KR102382680B1 - Apparatus and method for predicting body style and weight component ratio through medical image - Google Patents

Abstract

The present invention relates to an apparatus and method for estimating body type and weight composition through a medical image, and the total or local body type and weight composition ratio (eg, fat, muscle, tissue, bone, moisture, etc.), and by reflecting the trend of changes in body shape and weight composition before the specific point in time, and by estimating and providing the body shape and weight composition ratio after a specific point in time or after a specific point in time, The body shape and weight composition ratio are more precisely diagnosed through the medical image, the results are accumulated, and the body shape and weight composition ratio that will change at a later time point without a medical image is estimated using the trend of the body shape and weight composition ratio before the specific point in time. It relates to an apparatus and a method for providing the same.

Description

Apparatus and method for estimating body shape and weight composition through medical images {APPARATUS AND METHOD FOR PREDICTING BODY STYLE AND WEIGHT COMPONENT RATIO THROUGH MEDICAL IMAGE}

The present invention relates to an apparatus and method for estimating body shape and weight composition through a medical image, and more particularly, to a total or local body shape and weight composition ratio (eg: By analyzing fat, muscle, tissue, bone, moisture, etc.) and reflecting the trend of changes in body shape and weight composition before the specific point in time, estimate and provide the body shape and weight composition ratio after a specific point in time or after a specific point in time, the user The body shape and weight composition ratio are more precisely diagnosed and the results are accumulated through the medical image at a specific time of It relates to an apparatus and method for estimating and providing body weight composition.

Medical devices are being developed to examine a number of diseases that occur depending on a person's body parts. With the development of the medical device, medical images of various modalities such as X-rays, computed tomography (CT), and magnetic resonance imaging (MRI) are acquired.

However, most of the medical images acquired with various modalities as described above are left unattended without any special use other than being diagnosed by a doctor for the purpose of reading lesions.

Therefore, it is necessary to consider introducing a technical method to improve the inefficient use or no use of medical images acquired with various modalities.

For example, if the user's body size is measured from the medical images of each body part acquired with various modalities, and the measured body size can be used for the purpose of customization, body shape analysis, etc., the conventional reading In addition to the purpose, medical images can be used in various ways.

Therefore, in the present invention, the body shape and weight composition ratio are analyzed by integrating the medical images of each body part at a specific time point provided by the user, and the trend of the change of the body shape and weight composition ratio before the specific time point is reflected to a specific time point or a specific time point. By estimating and providing the body shape and weight composition ratio after the time point, the user more precisely diagnoses the body shape and weight composition ratio through the medical image at a specific point in time, accumulates the results, and uses the trend of the body shape and weight composition ratio at the previous time point Therefore, we would like to suggest a method that can estimate and provide the body shape and weight composition that will change at a later point in time without the need for medical images.

Next, the prior art existing in the technical field of the present invention will be briefly described, and then the technical matters that the present invention intends to achieve differently from the prior art will be described.

First, Korean Patent No. 1322297 (October 28, 2013) relates to an apparatus and method for measuring body fat using image processing of a medical image, and selects a slice image to be used for measurement from among a plurality of slice images taken tomography, and selects the selected slice. Technical features of generating an external closed curve and an internal closed curve from the image to distinguish visceral fat and subcutaneous fat, displaying the external and internal closed curves on the selected slice image, and displaying the visceral and subcutaneous fat differently on the selected slice image. do it with

That is, the prior art describes an apparatus and method for selecting a slice image to be used for measurement from among a plurality of slice images taken tomography, and measuring body fat by separating subcutaneous fat and visceral fat from the selected slice image. However, since the present invention provides by estimating the body shape or weight composition ratio at a specific time point or after a specific time point from the medical image of each body part at a specific time point provided by the user, the difference in technical configuration is clear.

In addition, Korean Patent Registration No. 1092211 (2011.12.08.) relates to a functional X-ray medical imaging device with integrated imaging function and component analysis function and an X-ray image analysis method using the same. To a functional X-ray medical imaging apparatus that obtains image information, analyzes and maps components with a spectrometer function, and provides overall information by overlapping image information and mapping information, and an X-ray image analysis method using the same.

That is, the prior art can obtain fine internal information of the measurement object based on the excellent resolution and penetrability of the X-ray image, and integrates an X-ray imaging device and an X-ray component analysis device into one X-ray imaging device. A convenient and inexpensive functional X-ray medical imaging device is described. However, the present invention provides by estimating the body shape and weight composition ratio at a specific point in time or after a specific point in time from a medical image of each body part at a specific point in time, unlike the prior art, which allows to obtain minute internal information of an object to be measured with X-rays. Therefore, the technical composition is different.

As a result of examining the prior art above, the prior art suggests a configuration for measuring body fat by dividing subcutaneous fat and visceral fat, a configuration for acquiring micro-information inside an object to be measured using X-rays, etc. Unlike the prior art, the present invention proposes a technical feature of estimating the body shape and weight composition ratio at a specific point in time or after a specific point in time by referring to the change trend of the medical image at a previous point in time from the medical image of the user at a specific point in time. Since there is no description or any suggestion in the prior art for a related configuration, the technical difference between the prior art and the present invention is clear.

The present invention was created to solve the above problems, and an object of the present invention is to provide an apparatus and method for estimating a body shape and weight composition ratio from a medical image at a specific time provided by a user.

In addition, the present invention analyzes the overall or local body type from the medical image of each body part at a specific point in time provided by the user, and reflects the trend of body shape change before the specific point in time to estimate the body shape after a specific point in time. It is another object to provide an apparatus and a method for doing so.

In addition, the present invention measures the weight composition ratio (eg, fat, muscle, tissue, bone, moisture, etc.) based on the density in the medical image of each body part at a specific time point provided by the user, and Another object of the present invention is to provide an apparatus and method for estimating the weight composition ratio after a specific point in time by reflecting the trend of the change in the weight composition ratio.

In addition, the present invention provides an apparatus and method for allowing a user to maintain or improve health by planning an exercise or diet based on the results of estimation of body type and weight composition ratio at a specific time point or after a specific time point from a medical image. for another purpose.

In addition, the present invention analyzes the body type (weight composition) from the medical image of each body part at a specific time point provided by the user, and reflects the trend of the change of the body type (weight composition) before the specific time point after the specific time point. When estimating body type (weight composition), if there is insufficient data on time-series changes in body type (weight composition) to judge the trend of changes in the user's body type (weight composition), a third party's time-series changes in body type (weight composition) Another object of the present invention is to provide an apparatus and method for estimating the body type (weight composition) after a specific point in time based on the trend of

According to an embodiment of the present invention, an apparatus for estimating body shape and weight composition through a medical image includes: a body shape analyzer configured to analyze a body shape based on a medical image of each body part provided by a user at a specific point in time; and a weight composition ratio estimator for estimating the weight composition ratio by analyzing the body weight and components constituting the body weight with respect to the analyzed body weight, wherein the body shape of the user at the specific time point from the medical image for the specific time point of the user Including, it characterized in that it comprises providing by estimating the body weight and the weight composition ratio occupied by the body weight.

