KR102015469B1 - Management System for Treatment of Neurological Disorder and Method thereof - Google Patents
Management System for Treatment of Neurological Disorder and Method thereof Download PDFInfo
- Publication number
- KR102015469B1 KR102015469B1 KR1020170079228A KR20170079228A KR102015469B1 KR 102015469 B1 KR102015469 B1 KR 102015469B1 KR 1020170079228 A KR1020170079228 A KR 1020170079228A KR 20170079228 A KR20170079228 A KR 20170079228A KR 102015469 B1 KR102015469 B1 KR 102015469B1
- Authority
- KR
- South Korea
- Prior art keywords
- attribute information
- face
- symmetric
- facial
- nervous system
- Prior art date
Links
- 208000012902 Nervous system disease Diseases 0.000 title claims abstract description 105
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000001815 facial effect Effects 0.000 claims abstract description 108
- 208000025966 Neurological disease Diseases 0.000 claims abstract description 52
- 230000005856 abnormality Effects 0.000 claims abstract description 38
- 210000000653 nervous system Anatomy 0.000 claims abstract description 35
- 238000012545 processing Methods 0.000 claims abstract description 20
- 230000000694 effects Effects 0.000 claims description 83
- 238000003745 diagnosis Methods 0.000 claims description 75
- 230000008859 change Effects 0.000 claims description 63
- 208000005736 Nervous System Malformations Diseases 0.000 claims description 25
- 238000010801 machine learning Methods 0.000 claims description 22
- 201000010099 disease Diseases 0.000 claims description 16
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 16
- 239000000284 extract Substances 0.000 claims description 15
- 230000001537 neural effect Effects 0.000 claims description 15
- 230000002159 abnormal effect Effects 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000036962 time dependent Effects 0.000 claims 1
- 239000013598 vector Substances 0.000 description 20
- 238000007637 random forest analysis Methods 0.000 description 19
- 238000004891 communication Methods 0.000 description 17
- 238000004422 calculation algorithm Methods 0.000 description 16
- 238000012706 support-vector machine Methods 0.000 description 15
- 238000010586 diagram Methods 0.000 description 14
- 238000004590 computer program Methods 0.000 description 10
- 210000001508 eye Anatomy 0.000 description 10
- 210000001331 nose Anatomy 0.000 description 9
- 230000000926 neurological effect Effects 0.000 description 8
- 208000006011 Stroke Diseases 0.000 description 7
- 230000001225 therapeutic effect Effects 0.000 description 7
- 230000006872 improvement Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000010224 classification analysis Methods 0.000 description 4
- 230000035945 sensitivity Effects 0.000 description 4
- 208000019770 Abnormality of the nervous system Diseases 0.000 description 3
- 206010008118 cerebral infarction Diseases 0.000 description 3
- 208000026106 cerebrovascular disease Diseases 0.000 description 3
- 210000004709 eyebrow Anatomy 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 239000004065 semiconductor Substances 0.000 description 3
- 206010008111 Cerebral haemorrhage Diseases 0.000 description 2
- 102100033571 Tissue-type plasminogen activator Human genes 0.000 description 2
- 210000004204 blood vessel Anatomy 0.000 description 2
- 210000004556 brain Anatomy 0.000 description 2
- 230000009172 bursting Effects 0.000 description 2
- 238000013145 classification model Methods 0.000 description 2
- 230000037213 diet Effects 0.000 description 2
- 235000005911 diet Nutrition 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 206010061216 Infarction Diseases 0.000 description 1
- 238000012896 Statistical algorithm Methods 0.000 description 1
- 108090000373 Tissue Plasminogen Activator Proteins 0.000 description 1
- 108050006955 Tissue-type plasminogen activator Proteins 0.000 description 1
- 206010000891 acute myocardial infarction Diseases 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000013399 early diagnosis Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000007574 infarction Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 210000000214 mouth Anatomy 0.000 description 1
- 235000015097 nutrients Nutrition 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- ZMRUPTIKESYGQW-UHFFFAOYSA-N propranolol hydrochloride Chemical compound [H+].[Cl-].C1=CC=C2C(OCC(O)CNC(C)C)=CC=CC2=C1 ZMRUPTIKESYGQW-UHFFFAOYSA-N 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000013515 script Methods 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 230000008733 trauma Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/40—Detecting, measuring or recording for evaluating the nervous system
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
- A61B5/0077—Devices for viewing the surface of the body, e.g. camera, magnifying lens
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/22—Social work or social welfare, e.g. community support activities or counselling services
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Medical Informatics (AREA)
- Theoretical Computer Science (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Molecular Biology (AREA)
- Heart & Thoracic Surgery (AREA)
- Tourism & Hospitality (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Biophysics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Primary Health Care (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Neurology (AREA)
- Neurosurgery (AREA)
- Physiology (AREA)
- Child & Adolescent Psychology (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a system and a method for managing a nervous system disease, wherein the apparatus for managing a neurological disease includes a feature point extracting unit for extracting feature points from a face image, and facial symmetric attribute information including distances or angles between the extracted feature points. And calculating a facial symmetric attribution information calculating unit, and a diagnostic processing unit for diagnosing abnormalities in the nervous system using the calculated facial symmetric attribution information.
Description
The present invention relates to systems and methods for the management of diseases of the nervous system. More specifically, the present invention relates to a system and method for neurological disease management that can diagnose neural system abnormalities using a facial image of a user and predict the progress of treatment.
