JP2017074217A - Skin state estimation device and operation method thereof - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a skin state estimation device capable of appropriately estimating a skin state.SOLUTION: A skin state estimation device 10 and 110 includes a skin temperature acquisition means 20 and/or image data acquisition means 120, skin state estimation means 30 and 130, and state visualization means 200. The skin temperature acquisition means 20 acquires skin temperature data in a time-series manner. The image data acquisition means 120 acquires captured skin image data on an examination object region in a time-series manner. The skin state estimation means 30 and 130 estimate a skin state of the examination object region based on a plurality of components acquired by breaking down the skin temperature data and/or skin blood circulation data by singular value decomposition, principal component analysis or independent component analysis. The state visualization means 200 determines whether or not the examination object region is abnormal based on a skin state activity estimated by the skin state estimation means 30.SELECTED DRAWING: Figure 5

Description

  The present invention relates to a skin condition estimation apparatus.

  In recent years, techniques for analyzing skin images and using them for treatment and diagnosis have been studied. For example, Patent Document 1 (Japanese Patent Laid-Open No. 7-124126) discloses a technique for extracting biological information as a moving image without touching or constraining an electrode to a subject. Patent Document 2 (Japanese Translation of PCT International Publication No. 2008-505684) discloses a technique that can identify breast cancer from a thermographic image. Patent Document 3 (Japanese Translation of PCT International Publication No. 2003-524490) discloses a technique for comprehensively determining inflammation such as joints from swelling, color, joint range of motion, and the like.

  However, since the skin image is affected by various conditions, it is difficult to specify the cause of the image change. As a result, a situation in which the skin condition cannot be properly grasped and it is difficult to effectively treat or diagnose a specific disease or the like has occurred.

  The subject of this invention is providing the skin state estimation apparatus which can estimate a skin state appropriately.

  A skin condition estimation apparatus according to a first aspect of the present invention includes skin temperature acquisition means and / or skin condition acquisition means, skin condition estimation means, and abnormality determination means. The skin temperature acquisition means acquires skin temperature data in time series. The skin temperature data is skin temperature data detected from the skin of the inspection target part of the human body and includes position data of the detection part. The skin condition acquisition means acquires skin blood flow data in time series. The skin blood flow data is obtained based on RGB data of the captured image data obtained by the RGB processing by performing RGB processing on the captured image data obtained by photographing the skin of the examination target part of the human body in time series. The skin condition estimating means determines the skin condition of the site to be inspected based on a plurality of components obtained by decomposing the skin temperature data and / or skin blood flow data by singular value decomposition, principal component analysis or independent component analysis. presume. The abnormality determination unit determines whether or not the inspection target part is abnormal based on the skin state of the inspection target part estimated by the skin state estimation unit.

  In the skin condition estimation apparatus according to the first aspect of the present invention, based on a plurality of components obtained by decomposing skin temperature data and / or skin blood flow data by singular value decomposition, principal component analysis, or independent component analysis. Since the skin state of the site to be inspected is estimated, the cause of the image change can be specified regardless of external factors, and the skin state can be estimated appropriately.

  The skin state estimation device according to a second aspect of the present invention is the skin state estimation device according to the first aspect, wherein the skin state estimation means includes a plurality of components whose amplitude of the component waveform is not activated when the skin is activated. A component having a correlation with a change at the time of activation is extracted as a determination component. Then, the skin state estimation means determines whether or not the inspection target site is abnormal based on the determination component.

  In the skin state estimation apparatus according to the second aspect of the present invention, a component having a correlation with skin activation / non-activation among a plurality of components is extracted as a determination component for estimating the skin state of the subject. For this reason, a skin state can be estimated from a component that is presumed to be highly related to the skin state of the subject. As a result, it is possible to increase the validity of the abnormality determination of the inspection target part.

  A skin condition estimation apparatus according to a third aspect of the present invention is the skin condition estimation apparatus according to any one of the first to third aspects, and further includes a disease information storage unit. The disease information storage unit stores the skin state and the disease information in association with each other. In addition, the abnormality determination unit determines that the examination target site is abnormal based on the skin state, and presents the disease information extracted from the disease information storage unit.

  In the skin state estimation device according to the third aspect of the present invention, the accuracy of abnormality determination can be improved by optimizing the association between the skin state stored in the disease information storage unit and the disease information.

  A skin condition estimation apparatus according to a fourth aspect of the present invention is the skin condition estimation apparatus according to any one of the first to third aspects, wherein the skin temperature acquisition means and / or the skin condition acquisition means, the abnormality determination means, Is stored in the smart device.

  In the skin state estimation apparatus according to the fourth aspect of the present invention, information is input / output by the smart device, so that the subject can easily determine whether or not the region to be examined is abnormal. In addition, the calculation load can be reduced by providing the abnormality determination means in the server.

  A skin condition estimation apparatus according to a fifth aspect of the present invention is the skin condition estimation apparatus according to any one of the first to fourth aspects, wherein the skin temperature acquisition means and / or the skin condition acquisition means, and the skin condition estimation means And the abnormality determination means are stored in the smart device.

In the skin condition estimation apparatus according to the fifth aspect of the present invention, information is input / output and calculated by the smart device, so that the subject can easily determine whether or not the region to be examined is abnormal. The skin state estimation method according to the sixth aspect is executed using the skin state estimation device according to any one of the first to fifth aspects. In this skin state estimation method, the skin at the site to be examined is cooled and the skin at the site to be examined is activated. Then, based on the skin temperature data and / or the blood flow data before and after activation, it is determined whether or not the site to be examined corresponds to at least one symptom of skin cancer, acne, breast cancer, coli and non-disease To do. Here, “non-disease” means a range of health conditions but close to illness.

  In the skin condition estimation method according to the sixth aspect of the present invention, the skin at the site to be examined is cooled and the skin at the site to be examined is activated, so skin temperature data and / or skin blood flow data before and after activation. Based on the above, it can be easily determined whether or not the region to be examined is abnormal (whether or not it corresponds to at least one symptom of skin cancer, acne, breast cancer, stiffness, and non-disease).

  In the skin state estimation apparatus according to the first aspect of the present invention, the skin state of the site to be examined can be appropriately estimated.

  In the skin condition estimation apparatus according to the second aspect of the present invention, the validity of the abnormality determination of the inspection target part can be increased.

  In the skin state estimation device according to the third aspect of the present invention, the accuracy of abnormality determination can be increased.

  In the skin condition estimation apparatus according to the fourth and fifth aspects of the present invention, it is possible to easily determine the abnormality of the inspection target site using a smart device.