In addition, the body shape analysis unit includes measuring a body size from a medical image of each body part of the user, and analyzing the body shape of the user by comparing the measured body size with a preset standard body size, The weight composition estimator includes estimating the weight composition ratio of the user by measuring the weight of a component including fat, muscle, tissue, bone, water, or a combination thereof based on the intensity of the medical image characterized in that

In addition, the apparatus for estimating body shape and weight composition through the medical image includes: a body shape change estimator for estimating a change in body shape after the plurality of specific time points from a change trend of the body shape for the user at a plurality of specific time points; and a weight composition change estimator for estimating changes in the weight composition ratio after the plurality of specific time points from the change trend of the weight composition ratio at a plurality of the specific time points for the user; further comprising: Estimating the change is to divide the plurality of previous specific time points of the user into a plurality of sections and match the trends for the changes in the body shape and weight composition ratio analyzed through each medical image to the most closely matched trend of the change. It is characterized by estimating the body shape and weight composition ratio at a later time point by reflecting the section with

In addition, the apparatus for estimating body type and body weight composition through the medical image analyzes body shape changes analyzed from medical images from at least two different viewpoints provided by the user, a plurality of anonymized third party medical images constructed as a database Analyze and match with the body shape changes listed in time series, extract the body shape change part of the most closely matched third party, and give the user from the change trend at a later time point for the extracted body shape change part of the specific third party a body shape change estimator for estimating body shape changes after the at least two different time points; and a change in body weight composition estimated from medical images provided by the user at at least two different time points, estimated from a plurality of anonymized third-party medical images constructed as a database, and matched with changes in weight composition arranged in time series Thus, the most closely matched third party's weight composition change part is extracted, and the at least two different time points for the user from the change trend at a later time point for the extracted weight composition ratio change part of the specific third party It characterized in that it further comprises; a weight composition ratio change estimator for estimating the subsequent change in the weight composition ratio.

In addition, the apparatus for estimating body shape and weight composition through the medical image further includes a medical image integrator for integrating medical images of each body part provided by the user at the specific point in time, wherein the body shape analyzer and the body weight composition estimation unit are further included. and analyzing the body shape of the user based on the integrated medical image, and estimating a weight composition ratio constituting the body weight with respect to the analyzed body shape, wherein the body shape change estimating unit and the body weight composition change estimating unit include: It is characterized in that it includes estimating a change in the user's body type based on the integrated medical image, and estimating a change in the weight composition ratio constituting the body weight with respect to the change trend of the estimated body shape.

In addition, the apparatus for estimating body shape and weight composition through the medical image learns at least one feature point determined by a medical professional and an anonymized third party medical image labeling the feature point for each body part, and generates a learning model It further includes a model generation unit, wherein the body shape analysis unit extracts the body size through the created learning model when measuring the body size from the medical image for each body part of the user, and calculates the extracted body size. The method further comprises analyzing the body shape using do.

In addition, the method for estimating body shape and weight composition through a medical image according to an embodiment of the present invention provides an apparatus for estimating body shape and weight composition through a medical image, based on a medical image of each body part provided by a user at a specific point in time. body shape analysis step to analyze; and a body weight composition ratio estimation step of estimating the body weight composition ratio by analyzing the body weight and components constituting the body weight with respect to the analyzed body shape in the apparatus for estimating the body shape and weight composition ratio through the medical image; Including the user's body type at the specific point in time from the medical image of

In addition, the body shape analysis step may include measuring a body size from the medical image for each body part of the user in the device for estimating body shape and weight composition through the medical image, and setting the measured body size with a preset standard body size and analyzing the user's body type by comparison, wherein the estimating of the body weight composition includes fat, muscle, tissue, and bone based on the intensity of the medical image in the apparatus for estimating the body shape and weight composition through the medical image. , by measuring the weight of components including water or a combination thereof, and estimating the weight component ratio of the user.

In addition, the method for estimating body type and weight composition through the medical image, in the apparatus for estimating body type and weight composition through the medical image, from the change trend of the body shape at the plurality of specific time points for the user after the plurality of specific time points body shape change estimating step of estimating the body shape change; and in the apparatus for estimating body type and body weight composition through the medical image, estimating a change in body weight composition for estimating a change in the weight composition ratio after the plurality of specific time points from the change trend of the weight composition ratio at a plurality of the specific time points for the user Further comprising; estimating the change in the body type and weight composition ratio, the change in body shape and weight composition ratio analyzed through each medical image divided into a plurality of sections for a plurality of previous specific time points of the user It is characterized by estimating the body shape and weight composition ratio at a later point in time by reflecting the section with the trend for the most closely matched change by matching the trend.

In addition, the method for estimating body shape and weight composition through the medical image, in the apparatus for estimating body shape and weight composition through the medical image, analyzes changes in body shape from medical images provided by the user at at least two different viewpoints, a database Analyze from a plurality of anonymized third-party medical images constructed with a body shape change estimating step of estimating a body shape change after the at least two different time points for the user from a change trend at a later time point for the part; and in the apparatus for estimating body shape and body weight composition through the medical image, a plurality of anonymized third-party medical services in which a change in weight composition estimated from medical images of at least two different viewpoints provided by the user is constructed as a database. By matching with the changes in the weight composition ratio that are estimated from the image and listed in time series, the weight composition change portion of a specific third party that is most closely matched is extracted, and the change trend of the weight composition ratio change portion of the specific third party at a later time point is extracted It characterized in that it further comprises; weight composition ratio change estimating step of estimating the weight composition ratio change after the at least two different time points for the user.

In addition, the method for estimating body shape and weight composition through the medical image includes a medical image integration step of integrating the medical images of each body part provided by the user at the specific point in time in the apparatus for estimating the body shape and weight composition through the medical image; Further comprising, wherein the body shape analysis step and the weight composition ratio estimation step include analyzing the user's body type based on the integrated medical image, and estimating the weight composition ratio constituting the body weight with respect to the analyzed body shape, The body shape change estimating step and the body weight composition change estimating step include estimating a change in the user's body shape based on the integrated medical image, and determining the change in the body weight composition ratio constituting the body weight with respect to the estimated body shape change trend. It is characterized in that it includes estimating.

In addition, the method for estimating body shape and weight composition through the medical image, in the apparatus for estimating body shape and weight composition through the medical image, includes at least one or more feature points determined by a medical professional and an anonymized third party medical image labeled with the feature points. The method further includes; a learning model generation step of generating a learning model by learning for each body part, wherein the body shape analysis step includes: when measuring a body size from a medical image for each body part of the user, the generated learning The method further comprises extracting a body size through a model and analyzing the body type using the extracted body size, wherein the feature point represents a specific point in the medical image for each body part, and the coordinates of the point; It is characterized in that it is displayed including the label and the data value of the coordinates.