Recently, the average age of survival has increased greatly due to the advancement of medical technology and the improvement of the standard of living, and Korea is going to enter the ultra-old society due to the low birth rate. Nervous system disorders are common in older age groups and typically include stroke. Stroke is one of the three major emergency diseases in Korea, and is one of the leading causes of death in Korea. Stroke is largely divided into cerebral hemorrhage and cerebral infarction. Cerebral infarction refers to a condition in which the blood vessels that supply nutrients and oxygen do not penetrate the brain because the blood vessels are blocked and cerebral hemorrhage refers to a disease caused by the brain vessels bursting. Stroke is a disease caused by sudden cerebrovascular blockage or sudden bursting of the cerebrovascular vessel. It is characterized by sudden symptoms. It is characterized by acute myocardial infarction and severe trauma. The temporal characteristics are very important to reduce the mortality and sequelae caused by stroke.In 2015, 94,813 domestic stroke patients had more than 6 hours of arrival in the emergency room after the onset. Can be. If Tissue-type Plasminogen activator (t-PA) is administered within 3 hours after the actual infarction, it is known to be effective in all types of cerebral infarction. Therefore, the early treatment of stroke is very important. The number of patients with nervous system abnormalities is expected to increase even when considering the situation in Korea, which is going to enter the elderly society, and due to the development of portable devices and mobile hardware, an environment in which personalization service for determining the nervous system abnormalities is being established. Currently, applications related to emergency diseases in Korea as well as abroad provide only information such as telephone connection and hospital location when an emergency occurs, and there is no service for diagnosing or managing diseases.
Therefore, for early treatment of neurological disorders, which occupy a high proportion of emergency diseases, a solution for promptly determining and managing a patient's disease is required.
It is an object of the present invention to provide a system and method for the management of neurological diseases, which enables a patient suspected of a neurological disorder to relatively easily determine the degree of neurological abnormality and the course of treatment.
It is another object of the present invention to provide a solution tailored to individuals with neurological disorders by predicting the therapeutic effect of the neurological disorder.
According to an aspect of the present invention, a feature point extractor for extracting feature points from a face image, a face symmetric attribute information calculation unit for calculating face symmetric attribute information including a distance or angle between the extracted feature points, the calculated face symmetry Provided is an apparatus for managing a nervous system disease, including a diagnostic processing unit for diagnosing an abnormality of a nervous system using attribute information.
The apparatus for managing the nervous system disease may generate at least one diagnostic model for diagnosing abnormalities of the nervous system by learning facial symmetric attribute information of a plurality of normal persons and facial symmetric attribute information of a plurality of patients by machine learning. The apparatus may further include a diagnostic model generator.
In addition, the apparatus for managing the nervous system disease learning effect prediction model generator for generating at least one therapeutic effect prediction model for predicting the neurological disorder treatment effect by learning the amount of facial symmetric attribution information change of a plurality of patients by machine learning It may further include.
The diagnosis processor determines whether the same face symmetry attribute information of the same user exists, calculates a change amount according to time of the previous face symmetry attribute information and the calculated face symmetry attribute information, if present, and calculates the calculated face symmetry. The amount of attribute change is applied to the treatment effect prediction model to predict the treatment effect, and if it is not present, the calculated facial symmetry attribute information can be applied to the diagnosis model to diagnose the abnormalities of the nervous system.
The diagnostic processor may select and apply a diagnostic model in consideration of at least one of facial symmetric attribute information, medical history information, and risk of nervous system disease among a plurality of diagnostic models.
The feature point extractor may select a face component region from the face image and extract a feature point corresponding to a preset reference point from the selected face component region.
According to another aspect of the present invention, a user device for extracting feature points from a facial image, calculating face symmetric attribute information including a distance or angle between the extracted feature points, and transmitting the feature symmetric attribute information to the diagnostic server, using the face symmetric attribute information By providing a system for neurological disease management, including a diagnostic server for diagnosing whether the user's nervous system abnormalities.
The user device may select a face component region from the face image, and extract a feature point corresponding to a preset reference point from the selected face component region, and extract feature vectors from positions of the extracted feature points. And a face symmetric attribute information calculating unit for calculating face symmetric attribute information including a distance or an angle between the extracted feature vectors, and transmitting a diagnostic request signal including the calculated face symmetric attribute information to the management server. It may include a diagnostic request processing unit for receiving a diagnosis result for the nervous system abnormalities from the management server.
When the diagnostic request signal is received from the user device, the diagnosis server determines whether the previous face symmetric attribute information of the same user exists, and if present, at the time of the previous face symmetric attribute information and the received face symmetric attribute information. Calculate the amount of change according to the change, and apply the calculated amount of facial symmetry change to the treatment effect prediction model to predict the treatment effect, and if it does not exist, apply the received face symmetry attribute information to the diagnosis model to diagnose neural system abnormalities. It may include a diagnostic processing unit.
The diagnostic processor may select and apply the diagnostic model in consideration of at least one of the facial symmetric attribute information, the medical history information of the user, and the risk of nervous system disease when the plurality of diagnostic models exist. .
The diagnosis server generates at least one diagnostic model for diagnosing abnormalities in the nervous system by learning face symmetric attribute information of a plurality of normal persons and face symmetric attribute information of a plurality of patients by machine learning. The method may further include a treatment effect prediction model generator configured to generate at least one treatment effect prediction model for predicting a neurological disorder treatment effect by learning a change in facial symmetry attribute information of a plurality of patients by machine learning.
According to another aspect of the present invention, in the method for the management of nervous system diseases in the apparatus for the management of nervous system diseases, extracting feature points from the facial image, facial symmetric attribute information including the distance or angle between the extracted feature points Comprising a step of diagnosing the nervous system abnormality using the calculated facial symmetric attribute information is provided a method for the management of diseases of the nervous system.