  In the skin state estimation method according to the sixth aspect of the present invention, it is possible to easily determine whether or not the region to be examined is abnormal.

Schematic of the skin condition estimation apparatus which concerns on one Embodiment of this invention. The flowchart which shows an example of the flow of a process at the time of identifying the component which shows the change of the skin temperature relevant to a specific disease etc. in a skin state estimation apparatus. Schematic of the skin condition estimation apparatus which concerns on one Embodiment of this invention. The flowchart which shows an example of the flow of a process at the time of identifying the component which shows the RGB change of the skin relevant to a specific disease etc. in a skin state estimation apparatus. 1 is a schematic diagram of an abnormality determination device according to an embodiment of the present invention.

  Before describing the embodiments of the present invention, first, the knowledge obtained by the present inventors, which is an important basis for the inventors of the present invention, will be described.

(1) The main points of knowledge by the present inventors As a result of intensive studies, the present inventors have detected the skin temperature of the human body, and time-series skin temperature data including the position data (coordinate data) of the detection site, or Decompose time-series skin blood flow data calculated based on RGB data obtained from time-series skin image data into multiple components using singular value decomposition, principal component analysis, or independent component analysis Then, it was found that by analyzing the plurality of decomposed components, it is possible to identify components that show changes in skin temperature or blood flow that reflect specific diseases and the like. And the present inventors arrived at this invention which can visualize a subject's physiological state based on the estimated skin state by estimating a subject's skin state and analyzing this.

(2) Method for acquiring various skin data and method for analyzing various acquired data (2-1) Method for acquiring skin temperature data and method for analyzing skin temperature data Next, the present inventors have obtained the above knowledge. A method for acquiring skin temperature data used for obtaining and a method for analyzing skin temperature data will be described.

  The infrared thermography device detects the infrared radiation energy emitted from the object with an infrared camera, converts the detected infrared radiation energy into the temperature of the object surface (in this case, the temperature in degrees Celsius), and converts the temperature distribution. It is a device that can display and accumulate as skin temperature data (for example, image data representing temperature distribution). In addition, NEC Avio Infrared Technology Co., Ltd. R300 was used as an infrared thermography apparatus.

  Also, in this test, the skin was activated for the subject while acquiring skin temperature data. Thereby, the skin temperature data at the time of non-activation and the skin temperature data at the time of activation were acquired. As a method of activating the skin, a method of cooling the skin at the site to be inspected in the human body and then leaving it for a predetermined time can be employed. Note that the skin of the subject was cooled for 10 minutes after 5 minutes from the start of skin temperature data acquisition.

  For analysis of skin temperature data, singular value decomposition was performed using a MATLAB® (registered trademark) SVD (Singular Value Decomposition) as an analysis tool. In singular value decomposition, all skin temperature data (data for 30 minutes) acquired in time series are targeted, the factor is time data every 30 seconds (60 time points in 30 minutes), and the measure is the period (30 seconds) ) Skin temperature data (240 × 320 pixels). Then, skin temperature data X was decomposed into a plurality of components by singular value decomposition, and a time distribution V, a spatial distribution U of each component, and a singular value S indicating the size of each component were calculated. These relationships are expressed by the following equations. V ′ is a matrix in which the rows and columns of V are exchanged.

  Here, in this infrared thermography apparatus, as described above, infrared radiation energy detected from an object is converted into temperature, and the temperature distribution is used as skin temperature data. By the way, when skin temperature is acquired using an infrared thermography apparatus for human subjects, the skin is also affected by temperature changes (so-called noise) that are not related to various specific diseases such as body movement and / or autonomic nerve activity. It is acquired as temperature data. Therefore, in order to detect a temperature change not related to such a specific disease or the like, relative skin temperature data was created by creating a total average value of “0” for every 30 seconds of skin temperature data. The skin temperature data is also analyzed by using singular value decomposition using MATLAB (registered trademark) SVD as an analysis tool, and component waveform diagrams and temperature distribution diagrams of each component corresponding to the singular value S are created. Analyzes are performed to identify components that show changes in skin temperature reflecting the above.

  In the following, for convenience of explanation, the skin temperature data acquired by the infrared thermography device is referred to as “skin temperature data according to temperature converted data”, and is based on the temperature converted data every predetermined time (in this test, every 30 seconds). The relative skin data in which the total average value of the temperature data included in the skin temperature data is “0” is referred to as “skin temperature data corresponding to the relative temperature conversion data”.

(2-2) Captured Image Data Acquisition Method and Captured Image Data Analysis Method Next, the captured image data acquisition method and captured image data analysis method used by the present inventors for obtaining the above knowledge explain.

  In addition, as a photographing device, a liquid crystal screen photographing device provided in iPad Air (registered trademark) manufactured by Apple Inc. was used, and color moving image data was obtained as time-series photographed image data.

  Furthermore, in this test, the skin was activated with respect to the test subject while acquiring moving image data of the skin at the site to be examined. Thereby, the moving image data of the skin at the time of non-activation and the moving image data of the skin at the time of activation were acquired. Similarly to the above, as a method for activating the skin, a method of cooling the skin of the human body to be inspected and then leaving it for a predetermined time can be employed. Note that the skin of the subject was cooled for 10 minutes after 5 minutes had elapsed since the start of the acquisition of skin moving image data.

For analysis of skin moving image data, blood flow data is calculated based on RGB data obtained from the captured skin moving image data, and MATLAB® SVD is used for the calculated time-series blood flow data. Singular value decomposition was performed as an analytical tool. Here, according to the CIE-L ^* a ^* b ^* color system, an erythema index “a ^* ” correlated with the redness and hemoglobin amount calculated from the RGB data of the image is obtained, and this is used as blood flow data. . In the singular value decomposition, blood flow volume data (here, erythema index) based on RGB data obtained from all moving image data (30-minute data) acquired in time series is targeted, and the factor is set every 30 seconds. Erythema index calculated from time data (60 time points in 30 minutes) and RGB data in that period (every 30 seconds) (taken out frame data for 1 second every 30 seconds, and RGB values obtained from the frame data) Erythema index calculated from the average value of 240 × 320 pixels). Then, by singular value decomposition, time-series blood flow data based on RGB data obtained from facial moving image data is decomposed into a plurality of components, and each component's time distribution V, spatial distribution U, and each component And a singular value S indicating the magnitude of. In addition, these relationships are represented by the same formula as the above formula (Formula 1).

  Then, based on the time distribution V and the spatial distribution U of each component obtained by singular value decomposition, a component indicating a change in the blood circulation volume of the skin reflecting a specific disease or the like, that is, a component indicating an RGB change in the skin is identified.