As described above, according to the apparatus and method for estimating body type and weight composition through medical images of the present invention, the entire or local body type and weight composition ratio are analyzed by integrating the medical images for each body part at a specific point in time provided by the user. And, by reflecting the trend of changes in body shape and weight composition before the specific point in time and estimating the body shape and weight composition ratio after a specific point in time or after a specific point in time, the user can determine the body shape and weight composition ratio through a medical image at a specific point in time. It has the effect of estimating and providing the body shape and body weight composition ratio that will change at a later time point without a medical image by using the trend of the body shape and weight composition ratio at the previous time point by accumulating the results more precisely and by accumulating the results.

In addition, according to the present invention, each user can easily check the result of estimating the body shape and weight composition ratio at a specific time or after a specific time from the medical image, and based on this, it is possible to easily establish an exercise or diet plan to maintain or improve health. there is an effect

1 is an overall block diagram of an apparatus for estimating body shape and weight composition through a medical image according to an embodiment of the present invention.
FIG. 2 is a view for explaining the overall process of estimating body shape and weight composition ratio through a medical image according to an embodiment of the present invention.
3 is a diagram for explaining in detail a learning model creation process and a learning network structure applied to the present invention.
4 is a diagram for explaining an example of estimating a body weight component ratio from a medical image applied to the present invention.
5 is a diagram for explaining an example of estimating a body shape change through a medical image applied to the present invention.
6 is a diagram for explaining an example of estimating a change in body weight composition through a medical image applied to the present invention.
7 is a diagram for explaining an example of estimating a change in body shape through a medical image of a user from a change in body shape of a third person applied to the present invention.
8 is a block diagram showing in detail the configuration of an apparatus for estimating body type and weight composition according to an embodiment of the present invention.
9 is a flowchart illustrating in detail a process of estimating a body shape and a weight component ratio through a medical image according to an embodiment of the present invention.
10 is a detailed diagram of a process of constructing a learning model based on anonymized third-party medical images collected for each body part according to an embodiment of the present invention and building a database of medical images for each body part prior to each user. It is a flowchart shown.
11 is a diagram illustrating a hardware structure of an apparatus for estimating body type and weight composition according to an embodiment of the present invention.

Hereinafter, with reference to the accompanying drawings, a preferred embodiment of the apparatus and method for estimating body shape and body weight composition through a medical image of the present invention will be described in detail. Like reference numerals in each figure indicate like elements. In addition, specific structural or functional descriptions of the embodiments of the present invention are only exemplified for the purpose of describing the embodiments according to the present invention, and unless otherwise defined, all terms used herein, including technical or scientific terms They have the same meaning as commonly understood by those of ordinary skill in the art to which the present invention pertains. Terms such as those defined in a commonly used dictionary should be interpreted as having a meaning consistent with the meaning in the context of the related art, and should not be interpreted in an ideal or excessively formal meaning unless explicitly defined in the present specification. It is preferable not to

1 is an overall block diagram of an apparatus for estimating body shape and weight composition through a medical image according to an embodiment of the present invention.

As shown in FIG. 1 , the present invention is configured to include an apparatus 100 for estimating body shape and weight composition, a database 200 , a medical image providing terminal 300 , a user terminal 400 , and the like.

When a medical image of a body part at a specific point in time is received from the user terminal 400, the apparatus 100 for estimating body shape and weight composition analyzes the user's body shape from the medical image at the specific point in time, and the body weight and The weight component ratio that occupies the body weight is estimated and provided to the user terminal 400 . That is, by accurately diagnosing the body shape and weight composition ratio through the medical image provided by the user at a specific point in time and accumulating the results, using the trend of the body shape and weight composition ratio before the specific point in time, changes at a later time point without a medical image It can be provided by estimating the body type and weight composition to be used.

Accordingly, the user can easily check the result of estimating the body shape and weight composition ratio from the medical image at a specific point in time or after a specific point in time. can be improved

To this end, when a medical image for each body part of the user is received from the user terminal 400 at a specific point in time, the apparatus 100 for estimating the body type and weight composition applies the medical image to a previously set learning model. Measure your body size. The user's body type is analyzed by comparing the measured body size with a preset standard body size.

For example, if the user's body size is within a predetermined range of the standard body size, it is determined as a normal body type, and if the user's body size is smaller than a predetermined range of the standard body size, it is determined as slim, and the user's body If the size is larger than a predetermined range of the standard body size, it is determined as obese. At this time, when determining the user's body type, slim, normal, and obese may be divided into several stages according to the size of the user's body size.

In addition, the body shape and body weight composition estimating apparatus 100 may analyze fat, muscle, tissue, bone, moisture or By measuring the weight of the components including these combinations, the weight component ratio of the user is estimated (see FIG. 4).

In addition, when the medical image of a plurality of specific points in time is received from the user terminal 400 , the apparatus 100 for estimating the body shape and body weight composition ratio is performed at a plurality of specific points in time from the trend of changes in the body shape and body composition ratio at the plurality of specific points in time. Subsequent changes in body shape and weight composition can be estimated (refer to FIGS. 5 and 6).

For example, the trend of changes in body type and body composition ratio confirmed through medical images at a plurality of specific points in time provided by the user is divided into a plurality of sections for a plurality of previous specific points of time of the user and analyzed through each medical image. It is possible to estimate the body shape and weight composition ratio at a later point in time by matching with the change trend of the body shape and weight composition ratio, and reflecting the section having the change trend most closely matched as a result of the matching.

On the other hand, when estimating the body shape and weight composition ratio through the medical image of each body part of the user received from the user terminal 400, the apparatus 100 for estimating the body shape and weight composition ratio, each The medical images of body parts may be integrated into one, the user's body type may be analyzed using the integrated medical image, and the weight composition ratio constituting the body weight may be estimated with respect to the analyzed body type.

In addition, the body shape and body weight composition estimation apparatus 100 reflects the trend of changes in body shape and weight composition ratio analyzed through the integrated medical image prior to a specific point in time, based on the integrated medical image at the specific point in time, so as to determine the user's body shape and It is possible to estimate the change in the proportion of the body weight constituting the body weight.

The database 200 includes an anonymized third-party medical image database 210 , a learning model database 220 , and a user-specific medical image database 230 . Here, the database 200 is treated and described as a database management system (DBMS) that serves to store and manage data in individual DBs.

The anonymized third-party medical image database 210 divides a plurality of anonymized third-party medical images collected from the medical image providing terminal 300 by the body shape and weight composition estimation apparatus 100 for each body part. to save

The learning model database 220 provides a learning model generated by learning a plurality of anonymized third-party medical images collected from the medical image providing terminal 300 in the body type and weight composition estimation apparatus 100 for each body part. Separate and save

The user-specific medical image database 230 accumulates and stores medical images for each body part prior to a specific point in time provided by each user from the user terminal 400 in time-series.

In addition, the database 200 stores and updates various operation programs performed by the apparatus 100 for estimating body shape and weight composition.

The medical image providing terminal 300 includes a wired/wireless communication terminal operated or possessed by a medical institution or a medical institution worker, a communication terminal operated in a data center that comprehensively manages medical images, and a communication terminal owned by individual users. The third party's medical image is provided to the apparatus 100 for estimating the body shape and weight composition through a network.

In this case, the anonymized third party medical image is a medical image taken for each body part such as the head, chest, arm, leg, etc., and is collected for a certain period according to the request of the body type and weight composition estimation apparatus 100 . may be provided in a period of , or may be provided in real time.