The diagnosing may include determining whether the same face symmetry attribute information of the same user is present, calculating the amount of change over time of the previous face symmetry attribute information and the calculated face symmetry attribute information, if present. And predicting a treatment effect by applying the calculated amount of facial symmetry change to a treatment effect prediction model, and if not present, applying the calculated face symmetry attribute information to a diagnosis model to diagnose neural abnormalities. have.
According to another aspect of the invention, the user device, if the facial image is obtained, extracting the predetermined feature points from the face image, the user device facial symmetry attribute including the distance and angle between the extracted feature points Calculating information and transmitting a diagnosis request signal including the calculated face symmetry attribute information to a diagnosis server, and when the diagnosis request signal is received, the diagnosis server determines whether the previous face symmetry attribute information of the same user exists. If the result of the determination is present, the amount of change of the previous face symmetry attribute information and the face symmetry attribute information with time is calculated, and the calculated face symmetry attribute change is applied to the treatment effect predictive model to predict the treatment effect and not exist. If not, diagnosing neurological abnormalities by applying the face-symmetric attribute information to a diagnosis model. It can be included.
The present invention also discloses a computer program stored in a computer readable recording medium for executing the above method for managing the nervous system disease in a computer.
According to the present invention, it is possible to diagnose the abnormalities of the nervous system by patients themselves without visiting the hospital through the apparatus for the management of diseases of the nervous system, thereby increasing the possibility of early diagnosis.
In addition, by measuring the amount of change in the facial symmetry attribute value can predict the progress (effect) of treatment of neurological disorders even if the patients do not come to the hospital.
1 is a diagram showing a system for managing nervous system diseases according to an embodiment of the present invention.
2 is a block diagram illustrating a configuration of a user device for managing a nervous system disease according to an embodiment of the present invention.
3 is a diagram for commanding facial symmetric attribute information according to an embodiment of the present invention.
4 is a diagram illustrating a method of calculating facial symmetric attribute information according to an embodiment of the present invention.
5 is a block diagram showing the configuration of a management server according to an embodiment of the present invention.
6 is a view for explaining a machine learning algorithm according to the present invention.
7 is a view showing a method for managing a nervous system disease according to an embodiment of the present invention.
8 is a block diagram showing the configuration of an apparatus for managing nervous system diseases according to another embodiment of the present invention.
9 is a diagram showing a method for managing a nervous system disease according to another embodiment of the present invention.
FIG. 10 is a view for explaining a method for managing a nervous system disease using a difference in angles of both mouths from a lower lip according to another embodiment of the present invention.
Hereinafter, an embodiment of the present invention will be described in detail with reference to the accompanying drawings.
In the description with reference to the accompanying drawings, the same or corresponding components will be given the same reference numerals and redundant description thereof will be omitted.
In describing the present invention, when it is determined that detailed descriptions of related well-known structures or functions may obscure the gist of the present invention, the detailed description may be omitted.
The terminology used herein is for the purpose of describing particular example embodiments only and is not intended to be limiting of terms. Singular expressions include plural expressions unless the context clearly indicates otherwise.
Each step described below may be provided by one or several software modules or may be implemented by hardware that is responsible for each function, or may be a combination of software and hardware.
Specific meanings and examples of each term will be described below in the order of the drawings.
Hereinafter, a system and method for managing a neurological disease according to an embodiment of the present invention will be described in detail with reference to the accompanying drawings.
1 is a diagram showing a system for managing nervous system diseases according to an embodiment of the present invention.
Referring to FIG. 1, a system for managing a nervous system disease includes a
The
In addition, when there is previously calculated face symmetric attribute information of the same user, the
The
Detailed description of the
The diagnosis server 200 generates a diagnostic model for diagnosing the abnormalities of the nervous system by learning the face symmetric attribute information of the nervous system abnormal patients and normal persons by machine learning.
When the diagnosis server 200 receives the face symmetric attribute information from the
In addition, when the diagnosis server 200 receives a change amount of the face symmetric attribute information from the
According to another embodiment of the present invention, the
Detailed description of the diagnostic server 200 will be described with reference to FIG. 5.
In the above description, the
2 is a block diagram showing a configuration of a user device for managing a nervous system disease according to an embodiment of the present invention, FIG. 3 is a view for commanding facial symmetric attribution information according to an embodiment of the present invention, and FIG. A diagram for describing a method of calculating facial symmetric attribute information according to an embodiment of the present invention.
Referring to FIG. 2, the
The
The
That is, the
The face symmetric
From here,
Is the angle between the two plane vectors, Are two vectors containing the feature points on the plane. A1, a2, b1, and b2 mean components of plane vectors. In other words, the cosine of an angle between two plane vectors can be obtained as a product of the dot product between two vectors and the magnitude between the two vectors.For example, a method of calculating face symmetric attribution information will be described with reference to FIG. 4. Both mouth-
The
In addition, the diagnostic
That is, when a patient first uses the
Meanwhile, each of the
The communication unit 150 is a configuration for transmitting and receiving data with various electronic devices. In particular, the communication unit 150 may be connected to two or more devices, and may transmit and receive various information such as facial symmetry attribute information, diagnosis result, facial symmetry attribute change amount, treatment effect prediction information, and the like.
The storage unit 160 is a component that stores data related to the operation of the
In addition, the storage unit 160 may store an application (or an applet) for performing a neurological disease management service, and the stored information may be selected by the controller 170 as necessary.
