Children neuropsychological development monitoring and management system

Abstract

The invention provides a child neuropsychological development monitoring and management system. According to the system, brain physiological parameters, brain MR I images, development scale features and corresponding child neuropsychological development morbidity levels are utilized to construct a child neuropsychological development evaluation model; a constructed child neurological psychological development evaluation model generates a current child neurological psychological development attack grade of a user according to real-time brain physiological parameters collected by a system terminal, a real-time brain MRI image monitored by a hospital and corresponding real-time development scale features. A basis is provided for further monitoring whether the corresponding child needs to be further monitored according to the current child neuropsychological development morbidity level, and the probability of finding potential abnormally developed children is increased. According to the invention, a high-precision real-time processing model is constructed by using fusion parameters of three features, such as brain physiological parameters, brain image features and subjective measurement table features, which are related to child brain nerves, so that doctors can intelligently monitor the morbidity of child neurodevelopmental disorder diseases, and family burdens are reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of neural engineering detection, and in particular relates to a child neuropsychological development monitoring and management system. Background Art

[0002] In recent years, the incidence of children's neuropsychological developmental behavior-related diseases has been increasing year by year. The proportion of children under 5 years old with developmental delay is as high as 15% worldwide. A study on the prevalence of ASD (Autism Spectrum Disorder) was conducted on children aged 6 to 12 years old. The estimated prevalence of ASD in the target population is about 0.7%, and 68.8% of ASD children have at least one comorbidity; while the prevalence of ADHD (Attention Deficit Hyperactivity Disorder) children is about 5.59%, and there is a trend of increasing year by year. Due to the complex pathogenesis of neurodevelopmental disorders, which are often caused by complex interactions between susceptibility factors and the environment, and the strong heterogeneity of clinical phenotypes, it is difficult to identify and diagnose such diseases early. However, if they can be identified and intervened early, the symptoms of most children can be effectively improved.

[0003] Child neuropsychological developmental assessment refers to the use of standardized assessment tools to conduct a comprehensive developmental assessment of the child subject in order to identify developmental delays or abnormalities in the child. As the most commonly used assessment tool, the developmental scale can conduct a comprehensive assessment and observation of the child's developmental behavior to assist child health physicians in making correct clinical judgments. Therefore, it is widely used in group child preventive health care. There are many types of child neurodevelopmental scales, which can be divided into screening tests and diagnostic tests according to their scope of application and purpose of application: developmental screening scales are mostly simple and time-saving. When the developmental screening results are suspicious or even abnormal, further diagnostic tests are required to assist in the diagnosis to clarify whether the child subject needs intervention.

[0004] It can be seen that the existing child neuropsychological development assessment only relies on subjective scales, the detection of child neuropsychological development is single, and there is no good use of big data models in specific application scenarios to process relevant data to obtain accurate child neurodevelopmental disorder monitoring methods.

[0005] Based on the above problems, the present invention designs a child neuropsychological development monitoring and management system, which uses the fusion parameters of brain physiological data and subjective measurement table characteristics to build a high-precision real-time processing model to enable doctors to intelligently monitor the prevalence of children's neurodevelopmental disorders and reduce the burden on families. The present invention meets the problem that there are few relevant pediatric doctors and it is not possible to make real-time diagnosis for children and monitor the neuropsychological development of children in real time. The present invention ensures the health and quality of children's neuropsychological development through intelligent monitoring and evaluation effects. Summary of the invention

[0006] In order to solve the above technical problems, the present invention proposes a child neuropsychological development monitoring and management system.

[0007] In a first aspect of the present invention, a method for monitoring and managing the neuropsychological development of children is provided, characterized in that the method comprises:

[0008] Obtaining the child's first brain physiological parameter, first brain MRI image, first developmental scale feature, and corresponding first child neuropsychological development morbidity grade;

[0009] generating a first child neuropsychological development vector using the first brain physiological parameter, the first brain MRI image, and the first developmental scale feature;

[0010] constructing a child neuropsychological development assessment model according to the first child neuropsychological development vector and the first child neuropsychological development affliction level;

[0011] A second brain physiological parameter, a second brain MRI image and a second developmental scale feature of the child are received, a second neuropsychological development vector of the child is generated based on the second brain physiological parameter, the second brain MRI image and the second developmental scale feature, a second neuropsychological development affliction grade of the child is generated based on the second neuropsychological development vector of the child using the child neuropsychological development assessment model, and the prevalence of neurodevelopmental disorders in the child is intelligently monitored based on the second neuropsychological development affliction grade of the child.