The user terminal 400 is a wired/wireless communication terminal such as a smart phone, PC, tablet, etc. used by class users, and uses a network to transmit medical images of body parts taken at a specific point in time according to a user's operation using a pre-installed application program. It is transmitted to the body shape and body weight composition estimating device 100 through and a result of estimating the weight composition ratio is provided.

That is, the user terminal 400 estimates the body shape and weight composition ratio to change at a later point in time from the body shape and weight composition estimating apparatus 100 without a medical image by using the trend of the body shape and weight composition ratio before a specific point in time. can be provided. Through this, the user can plan an exercise or diet that can continuously maintain or improve health by changing the body shape and weight composition at a specific point in time or after a specific point in time, or get help from a professional.

Next, a process of estimating body shape and weight composition through a medical image according to an embodiment of the present invention will be described in detail with reference to FIG. 2 .

FIG. 2 is a diagram for explaining the overall process of estimating a body shape and weight composition ratio through a medical image according to an embodiment of the present invention.

As shown in FIG. 2 , the apparatus 100 for estimating body shape and weight composition provides a plurality of anonymized data for various body parts such as head, chest, hands, and feet from the medical image providing terminal 300 through a network. The third-party medical images are collected according to a certain period or are collected in real time and stored in the anonymized third-party medical image database 210 (①).

At this time, the anonymized third party's medical image is a medical image of people who have consented to the use of personal information, and since personal information is deleted, there is no risk of personal information being exposed. Includes all medical images such as CT or MRI of In addition, the anonymized third-party medical image may include various information on age, gender, race, country, and environmental factors (season, region, etc.).

On the other hand, the body type and body weight composition estimation apparatus 100 collects medical images of each user's body parts before a specific time point from the user terminal 400 and accumulates them in the medical image database 230 for each user in time series. to store and manage.

Subsequently, after collecting the third party's anonymized medical image from the medical image providing terminal 300 , the body shape and weight composition estimating apparatus 100 collects a plurality of the collected medical images through a medical expert (a doctor or an image reading expert). At least one feature point is determined for each medical image of an anonymized third party body part, and the corresponding feature point is labeled, and then the feature point is determined and labeled and the medical image of the anonymized third party and the collected original medical care A learning model is generated by learning an image, and the created learning model is stored and managed in the learning model database 220 (②). In this case, the feature point indicates a specific point of a medical image for a body part, and includes coordinates of the point, a label, and data values of the coordinates.

Here, the generation of the learning model will be described in detail with reference to FIG. 3 as follows.

3 is a diagram for explaining in detail a learning model creation process and a learning network structure applied to the present invention.

As shown in (a) of FIG. 3 , the apparatus 100 for estimating body shape and weight composition performs learning by inputting the plurality of anonymized medical images of a third party including feature point coordinates, pixel values, or voxel values. Thus, a learning model is generated for each characteristic point of each body part, and the created learning model is stored and managed in the learning model database 220 . In this case, the learning may use various learning methods such as supervised learning, unsupervised learning, and reinforcement learning.

In addition, as shown in FIG. 3(b), the network structure for the learning may use a convolutional neural network (CNN) method, and the CNN is an input layer to which the collected medical images are input, convolution (convolution). ) layer, a pooling layer, and a fully connected layer.

Referring again to FIG. 2 , the apparatus 100 for estimating the body shape and weight composition receives a medical image of a specific point in time for each body part provided by the user from the user terminal 400 through the network (③).

In addition, the body shape and body weight composition estimating apparatus 100 measures the body size by applying the received medical image at a specific point in time for each body part to the learning model for the corresponding body part stored in the learning model database 220 . and compares the measured body size with a standard body size to analyze the user's body type (④). That is, a normal, slim, or obese body type is determined according to whether the measured body size of the user is included in a predetermined range of the standard body size or is smaller or larger than the predetermined range of the standard body size.

In addition, the body shape and body weight component ratio estimation apparatus 100 estimates the body weight component ratio by analyzing the body weight and components constituting the body weight for the analyzed body shape (⑤). For example, a portion including fat, muscle, tissue, bone, moisture, or a combination thereof is identified in the medical image at the specific point in time through the density of the medical image at the specific point in time, and the proportion of each identified component is to estimate the weight composition ratio of the user by measuring .

In addition, the apparatus 100 for estimating body shape and body weight composition may estimate changes in body shape and weight composition ratio after a plurality of specific time points from the change trend of the medical images at a plurality of specific time points received from the user terminal 400 . (⑥).

That is, after checking the body shape and weight composition ratio of the medical images received from the user terminal 400 at a plurality of specific points in time, the confirmed change trend of the body shape and body composition ratio is stored in the medical image database 230 for each user. Matches with the trend of change of body shape and weight composition analyzed through medical images constructed time-series before the specific point in time, and when a specific section with the closest change trend is identified as a result of the matching, the figure and weight composition ratio of the next section The change is estimated as the body shape and weight composition ratio of the user after the plurality of specific time points.

On the other hand, when the body type and body weight composition ratio estimation apparatus 100 performs body shape analysis and weight composition ratio estimation, the medical image of each body part provided by the user at a specific point in time is not targeted for medical images for each body part. It can be performed on integrated medical images.

In this case, the body shape and body weight composition estimating apparatus 100 analyzes changes in the body shape and weight composition ratio through the integrated medical images stored in the user-specific medical image database 230 prior to a specific point in time of the user. By reflecting the trend, it is possible to estimate changes in body shape and weight composition ratio after a specific point in time from the integrated medical image at the specific point in time.

Next, a detailed process of estimating the weight component ratio from the medical image provided by the user will be described in detail with reference to FIG. 4 .

4 is a diagram for explaining an example of estimating a body weight component ratio from a medical image applied to the present invention.

As shown in FIG. 4 , the apparatus 100 for estimating body type and weight composition classifies each component in the medical image at a specific point in time provided by the user (①), and divides each classified component into the learning model database. By applying to the learning model stored in (220), the body size for each component is measured, and the integrated area ratio for each component is calculated (②).

After calculating the proportion of each area integrated with the body size of each component classified from the medical image at the specific point in time as described above, the body and weight composition estimating apparatus 100 calculates the average density of each of the calculated integrated areas. Do (③).

Then, the body and weight composition estimation apparatus 100 reflects the body size of each component measured in step ②, the integrated area ratio for each component, and the average density of each integrated area confirmed in step ③. , to estimate the weight component ratio constituting the user's weight (④).

That is, by reflecting the size and area composition ratio of each component measured from the medical image and the integrated area ratio of each component, the proportion of fat, muscle, tissue, bone, water, etc. occupied in the user's body is estimated. .

Next, a detailed process of estimating changes in body shape and weight composition through medical images at a plurality of specific points in time provided by the user will be described in detail with reference to FIGS. 5 and 6 .

5 is a diagram for explaining an example of estimating a change in body shape through a medical image applied to the present invention, and FIG. 6 is a diagram for explaining an example of estimating a change in body weight composition through a medical image applied to the present invention It is a drawing.