  About the component waveform figure of each component, it analyzes about the presence or absence of the correlation of the amplitude of the component waveform, and the time of skin non-activation and the time of skin activation. Specifically, it is evaluated whether or not there is a correlation between the amplitude shown in the component waveform diagram of each component and the skin non-activation period / skin activation period.

  Regarding the blood flow distribution chart of each component, the presence or absence of a change in blood flow at a predetermined part of the face was analyzed. The blood circulation distribution map is created by arranging the spatial distribution U calculated for each pixel at the position of each pixel. It is evaluated whether or not there is a change in the blood flow volume at the examination site in the blood flow volume distribution chart of each component created in this way. In addition, regarding the presence or absence of changes in blood flow volume at the site to be examined in the blood flow distribution map, the blood flow volume change is determined by visual inspection or if the blood flow volume value at the site to be examined is not “0.000”. The standard for the presence or absence of

  Note that the polarity (plus or minus) of the blood flow data X is determined by the relationship between the spatial distribution U, the singular value S, and the time distribution V. Therefore, the polarity is reversed in the component waveform diagram and the blood flow distribution diagram of each component. May appear. For this reason, regarding the evaluation of the component waveform diagram and the blood flow distribution diagram, the polarity is not an evaluation target.

  By the way, when skin image data is acquired using an imaging device, light may be reflected by the skin during imaging, and this reflected light may enter the lens of the imaging device. Then, this reflected light is recorded in the photographed image data of the photographed skin. Here, in the RGB data obtained from the photographed image data, the change in brightness based on the blood circulation amount of the skin may be smaller than the change in brightness based on the reflected light, and the RGB obtained from the photographed image data in which the reflected light is recorded. When the blood flow calculated based on the data is analyzed, it is considered that there is a possibility that RGB changes (so-called noise) of the skin not related to a specific disease or the like may be mixed. Therefore, in order to prevent the mixture of RGB changes in the skin that are not related to such specific diseases, the relative blood flow from the relative RGB data in which the total average value of the RGB data every 30 seconds is set to “0”. Data is created, and the created blood flow data is also subjected to singular value decomposition using the MATLAB (registered trademark) SVD as an analysis tool, and a component waveform diagram and blood flow distribution diagram of each component according to the singular value S To identify the component showing the RGB change of the skin reflecting a specific disease or the like.

  In the following, for convenience of explanation, relative blood flow data based on relative RGB data with a total average value of RGB data every predetermined time (every 30 seconds in this test) being “0” is referred to as “relative conversion. The blood flow data is referred to as “blood flow data”, and the blood flow data based on the RGB data before conversion into relative RGB data is simply referred to as “blood flow data”.

(3) Skin condition estimation apparatus Next, based on the knowledge demonstrated above, the skin condition estimation apparatuses 10 and 110 which concern on one Embodiment of this invention which the present inventors came to complete are demonstrated. In addition, the skin state estimation apparatus which concerns on this invention is not limited to the following embodiment, In the range which does not deviate from a summary, it can change suitably.

  Skin condition estimation apparatuses 10 and 110 according to an embodiment of the present invention include a skin condition estimation unit 30 that estimates a skin condition based on skin temperature data, and / or a skin condition that estimates a skin condition based on captured image data of the skin. Estimating means 130 is provided. Below, before demonstrating the skin state estimation apparatuses 10 and 110 which concern on one Embodiment of this invention, each skin state estimation means 30 and 130 are demonstrated.

(3-1) Skin condition estimating means 30 for estimating the skin condition based on the skin temperature data
FIG. 1 is a schematic diagram of a skin condition estimation apparatus 10 according to an embodiment of the present invention. FIG. 2 is a flowchart showing the flow of processing when the skin state estimation apparatus 10 identifies a component indicating a change in skin temperature related to a specific disease or the like.

  The skin condition estimation means 30 provided in the skin condition estimation apparatus 10 estimates the skin condition of the inspection target part from the skin temperature of the inspection target part of the human body. As shown in FIG. 1, the skin state estimation device 10 includes a skin temperature acquisition unit 20, a skin state estimation unit 30, and a state visualization unit 200.

  The skin temperature acquisition means 20 detects the skin temperature of the inspection target part of the human body, and acquires skin temperature data including the detected temperature data and the position data of the detected part in time series (step S1). Here, the skin temperature acquisition means 20 is an infrared thermography apparatus, and includes an infrared camera 21 and a processing unit 22 as shown in FIG. The infrared camera 21 is for detecting infrared radiant energy emitted from the skin at the site to be examined. In this case, it is assumed that the infrared camera 21 detects infrared radiation energy from the skin at the site to be examined. The processing unit 22 converts the infrared radiant energy detected by the infrared camera 21 into temperature to obtain temperature data, and the temperature distribution of the skin temperature at the examination target site with the location where the infrared radiant energy is detected as position data (coordinate data). A diagram is created, and the created temperature distribution diagram is processed as skin temperature data corresponding to the temperature conversion data. Skin temperature data corresponding to the temperature conversion data is accumulated in a storage unit (not shown) of the processing unit 22.

  Here, the skin is activated while the skin temperature acquisition means 20 acquires the skin temperature data corresponding to the temperature-converted data. That is, the skin temperature data corresponding to the temperature conversion data acquired by the skin temperature acquisition means 20 includes data of a period during which skin is activated for an individual. The skin activation at the site to be inspected is not particularly limited as long as it is estimated that the skin is in an activated state. For example, the content is appropriately determined according to the purpose of use of the skin state estimating device 10. It may be configured to be determined.

  The skin condition estimation means 30 estimates the skin condition of the site to be examined based on the skin temperature data corresponding to the temperature conversion data acquired by the skin temperature acquisition means 20. Specifically, as shown in FIG. 1, the skin state estimation unit 30 includes a conversion unit 31, an analysis unit 32, and an estimation unit 33.

  The conversion unit 31 converts temperature data included in the skin temperature data corresponding to the temperature conversion data into relative temperature data, and skin temperature data based on the converted relative temperature data, that is, skin corresponding to the relative temperature conversion data. Temperature data is created (step S2). Specifically, the conversion unit 31 uses the average value of the temperature data included in the skin temperature data corresponding to the temperature conversion data every predetermined time (for example, 30 seconds) as a reference value, and converts the temperature data into a relative temperature. Convert to data. And the conversion part 31 produces the skin temperature data according to relative temperature conversion data using the converted relative temperature data and position data.