[0012] Further, the first brain physiological parameter or the second brain physiological parameter includes brain electrical data or brain neurotransmitter data, and the first brain MRI image includes a historical brain MRI image.

[0013] Furthermore, the brain EEG data is collected by using a wireless EEG acquisition device Neuro Scan, which can collect EEG signals at 128 brain-computer interfaces. The first developmental scale feature or the second developmental scale feature Q is obtained through a preschool children's ability screening form or an ASQ questionnaire.

[0014] Furthermore, the specific brain areas for collecting the electroencephalographic data are T3, T4, C3, C4, CZ, OZ, O1, O2, P7 and P8;

[0015] Further, the first brain MRI image or the second brain MRI image is feature processed to obtain a first brain MRI optimized image or a second brain MRI optimized image, and step S1 is first as follows:

[0016] A first brain MRI image or a second brain MRI image is acquired by using an MRI device, and the acquired image is subjected to regional subdivision processing, and the acquired equal-area image is divided into 12 equal parts. The first brain MRI image parameter or the second brain MRI image parameter is a feature processing value of each regional image after the acquired first brain MRI image or the second brain MRI image is divided into 12 equal parts.

[0017] Further, the first brain MRI image parameter or the second brain MRI image parameter is subjected to feature processing to obtain the first brain MRI image optimization parameter or the second brain MRI image optimization parameter, and the final step S2 is as follows:

[0018] The first brain MRI image parameter or the second brain MRI image parameter is processed by using an image unification processing method.

[0019] Further, the feature vector B of the first brain physiological parameter or the second brain physiological parameter f , T obtained by unifying the corresponding first brain MRI image parameters or the second brain MRI image parameters and the first developmental scale features or the second developmental scale features Q are spliced ​​to obtain the first child neuropsychological development vector or the second child neuropsychological development vector.

[0020] Furthermore, the child neuropsychological development assessment model adopts a classifier based on Fisher's criterion.

[0021] A child neuropsychological development monitoring and management system is also provided, the system comprising a brain physiological data acquisition module, a development scale feature acquisition module, an MRI equipment acquisition module, a neuropsychological development data storage module, a child neuropsychological development assessment model construction module, and a child neurodevelopmental disorder monitoring module, characterized in that:

[0022] The brain physiological data acquisition module is used to acquire the first brain physiological parameter or the second brain physiological parameter of the child;

[0023] The first brain physiological parameter or the second brain physiological parameter comprises brain electrical data or brain neurotransmitter data;

[0024] The developmental scale feature acquisition module is used to acquire the first developmental scale feature or the second developmental scale feature, wherein the first developmental scale feature or the second developmental scale feature is acquired through a preschool children's ability screening form or an ASQ questionnaire;

[0025] The MRI device acquisition module is used to acquire a first brain MRI image or a second brain MRI image, wherein the first brain MRI image includes a historical brain MRI image;

[0026] The neuropsychological development data storage module is used to receive the first brain physiological parameter or the second brain physiological parameter in the brain physiological data acquisition module, the first development scale feature or the second development scale feature in the development scale feature acquisition module, and the first brain MRI image or the second brain MRI image in the MRI device acquisition module, and process the first brain physiological parameter, the first development scale feature and the first brain MRI image to obtain a first child neuropsychological development vector, and process the second brain physiological parameter, the second development scale feature and the second brain MRI image to obtain a second child neuropsychological development vector;

[0027] The child neuropsychological development assessment model construction module is configured to obtain the first child neuropsychological development vector and the corresponding first child neuropsychological development affliction level, and to construct a child neuropsychological development assessment model using the first child neuropsychological development vector and the corresponding first child neuropsychological development affliction level;

[0028] The child neurodevelopmental disorder monitoring module receives the second child neuropsychological development vector, retrieves the child neuropsychological development assessment model to obtain the second child neuropsychological development affliction level, and intelligently monitors the prevalence of child neurodevelopmental disorders based on the second child neuropsychological development affliction level.