As shown in FIG. 5 , when user A transmits medical images of a body part at a plurality of specific points in time to the apparatus 100 for estimating the body shape and weight composition through the user terminal 400 , the body shape and weight composition ratio The estimation apparatus 100 measures the body size by applying the medical images at a plurality of specific time points of the user A received from the user terminal 400 to a preset learning model, and sets the measured body size with the standard body size. By comparison, the change trend of user A's body type is estimated (1).

At this time, the apparatus 100 for estimating body type and weight composition will be described as an example of classifying a change in a person's body type into slim, normal, and obese, and subdividing into three stages for each stage of slim, normal, and obesity.

As a result of estimating the change trend of the user A's body shape at a plurality of specific points in time, if it is assumed that the change from normal 1 to slim 3 is assumed, the body shape and weight composition estimating apparatus 100 of the user A after the specific point in time How this will change can be estimated as follows.

That is, the apparatus 100 for estimating body shape and weight composition searches the time-series body shape change trend analyzed through the medical image before a specific point in time of the user A, which is stored and managed in the database 200, and in step (1) A section having a change trend that most closely matches the change trend of the estimated user A's body shape at a plurality of specific time points is detected (2).

As a result of performing in step (2), if a section having a change trend that most closely matches the change trend of user A's body shape at a plurality of specific time points estimated in step (1) is detected, the body shape and weight The component ratio estimation apparatus 100 detects what kind of change in the body shape of the section immediately following the section having the most closely matched change trend (3).

If, as a result of the detection in step (3), the change in the body shape of the user A in the next section is usually 1, the body shape and weight composition estimating apparatus 100 sets the body shape of the user A after the specific point in time to usually 1 By estimating it, the estimation result for the body shape change of usually 1 is provided to the user terminal 400 (4).

Accordingly, user A checks the estimated result of his body shape that will change after a specific point in time from the medical images at a plurality of specific points in time provided by the user, so as to maintain the body shape at a specific point in time or exercise or lose more weight. You can get help in formulating a diet plan.

In addition, since the estimation of the change in the body weight composition shown in FIG. 6 is performed in the same manner as the method of estimating the change in the body shape of FIG. 5 , a detailed description thereof will be omitted.

On the other hand, the estimation of changes in body shape and body weight composition described in FIGS. 5 and 6 is time-series body shape and weight composition ratio analyzed through medical images at each point of time that one user stores and manages in the database 200 . It is a method of confirming the estimated results of one's body type and weight composition ratio that will change after a certain point in time from the change trend.

However, if data on time-series changes in body shape and body weight composition that can estimate changes in body shape and weight composition of each user are not sufficiently accumulated and managed in the database 200, accurate estimation results cannot be obtained. .

In preparation for such a case, in the present invention, when there is insufficient data on time-series changes in body shape to estimate changes in the body shape and weight composition of each user, the time-series body shape and weight of a third party that is stored and managed in the database 200 Based on the trend of the change in the composition ratio, it is possible to obtain an estimation result for the body type and weight composition ratio that will change after a specific point in time for each user.

7 is a diagram for explaining an example of estimating a change in body shape through a medical image of a user from a change in body shape of a third person applied to the present invention.

As shown in FIG. 7 , when user B provides medical images at a plurality of specific time points for body parts to the body shape and body weight ratio estimation device 100 , the body shape and body weight ratio estimation device 100 provides the user with The body size is measured by applying the medical image of B to a preset learning model, and the measured body size is compared with the standard body size to estimate the change trend of user B's body type (1).

For example, if it is assumed that user B's body shape at a plurality of specific points in time is changed from normal 1 to slim 3, the body shape and weight composition estimation apparatus 100 is anonymized for each third party constructed with the database 200 . By matching with the time-series body shape change, the body shape change part of a specific third person that most closely matches the change trend of user B's body shape is extracted (2).

As a result of performing in step (2), when the body shape change portion of a specific third person that most closely matches the body shape change trend of user B at a plurality of specific time points is extracted, the body shape and weight composition estimating apparatus 100 detects what kind of change in the body shape in the section immediately following the body shape change section of a specific third person that most closely matches the body shape change trend of user B (3).

If, as a result of the detection in step (3), the change in the body shape of the next section of the body shape change section of a specific third person similar to the body shape change of user B is usually 1, the body shape and weight composition estimating apparatus 100 is The body shape of the user B after a specific point in time is usually estimated as 1, and the estimation result is provided to the user B (4).

On the other hand, since the estimation of the change in the specific user's weight composition ratio using third-party data is performed in the same manner as the estimation of the body shape change shown in FIG. 7 , a detailed description thereof will be omitted.

Next, a detailed configuration of an apparatus for estimating body type and body weight composition according to an embodiment of the present invention will be described in detail with reference to FIG. 8 .

8 is a block diagram showing in detail the configuration of an apparatus for estimating body type and weight composition according to an embodiment of the present invention.

As shown in FIG. 8 , the apparatus 100 for estimating body type and weight composition includes a collection unit 110 , a learning model generation unit 120 , a medical image receiving unit 130 , a body shape analysis unit 140 , and a weight component ratio weight. The government 150, the body shape change estimator 160, the weight composition change estimator 170, the medical image integration unit 180, the estimation result providing unit 190 and the like are included.

In addition, although not shown in the drawing, the apparatus 100 for estimating body type and weight composition includes a power supply unit for supplying operating power to each component, an input unit for data input for various functions, a memory for storing various operation programs, and various programs. It may further include an update management unit for managing updates, a control unit for controlling each component in general, and an interface unit for transmitting and receiving data with an external device such as a database.

The collection unit 110 collects medical images for each body part of a plurality of anonymized third parties in a predetermined period or in real time from the medical image providing terminal 300 through a network, and the anonymized third to be stored in the child medical image database 210 .

In addition, the collection unit 110 collects medical images of body parts taken before a plurality of specific points in time from the user terminal 400 through a network, divides them in time series, and divides them into a medical image database 230 for each user. to be saved in

The learning model generating unit 120 includes at least one or more feature points determined by a medical professional who has identified a plurality of anonymized third-party medical images received from the collection unit 110 and anonymized third-party medical care that labels the feature points. An image is learned for each body part to generate a learning model, and the generated learning model for each body part is stored and managed in the learning model database 220 .

At this time, the learning model generator 120 verifies the error of the created learning model, and adjusts the learning parameters to minimize the error based on the verified result to optimize the learning model (that is, back propagation). (back-propagation) function) and continuously updates the created learning model.

The medical image receiving unit 130 receives a medical image of a body part photographed at at least one specific point in time provided through the user terminal 400 by a user who wants to know the estimation result of the body shape and weight composition ratio after a specific point in time. receive

The body shape analyzer 140 performs a function of analyzing the body shape based on the medical image of each body part provided by the user at a specific time received through the medical image receiving unit 130 .

At this time, the body shape analysis unit 140 extracts the body size through the learning model generated by the learning model generation unit 120 when measuring the body size from the medical image of each body part of the user, and The user's body type is analyzed by comparing the body size with a preset standard body size.