  The analysis unit 32 decomposes each of the skin temperature data corresponding to the time-series temperature conversion data and the skin temperature data corresponding to the relative temperature conversion data into a plurality of components by singular value decomposition, principal component analysis, or independent component analysis. (Step S3). Here, the analysis unit 32 uses the SVLAB of MATLAB (registered trademark) as an analysis tool for each of the skin temperature data according to the acquired temperature conversion data and the skin temperature data according to the converted relative temperature conversion data. And singular value decomposition. In singular value decomposition, the skin temperature data corresponding to the temperature conversion data acquired in time series and the skin temperature data corresponding to the relative temperature conversion data are converted into time data for each predetermined period (for example, 30 seconds), and the measure is It is performed as skin temperature data corresponding to the temperature converted data and relative temperature converted data corresponding to the temperature converted data in that period. Then, by singular value decomposition, each of the skin temperature data according to the temperature conversion data and the skin temperature data according to the relative temperature conversion data is decomposed into a plurality of components, and the time distribution, the spatial distribution, and the size of each component And a singular value indicating.

  In addition, the analysis unit 32 determines whether each component satisfies the first condition and the second condition in order to identify a component indicating a change in skin temperature related to a specific disease from a plurality of components decomposed by singular value decomposition. It is determined whether or not (step S4a, step S4b, step S5a, and step S5b). Here, the analysis unit 32 first determines whether or not the first condition is satisfied for each component based on the skin temperature data corresponding to the temperature conversion data (step S4a), and the first condition is determined in step S4a. It is determined whether or not the second condition is satisfied for the component based on the skin temperature data corresponding to the temperature conversion data determined to be satisfied (step S4b). Of the components based on the skin temperature data corresponding to the relative temperature conversion data, the first condition is satisfied only for the components that match the components determined to satisfy the first condition and the second condition in step S4a and step S4b. (Step S5a), and then the second condition is satisfied for the component based on the skin temperature data corresponding to the relative temperature conversion data determined that the first condition is satisfied in Step S5a. It is determined whether or not there is (step S5b). However, the order of the determination in the analysis unit 32 is not limited to this. For example, each component based on the skin temperature data corresponding to the temperature conversion data and each of the components based on the skin temperature data corresponding to the relative temperature conversion data It may be determined whether or not the component satisfies the first condition and the second condition, and the component having the matching determination result may be finally extracted.

  The first condition is a condition that the amplitude of the component waveform of the component decomposed by the singular value decomposition has a correlation with a change when the skin is not activated and when the skin is activated. The analysis unit 32 extracts a component that satisfies the first condition from the plurality of components as a determination component. Here, there is a certain period of time for activating the skin of the site to be inspected while acquiring skin temperature data corresponding to the temperature conversion data. The analysis unit 32 sets a period during which the skin of the examination target site is not activated, a period when the skin of the examination target site is activated, and a period when the skin of the examination target site is activated. And the period which is not activated, and the component waveform of each component are compared and analyzed. The analysis unit 32 uses the comparison analysis result based on the component waveform data to evaluate whether or not the component waveform of each component and the skin non-activation time and the skin activation time are correlated, and a plurality of components Among these, the component evaluated as having a correlation is extracted as a determination component that satisfies the first condition. On the other hand, the analysis unit 32 determines that a component evaluated as having no correlation among the plurality of components is not a component that does not satisfy the first condition and shows a temperature change related to a specific disease or the like (step S6).

  Here, a period for activating the skin of the site to be inspected is given for a certain period when acquiring skin temperature data according to the temperature conversion data, and based on this, the analysis unit 32 extracts the determination component, The content of the first condition, that is, the means for extracting the determination component in the analysis unit 32 is not limited to this. For example, when a component showing a component waveform that is correlated with the non-activation time and the activation time of the skin among the plurality of components by performing an experiment or the like in advance, the analysis unit 32 The component specified from the plurality of components is extracted as a determination component. Note that the criterion for determining whether or not the first condition is satisfied by the analysis unit 32 is appropriately determined by simulation, experiment, desktop calculation, or the like according to the purpose of use of the skin state estimation device 10 or the like.

  The second condition is a condition that, in the extracted determination component, there is a temperature change in the skin of a predetermined part of the human body. The analysis unit 32 determines a component that satisfies the second condition among the determination components as a component that has a high possibility of being related to a specific disease or the like, and extracts it as a candidate component. That is, the analysis unit 32 determines whether or not the determination component is related to a specific disease or the like based on the presence or absence of a temperature change in the skin of a predetermined part of the human body. On the other hand, the analysis unit 32 does not satisfy the second condition and does not indicate a change in skin temperature related to a specific disease or the like when no temperature change occurs in the predetermined part of the skin. (Step S6). Note that the criterion for determining whether or not the second condition is satisfied by the analysis unit 32 is appropriately determined by simulation, experiment, desktop calculation, or the like according to the purpose of use of the skin state estimation device 10 or the like.

  And the analysis part 32 identifies the component determined to satisfy | fill 2nd conditions in step S5b as a component which shows the change of skin temperature reflecting a specific disease etc. (step S7). That is, the component identified as the component indicating the change in skin temperature reflecting the specific disease or the like in step S7 is a candidate extracted by analyzing and analyzing the skin temperature data corresponding to the temperature conversion data by singular value decomposition. This is a component that matches between the component and the candidate component extracted by decomposing and analyzing the skin temperature data corresponding to the relative temperature conversion data by singular value decomposition. Note that candidate components that do not match in both analyzes are determined not to be components that show changes in skin temperature related to a specific disease or the like in step S6.

  The estimation unit 33 estimates the skin state of the site to be examined based on the component identified by the analysis unit 32 as a component indicating a change in skin temperature related to a specific disease or the like.

(3-1-1) Modification 1A
The skin condition estimation means 30 has a conversion unit 31, and skin temperature data corresponding to the relative temperature conversion data is created by the conversion unit 31. And the analysis part 32 not only skin temperature data according to the temperature conversion data acquired by the skin temperature acquisition means 20, but the skin temperature according to the relative temperature data based on the temperature data converted into relative temperature data. The data is also decomposed into a plurality of components by singular value decomposition, and each component is analyzed.

  It replaces with this and the skin state estimation means 30 does not need to have the conversion part 31. FIG. In this case, it is possible to omit the process of creating skin temperature data corresponding to the relative temperature conversion data or analyzing data based on the skin temperature data corresponding to the relative temperature conversion data.