[0029] The present invention combines brain MRI image data and brain physiological parameter data, especially electrophysiological parameter data, in the detection and management of children's neuropsychological development, and can more accurately evaluate the neuropsychological development of children. Through the monitoring scene of specific neuropsychological development children, the brain MRI image is processed into a specific image channel, so that the data quality of the training model is enhanced, and the multi-dimensional data is used to monitor the neuropsychological development of children, so that more accurate and targeted management plan changes can be achieved. At the same time, the EEG data used can be wirelessly transmitted and collected in real time, which can more conveniently process the monitoring data. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a flow chart of a method for monitoring and managing the neuropsychological development of children of the present invention;

[0031] Figure 2 It is a schematic diagram of the structure of a child neuropsychological development monitoring and management system of the present invention;

[0032] Figure 3 It is a classification principle diagram of the classifier based on Fisher's criterion in the present invention;

[0033] Figure 4 This is a partial schematic diagram of a preschool children's ability screening table in an embodiment of the present invention;

[0034] Figure 5 It is a brain MRI image after processing in an embodiment of the present invention. DETAILED DESCRIPTION

[0035] The invention is further described below in conjunction with the accompanying drawings and specific implementation methods.

[0036] The first embodiment of the present invention:

[0037] In order to solve the above technical problems, the present invention proposes a child neuropsychological development monitoring and management system.

[0038] In a first aspect of the present invention, a method for monitoring and managing the neuropsychological development of children is provided, characterized in that the method comprises:

[0039] Obtaining the child's first brain physiological parameter, first brain MRI image, first developmental scale feature, and corresponding first child neuropsychological development morbidity grade;

[0040] generating a first child neuropsychological development vector using the first brain physiological parameter, the first brain MRI image, and the first developmental scale feature;

[0041] constructing a child neuropsychological development assessment model according to the first child neuropsychological development vector and the first child neuropsychological development affliction level;

[0042] A second brain physiological parameter, a second brain MRI image and a second developmental scale feature of the child are received, a second neuropsychological development vector of the child is generated based on the second brain physiological parameter, the second brain MRI image and the second developmental scale feature, a second neuropsychological development affliction grade of the child is generated based on the second neuropsychological development vector of the child using the child neuropsychological development assessment model, and the prevalence of neurodevelopmental disorders in the child is intelligently monitored based on the second neuropsychological development affliction grade of the child.

[0043] In this embodiment, the first child neuropsychological developmental affliction level or the second child neuropsychological developmental affliction level is divided into three levels: normal, mild, and severe, and is set by experts based on professional judgment of the diagnosis of the child.

[0044] Furthermore, the first brain physiological parameter or the second brain physiological parameter includes brain electrical data or brain neurotransmitter data, and the first brain MRI image includes a historical brain MRI image.

[0045] Furthermore, the brain EEG data is collected by using a wireless EEG acquisition device Neuro Scan, which can collect EEG signals at 128 brain-computer interfaces. The first developmental scale feature or the second developmental scale feature Q is obtained through a preschool children's ability screening form or an ASQ questionnaire.

[0046] In this embodiment, the preschool children's ability screening form is 50 items, including Figure 4 Only 12 of them are given as examples. Each item is scored 0-2 points according to the completion status, and the score obtained by answering is the first development scale feature or the second development scale feature Q. In this embodiment, Q can be set to 75.

[0047] In this embodiment, since the degree of completeness of children's brain development is different, the ratio of mature development days to the actual development days of the children is set and corrected to obtain conventional brain electrophysiological parameters. The deviation obtained after processing the brain electrophysiological parameters is corrected so that the subsequent feature vectors are of higher quality and more suitable for children.