The control unit 170 may store an application (or applet) for performing a neurological disease management service in the storage unit 160, and control the output of information provided from the management server by driving the application. have.
The controller 170 may include at least one arithmetic unit, wherein the arithmetic unit is a general purpose central arithmetic unit (CPU), programmable device elements (CPLD, FPGA) implemented for a specific purpose, and custom semiconductor arithmetic. It may be an apparatus (ASIC) or a microcontroller chip.
Meanwhile, the
In addition, the user device may further include an input unit (not shown) that receives a command from the user.
5 is a block diagram showing the configuration of a management server according to an embodiment of the present invention, Figure 6 is a view for explaining a machine learning algorithm according to the present invention.
Referring to FIG. 5, the management server 200 may include a communication unit 210, a database 220, a
The communication unit 210 may receive face symmetric attribute information and face symmetric attribute variation from a user device through a communication network, and transmit a diagnosis result to the user device. Here, the communication network includes both wired and wireless communication, and the user device and the management server 200 are interconnected through the communication network.
The database 220 stores user information (eg, name, user identification information, user device identification information, etc.), neurological abnormality diagnosis results of each user, facial symmetry attribute information, facial symmetry attribute variation, treatment effect prediction information, and the like. Here, the user may include a user who does not have a neurological disorder (hereinafter, referred to as a 'normal person'), a user who has a neurological disorder (hereinafter, referred to as a 'patient'), and the like.
In addition, the database 220 stores information that divides neurological disease patients into groups by treatment effect. For example, in the form of treatment effect group 1, treatment effect group 2,
The database 220 is a device for storing data, and basically stores data such as environment variables for searching, classifying, analyzing, and the like. The function of the database 220 may be implemented using conventional techniques. Detailed description thereof will be omitted.
When the
In addition, when a diagnostic request signal including a face image is received from the user device, the
In addition, when the amount of face symmetry change is received from the user device, the
In addition, when face-symmetric attribute information is received from the user device, the
The
As such, the
Logistic Classification is a statistical algorithm that analyzes and predicts which items the input variables can be classified into. Depending on whether there are two or more classification items, it can be divided into binary logistic analysis and polynomial logistic analysis. In the present invention, binomial logistic discriminant analysis is performed. That is, the items for the neural system abnormality can be divided into two, and the facial symmetry attributes extracted from the training image including any patient and normal people can be classified into two items.
The support vector machine (SVM) is an algorithm mainly used for pattern recognition, and may be used for character recognition, object recognition, medical image analysis, and the like. For example, given a set of data in either category, the support vector machine (SVM) algorithm can generate a binary linear classification model that determines which category the new data belongs to based on the given data set. Can be. Binary linear classification model is represented as the boundary in the space where data is mapped, which means the algorithm to find the boundary with the largest width. In particular, mapping a given data into a high-dimensional feature space is called a kernel trick. To more easily classify input data, you can use a kernel trick to map a high-level space.
The random forest (RF) is a classifier based on a binary decision tree, and the machine learning by the random forest algorithm may appear as a process of classifying each feature vector into two or more items. Random forest classification is an algorithm that generates multiple diagnostic data through random reconstruction sampling from the same data set, generates multiple trees through multiple trainings, combines them, and finally predicts the result.
Statistical indicators for evaluating the performance of the diagnostic model generated by the algorithm of the Logistic Classification, the Support Vector Machine (SVM), and the Random Forest (RF) are as shown in FIG. ), Area Under Cover (712), Sensitivity (714) and Specificity (716). The accuracy of the algorithm used by machine learning is evaluated as a statistical indicator.
For example, accuracy (710) refers to the ratio of hits of the nervous system abnormality, and sensitivity (714) refers to the ratio of cases in which the
The performance of the logistic classification analysis (Logistic Classification, 704), the support vector machine (SVM, 706), and the random forest (RF, 708) algorithm used by the machine learning in the present invention may vary depending on the number of feature points. Since the accuracy (Accuracy, 710) and the area under cover (712) value of the random forest (RF) 708 are measured with respect to a predetermined number of feature points, the
As such, the
The treatment effect prediction model generation unit 250 generates a treatment effect prediction model for predicting a neurological disorder treatment effect by learning the amount of change in facial symmetry attribute information of a plurality of patients over time by machine learning. That is, the treatment effect prediction model generation unit 250 generates a treatment effect prediction model by learning the amount of change in facial symmetry of the group of patients with neurological disorders by machine learning. In this case, the treatment effect prediction model generator 250 may generate the treatment effect prediction model using algorithms such as logistic discriminant analysis, support vector machine, and random forest.
In detail, the treatment effect prediction model generator 250 may generate a treatment effect prediction model by obtaining an average value of the amount of change in facial symmetry for each treatment order of patients belonging to each treatment effect group. For example, the average of the change in facial symmetry attribute of the treatment effect group 1 is 10 at the first treatment, 8 at the second treatment, and 5 at the third treatment, and the average of the change in the face symmetry attribute of the treatment effect group 2 is 5 at the first treatment. The average of the change in facial symmetry of the
As described above, the treatment effect prediction model generator 250 learns data on the period of improvement including the amount of change in the facial symmetry property value of patients suffering from neurological diseases by using a machine learning method to determine the state of improvement of the neurological disease. Therapeutic effect prediction model can be generated.
Meanwhile, each of the
The
The
7 is a view showing a method for managing a nervous system disease according to an embodiment of the present invention.
Referring to FIG. 7, when a face image is acquired (S702), the user device extracts predefined feature points from the face image (S704).