  However, in order to accurately identify a component related to a specific disease or the like, the skin state estimation unit 30 includes the conversion unit 31 as in the above-described embodiment, and the skin temperature acquisition unit 20 is analyzed by the analysis unit 32. In addition to the skin temperature data corresponding to the temperature conversion data acquired by the above, the skin temperature data corresponding to the relative temperature data based on the temperature data converted to the relative temperature data is also converted into a plurality of components by singular value decomposition. It is desirable to decompose and analyze each component.

(3-1-2) Modification 1B
The skin temperature acquisition means 20 is an infrared thermography device that can acquire temperature data in a non-contact state with an object.

  However, the skin temperature acquisition means is limited to the infrared thermography apparatus as long as the skin temperature of the inspection target part of the human body is detected and the skin temperature data including the detected temperature data and the position data of the detection part can be acquired in time series. Not.

  For example, the skin temperature acquisition means may be a device including a temperature sensor. Specifically, a temperature sensor is attached to a part to be inspected in the human body, and time-series skin temperature data is acquired based on temperature data detected by the temperature sensor and position data of the part to which the temperature sensor is attached. May be. As described above, even when skin temperature data is acquired in a state in which the temperature sensor is in contact with a target individual, the temperature sensor is a conventional sensor such as an electroencephalogram measurement method, magnetic resonance imaging method, and near infrared spectroscopy. Compared with the detection method, data can be easily acquired. Thereby, the skin state of the region to be examined can be easily estimated.

(3-2) Skin condition estimating means 130 for estimating the skin condition based on the photographed image data
FIG. 3 is a schematic diagram of the skin condition estimation apparatus 110 according to the embodiment of the present invention. FIG. 4 is a flowchart showing an example of the flow of processing when the skin state estimation apparatus 110 identifies a component indicating RGB changes in skin related to a specific disease or the like.

  The skin condition estimating means 130 provided in the skin condition estimating apparatus 110 is an apparatus for estimating abnormal skin conditions, specific diseases, and the like from the photographed image data of the skin of the inspection target part of the human body. As shown in FIG. 3, the skin state estimation device 110 includes an image data acquisition unit 120, a skin state estimation unit 130, and a state visualization unit 200.

  The image data acquisition unit 120 acquires captured image data of at least a part of the skin of the examination target part of the human body in time series (step S101). The image data acquisition unit 120 is not particularly limited as long as it has at least a photographing device, and examples thereof include a portable terminal with a photographing device such as a smartphone or a tablet (for example, iPad: registered trademark). It is done. Here, as shown in FIG. 3, the image data acquisition unit 120 includes a camera 121 as a photographing apparatus and a storage unit 122. The camera 121 is for acquiring captured image data of the skin of the examination target part in time series. Here, the camera 121 captures a moving image of the region to be examined and acquires the captured moving image data. The storage unit 122 accumulates time-series photographed image data photographed by the photographing apparatus. Here, the storage unit 122 accumulates moving image data acquired by the camera 121.

  Further, here, while the time-series captured image data of the skin of the examination target site is acquired by the image data acquisition unit 120, the period for activating the skin of the test target site is given. That is, the captured image data acquired by the image data acquisition unit 120 includes data for a period for activating the skin of the examination target site. The skin activation at the site to be inspected is not particularly limited as long as the skin is estimated to be in an activated state. For example, the content is appropriately determined according to the purpose of use of the skin state estimating device 110. It may be configured to be.

  The skin state estimation unit 130 estimates the skin state of the site to be inspected based on the time-series captured image data of the skin acquired by the image data acquisition unit 120. Specifically, as shown in FIG. 3, the skin state estimation unit 130 includes an RGB processing unit 131, a conversion unit 132, a blood flow amount calculation unit 133, an analysis unit 134, and an estimation unit 135. Note that FIG. 3 shows an aspect in which the skin condition estimation unit 130 exists as one apparatus having the RGB processing unit 131, the conversion unit 132, the blood flow amount calculation unit 133, the analysis unit 134, and the estimation unit 135. However, the present invention is not limited to this, and part or each of the RGB processing unit 131, the conversion unit 132, the blood flow volume calculation unit 133, the analysis unit 134, and the estimation unit 135 exists as an independent device. May be. Further, here, the blood flow volume acquisition means is constituted by the image data acquisition means 120, the RGB processing section 131, the conversion section 132, and the blood flow volume calculation section 133.

  The RGB processing unit 131 performs RGB processing that decomposes the captured image data acquired by the image data acquisition unit 120 into three color components, an R component, a G component, and a B component (step S102).

  The conversion unit 132 converts the RGB data of the captured image data obtained by the RGB processing into relative RGB data (step S103). Specifically, the conversion unit 132 converts the RGB data into relative RGB data using the average value of the RGB data obtained from the acquired captured image data every predetermined time (for example, 30 seconds) as a reference value. To do.

  The blood flow volume calculation unit 133 calculates time-series blood flow volume data of the skin based on the RGB data of the captured image data obtained by the RGB processing (step S104).

  The analysis unit 134 decomposes the time-series relative converted blood flow data into a plurality of components by singular value decomposition, principal component analysis, or independent component analysis (step S105). Here, the analysis unit 134 performs singular value decomposition on the relative converted blood flow data using the SVLAB of MATLAB (registered trademark) as an analysis tool. Specifically, the singular value decomposition is performed on time-series relative converted blood flow data, with the factor being time data for each predetermined period (for example, 30 seconds), and the measure is calculated from relative RGB data for each period. This is performed as the calculated relative blood flow volume data for each pixel. Then, by singular value decomposition, the time-series relative converted blood flow data is decomposed into a plurality of components, and a time distribution, a spatial distribution, and a singular value indicating the size of each component are calculated.

  In addition, the analysis unit 134 determines whether each component satisfies a predetermined condition in order to identify a component indicating RGB change of skin related to a specific disease or the like from a plurality of components decomposed by singular value decomposition. (Step S106). Here, as the predetermined condition, for example, the condition that the amplitude of the component waveform of the component decomposed by the singular value decomposition is correlated with the change at the time of non-activation of the skin and the activation of the skin (hereinafter referred to as the first condition). ), A condition that the blood flow rate changes in the examination target region in the component decomposed by singular value decomposition (hereinafter referred to as a second condition), and the like. As the predetermined condition determined by the analysis unit 134, one or a plurality of conditions may be set. Here, it is assumed that the first condition is set as the predetermined condition.

  And the analysis part 134 extracts the component which satisfy | fills predetermined conditions among several components as a component for determination. Further, the analysis unit 134 identifies a component satisfying all the conditions included in the predetermined condition among the extracted determination components as a component indicating the RGB change of the skin related to a specific disease or the like (step S107). On the other hand, the analysis unit 134 determines that the component determined not to satisfy at least one condition included in the predetermined condition among the plurality of components is not a component indicating the RGB change of the skin related to the specific disease or the like ( Step S108).