[0048] Furthermore, the specific brain areas for collecting the electroencephalographic data are T3, T4, C3, C4, CZ, OZ, O1, O2, P7 and P8;

[0049] Furthermore, the feature vector B of the first brain physiological parameter or the second brain physiological parameter f The calculation formula is as follows:

[0050]

[0051] In the formula, k is the adjustment coefficient, D is the number of days for children to develop, B is the number of days for the brain to fully develop, S1, S2, ..., S 10 It is the amplitude of the EEG signal measured at the 10 brain-computer interfaces, namely T3, T4, C3, C4, CZ, OZ, O1, O2, P7 and P8, over a period of time, in μV.

[0052] In this embodiment, B f The value can be 3.223μV

[0053] Further, the first brain MRI image or the second brain MRI image is feature processed to obtain a first brain MRI optimized image or a second brain MRI optimized image, and step S1 is first as follows:

[0054] The first brain MRI image or the second brain MRI image is acquired by using an MRI device, and the acquired image is subjected to regional subdivision processing, and the acquired equal-area image is divided into 12 equal parts. The first brain MRI image parameter or the second brain MRI image parameter is a feature processing value of each regional image after the first brain MRI image or the second brain MRI image is divided into 12 equal parts. The processing formula is:

[0055]

[0056] F s =(E(i,j),N(i,j),U(i,j))

[0057] In the formula, E(i,j), N(i,j), and U(i,j) are the grayscale eigenvalues ​​of the three channels of the image, and k R , k G , k B is the correction factor, R n , G n , B n It is the image feature value of the three color channels of the nth image after equal division.

[0058] Further, the first brain MRI image parameter or the second brain MRI image parameter is subjected to feature processing to obtain the first brain MRI image optimization parameter or the second brain MRI image optimization parameter, and the final step S2 is as follows:

[0059] The first brain MRI image parameter or the second brain MRI image parameter is processed by an image unification processing method, and the image unification processing method formula is:

[0060] T=G*E(i,j)+H*N(i,j)+J*U(i,j)

[0061] Where T is the image feature value after image unification, E(i,j), N(i,j), and U(i,j) are the grayscale feature values ​​of the three channels of the image, i and j are both pixel values, and G, H, and J are the weighted value parameters of the image unification feature.

[0062] In this embodiment, the image feature value T after integration may be 123.

[0063] Further, the feature vector B of the first brain physiological parameter or the second brain physiological parameter f, T obtained by unifying the corresponding first brain MRI image parameters or the second brain MRI image parameters and the first developmental scale features or the second developmental scale features Q are spliced ​​to obtain the first child neuropsychological development vector or the second child neuropsychological development vector.

[0064] In this embodiment, the first child neuropsychological development vector after splicing is (B f , T, Q) = (3.223, 123, 75).

[0065] Furthermore, the child neuropsychological development assessment model adopts a classifier based on the Fisher criterion, and the calculation formula is as follows:

[0066]

[0067] M is the first child neuropsychological development vector or the second child neuropsychological development vector, D(M) is the output first child neuropsychological development affliction level or the second child neuropsychological development affliction level, W T is the normal vector perpendicular to the hyperplane, which is obtained by training the first child neuropsychological development vector and the first child neuropsychological development affliction level, |V is one of the G, H, and J image integration feature weight coefficients selected according to the brightness of the first brain MRI image or the second brain MRI image, k is the adjustment coefficient, D is the number of days of child development, and B is the number of days of complete brain development.

[0068] In this embodiment, the first child's neuropsychological developmental condition or the second child's neuropsychological developmental condition is judged based on the value of D(M). When D(M) is less than 0, it indicates that the child's neuropsychological developmental condition is mild. When D(M) is equal to 0, it indicates that the child's neuropsychological developmental condition is normal. When D(M) is greater than 0, it indicates that the child's neuropsychological developmental condition is severe and requires further examination and diagnosis.