Thereafter, the user device calculates face symmetry attribute information including the distance and angle between the extracted feature points (S706), and transmits a diagnosis request signal including the calculated face symmetry attribute information to the diagnosis server (S708).
The diagnosis server applies face-symmetry attribute information received from the user device to a preset diagnosis model to diagnose whether the user's nervous system is abnormal (S710), and transmits the diagnosis result to the user device (S712). At this time, when the face symmetric attribute information is received from the user device, the diagnostic server determines whether the face symmetric attribute information of the same user exists, and if present, calculates the amount of change of the previous face symmetric attribute information and the current face symmetric attribute information, The calculated amount of change can also be applied to a model for predicting treatment effects to predict the treatment effect.
8 is a block diagram showing the configuration of an apparatus for managing nervous system diseases according to another embodiment of the present invention.
Referring to FIG. 8, an apparatus for managing nervous system diseases (hereinafter, referred to as a neurological disease management apparatus) 800 may include an
Since the
Here, the
When the face symmetry attribute information is calculated by the face symmetry attribute calculation unit 830, the
In addition, when the face symmetric attribute information is calculated by the face symmetric attribute calculator 830, the
The
Meanwhile, each of the feature point extractor 820, the face symmetric attribute information calculator 830, and the
The storage unit 850 is configured to store data related to the operation of the neurological disease management apparatus 800. The storage unit 850 may use a known storage medium. For example, the storage unit 850 may use any one or more of known storage media such as a ROM, a PROM, an EPROM, an EEPROM, and a RAM. In particular, the storage unit 850 stores information about a reference point, which is a reference for determining whether the user's nervous system is abnormal. The storage unit 850 may store an application (or applet) for performing a neurological disease management service, and the stored information may be selected by the
The
The
On the other hand, the neurological disease management apparatus 800 according to the present invention is to diagnose the facial symmetry attribute information of a plurality of normal people, facial symmetry attribute information of a plurality of patients by machine learning to generate a diagnostic model for determining the degree of nervous system abnormality The model generator 870 may be further included. The diagnostic model can be generated in consideration of the risk of nervous system abnormalities as well as fixed information on the presence or absence of nervous system abnormalities, and facial symmetric attribution information of normal people and patients can be generated from a database of a hospital or a medical research institution that manages nervous system diseases. The data may be shared in real time. The diagnostic model generator may generate a diagnostic model using algorithms such as logistic classification analysis, support vector machine (SVM), and random forest (RF).
In addition, the neurological disease management apparatus 800 is a treatment effect model generation unit for generating a treatment effect prediction model for predicting the treatment effect on the nervous system by learning the amount of change of facial symmetry attribute information of a plurality of patients over time by machine learning techniques 880 may be further included.
In addition, the neurological disease management apparatus 800 may further include a display unit (not shown) for displaying various information related to the operation of the neurological disease management apparatus 800. In particular, the display unit may display various information such as a face image acquired by the
In addition, the neurological disease management apparatus 800 according to the present invention may further include an input unit (not shown) that receives a command from a user.
The neurological disease management apparatus 800 configured as described above may be a portable device or a mobile terminal provided with a camera and installed with an application capable of managing the neurological disease management service. In addition, the neurological disease management apparatus 800 may obtain a facial image from the outside, and may be a device capable of managing a neurological disease management service.
9 is a diagram showing a method for managing a nervous system disease according to another embodiment of the present invention.
Referring to FIG. 9, when the facial image is acquired (S902), the neurological disease management apparatus extracts predefined feature points from the facial image (S904). That is, the apparatus for managing a nervous system disease may select a facial component region on a face image including an eye, a nose, and a mouth, and extract a feature point according to a predetermined extraction criterion from the facial component region.
Thereafter, the neurological disease management apparatus calculates face symmetry attribute information including the distance and angle between the extracted feature points (S906), and determines whether there is face symmetric attribute information of the same user as the user of the calculated face symmetric attribute information. (S908). The determination of the presence of facial symmetric attribution information of the same user is to determine whether to diagnose the neurological abnormality by determining the degree of neurological abnormality or to predict the treatment effect by judging the progress of the neurological abnormality treatment.
As a result of the determination in S908, if there is no face symmetric attribute information of the same user, the neurological disease management apparatus diagnoses the neural system abnormality of the user by applying the face symmetric attribute information to a preset diagnosis model (S910), and diagnoses the diagnosis result. Output (S912). In this case, the apparatus for managing a neurological disease may store facial symmetric attribute information and a diagnosis result of the user and share the same with an external server through wired or wireless communication.
If it is determined in S908 that the face-symmetric attribution information of the same user exists, the neurological disease management apparatus calculates the amount of change in the previous face-symmetry attribution information and the current face-symmetry attribution information (S914). Thereafter, the neurological disease management apparatus applies the calculated change amount to the treatment effect prediction model to predict the treatment effect (S916), and outputs the predicted treatment effect (S918). In this case, the neurological disease management apparatus may store facial symmetry attribute information, treatment effect prediction information, and share it with an external server through wired or wireless communication.
As such, the neurological disease management apparatus for managing the neurological disease may diagnose the progress of treating the neurological disorder so that the improvement of the neurological disease may be known.
FIG. 10 is a view for explaining a method for managing a nervous system disease using a difference in angles of both mouths from a lower lip according to another embodiment of the present invention.
Referring to FIG. 10, the apparatus for managing a neurological disease takes a face picture of a patient through a photographing unit (S1002), and acquires a face image (S1004).
Thereafter, the neurological disease management apparatus checks the facial component region including the eyes, the nose, the mouth, and the like in the facial image (S1006), and detects the facial component in the facial component region (S1008).