The weight composition estimating unit 150 performs a function of estimating the body weight composition ratio by analyzing the body weight and components constituting the body weight for the body shape analyzed by the body shape analysis unit 140 .

That is, the body weight component estimating unit 150 determines whether a component including fat, muscle, tissue, bone, water, or a combination thereof is calculated from the body weight based on the intensity of the medical image received through the medical image receiving unit 130 . By measuring the occupancy, the weight composition ratio of the user is estimated.

The body shape change estimator 160 performs a function of estimating a change in body shape after the plurality of specific points in time from the change trend of the body shape at the plurality of specific time points for the user.

That is, the body shape change estimating unit 160 receives from the medical image receiving unit 130 and checks the change trend of the user's body shape at a plurality of specific points in time through the body shape analysis unit 140 in the medical image database for each user. A section having a change trend most closely matched with the change trend of the user's body shape at a plurality of specific points in time is matched with the change trend of the body shape of the medical image at a plurality of previous specific points in time stored in 230 . It is checked, and the body shape at that point in time is estimated as the body shape that will change after a specific point in time of the user.

In addition, the body shape change estimating unit 160 is different from estimating the body shape to be changed after a specific point in time based on the body shape change trend of any one of the users described above, the body shape change estimating unit 160 after a specific time point based on the body shape change trend of a third person. The body shape to change can be estimated.

For example, the body shape change estimating unit 160 analyzes body shape changes from medical images from at least two different viewpoints provided by the user, an anonymized plurality of third parties built into the database 200 . After analyzing and matching the body shape changes listed in time series from the medical image of estimating the change in body shape after the at least two different time points for the user from the change trend of .

The weight composition change estimating unit 170 is configured to determine the change trend of the body type analyzed by the body type change estimating unit 160 from the change trend of the body weight composition ratio at a plurality of the specific time points for the user at the plurality of specific time points. It performs the function of estimating the subsequent change in the weight composition ratio.

That is, the weight composition change estimating unit 170 receives from the medical image receiving unit 130 and checks the change trend of the user's body weight composition ratio at a plurality of specific points in time through the body composition ratio estimator 150 for each user. A change that most closely matches the change trend of the weight composition ratio of the user at a plurality of specific time points by matching with the change trend of the weight composition ratio of the medical images at a plurality of previous specific time points stored in the medical image database 230 A section with a trend is identified, and the weight composition ratio at that point in time is estimated as the weight composition ratio that will change after the user's specific point in time.

In addition, the weight composition change estimating unit 170 is different from the one of the above-described users estimating the weight composition ratio that will change after a specific point in time based on the user's own weight composition change trend, based on the third person's weight composition change trend. It is possible to estimate the weight composition ratio that will change after a certain point in time.

For example, the weight composition change estimating unit 170 estimates the change in weight composition from medical images of at least two different viewpoints provided by the user, an anonymized third After matching with changes in the weight composition ratio listed in time series by estimating from a plurality of medical images for each individual, and extracting the weight composition change portion of a specific third party that is the closest match as a result of the matching, the extracted weight composition ratio change portion of the specific third party It is to estimate the change in the weight composition ratio after the at least two different time points for the user from the change trend at the later time points.

The medical image integrator 180 integrates medical images of each body part provided by the user at the specific time point. In other words, it is not a medical image for each body part, but a medical image that integrates the medical image of each body part provided by the user so that body type analysis and weight composition estimation can be performed.

Accordingly, the body shape analysis unit 140 and the body weight composition estimator 150 analyze the user's body type based on the medical image integrated by the medical image integration unit 180, and calculate the weight for the analyzed body type. It is possible to estimate the composition of the body weight composition. In addition, the body shape change estimator 160 and the body weight composition ratio change estimator 170 estimate a change in the user's body shape based on the medical image integrated by the medical image integrator 180, and With respect to the change trend, it is possible to estimate a change in the weight composition ratio constituting the body weight.

The estimation result providing unit 190 uses the estimation result of the body shape analysis unit 140 , the body weight composition ratio estimation unit 150 , the body shape change estimation unit 160 , the body weight composition ratio change estimation unit 170 , and the like. It is transmitted to the user terminal 400 so that the user can immediately check it through the application program installed in the user terminal 400 . In this case, the estimation result of the body type and weight composition ratio output to the user terminal 400 may be provided in various forms such as text, graphic, or a combination thereof.

Next, an embodiment of the method for estimating body shape and weight composition through a medical image according to the present invention configured as described above will be described in detail with reference to FIGS. 9 and 10 . At this time, the order of each step according to the method of the present invention may be changed by the environment of use or by those skilled in the art.

9 is a flowchart illustrating in detail a process of estimating a body shape and a weight component ratio through a medical image according to an embodiment of the present invention.

As shown in FIG. 9 , the apparatus 100 for estimating body type and weight composition determines whether a medical image of a body part photographed at at least one specific time is received from the user terminal 400 through a network ( S110). That is, it is determined whether the user provides a medical image of a body part photographed at a specific point in time in order to estimate the body shape or weight composition to change after a specific point in time.

As a result of the determination in step S110, when a medical image of a body part photographed at a specific point in time is received from the user terminal 400, the apparatus 100 for estimating body shape and weight composition provides each body part provided by the user at a specific point in time. The body shape analysis step of analyzing the body shape based on the medical image of

That is, the apparatus 100 for estimating the body type and weight composition applies the medical image of the body part received from the user terminal 400 to a preset learning model to measure the body size (S120), and the measured body The user's body type is analyzed by comparing the size with the standard body size stored in advance (S130). Through this, it is possible to determine whether the user's body type is included among slim, normal, and obese.

Also, the body shape and body weight composition estimating apparatus 100 analyzes the body weight and components constituting the body weight for the body shape analyzed in step S130, and performs a weight component estimating step of estimating the body weight composition ratio (S140). That is, in the body shape identified from the medical image for the specific time point of the user, the weight and the weight component ratio occupied by the body weight are estimated.

This can be confirmed through the density of the medical image at the specific point in time. For example, according to the difference in density, parts including fat, muscle, tissue, bone, moisture, or a combination thereof are identified in the medical image according to the difference in density, and each It is possible to estimate the weight component ratio of the corresponding user by measuring the proportion of the components of the part.

Meanwhile, the apparatus 100 for estimating body shape and weight composition determines whether it is necessary to estimate body shape and weight composition after a specific time (S150). That is, the change in body shape and weight composition ratio after a plurality of specific time points is estimated from the change trend of the medical images at a plurality of specific points in time received from the user terminal 400 according to a user's request.

To this end, the body shape and body weight composition estimating apparatus 100 is a body shape change for estimating changes in the body shape after the plurality of specific time points from the change trend of the body shape at a plurality of specific time points received from the user terminal 400 . The estimating step is performed, and at the same time, the weight composition ratio change estimation step of estimating changes in the weight composition ratio after the plurality of specific time points from the change trend of the body weight composition ratio at the plurality of specific time points is performed (S160).