[0069] A child neuropsychological development monitoring and management system is also provided, the system comprising a brain physiological data acquisition module, a development scale feature acquisition module, an MRI equipment acquisition module, a neuropsychological development data storage module, a child neuropsychological development assessment model construction module, and a child neurodevelopmental disorder monitoring module, characterized in that:

[0070] The brain physiological data acquisition module is used to acquire the first brain physiological parameter or the second brain physiological parameter of the child;

[0071] The first brain physiological parameter or the second brain physiological parameter comprises brain electrical data or brain neurotransmitter data;

[0072] The developmental scale feature acquisition module is used to acquire the first developmental scale feature or the second developmental scale feature, wherein the first developmental scale feature or the second developmental scale feature is acquired through a preschool children's ability screening form or an ASQ questionnaire;

[0073] The MRI device acquisition module is used to acquire a first brain MRI image or a second brain MRI image, wherein the first brain MRI image includes a historical brain MRI image;

[0074] The neuropsychological development data storage module is used to receive the first brain physiological parameter or the second brain physiological parameter in the brain physiological data acquisition module, the first development scale feature or the second development scale feature in the development scale feature acquisition module, and the first brain MRI image or the second brain MRI image in the MRI device acquisition module, and process the first brain physiological parameter, the first development scale feature and the first brain MRI image to obtain a first child neuropsychological development vector, and process the second brain physiological parameter, the second development scale feature and the second brain MRI image to obtain a second child neuropsychological development vector;

[0075] The child neuropsychological development assessment model construction module is configured to obtain the first child neuropsychological development vector and the corresponding first child neuropsychological development affliction level, and to construct a child neuropsychological development assessment model using the first child neuropsychological development vector and the corresponding first child neuropsychological development affliction level;

[0076] The child neurodevelopmental disorder monitoring module receives the second child neuropsychological development vector, retrieves the child neuropsychological development assessment model to obtain the second child neuropsychological development affliction level, and intelligently monitors the prevalence of child neurodevelopmental disorders based on the second child neuropsychological development affliction level.

[0077] The present invention combines brain MRI image data and brain physiological parameter data, especially electrophysiological parameter data, in the detection and management of children's neuropsychological development, and can more accurately evaluate the neuropsychological development of children. Through the monitoring scene of specific neuropsychological development children, the brain MRI image is processed into a specific channel unification, so that the data quality of the training model is enhanced, and the multi-dimensional data is used to monitor the neuropsychological development of children, so that more accurate and targeted management plan changes can be achieved. At the same time, the EEG data used can be wirelessly transmitted and collected in real time, which can more conveniently process the monitoring data.

[0078] A combination of multiple embodiments of the present invention can achieve all of the above effects, but it is not required that each embodiment of the present invention achieve all of the above advantages and effects, because each embodiment of the present invention can constitute an independent technical solution and make one or more contributions to the prior art.

[0079] The present invention does not particularly specify the structure of some modules, which shall be subject to the contents recorded in the prior art. The prior art mentioned in the above background technology section and the specific embodiment section of the present invention can be used as part of the present invention to understand the meaning of some technical features or parameters. The scope of protection of the present invention shall be subject to the contents actually recorded in the claims.

Claims

1. A method for monitoring and managing the neuropsychological development of children, characterized in that: The method comprises: Obtaining the child's first brain physiological parameter, first brain MRI image, first developmental scale feature, and corresponding first child neuropsychological development morbidity grade; generating a first child neuropsychological development vector using the first brain physiological parameter, the first brain MRI image, and the first developmental scale feature; constructing a child neuropsychological development assessment model according to the first child neuropsychological development vector and the first child neuropsychological development affliction level; A second brain physiological parameter, a second brain MRI image and a second developmental scale feature of the child are received, a second child neuropsychological development vector is generated based on the second brain physiological parameter, the second brain MRI image and the second developmental scale feature, a second child neuropsychological development affliction grade is generated based on the second child neuropsychological development affliction grade using the child neuropsychological development assessment model, and the prevalence of child neurodevelopmental disorders is intelligently monitored based on the second child neuropsychological development affliction grade.

2. A method for monitoring and managing children's neuropsychological development as claimed in claim 1, characterized in that: The first brain physiological parameter or the second brain physiological parameter includes brain electrical data or brain neurotransmitter data, and the first brain MRI image includes a historical brain MRI image.

3. A method for monitoring and managing children's neuropsychological development as claimed in claim 2, characterized in that: The brain EEG data is collected by using a wireless EEG acquisition device Neuro Scan, which can collect EEG signals at 128 brain-computer interfaces. The first developmental scale feature or the second developmental scale feature Q is obtained through a preschool children's ability screening form or an ASQ questionnaire.