Thereafter, the neurological disease management apparatus checks coordinate values of feature points corresponding to a preset reference point in the detected face component (S1010). In this case, the apparatus for managing a nervous system disease extracts feature points corresponding to a reference point set to calculate angle differences between both mouth tails from the lower lips, and checks coordinate values of the extracted feature points.
Thereafter, the apparatus for managing a neurological disease calculates an angle difference between both mouth tails from the lower lip using coordinates of special points (S1012), and applies the difference in the angles of both mouth tails from the calculated lower lip to a preset diagnostic model to determine whether there is an abnormal nervous system. Diagnose it (S1014). That is, the neurological disease management apparatus may diagnose that the nervous system is abnormal when the angle difference between the two corners of the mouth from the lower lip is greater than or equal to a predetermined predetermined angle.
The neurological disease management apparatus transmits a diagnosis result of the neural system abnormality to the patient (S1016). In this case, the apparatus for managing a nervous system disease may provide a patient with a diagnosis result of nervous system abnormality through a text, an e-mail, or an SNS.
On the other hand, such a method for managing the nervous system disease can be written as a program, codes and code segments constituting the program can be easily inferred by a programmer in the art. In addition, a program related to a method for managing a nervous system disease may be stored in a readable media that can be read by an electronic device, and read and executed by the electronic device.
As such, those skilled in the art will recognize that the present invention can be implemented in other specific embodiments without changing the technical spirit or essential features thereof. Therefore, it should be understood that the embodiments described above are merely exemplary and are not limitative in scope. In addition, the flowcharts shown in the drawings are merely sequential orders illustrated to achieve the most desirable results in practicing the present invention, and other additional steps may be provided or some steps may be omitted. .
The technical features and implementations described herein may be embodied in digital electronic circuitry, implemented in computer software, firmware, or hardware, including the structures and structural equivalents described herein, or a combination of one or more of these. It can be implemented. An implementation that implements the technical features described herein is also a module relating to computer program instructions encoded on a program storage medium of tangible type for controlling or by the operation of a computer program product, ie a processing system. It may be implemented.
In addition, all or part of the method of the embodiment of the present invention may be implemented in the form of a computer-executable recording medium such as a program module executed by the computer. Here, computer readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. In addition, computer readable media may include both computer storage media and communication media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.
In addition, all or part of the method according to the embodiment of the present invention includes instructions executable by a computer, and may be implemented as a computer program (or computer program product) recorded on a medium. The computer program includes programmable machine instructions processed by the processor and may be implemented in a high-level programming language, an object-oriented programming language, an assembly language, or a machine language. . The computer program may also be recorded on tangible computer readable media (eg, memory, hard disks, magnetic / optical media or solid-state drives, etc.).
Thus, a method according to an embodiment of the present invention may be implemented by executing a computer program as described above by a computing device. The computing device may include at least a portion of a processor, a memory, a storage device, a high speed interface connected to the memory and a high speed expansion port, and a low speed interface connected to the low speed bus and the storage device. Each of these components are connected to each other using a variety of buses and may be mounted on a common motherboard or otherwise mounted in a suitable manner.
As used herein, the term "apparatus" or "system" includes all the apparatus, apparatus, and machines for processing data, including, for example, a processor, a computer, or a multiprocessor or a computer. The processing system includes, in addition to hardware, all code that forms an execution environment for a computer program on demand, such as code constituting processor firmware, a protocol stack, a database management system, an operating system, or a combination of one or more thereof. can do.
Computer programs, known as programs, software, software applications, scripts, or code, may be written in any form of programming language, including compiled or interpreted languages, or a priori or procedural languages. It may be implemented in any form, including other units suitable for use in a routine or computer environment.
On the other hand, the components for implementing the technical features of the present invention included in the block diagram and the flowchart shown in the drawings attached to this specification means a logical boundary between the components. However, according to an embodiment of the software or hardware, the illustrated configuration and its functions are executed in the form of stand-alone software modules, monolithic software structures, codes, services, and combinations thereof, and can execute stored program codes, instructions, and the like. All such embodiments should also be considered to be within the scope of the present invention, as the functions may be implemented by being stored in a computer executable processor.
Accordingly, although the accompanying drawings and descriptions thereof illustrate technical features of the present invention, they should not be inferred simply unless the specific arrangement of software for implementing such technical features is clearly stated. That is, there may be various embodiments described above, and such embodiments may be modified in part while having the same technical features as the present invention, which should also be regarded as falling within the scope of the present invention.
In addition, although flowcharts depict operations in the drawings in a particular order, they are shown to obtain the most desirable results, which must be performed in the specific order shown or in the sequential order shown or all illustrated actions must be executed. It should not be understood to be. In certain cases, multitasking and parallel processing may be advantageous. In addition, the separation of the various system components of the embodiments described above should not be understood as requiring such separation in all embodiments, and the described program components and systems are generally integrated together into a single software product or may be combined into multiple software products. It should be understood that it can be packaged.
As such, this specification is not intended to limit the invention by the specific terms presented. Thus, although the present invention has been described in detail with reference to the embodiments described above, those skilled in the art to which the present invention pertains without departing from the scope of the invention modifications, changes and Modifications can be made.
The scope of the present invention is shown by the following claims rather than the detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts are included in the scope of the present invention. Should be.