  Here, as described above, only one condition (first condition) is set as the predetermined condition, and the skin of the examination site is activated while acquiring time-series captured image data of the skin. There is a certain period. For this reason, the analysis unit 134 activates the skin of the region to be inspected with the period when the skin of the region to be inspected is not activated as the time of non-activation of the skin, and the period of activation of the skin with the region of inspection as the time of skin activation The period to be activated and the period not to be activated and the component waveform of each component are comparatively analyzed. And the analysis part 134 evaluates whether the component waveform of each component, the time of non-activation of skin, and the time of skin activation have a correlation using the comparative analysis result based on component waveform data, Among these components, a component evaluated to be correlated is extracted as a determination component that satisfies a predetermined condition, and is identified as a component that indicates a change in skin RGB related to a specific disease or the like. On the other hand, the analysis unit 134 determines that a component evaluated as having no correlation among the plurality of components is not a component that does not satisfy the predetermined condition and indicates a change in RGB of the skin related to a specific disease or the like.

  Here, a period for activating the skin of the region to be inspected is obtained when time-series captured image data of the skin is acquired, and based on this, the analysis unit 134 extracts the determination component. The contents of one condition, that is, the determination component extraction means in the analysis unit 134 is not limited to this. For example, when a component showing a component waveform that is correlated with the non-activation time of the skin and the activation time of the skin among the plurality of components by performing an experiment or the like in advance, the analysis unit 134 The component specified from the plurality of components is extracted as a determination component. Note that the criterion for determining whether or not the first condition is satisfied by the analysis unit 134 is appropriately determined by simulation, experiment, desktop calculation, or the like according to the purpose of use of the skin state estimation device 110 or the like.

  When the second condition is set as the predetermined condition, the analysis unit 134 extracts a determination component based on whether or not there is a change in the blood flow rate of the skin at the examination target site. Specifically, the analysis unit 134 determines whether there is a change in the blood flow volume in the examination target site based on the blood flow volume distribution map corresponding to the plurality of components decomposed by the singular value decomposition, and the blood flow volume If the change occurs, it is determined that the component satisfies the second condition. On the other hand, when there is no change in blood flow volume at the examination site, the analysis unit 134 determines that the component does not satisfy the second condition. Note that the criterion for determining whether or not the second condition is satisfied by the analysis unit 134 is appropriately determined by simulation, experiment, desktop calculation, or the like according to the purpose of use of the skin state estimation device 110 or the like.

  Further, when time-series blood flow data based on RGB data before being converted into relative RGB data is calculated by the blood flow calculation unit 133, the blood flow data is subjected to singular value decomposition by the analysis unit 134. With respect to a plurality of components obtained by performing the same, it may be determined whether or not the first condition and / or the second condition is satisfied, and a determination component may be extracted.

  The estimation unit 135 estimates the skin state of the site to be examined based on the component identified by the analysis unit 134 as a component indicating the RGB change of the skin related to a specific disease or the like.

(3-2-1) Modification 2A
Note that the blood flow rate calculation unit 133 may calculate blood flow rate data of the skin at the site to be inspected mainly using the R component of each pixel included in the RGB data. In addition, blood flow volume data is not necessarily limited to the erythema index as long as blood flow volume data can be calculated based on RGB data.

(3-2-2) Modification 2B
The blood flow volume calculation unit 133 calculates relative converted blood flow volume data based on the relative RGB data converted by the conversion unit 132, but instead of or in addition to this, the blood flow volume calculation unit 133 converts the blood flow volume data into relative RGB data. The blood flow volume data may be calculated based on the RGB data before the check. Here, since the blood flow data calculated based on the RGB data before being converted into the relative RGB data is likely to have a component that correlates with a specific disease or the like (the test power is high), for example, relative The blood flow volume data calculated based on the RGB data before being converted into such RGB data may be analyzed prior to the relative converted blood flow volume data calculated based on the relative RGB data. In addition, for example, first, the blood flow data is analyzed to extract a component having a significant correlation, and the relative conversion blood flow data is calculated by analyzing only the component corresponding to the extracted component. Can be reduced.

(3-3) State visualization means 200
The state visualization unit 200 visualizes the subject by displaying the physiological state of the subject based on the skin state of the examination target site estimated by the skin state estimation unit 30 and / or the skin state estimation unit 130. For example, the state visualization unit 200 may include an analysis unit 201 that analyzes the physiological state of the subject by analyzing changes in the blood circulation state of the subject. Specifically, the analysis unit 201 determines the physiological state of the subject by analyzing changes in the blood circulation state in response to a stimulus applied to the skin of the detection target site. In addition, about the kind and level of a physiological state, based on the raise degree and / or duration of a blood circulation state, according to the use of the skin state estimation apparatuses 10 and 110, you may be able to install suitably. Then, the physiological state of the subject analyzed by the analysis unit 201 is output from the display unit 202 of the state visualization means 200 to the administrator, so that the administrator can know the physiological state of the subject. As the display unit 202, any display device that displays an image or a message can be adopted as long as it can visualize information on the analyzed physiological state of the subject person to the administrator. .

  In addition, after various components related to a specific disease or the like are identified in the analysis units 32 and 134, when various types of time series data are acquired by the skin temperature acquisition unit 20 and / or the image data acquisition unit 120, In the skin state estimation devices 10 and 110, the acquired various data are further decomposed into a plurality of components by singular value decomposition, and only the identified components are analyzed, so that the physiological state of the subject can be known in real time. it can.

  Furthermore, there is already a technique for acquiring heart rate information, biological information, etc. of a subject from the skin temperature of a detection target site or a photographed image, but various data obtained from the skin temperature acquisition means 20 and / or the image data acquisition means 120. By adopting a conventional technique for a component obtained by performing singular value decomposition or the like, heartbeat information and biological information can be obtained with high accuracy. Therefore, the analysis unit 32 and / or the analysis unit 134 have a function of analyzing a plurality of components subjected to singular value decomposition to acquire heart rate information and biological information, and based on the acquired heart rate information and biological information, the exchange nerve / parasympathy You may give the estimation part 33,135 of the said embodiment the function which estimates the function of a nerve.

(4) Features (4-1)
In the present embodiment, the skin state of the site to be examined is estimated based on the time-series skin temperature data and / or skin state data acquired by the skin temperature acquisition unit 20 and / or the image data acquisition unit 120. Therefore, it is possible to simply estimate the skin state of the site to be inspected and visualize the physiological state of the subject based on the estimated skin state without wearing a sensor or the like.