4. A method for monitoring and managing children's neuropsychological development as claimed in claim 3, characterized in that: The specific brain areas for collecting the electroencephalographic data are T3, T4, C3, C4, CZ, OZ, O1, O2, P7 and P8.

5. A method for monitoring and managing children's neuropsychological development as claimed in claim 4, characterized in that: The feature vector B of the first brain physiological parameter or the second brain physiological parameter f Calculation.

6. A method for monitoring and managing children's neuropsychological development as claimed in claim 1 or 2, characterized in that: The first brain MRI image or the second brain MRI image is feature processed to obtain a first brain MRI optimized image or a second brain MRI optimized image. Step S1 is first as follows: A first brain MRI image or a second brain MRI image is acquired by using an MRI device, and the acquired image is subjected to regional subdivision processing, and the acquired equal-area image is divided into 12 equal parts. The first brain MRI image parameter or the second brain MRI image parameter is a feature processing value of each regional image after the acquired first brain MRI image or the second brain MRI image is divided into 12 equal parts.

7. A method for monitoring and managing children's neuropsychological development as claimed in claim 6, characterized in that: The first brain MRI image parameter or the second brain MRI image parameter is subjected to feature processing to obtain the first brain MRI image optimization parameter or the second brain MRI image optimization parameter, and the final step S2 is as follows: The first brain MRI image parameter or the second brain MRI image parameter is processed using an image unification processing method.

8. A method for monitoring and managing children's neuropsychological development as claimed in claim 7, characterized in that: The feature vector B of the first brain physiological parameter or the second brain physiological parameter is f , T obtained by unifying the corresponding first brain MRI image parameters or the second brain MRI image parameters and the first developmental scale features or the second developmental scale features Q are spliced ​​to obtain the first child neuropsychological development vector or the second child neuropsychological development vector.

9. A method for monitoring and managing children's neuropsychological development as claimed in claim 8, characterized in that: The child neuropsychological development assessment model adopts a classifier based on the Fisher criterion.

10. A child neuropsychological development monitoring and management system, the system implements the method according to any one of claims 1 to 9, the system comprises a brain physiological data acquisition module, a development scale feature acquisition module, an MRI equipment acquisition module, a neuropsychological development data storage module, a child neuropsychological development assessment model construction module, and a child neurodevelopmental disorder monitoring module, characterized in that: The brain physiological data acquisition module is used to acquire the first brain physiological parameter or the second brain physiological parameter of the child; The first brain physiological parameter or the second brain physiological parameter comprises brain electrical data or brain neurotransmitter data; The developmental scale feature acquisition module is used to acquire the first developmental scale feature or the second developmental scale feature, wherein the first developmental scale feature or the second developmental scale feature is acquired through a preschool children's ability screening form or an ASQ questionnaire; The MRI device acquisition module is used to acquire a first brain MRI image or a second brain MRI image, wherein the first brain MRI image includes a historical brain MRI image; The neuropsychological development data storage module is used to receive the first brain physiological parameter or the second brain physiological parameter in the brain physiological data acquisition module, the first development scale feature or the second development scale feature in the development scale feature acquisition module, and the first brain MRI image or the second brain MRI image in the MRI device acquisition module, and process the first brain physiological parameter, the first development scale feature and the first brain MRI image to obtain a first child neuropsychological development vector, and process the second brain physiological parameter, the second development scale feature and the second brain MRI image to obtain a second child neuropsychological development vector; The child neuropsychological development assessment model construction module is configured to obtain the first child neuropsychological development vector and the corresponding first child neuropsychological development affliction level, and construct a child neuropsychological development assessment model using the first child neuropsychological development vector and the corresponding first child neuropsychological development affliction level; The child neurodevelopmental disorder monitoring module receives the second child neuropsychological development vector, retrieves the child neuropsychological development assessment model to obtain the second child neuropsychological development affliction level, and intelligently monitors the prevalence of child neurodevelopmental disorders based on the second child neuropsychological development affliction level.

Images