" Multiple regression analysis was performed using the seven stratum corneum parameter values of the present invention that showed a correlation with the total protein amount as explanatory variables. The equation of the multiple regression line (Y = a1X1 + a2X2 + ··· + a7X7 + b, where Xn is each stratum corneum parameter value and Y is the total protein amount) is shown in Table 2. The correlation coefficient |r| was 0.616 and the p-value < 0.0001, and a high correlation was recognized by the multiple regression analysis.

[0025]

Table 2

[0026] Furthermore, multiple regression analysis was performed using 14 stratum corneum parameter values including 7 stratum corneum parameters that did not show a correlation with the total protein amount as explanatory variables. The equation of the multiple regression line (Y = a1X1 + a2X2 + ··· + a 14 X 14+b, Xn are the parameter values of each horny layer, and Y is the total protein amount) are shown in Table 3. The correlation coefficient |r| was 0.632 and the p-value <0.0001. A high correlation was observed by combining the horny layer parameter values of the present invention with other parameter values.

[0027] [Table 3]

Claims

Claim 1 Specify the cell region, stratified exfoliation region, and single cell region of the stratum corneum image, Based on the specified cell region, stratified exfoliation region, and single cell region of the stratum corneum image, quantify the stratum corneum parameter value selected from the group consisting of cell region area, stratified exfoliation area, stratified exfoliation rate, single cell luminance average value, single cell luminance standard deviation, single cell luminance median value, and single cell luminance minimum value, and including at least the single cell luminance minimum value, A method for estimating the total protein amount of the stratum corneum, which estimates the amount of the total protein of the stratum corneum by performing simple regression analysis or multiple regression analysis using the stratum corneum parameter value as an index. Claim 2 The method for estimating the total protein amount of the stratum corneum according to claim 1, wherein one or more of the cell region, the stratified exfoliation region, and the single cell region are specified using a machine learning model obtained by machine learning one or more of the cell region, the stratified exfoliation region, and the single cell region in a plurality of pre-acquired learning stratum corneum images and the visual evaluation in each learning stratum corneum image.

Images