At this time, estimating the change in body shape and weight composition ratio is the closest by matching the trends for changes in body shape and weight composition ratio analyzed through each medical image by dividing the plurality of previous specific time points of the user into a plurality of sections. It means estimating the body shape and weight composition ratio at a later point in time by reflecting a section with a trend for changes that are closely matched.

In addition, the body shape and weight composition estimating apparatus 100 includes the user body shape at a specific point in time analyzed in step S130 and the user body weight composition ratio at a specific point in time estimated in step S140, or body shape after a specific point in time estimated in step S160, and The weight composition ratio estimation result is transmitted to the user terminal 400 so that the user can check it immediately (S170).

In addition, although not shown in the drawings, the apparatus 100 for estimating body type and weight composition integrates the medical images of each body part provided by the user at the specific time point, and analyzes the user's body type based on the integrated medical image, and With respect to the analyzed body type, it is possible to estimate the weight composition ratio constituting the body weight, estimate the change of the user's body type based on the integrated medical image, and the weight composition ratio constituting the body weight with respect to the estimated body shape change trend. A function of estimating the change of .

On the other hand, the apparatus 100 for estimating body shape and weight composition is a learning model used to estimate changes in body shape and weight composition at a specific point in time or after a specific point in time from a medical image provided by a user or a medical image before a specific point in time of the user. The information on the data should be stored and managed in the database 200, which will be described in detail with reference to FIG. 10 as follows.

10 is a detailed diagram of a process of constructing a learning model based on anonymized third-party medical images collected for each body part according to an embodiment of the present invention and building a database of medical images for each body part prior to each user. It is a flowchart shown.

First, the apparatus 100 for estimating body shape and weight composition collects a plurality of anonymized medical images of third parties from the medical image providing terminal 300 (S210), and collects the plurality of anonymized medical images of the third parties. At least one feature point is determined through the identified medical expert, and the determined feature point is labeled (S220).

In addition, the body shape and weight composition estimation apparatus 100 learns at least one feature point and a plurality of anonymized third-party medical images labeled with the feature point for each body part, and performs a learning model creation step of generating a learning model. do.

That is, a learning model for each body part is generated by learning the plurality of anonymized medical images that are determined and labeled through the step S220 (S230), and the generated learning model for each body part is stored in the learning model database 210 (S230). Store and manage (S240).

In addition, the apparatus 100 for estimating body type and weight composition collects a medical image of a body part before a specific time for each user from the user terminal 400 (S250), and for each body part before the collected specific time point The medical images are divided time-series for each user, and the medical images are stored and managed in the medical image database 230 for each user (S260).

On the other hand, as described in FIGS. 9 and 10, each user's body shape and weight composition ratio change are estimated from the user's own time-series body shape and weight composition change trend analyzed through medical images at different time points. There may be insufficient data on time-series body shape changes to estimate changes in the user's body type and weight composition.

To this end, the body shape and body weight composition estimating apparatus 100 analyzes body shape changes analyzed from medical images from at least two different viewpoints provided by the user, in a plurality of anonymized third parties constructed with the database 200 . It is analyzed from the medical image and matched with the body shape changes listed in time series to extract the body shape change part of a specific third party that matches most closely.

Next, the body shape change after the at least two different time points for the user is estimated from the change trend at a later time point for the extracted body shape change part of the specific third person.

Similarly, even when estimating the user's weight composition ratio after a specific time point, the body shape and weight composition estimating apparatus 100 calculates the weight composition ratio change estimated from the medical images of at least two different time points provided by the user, By estimating from a plurality of medical images for each anonymized third party constructed in the database 200 and matching with changes in weight composition arranged in a time series, a portion of the change in weight composition of a specific third party that is most closely matched is extracted.

Then, the body shape and body weight composition estimating apparatus 100 estimates the change in the weight composition ratio after the at least two different time points for the user from the change trend at a later time point for the extracted specific third party's weight composition change part do.

11 is a diagram illustrating a hardware structure of an apparatus for estimating body type and weight composition according to an embodiment of the present invention.

As shown in FIG. 11 , the hardware structure of the apparatus 100 for estimating body type and weight composition includes a central processing unit 1000 , a memory 2000 , a user interface 3000 , a database interface 4000 , and a network interface ( 5000), and a web server 6000, and the like.

The user interface 3000 provides an input and output interface to a user by using a graphical user interface (GUI).

The database interface 4000 provides an interface between a database and a hardware structure.

The network interface 5000 provides a network connection between devices owned by a user.

The web server 6000 provides a means for a user to access the hardware structure via a network. Most users can remotely access the web server and use the apparatus 100 for estimating body shape and weight composition.

Each step of the above-described configuration or method may be implemented as computer-readable code on a computer-readable recording medium or transmitted through a transmission medium. The computer-readable recording medium is a data storage device capable of storing data that can be read by a computer system.

Examples of computer-readable recording media include, but are not limited to, databases, ROMs, RAMs, CD-ROMs, DVDs, magnetic tapes, floppy disks, and optical data storage devices. The transmission medium may include a carrier wave transmitted through the Internet or various types of communication channels.

In addition, the computer readable recording medium may be distributed through a network coupled computer system so that the computer readable code is stored and executed in a distributed manner.

In addition, at least one or more components applied to the present invention may include or be implemented by a processor such as a central processing unit (CPU), a microprocessor, etc. that perform each function, and two or more of the components are one single It may be combined as a component to perform any operation or function for two or more combined components.

In addition, a part of at least one or more components applied to the present invention may be performed by other components among these components. In addition, communication between the components may be performed through a bus (not shown).

As such, in the present invention, the user more precisely diagnoses the body shape and weight composition ratio through the medical image at a specific time point and accumulates the results, so that the user can use the trend for the body shape and weight composition ratio at the previous time point at a later time point without a medical image. It can be provided by estimating the body shape to be changed and the weight composition ratio.

In addition, according to the present invention, each user can easily check the result of estimating the body shape and weight composition ratio at a specific time or after a specific time from the medical image, and based on this, it is possible to easily establish an exercise or diet plan to maintain or improve health. there is.

As described above, the present invention has been described with reference to the embodiments shown in the drawings, but these are merely exemplary, and those of ordinary skill in the art can make various modifications and equivalent other embodiments therefrom. You will understand that it is possible. Therefore, the technical protection scope of the present invention should be determined by the following claims.