Claims (15)
A face symmetric attribute information calculating unit for calculating face symmetric attribute information including a distance or an angle between the extracted feature points; And
Dynamically select a diagnostic model using at least one of the medical history information and the risk of nervous system disease and the calculated facial symmetry attribute information, and the facial symmetry attribute information already stored in relation to the user. A diagnostic processor for diagnosing abnormalities in the nervous system by applying the time-dependent change amount of the face-symmetric attribute information calculated by the face-symmetric attribute information calculation unit and the already stored face-symmetric attribute information to the selected diagnostic model; Apparatus for the management of diseases of the nervous system comprising a.
The nervous system further includes a diagnostic model generation unit configured to generate at least one diagnostic model for diagnosing abnormalities of the nervous system by learning face-symmetric attribute information of a plurality of normal persons and face-symmetric attribute information of a plurality of patients by machine learning. Device for Disease Management.
And a treatment effect prediction model generation unit for generating at least one treatment effect prediction model for predicting a neurological disorder treatment effect by learning the amount of change of facial symmetric attribution information of a plurality of patients by a machine learning technique.
The diagnosis processor determines whether the same face symmetry attribute information of the same user exists, calculates a change amount according to time of the previous face symmetry attribute information and the calculated face symmetry attribute information, if present, and calculates the calculated face symmetry. Apparatus for managing the nervous system disease, characterized in that to predict the treatment effect by applying the amount of attribute change to the predictive effect model, and if it does not exist by applying the calculated face symmetric attribute information to the diagnostic model.
The diagnostic processing unit may select and apply a diagnosis model in consideration of at least one of the facial symmetric attribution information, medical history information, and risk of nervous system disease among a plurality of diagnostic models. Device for.
The feature point extracting unit selects a facial component region from the face image, and extracts a feature point corresponding to a predetermined reference point from the selected facial component region.
And a diagnosis server for diagnosing a neural system abnormality of a corresponding user using the face symmetric attribute information.
The user device may include a feature point extractor which extracts feature points from a face image of a user;
A face symmetric attribute information calculating unit for calculating face symmetric attribute information including a distance or an angle between the extracted feature points; And
Dynamically selecting a diagnostic model using at least one of medical history information and risk of nervous system disease, and the calculated facial symmetry attribute information;
By applying the face symmetry attribute information already stored in relation to the user to the selected diagnostic model, the amount of change over time of the face symmetry attribute information and the face symmetry attribute information calculated by the face symmetry attribute information calculation unit are used. A diagnostic processor for diagnosing abnormalities in the nervous system; System for the management of diseases of the nervous system comprising a.
The user device,
And a diagnostic request processing unit for transmitting the diagnostic request signal including the calculated facial symmetry attribute information to the management server and receiving a diagnosis result for the neural system abnormality from the management server. system.
The diagnostic server,
When the diagnostic request signal is received from the user device, it is determined whether the same face-symmetric attribute information of the same user exists, and if present, calculates the amount of change over time of the previous face-symmetric attribute information and the received face-symmetric attribute information And predicting a treatment effect by applying the calculated amount of facial symmetry change to a treatment effect prediction model, and if not present, applying a received face symmetry attribute information to a diagnosis model to diagnose a neural system abnormality. System for the management of diseases of the nervous system, characterized in that.
The diagnostic processor selects and applies a diagnostic model in consideration of at least one of facial symmetric attribute information, medical history information, and risk of nervous system disease when a plurality of diagnostic models exist. System for the management of diseases of the nervous system.
A diagnostic model generator for generating at least one diagnostic model for diagnosing abnormalities in a nervous system by learning face-symmetric attribute information of a plurality of normal persons and face-symmetric attribute information of a plurality of patients by machine learning techniques; And
And a treatment effect prediction model generation unit for generating at least one treatment effect prediction model for predicting a neurological disorder treatment effect by learning a change in facial symmetric attribution information of a plurality of patients by machine learning.
Extracting feature points from the facial image by the feature point extractor;
Calculating, by the face symmetry attribute information calculating unit, the face symmetric attribute information including a distance or an angle between the extracted feature points; And
The diagnostic processor dynamically selects a diagnostic model using at least one of medical history information and neurological disease risk and the calculated facial symmetry attribute information, and the facial symmetry already stored in relation to the user. Applying attribute information to the selected diagnostic model and diagnosing a nervous system abnormality using a variation of the facial symmetric attribution information calculated by the facial symmetric attribution information calculation unit over time; A method for managing neurological disease, comprising.
Diagnosing whether the nervous system is abnormal,
Determining whether there is a previous facial symmetric attribute information of the same user;
As a result of the determination of the existence, if present, the change in time of the previous face symmetry attribute information and the calculated face symmetry attribute information is calculated and the treatment effect is applied by applying the calculated face symmetry attribute change to the treatment effect prediction model. Predicting and diagnosing abnormalities in the nervous system by applying the calculated facial symmetry attribute information to a diagnostic model if not present.