(4-2)
Here, when time-series skin temperature data and / or image data is acquired, the skin temperature and / or the blood flow rate change due to whether the skin of the site to be examined is not activated or not From this, a specific disease or the like can be estimated.

  In the present embodiment, while the time-series skin temperature data and / or image data is acquired by the skin temperature acquisition unit 20 and / or the image data acquisition unit 120, the skin of the examination target site is activated for a certain period. Yes. That is, in the present embodiment, a situation is created in which the skin is activated or not activated by not cooling the skin at the site to be examined. Then, the various time-series data acquired in this way are decomposed into a plurality of components by singular value decomposition, and the correlation between the component waveform and the skin activation time and non-activation time is evaluated for each component. Are extracted from a plurality of components as determination components. For this reason, for example, compared with a case where a predetermined component specified in advance by experiments or the like is extracted from a plurality of components as an extraction component, a plurality of components that are less relevant to a specific disease or the like are extracted as a plurality of extraction components. The possibility of being extracted from the components can be reduced.

  In the present embodiment, the term “disease” is a concept that includes not only a cause of a specific disease but also a cause that causes some abnormality in the human body.

(5) Application example of skin condition estimation apparatus Next, an application example of the skin condition estimation apparatus according to the present invention will be described.

  An example will be described in which the skin state estimation devices 10 and 110 of the embodiment or the modification are applied to an abnormality determination device 310 that determines an abnormality of the skin at the site to be examined.

  Specifically, as shown in FIG. 5, a disease information storage unit 210 is provided in the state visualization means 200. The disease information storage unit 210 is a memory that stores the estimation result of the skin condition and “disease information” in association with each other. Here, for example, skin temperature data and / or skin blood flow data are collected when the same skin function activation task is given to a subject suffering from a specific disease and a healthy subject for a certain period of time. To do. Then, the skin condition estimation result is classified based on the skin temperature data and / or skin blood flow data according to the symptoms of each subject, and the classified skin condition estimation result and the disease information are associated with each other to obtain a disease information storage unit 210. The disease information is data indicating, for example, skin cancer, breast cancer, acne, coli, non-disease and the like. The correlation between the skin condition estimation result and the disease information is optimized as appropriate.

  Then, the state visualization unit 200 extracts disease information from the disease information storage unit 210 based on the skin state estimation results calculated by the skin state estimation units 30 and 130. When the disease visualization unit 200 can extract the disease information from the disease information storage unit 210, the state visualization unit 200 determines that the examination target site is abnormal and presents the extracted disease information as the cause of the abnormality. On the other hand, when the disease visualization unit 200 cannot extract disease information from the disease information storage unit 210, the state visualization unit 200 determines that the examination target region is normal.

  In short, the abnormality determination device 310 includes skin temperature acquisition means 20 and / or image data acquisition means 120, skin state estimation means 30, 130, and state visualization means (abnormality determination means) 200. The skin temperature acquisition means 20 acquires skin temperature data in time series. The image data acquisition unit 120 acquires captured image data of the skin of the examination target part in time series. The skin condition estimation means 30, 130 is based on a plurality of components obtained by decomposing skin temperature data and / or skin blood flow data by singular value decomposition, principal component analysis, or independent component analysis. Estimate skin condition. The state visualization unit 200 presents to the subject whether or not the inspection target part is abnormal based on the skin state of the inspection target part estimated by the skin state estimation unit 30. Thus, according to the abnormality determination device 310, the skin state can be estimated easily.

  In the technique described in Patent Document 1, data obtained by taking the difference between the time T1 and the time T0 is used. If the difference is taken, the data of the portion that has not changed with time is canceled, and the spatial information indicating the “form” decreases. In short, only data that changes over time can be captured. On the other hand, in the technique using singular value decomposition or the like shown in the present embodiment, in addition to the component showing change, a component showing no change can be identified. Therefore, it is possible to capture the image change more accurately by using a lot of information.

  In addition, in the technique described in Patent Document 1, in order to take a difference, it is necessary to analyze after changing the frame rate of the video again when the subject “moves” (paragraph [0014] or the like). Changing the frame rate means "restarting the analysis from the beginning", so the amount of calculation increases dramatically and real-time processing becomes impossible. On the other hand, the technique using singular value decomposition or the like shown in the present embodiment has an advantage that it is not necessary to “update and record an image at a predetermined frame rate” because the motion can be extracted as one component.

(5-1) Abnormality determination of skin cancer and breast cancer An example in which the abnormality determination device 310 is used for abnormality determination of skin cancer, breast cancer, and acne will be described.

  When judging abnormality of skin cancer or breast cancer, ethanol is applied to the skin of the examination target site of the subject or the cold air of the air conditioner is applied to cool the skin of the site for a predetermined time. As the skin cools, the temperature drops, and when cooling is completed, the skin gradually returns to the original temperature. In this way, the skin is activated and deactivated.

  Here, when skin cancer or breast cancer occurs in the region to be examined, metabolism is accelerated and heat is locally generated. Therefore, even when the skin is cooled, the rate and amount of temperature decrease are small. Therefore, among the plurality of components obtained by the skin condition estimation means, the component that has a low temperature drop during cooling and the spatial component similar to the shape of skin cancer etc. in the spatial component map (specifically, on the face) A spatial component indicating a “spot” is extracted. That is, the size of the skin cancer or the like is set in advance based on the average diameter of the skin cancer or the like, and whether or not heat is locally generated in the region having the size is extracted. Note that changes other than the average size such as skin cancer are considered as spatial noise. Whether the noise is mere noise is determined by the fact that the temperature drops during cooling or that an image such as a spot is not extracted in the spatial component map.

  In this way, changes in the skin state before and after activation are analyzed, and it is suggested that the subject may have skin cancer or breast cancer.

  The technique described in Patent Document 2 is a technique for making a thermographic image three-dimensional, but the temperature of the skin varies depending on various factors. Therefore, it is difficult to distinguish between breast cancer and other heat sources. For example, in the state of wearing a garment such as that shown in Patent Document 2, heat is transmitted to the entire skin, making it difficult to specify the skin cancer site. On the other hand, if the technique using the singular value decomposition as shown in the present embodiment, it is possible to divide heat-related data into a spatial component and a time component, and analyze using a large amount of information. Can detect breast cancer with high probability.

(5-2) Acne Abnormal Judgment Acne is also accompanied by inflammation, so that the temperature is unlikely to decrease even if the skin is cooled. Therefore, it is also possible to determine whether acne has occurred by using the same principle as the above-described skin cancer and breast cancer abnormality determination. However, in this case, the size is set in advance for acne, not skin cancer.