100: device for estimating body type and weight composition
110: collection unit 120: learning model generation unit
130: medical image receiving unit 140: body shape analysis unit
150: weight composition ratio estimating unit 160: body shape change estimating unit
170: weight composition change estimating unit 180: medical image integration unit
190: estimation result providing unit 200: database
210: Anonymized third-party medical image database
220: learning model database 230: medical image database for each user
300: medical image providing terminal 400: user terminal

Claims (12)

a body shape analysis unit that analyzes a body shape based on a medical image of each body part provided by a user at a specific point in time;
a weight composition ratio estimator for estimating a weight composition ratio by analyzing a body weight and components constituting the body weight for the analyzed body shape;
a body shape change estimator for estimating a change in body shape after the plurality of specific points in time from a change trend of the body shape of the user at a plurality of specific points in time; and
and a weight composition change estimator for estimating changes in the weight composition ratio after the plurality of specific points in time from the change trend of the weight composition ratio at a plurality of specific time points for the user;
Estimating the change in the body shape and weight composition ratio is the closest to the user by matching the trends of the changes in the body shape and weight composition ratio analyzed through each medical image by dividing the plurality of previous specific time points into a plurality of sections. It is to estimate the body shape and weight composition ratio at a later point in time by reflecting the section with the trend for the matching change,
Body shape and body weight composition ratio through a medical image, comprising estimating the body weight of the user at the specific time point from the medical image for the specific time point of the user and estimating the body weight and the weight composition ratio occupied by the body weight estimation device. The method according to claim 1,
The body shape analysis unit,
Measuring a body size from a medical image of each body part of the user, and comparing the measured body size with a preset standard body size, further comprising analyzing the user's body type,
The weight composition estimating unit,
The method further comprises estimating the weight component ratio of the user by measuring the weight of a component including fat, muscle, tissue, bone, water, or a combination thereof based on the density of the medical image A device for estimating body type and weight composition through medical images. delete The method according to claim 1,
The body shape change estimating unit,
By analyzing changes in body shape analyzed from medical images of at least two different viewpoints provided by the user from a plurality of anonymized third-party medical images constructed as a database, and matching with changes in body shape listed in time series, the most Extracting a body shape change part of a specific third person that closely matches, and determining the body shape change for the user after at least two different time points from the change trend at a later time point for the extracted body shape change part of the specific third party further comprising estimating,
The weight composition ratio change estimating unit,
By matching the weight composition ratio change estimated from the medical images of at least two different time points provided by the user and estimating the changes in the weight composition ratio from a plurality of anonymized third-party medical images built into a database and listed in time series, , extracts the weight composition ratio change portion of a specific third party that most closely matches, and after the at least two different time points for the user from the change trend at a later time point for the extracted weight composition ratio change portion of the specific third party Body shape and body weight composition ratio estimation apparatus through a medical image, characterized in that it further comprises estimating the change in the body weight composition. The method according to claim 1,
The apparatus for estimating body type and weight composition through the medical image,
It further includes; a medical image integrator for integrating the medical image of each body part provided by the user at the specific time point;
The body shape analyzer and the body weight composition estimator further include analyzing the user's body shape based on the integrated medical image, and estimating the weight composition ratio constituting the body weight with respect to the analyzed body shape,
The body shape change estimator and the body weight composition change estimator estimate a change in the user's body shape based on the integrated medical image, and estimate a change in the body weight composition ratio constituting the body weight with respect to the estimated body shape change trend. Body shape and body weight composition ratio estimation apparatus through a medical image, characterized in that it further comprises. The method according to claim 1,
The apparatus for estimating body shape and weight composition through the medical image,
At least one feature point determined by a medical professional and an anonymized third party medical image labeled with the feature point are learned for each body part to generate a learning model, and the created learning model for each body part is stored in a database and managed It further includes; a learning model generation unit to
The body shape analysis unit, when measuring the body size from the medical image for each body part of the user, extracts the body size through the generated learning model, and further analyzes the body shape using the extracted body size includes,
wherein the feature point represents a specific point of the medical image for each body part, and the coordinates of the point, a label, and a data value of the coordinates are included. a body shape analysis step of analyzing a body shape based on a medical image of each body part provided by a user at a specific point in time in an apparatus for estimating body shape and weight composition through a medical image;
a weight component ratio estimation step of estimating a body weight component ratio by analyzing a body weight and components constituting the body weight for the analyzed body shape;
a body shape change estimating step of estimating a change in body shape after the plurality of specific points in time from a change trend of the body shape at a plurality of specific points in time for the user; and
The method further includes: a weight composition change estimation step of estimating changes in the weight composition ratio after the plurality of specific time points from the change trend of the weight composition ratio at a plurality of specific time points for the user;
Estimating the change in the body shape and weight composition ratio is the closest to the user by matching the trends for changes in the body shape and weight composition ratio analyzed through each medical image by dividing the plurality of previous specific time points into a plurality of sections. It is to estimate the body shape and weight composition ratio at a later point in time by reflecting the section with the trend for the matching change,
Body shape through a medical image, comprising estimating the body weight of the user from the medical image for the specific time point of the user and the body weight of the user at the specific time point, and estimating the body weight and the weight composition ratio occupied by the body weight and a method for estimating the weight composition ratio. 8. The method of claim 7,
The body shape analysis step is,
Measuring a body size from a medical image of each body part of the user, and comparing the measured body size with a preset standard body size, further comprising analyzing the user's body type,
The step of estimating the weight composition ratio,
The method further comprises estimating the weight component ratio of the user by measuring the weight of a component including fat, muscle, tissue, bone, water, or a combination thereof based on the density of the medical image A method of estimating body shape and weight composition through medical images. delete 8. The method of claim 7,
The body shape change estimation step is,
By analyzing changes in body shape analyzed from medical images of at least two different viewpoints provided by the user from a plurality of anonymized third-party medical images constructed as a database, and matching with changes in body shape listed in time series, the most Extracting a body shape change part of a specific third person that closely matches, and determining the body shape change for the user after at least two different time points from the change trend at a later time point for the extracted body shape change part of the specific third party further comprising estimating,
The step of estimating the change in the weight composition ratio,
By matching the weight composition ratio change estimated from the medical images of at least two different time points provided by the user and estimating the changes in the weight composition ratio from a plurality of anonymized third-party medical images built into a database and listed in time series, , extract the weight composition ratio change portion of a specific third party that most closely matches, and after the at least two different time points for the user from the change trend at a later time point for the extracted weight composition ratio change portion of the specific third party Body shape and body weight composition ratio estimation method through a medical image, characterized in that it further comprises estimating the change in the weight composition of the. 8. The method of claim 7,
The method of estimating body shape and weight composition through the medical image is,
A medical image integration step of integrating the medical images of each body part provided by the user at the specific point in time; further comprising,
The body shape analysis step and the weight composition estimating step further include analyzing the user's body type based on the integrated medical image, and estimating the weight component ratio constituting the body weight with respect to the analyzed body shape,
The body shape change estimating step and the body weight composition change estimating step include estimating a change in the user's body shape based on the integrated medical image, and determining the change in the body weight composition ratio constituting the body weight with respect to the estimated body shape change trend. A method of estimating a body shape and weight composition through a medical image, characterized in that it further comprises estimating. 8. The method of claim 7,
The method of estimating body shape and weight composition through the medical image is,
At least one feature point determined by a medical professional and an anonymized third party medical image labeled with the feature point are learned for each body part to generate a learning model, and the created learning model for each body part is stored in a database and managed It further comprises;
In the body shape analysis step, when measuring the body size from the medical image for each body part of the user, extracting the body size through the created learning model, and analyzing the body type using the extracted body size including more,
Wherein the feature point represents a specific point of the medical image for each body part, and the method for estimating a body shape and weight composition through a medical image, characterized in that it is indicated by including the coordinates of the point, a label, and data values of the coordinates.

Images