Calculating, by the user device, facial symmetric attribute information including distances and angles between the extracted feature points, and transmitting a diagnostic request signal including the calculated face symmetric attribute information to a diagnosis server; And
When the diagnostic server receives a diagnostic request signal, the diagnostic model is dynamically selected using at least one of medical history information and risk of nervous system disease, and the calculated facial symmetry attribute information. Diagnosing abnormalities in the nervous system using the already stored facial symmetry attribute information and the calculated facial symmetry attribute information over time by applying already stored facial symmetry attribute information with respect to the user to the selected diagnostic model; Method for the management of diseases of the nervous system comprising a.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020170079228A KR102015469B1 (en) | 2017-06-22 | 2017-06-22 | Management System for Treatment of Neurological Disorder and Method thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020170079228A KR102015469B1 (en) | 2017-06-22 | 2017-06-22 | Management System for Treatment of Neurological Disorder and Method thereof |
Publications (2)
Publication Number | Publication Date |
---|---|
KR20190000195A KR20190000195A (en) | 2019-01-02 |
KR102015469B1 true KR102015469B1 (en) | 2019-08-28 |
Family
ID=65021517
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
KR1020170079228A KR102015469B1 (en) | 2017-06-22 | 2017-06-22 | Management System for Treatment of Neurological Disorder and Method thereof |
Country Status (1)
Country | Link |
---|---|
KR (1) | KR102015469B1 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20220114715A (en) | 2021-02-09 | 2022-08-17 | 한양대학교 에리카산학협력단 | X-ray Images Analysis System And Method |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR102378212B1 (en) * | 2020-08-07 | 2022-03-25 | 주식회사 에이아이포펫 | Skin disease measuring system using a portable treminal and skin disease management method |
CN112084956A (en) * | 2020-09-11 | 2020-12-15 | 上海交通大学烟台信息技术研究院 | Special face crowd screening system based on small sample learning prototype network |
KR102274330B1 (en) * | 2020-09-18 | 2021-07-07 | 가천대학교 산학협력단 | Face Image Analysis Method and System for Diagnosing Stroke |
KR102497688B1 (en) * | 2020-10-14 | 2023-02-07 | 이세호 | Method for correcting facial asymmetry using expression training |
WO2022158737A1 (en) * | 2021-01-21 | 2022-07-28 | 한양대학교 에리카산학협력단 | Disease diagnosis device and method |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009520546A (en) * | 2005-12-21 | 2009-05-28 | コーニンクレッカ フィリップス エレクトロニクス エヌ ヴィ | Computer-based evaluation of facial palsy |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101894390B1 (en) * | 2011-02-28 | 2018-09-04 | 삼성전자주식회사 | Apparatus and method diagnosing health using voice |
KR101993716B1 (en) * | 2012-09-28 | 2019-06-27 | 삼성전자주식회사 | Apparatus and method for diagnosing lesion using categorized diagnosis model |
KR101602033B1 (en) | 2014-01-13 | 2016-03-09 | 울산대학교 산학협력단 | Apparatus for monitoring patients with epilepsy using the mobile communication terminal and method thereof |
KR20170023770A (en) * | 2014-06-25 | 2017-03-06 | 삼성전자주식회사 | Diagnosis model generation system and method |
-
2017
- 2017-06-22 KR KR1020170079228A patent/KR102015469B1/en active IP Right Grant
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009520546A (en) * | 2005-12-21 | 2009-05-28 | コーニンクレッカ フィリップス エレクトロニクス エヌ ヴィ | Computer-based evaluation of facial palsy |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20220114715A (en) | 2021-02-09 | 2022-08-17 | 한양대학교 에리카산학협력단 | X-ray Images Analysis System And Method |
Also Published As
Publication number | Publication date |
---|---|
KR20190000195A (en) | 2019-01-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR102015469B1 (en) | Management System for Treatment of Neurological Disorder and Method thereof | |
AU2021202168B2 (en) | A Method and System for Computer-Aided Triage | |
CN109447183B (en) | Prediction model training method, device, equipment and medium | |
KR101880678B1 (en) | System for interpreting medical images through machine learnings | |
KR102015473B1 (en) | Management System for Treatment of Neurological Disorder and Method thereof | |
CA2988416A1 (en) | Method and system for assessing mental state | |
US9408562B2 (en) | Pet medical checkup device, pet medical checkup method, and non-transitory computer readable recording medium storing program | |
KR102274330B1 (en) | Face Image Analysis Method and System for Diagnosing Stroke | |
Dadiz et al. | Detecting depression in videos using uniformed local binary pattern on facial features | |
WO2023097780A1 (en) | Classification method and device for classifying patient‑ventilator asynchrony phenomenon in mechanical ventilation process | |
Mahmud et al. | Non-invasive detection of anemia using lip mucosa images transfer learning convolutional neural networks | |
US11896375B2 (en) | Assessment of facial paralysis and gaze deviation | |
KR20220157330A (en) | Method for predicting dementia by incubation period based on machine learning and apparatus implementing the same method | |
CN114972241A (en) | Fetus ultrasonic section quantitative quality control assessment method and device based on residual error neural network | |
Alotaibi et al. | Detection of ischemic stroke tissue fate from the MRI images using a deep learning approach | |
Klinwichit et al. | The Radiographic view classification and localization of Lumbar spine using Deep Learning Models | |
Hu et al. | Personalized Heart Disease Detection via ECG Digital Twin Generation | |
Santhanakrishna et al. | Early Cerebral Infarction Detection and Classification Using Machine Learning Approaches | |
KR102608203B1 (en) | Dementia prediction method based on 2-dimensional magnetic resonance imaging and analysis apparatus | |
Asghar et al. | Harnessing Machine Learning Techniques for Intelligent Disease Prediction | |
KR102549558B1 (en) | Ai-based emotion recognition system for emotion prediction through non-contact measurement data | |
US11928817B2 (en) | Method for filtering normal medical image, method for interpreting medical image, and computing device implementing the methods | |
Meda et al. | Predicting Congenital Heart Diseases Using Machine Learning | |
Praditsangthong | Development of facial expression detection model for stroke patients | |
Priya et al. | Optimizing Ischemic Stroke Diagnosis: Enhanced Performance with MobileNetV2 in Automated Image Segmentation |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
A201 | Request for examination | ||
E902 | Notification of reason for refusal | ||
E701 | Decision to grant or registration of patent right | ||
GRNT | Written decision to grant |