  Moreover, skin cancer etc. and acne can also be determined simultaneously. The distinction between skin cancer or the like and acne is determined based on the size, the difference in temperature change, and the site to be examined.

  The technique described in Patent Document 3 determines the inflammation of a joint or the like from the swelling, color, range of motion of the joint, or the like. However, the technique using the thermography described in Patent Document 3 may not detect mild inflammation or the like. This is because temperature is influenced by various factors other than inflammation. On the other hand, in the technique using the singular value decomposition or the like shown in the present embodiment, it is possible to extract only the heat component related to inflammation by dividing the information about heat into the time component and the spatial component. Inflammation can be identified without measuring multiple measures (bulge, range of motion, etc.).

(5-3) Abnormality determination of stiffness Using the abnormality determination device 310, the stiffness can be objectively quantified. In this case as well, the skin of the subject is cooled for a predetermined time by applying ethanol to the skin of the subject to be examined or by applying cold air from an air conditioner.

  Here, when the muscle of the region to be inspected is in a state of stiffness, a low-temperature portion appears locally because the blood flow decreases. Therefore, from among the plurality of components obtained by the skin condition estimation means, extract a component that has a large temperature drop during cooling and that shows the same arrangement as the arrangement of muscles and blood vessels in the spatial component map Thus, it can be determined whether or not the state is a stiffness. If the correlation with cooling is low or the shape of the spatial component map is different from the arrangement of muscles or blood vessels, it is regarded as noise.

  In this way, the change in the skin state before and after activation is analyzed, and it is determined whether or not there is stiffness in the examination target site.

(5-4) Non-disease abnormality determination Since blood flow also decreases in the absence of disease, the temperature tends to decrease even when the skin is cooled. Therefore, it is possible to determine whether or not an illness has occurred by using the same principle as the above-described abnormality determination of stiffness. Here, “non-disease” means a state that is within the range of health conditions but is close to illness.

  It is also possible to determine whether the disease is unaffected or not. At this time, since the non-disease affects the blood flow of the entire body, the target site is wider than the stiffness. Accordingly, the stiffness can be detected from relative data in which the total average value of the temperature images is “0”. On the other hand, when the relative data in which the entire average value of the temperature image is “0” is used for the non-disease, the signal of the component disappears or decreases. Due to such a difference in properties, it is possible to simultaneously determine the stiffness and non-disease.

(6) Use of Smart Device Skin condition estimation apparatuses 10 and 110 according to the present embodiment may be stored in a smart device. Specifically, even if the skin temperature acquisition means 20 and / or the image data acquisition means 120, the skin state estimation means 30, 130, and the state visualization means 200 are stored in a smart device such as a multi-function mobile phone. Good. With this configuration, the user can input and output information and perform calculations using the smart device that is carried, so that the user can easily determine whether or not the examination target site is abnormal.

  In place of the above-described embodiment, the skin temperature acquisition unit 20 and / or the image data acquisition unit 120 and the state visualization unit 200 are stored in a smart device such as a multi-function mobile phone, and the skin state estimation units 30 and 130 are stored. You may employ | adopt the structure stored in a server apparatus. In this case, the calculation load on the smart device body can be reduced. Further, by managing data on the server device, it is possible to improve the accuracy of the output result by collecting and optimizing a large number of data. For example, the accuracy of the disease information can be improved by optimizing the relationship between the estimation result of the skin state and the disease information in a timely manner.

<Appendix>
In addition, this invention is not limited to the said embodiment as it is. The present invention can be embodied by modifying the components without departing from the scope of the invention in the implementation stage. In addition, the present invention can form various inventions by appropriately combining a plurality of constituent elements disclosed in the above embodiments. For example, some components may be deleted from all the components shown in the embodiment. Furthermore, constituent elements may be appropriately combined in different embodiments.

  According to the present invention, since the skin state can be estimated easily, application to a skin state estimation device that visualizes the physiological state of the subject based on the skin state is effective.

DESCRIPTION OF SYMBOLS 20 Skin temperature acquisition means 200 State visualization means 201 Analysis part 210 Disease information storage part 312 Abnormality determination apparatus 10,110 Evaluation apparatus 30,130 Skin state estimation means

JP-A-7-124126 Special table 2008-505684 gazette Special table 2003-524490 gazette

Claims (6)

Skin temperature acquisition means (20) for acquiring the skin temperature data detected from the skin of the body part to be examined and including the position data of the detected part in time series and / or the skin of the body part to be examined. Skin condition acquisition means for acquiring skin blood flow volume data in time series based on RGB data of the captured image data obtained by RGB processing performed on the captured image data taken in time series;
Obtained by decomposing the skin temperature data acquired by the skin temperature acquisition means and / or the skin blood flow data acquired by the skin condition acquisition means by singular value decomposition, principal component analysis, or independent component analysis. A skin condition estimating means (30, 130) for estimating the skin condition of the examination site based on a plurality of components;
An abnormality determining means (200) for determining whether or not the inspection target part is abnormal based on the skin state of the inspection target part estimated by the skin state estimation means;
A skin condition estimation apparatus (10, 110) comprising: The skin condition estimating means includes
Among the plurality of components, extract the component whose amplitude of the component waveform is correlated with the activation of the skin as a determination component,
Based on the determination component, estimate the skin state of the examination site,
The skin condition estimation apparatus according to claim 1. A disease information storage unit (210) for storing the skin state and the disease information in association with each other;
The abnormality determination unit determines that the examination target site is abnormal when the disease information is extracted from the disease information storage unit based on the skin state estimated by the skin state estimation unit, and is extracted. Presenting said disease information,
The skin state estimation apparatus according to claim 1 or 2. The skin temperature acquisition means and / or the skin condition acquisition means and the abnormality determination means are stored in a smart device.
The skin state estimation apparatus of any one of Claim 1 to 3. The skin temperature acquisition means and / or the skin condition acquisition means, the skin condition estimation means, and the abnormality determination means are stored in a smart device.
The skin state estimation apparatus of any one of Claim 1 to 4. A skin condition estimation method executed using the skin condition estimation apparatus according to any one of claims 1 to 5,
A skin activation step of cooling the skin of the inspection target part and activating the skin of the inspection target part;
Based on the skin temperature data and / or the blood circulation data before and after the activation step, whether or not the examination target site corresponds to at least one symptom of skin cancer, acne, breast cancer, coli and non-disease A symptom determination step for determining whether or not
A skin condition estimation method comprising:

Images